feat(bench): push OTLP traces and logs to VictoriaTraces/VictoriaLogs

Add --tracing-otlp and --logs-otlp flags to bench reth node startup,
pointing at VictoriaTraces and VictoriaLogs endpoints (configured via
secrets). OTEL_RESOURCE_ATTRIBUTES carries benchmark metadata
(benchmark_id, run_type, benchmark_run, git_ref) as resource attributes.

.changelog/cool-owls-rest.md

@@ -0,0 +1,5 @@
+---
+reth-trie-sparse: patch
+---
+
+Fixed a bug in `merge_subtrie_updates` where source insertions did not cancel destination removals (and vice versa), causing inconsistent trie updates accumulated across multiple `root()` calls without intermediate `take_updates()`. Added a test covering the cross-cancellation behavior.

.changelog/dark-ants-write.md

@@ -0,0 +1,5 @@
+---
+reth-tasks: patch
+---
+
+Added panic handler to all rayon thread pools that logs panics via `tracing::error` instead of aborting the process.

.changelog/dry-koalas-wink.md

@@ -0,0 +1,5 @@
+---
+reth-network-types: patch
+---
+
+Increased default maximum concurrent outbound dials from 15 to 30.

.changelog/fair-wolves-smile.md

@@ -0,0 +1,5 @@
+---
+reth-payload-builder: minor
+---
+
+Added observability metrics for payload resolve latency and new payload job creation latency to the payload builder service.

.changelog/fine-koalas-shout.md

@@ -0,0 +1,10 @@
+---
+reth-chain-state: minor
+reth-engine-primitives: minor
+reth-engine-tree: minor
+reth-node-core: minor
+reth-node-events: minor
+reth: patch
+---
+
+Added configurable slow block logging (`--engine.slow-block-threshold`) that emits a structured `warn!` log with detailed timing, state-operation counts, and cache hit-rate metrics for blocks whose total processing time exceeds the threshold. Introduced `ExecutionTimingStats`, `CacheStats`, `StateProviderStats`, and `SlowBlockInfo` types to carry execution statistics from block validation through persistence, and refactored `PersistenceResult` to carry commit duration alongside the last persisted block.

.changelog/icy-tigers-buzz.md

@@ -0,0 +1,6 @@
+---
+reth-trie-db: minor
+reth-engine-tree: minor
+---
+
+Added `PendingChangeset` and `PendingChangesetGuard` to `ChangesetCache` so concurrent readers wait for an in-progress computation instead of falling back to the expensive DB-based path. The guard automatically cancels the pending entry on drop (e.g. task panic), ensuring waiters always make progress.

.changelog/merry-bees-break.md

@@ -0,0 +1,8 @@
+---
+reth-engine-primitives: minor
+reth-engine-tree: minor
+reth-node-core: minor
+reth-trie-parallel: minor
+---
+
+Added `--engine.proof-jitter` CLI option behind the `trie-debug` feature flag. When set, each proof worker sleeps for a random duration up to the specified value before starting proof computation, useful for stress-testing timing-sensitive proof logic.

.changelog/mild-foxes-cook.md

@@ -0,0 +1,5 @@
+---
+reth-rpc-convert: patch
+---
+
+Updated `alloy-evm` dependency to git revision `9bc2dba` and adapted `TxEnvConverter` impl to the updated `TryIntoTxEnv` trait signature that now includes a `Spec` generic parameter.

.changelog/neat-ducks-whisper.md

@@ -0,0 +1,6 @@
+---
+reth-trie: patch
+reth-trie-sparse: patch
+---
+
+Refactored test harness for sparse trie tests by extracting `TrieTestHarness` into a shared `reth-trie` test utility, replacing duplicated inline harness code across multiple test modules. Updated `proof_v2` return type to include an optional root hash, and converted `original_root` and `storage` from public fields to accessor methods.

.changelog/nice-bears-cook.md

@@ -0,0 +1,5 @@
+---
+reth-trie: patch
+---
+
+Removed the local `increment_and_strip_trailing_zeros` function and `PATH_ALL_ZEROS` static in `proof_v2`, replacing them with the equivalent `Nibbles::next_without_prefix` and `Nibbles::is_zeroes` builtins. Also replaced manual `.get()` calls on `state_mask`/`hash_mask` with direct field access and switched to `Nibbles::unpack_array` over the unsafe `unpack_unchecked`.

.changelog/odd-frogs-break.md

@@ -0,0 +1,7 @@
+---
+reth-cli-commands: minor
+reth-node-core: minor
+reth: patch
+---
+
+Made v2 storage the default for all new databases, deprecating the `--storage.v2` flag to a hidden no-op kept for backwards compatibility. Updated CLI reference docs to remove the now-hidden flag from all command help pages.

.changelog/proud-slugs-fly.md

@@ -0,0 +1,7 @@
+---
+reth-engine-tree: patch
+reth-trie-sparse: patch
+reth-tasks: patch
+---
+
+Offloaded deallocation of expensive proof node buffers to a persistent background thread (`Runtime::spawn_drop`) to avoid blocking state root computation or lock-holding code.

.changelog/rare-tigers-nod.md

@@ -0,0 +1,6 @@
+---
+reth-trie-sparse: patch
+reth-engine-tree: patch
+---
+
+Removed the `skip_proof_node_filtering` flag, `revealed_account_paths`/`revealed_paths` tracking, and the `filter_revealed_v2_proof_nodes` function from the sparse trie implementation. Also removed the corresponding skipped-nodes metrics, simplifying the proof node reveal path to always pass nodes directly to the sparse trie without pre-filtering.

.changelog/rare-whales-pack.md

@@ -0,0 +1,5 @@
+---
+reth-trie-sparse: minor
+---
+
+Added a comprehensive generic `SparseTrie` test suite covering `set_root`, `reveal_nodes`, `update_leaves`, `root`, `take_updates`, `commit_updates`, `prune`, `wipe`/`clear`, `get_leaf_value`, `find_leaf`, `size_hint`, and integration lifecycle scenarios. Tests are stamped out for all concrete `SparseTrie` implementations via a macro.

.changelog/tall-fish-climb.md

@@ -0,0 +1,5 @@
+---
+reth-cli-commands: minor
+---
+
+Added `reth_version` field to `SnapshotManifest` to record the Reth version that produced a snapshot. The field is optional and populated automatically during manifest generation.

.changelog/vain-bats-bark.md

@@ -0,0 +1,8 @@
+---
+reth-trie-common: minor
+reth-trie: minor
+reth-trie-parallel: minor
+reth-engine-tree: patch
+---
+
+Moved `ProofV2Target`, `MultiProofTargetsV2`, and `ChunkedMultiProofTargetsV2` from `reth-trie-parallel::targets_v2` into a new `reth-trie-common::target_v2` module, making these types available at a lower level without pulling in the full parallel trie crate. Added a `multiproof_v2` method to `Proof` in `reth-trie` that generates a state multiproof using the V2 proof calculator with synchronous account value encoding.

.changelog/vain-birds-laugh.md

@@ -0,0 +1,14 @@
+---
+reth-engine-tree: patch
+reth-evm-ethereum: patch
+reth-evm: patch
+reth-primitives-traits: patch
+reth-revm: patch
+reth-rpc-eth-api: patch
+reth-rpc-eth-types: patch
+reth-provider: patch
+example-custom-evm: patch
+example-precompile-cache: patch
+---
+
+Bumped revm to v35.0.0, revm-inspectors to 0.35.0, and alloy-evm to 0.29.0. Updated call sites throughout the codebase to align with the new APIs, including `ExecutionResult` field changes (`gas_used` → `gas.used()`/`gas.final_refunded()`), removal of `.without_state_clear()`, updated `EthPrecompiles::new(spec)` constructor, and updated `block_hashes.lowest()` access.

.changelog/vain-goats-cook.md

@@ -0,0 +1,9 @@
+---
+reth-trie-sparse: minor
+reth-engine-primitives: minor
+reth-engine-tree: minor
+reth-node-core: minor
+reth-trie-common: patch
+---
+
+Added an arena-based sparse trie implementation (`ArenaParallelSparseTrie`) using `slotmap` arena allocation for node storage, enabling parallel subtrie mutation without per-node hashing overhead. Added `ConfigurableSparseTrie` enum to switch between the arena and hash-map implementations, and a `--engine.enable-arena-sparse-trie` CLI flag to opt in at runtime.

.changelog/young-horses-play.md

@@ -0,0 +1,7 @@
+---
+reth-trie: major
+reth-trie-db: major
+reth-provider: minor
+---
+
+Added `MaskedTrieCursorFactory` and `MaskedTrieCursor` to handle prefix-set-based hash invalidation at the cursor layer, replacing the `DatabaseTrieWitness` trait abstraction. Removed `with_prefix_sets_mut` from `TrieWitness` and deleted `DatabaseTrieWitness` — callers should now wrap their cursor factory with `MaskedTrieCursorFactory` to apply prefix sets during witness/proof computation.

.changelog/zesty-clouds-wave.md

@@ -0,0 +1,5 @@
+---
+reth-trie: patch
+---
+
+Fixed a potential panic in `ProofCalculator` by clearing internal computation state (`branch_stack`, `child_stack`, `branch_path`, etc.) after errors, preventing stale state from causing `usize` underflow panics when the calculator is reused. Added a test verifying correct behavior after simulated mid-computation errors.

.dockerignore

@@ -20,6 +20,11 @@
 # include dist directory, where the reth binary is located after compilation
 !/dist
 
+# include PGO build helper used by Dockerfile.depot
+!/.github
+!/.github/scripts
+!/.github/scripts/build_pgo_bolt.sh
+
 # include licenses
 !LICENSE-*
 

.github/scripts/bench-metrics-proxy.py

@@ -0,0 +1,276 @@
+#!/usr/bin/env python3
+"""
+Prometheus metrics proxy that fetches from a local reth node and
+re-exposes with additional benchmark labels.
+
+Reads labels from a JSON file (updated by local-reth-bench.sh between runs)
+and injects them into every Prometheus metric line.
+
+Returns empty 200 when reth is not running (clean Grafana gaps).
+"""
+import argparse
+import ipaddress
+import json
+import subprocess
+import sys
+import time
+from http.server import HTTPServer, BaseHTTPRequestHandler
+from urllib.request import urlopen
+from urllib.error import URLError
+
+
+def read_labels(path):
+    try:
+        with open(path) as f:
+            return json.load(f)
+    except (FileNotFoundError, json.JSONDecodeError):
+        return {}
+
+
+def inject_labels(metrics_bytes, label_str, label_names):
+    """Inject labels into Prometheus text format.
+
+    Operates on bytes and uses simple string ops instead of regex
+    for speed on large payloads (reth exposes thousands of metrics).
+
+    Skips injecting into lines that already contain any of the label names
+    to avoid duplicate labels (which Prometheus rejects).
+    """
+    if not label_str:
+        return metrics_bytes
+
+    label_bytes = label_str.encode("utf-8")
+    # Pre-encode label names for fast duplicate detection
+    label_name_bytes = [n.encode("utf-8") for n in label_names]
+    out = []
+    for line in metrics_bytes.split(b"\n"):
+        # Skip comments and blank lines
+        if line.startswith(b"#") or not line:
+            out.append(line)
+            continue
+
+        brace = line.find(b"{")
+        space = line.find(b" ")
+
+        if space == -1:
+            # Malformed, pass through
+            out.append(line)
+        elif brace != -1 and brace < space:
+            # Has labels: metric{existing="val"} 123
+            close = line.find(b"}", brace)
+            if close == -1:
+                out.append(line)
+                continue
+
+            # Filter out labels that already exist in this line
+            existing = line[brace + 1:close]
+            inject = label_bytes
+            if existing:
+                for name in label_name_bytes:
+                    if name + b"=" in existing:
+                        # Rebuild inject string excluding this label
+                        inject = _remove_label(inject, name)
+                if not inject:
+                    out.append(line)
+                    continue
+
+            if close == brace + 1:
+                # Empty braces: metric{} 123
+                out.append(line[:close] + inject + line[close:])
+            else:
+                out.append(line[:close] + b"," + inject + line[close:])
+        else:
+            # No labels: metric 123
+            out.append(line[:space] + b"{" + label_bytes + b"}" + line[space:])
+
+    return b"\n".join(out)
+
+
+def _remove_label(label_bytes, name):
+    """Remove a single label (name=\"...\") from a comma-separated label string."""
+    parts = []
+    for part in label_bytes.split(b","):
+        if not part.startswith(name + b"="):
+            parts.append(part)
+    return b",".join(parts)
+
+
+def build_label_str(labels):
+    """Pre-format the label injection string: key1="val1",key2="val2" """
+    if not labels:
+        return ""
+    return ",".join(f'{k}="{v}"' for k, v in sorted(labels.items()))
+
+
+def build_elapsed_gauge(labels):
+    """Build a bench_elapsed_seconds gauge from run_start_epoch in labels."""
+    start = labels.get("run_start_epoch")
+    if not start:
+        return b""
+    try:
+        elapsed = time.time() - float(start)
+    except (ValueError, TypeError):
+        return b""
+    # Build labels excluding internal keys
+    display = {k: v for k, v in labels.items()
+               if k not in ("run_start_epoch", "reference_epoch")}
+    lstr = build_label_str(display)
+    return (
+        f"# HELP bench_elapsed_seconds Seconds since benchmark run started\n"
+        f"# TYPE bench_elapsed_seconds gauge\n"
+        f"bench_elapsed_seconds{{{lstr}}} {elapsed:.1f}\n"
+    ).encode("utf-8")
+
+
+def compute_timestamp_ms(labels):
+    """Compute a synthetic timestamp so all runs share a common time origin.
+
+    Returns the timestamp in milliseconds, or None if not enough info.
+    Uses: reference_epoch + (now - run_start_epoch) → all runs overlay at
+    the same Grafana time range.
+    """
+    ref = labels.get("reference_epoch")
+    start = labels.get("run_start_epoch")
+    if not ref or not start:
+        return None
+    try:
+        elapsed = time.time() - float(start)
+        return int((float(ref) + elapsed) * 1000)
+    except (ValueError, TypeError):
+        return None
+
+
+def inject_timestamps(metrics_bytes, timestamp_ms):
+    """Append a Prometheus timestamp (ms) to every data line.
+
+    Prometheus text format: metric{labels} value [timestamp_ms]
+    Adding timestamps causes Prometheus to store all runs' samples
+    at the same relative time, enabling natural overlay in Grafana.
+    """
+    if timestamp_ms is None:
+        return metrics_bytes
+
+    ts = str(timestamp_ms).encode("utf-8")
+    out = []
+    for line in metrics_bytes.split(b"\n"):
+        if line.startswith(b"#") or not line:
+            out.append(line)
+        else:
+            out.append(line + b" " + ts)
+    return b"\n".join(out)
+
+
+class MetricsHandler(BaseHTTPRequestHandler):
+    # Use HTTP/1.1 so Content-Length is respected and Prometheus
+    # doesn't have to rely on connection close to detect end of body.
+    protocol_version = "HTTP/1.1"
+
+    def do_GET(self):
+        src = self.client_address[0]
+        try:
+            resp = urlopen(self.server.upstream, timeout=2)
+            metrics = resp.read()
+        except (URLError, ConnectionError, OSError):
+            # reth not running — return empty 200
+            self._send(b"")
+            #print(f"  scrape from {src}: empty (reth not running)", flush=True)
+            return
+
+        all_labels = read_labels(self.server.labels_file)
+        # Internal keys — not injected as Prometheus labels
+        internal = ("run_start_epoch", "reference_epoch")
+        labels = {k: v for k, v in all_labels.items() if k not in internal}
+        label_str = build_label_str(labels)
+        label_names = sorted(labels.keys())
+
+        t0 = time.monotonic()
+        result = inject_labels(metrics, label_str, label_names)
+        result += build_elapsed_gauge(all_labels)
+        ts_ms = compute_timestamp_ms(all_labels)
+        result = inject_timestamps(result, ts_ms)
+        dt = time.monotonic() - t0
+
+        self._send(result)
+        print(f"  scrape from {src}: {len(metrics)} -> {len(result)} bytes, "
+              f"inject {dt*1000:.1f}ms", flush=True)
+
+    def _send(self, body):
+        self.send_response(200)
+        self.send_header("Content-Type", "text/plain; version=0.0.4")
+        self.send_header("Content-Length", str(len(body)))
+        self.send_header("Connection", "close")
+        self.end_headers()
+        if body:
+            self.wfile.write(body)
+
+    def log_message(self, format, *args):
+        pass  # suppress per-request logging
+
+
+def resolve_bind_address(subnet_cidr):
+    """Find the local IP address that belongs to the given subnet.
+
+    Uses ``ip -j addr show`` to enumerate interfaces and returns the first
+    address that falls within *subnet_cidr* (e.g. ``10.10.0.0/24``).
+    """
+    network = ipaddress.ip_network(subnet_cidr, strict=False)
+    try:
+        result = subprocess.run(
+            ["ip", "-j", "addr", "show"],
+            capture_output=True, text=True, check=True,
+        )
+        interfaces = json.loads(result.stdout)
+    except (subprocess.CalledProcessError, FileNotFoundError, json.JSONDecodeError) as exc:
+        print(f"Error: cannot enumerate interfaces: {exc}", file=sys.stderr)
+        sys.exit(1)
+
+    for iface in interfaces:
+        for addr_info in iface.get("addr_info", []):
+            try:
+                addr = ipaddress.ip_address(addr_info["local"])
+            except (KeyError, ValueError):
+                continue
+            if addr in network:
+                return str(addr)
+
+    print(f"Error: no interface address found in subnet {subnet_cidr}", file=sys.stderr)
+    sys.exit(1)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Prometheus metrics proxy with label injection")
+    parser.add_argument("--labels", default="/tmp/bench-metrics-labels.json",
+                        help="Path to JSON file with labels to inject (default: /tmp/bench-metrics-labels.json)")
+    parser.add_argument("--upstream", default="http://127.0.0.1:9100/",
+                        help="Upstream reth metrics URL (default: http://127.0.0.1:9100/)")
+
+    bind_group = parser.add_mutually_exclusive_group()
+    bind_group.add_argument("--bind", default=None,
+                            help="Address to bind the proxy (default: 0.0.0.0)")
+    bind_group.add_argument("--subnet", default=None,
+                            help="Auto-detect bind address from a local interface in this subnet (e.g. 10.10.0.0/24)")
+
+    parser.add_argument("--port", type=int, default=9090,
+                        help="Port to bind the proxy (default: 9090)")
+    args = parser.parse_args()
+
+    if args.subnet:
+        bind_addr = resolve_bind_address(args.subnet)
+    elif args.bind:
+        bind_addr = args.bind
+    else:
+        bind_addr = "0.0.0.0"
+
+    server = HTTPServer((bind_addr, args.port), MetricsHandler)
+    server.upstream = args.upstream
+    server.labels_file = args.labels
+
+    print(f"bench-metrics-proxy listening on {bind_addr}:{args.port}")
+    print(f"  upstream: {args.upstream}")
+    print(f"  labels:   {args.labels}")
+    sys.stdout.flush()
+    server.serve_forever()
+
+
+if __name__ == "__main__":
+    main()

.github/scripts/bench-reth-build.sh

@@ -22,6 +22,22 @@ MODE="$1"
 SOURCE_DIR="$2"
 COMMIT="$3"
 
+# Tracy support: when BENCH_TRACY is "on" or "full", add Tracy cargo features
+# and frame pointers for accurate stack traces.
+EXTRA_FEATURES=""
+EXTRA_RUSTFLAGS=""
+if [ "${BENCH_TRACY:-off}" != "off" ]; then
+  EXTRA_FEATURES="tracy,tracy-client/ondemand"
+  EXTRA_RUSTFLAGS=" -C force-frame-pointers=yes"
+fi
+
+# Cache suffix: hash of features+rustflags so different build configs get separate cache entries
+if [ -n "$EXTRA_FEATURES" ] || [ -n "$EXTRA_RUSTFLAGS" ]; then
+  BUILD_SUFFIX="-$(echo "${EXTRA_FEATURES}${EXTRA_RUSTFLAGS}" | sha256sum | cut -c1-12)"
+else
+  BUILD_SUFFIX=""
+fi
+
 # Verify a cached reth binary was built from the expected commit.
 # `reth --version` outputs "Commit SHA: <full-sha>" on its own line.
 verify_binary() {
@@ -42,7 +58,7 @@ verify_binary() {
 
 case "$MODE" in
   baseline|main)
-    BUCKET="minio/reth-binaries/${COMMIT}"
+    BUCKET="minio/reth-binaries/${COMMIT}${BUILD_SUFFIX}"
     mkdir -p "${SOURCE_DIR}/target/profiling"
 
     CACHE_VALID=false
@@ -59,14 +75,23 @@ case "$MODE" in
     if [ "$CACHE_VALID" = false ]; then
       echo "Building baseline (${COMMIT}) from source..."
       cd "${SOURCE_DIR}"
-      cargo build --profile profiling --bin reth
+      FEATURES_ARG=""
+      WORKSPACE_ARG=""
+      if [ -n "$EXTRA_FEATURES" ]; then
+        # --workspace is needed for cross-package feature syntax (tracy-client/ondemand)
+        FEATURES_ARG="--features ${EXTRA_FEATURES}"
+        WORKSPACE_ARG="--workspace"
+      fi
+      # shellcheck disable=SC2086
+      RUSTFLAGS="-C target-cpu=native${EXTRA_RUSTFLAGS}" \
+        cargo build --profile profiling --bin reth $WORKSPACE_ARG $FEATURES_ARG
       $MC cp target/profiling/reth "${BUCKET}/reth"
     fi
     ;;
 
   feature|branch)
     BRANCH_SHA="${4:-$COMMIT}"
-    BUCKET="minio/reth-binaries/${BRANCH_SHA}"
+    BUCKET="minio/reth-binaries/${BRANCH_SHA}${BUILD_SUFFIX}"
 
     CACHE_VALID=false
     if $MC stat "${BUCKET}/reth" &>/dev/null && $MC stat "${BUCKET}/reth-bench" &>/dev/null; then
@@ -85,7 +110,14 @@ case "$MODE" in
       echo "Building feature (${COMMIT}) from source..."
       cd "${SOURCE_DIR}"
       rustup show active-toolchain || rustup default stable
-      make profiling
+      if [ -n "$EXTRA_FEATURES" ]; then
+        # Can't use `make profiling` when adding features; build explicitly
+        # --workspace is needed for cross-package feature syntax (tracy-client/ondemand)
+        RUSTFLAGS="-C target-cpu=native${EXTRA_RUSTFLAGS}" \
+          cargo build --profile profiling --workspace --bin reth --features "${EXTRA_FEATURES}"
+      else
+        make profiling
+      fi
       make install-reth-bench
       $MC cp target/profiling/reth "${BUCKET}/reth"
       $MC cp "$(which reth-bench)" "${BUCKET}/reth-bench"

.github/scripts/bench-reth-local.sh

@@ -0,0 +1,581 @@
+#!/usr/bin/env bash
+#
+# local-reth-bench.sh — Run the reth Engine API benchmark locally.
+#
+# Replicates the CI bench.yml workflow (build, snapshot, system tuning,
+# interleaved B-F-F-B execution, summary, charts) without any GitHub
+# Actions glue (no PR comments, no artifact upload, no Slack).
+#
+# Usage:
+#   local-reth-bench.sh <baseline-ref> <feature-ref> [options]
+#
+# Options:
+#   --blocks N      Number of blocks to benchmark (default: 500)
+#   --warmup N      Number of warmup blocks (default: 100)
+#   --cores N       Limit reth to N CPU cores, 0 = all available (default: 0)
+#   --samply        Enable samply profiling
+#   --tracy MODE    Tracy profiling: off, on, full (default: off)
+#   --tracy-filter F Tracy tracing filter (default: debug)
+#   --no-tune       Skip system tuning (useful on dev machines / macOS)
+#
+# Requires: the reth repo at RETH_REPO (default: ~/reth)
+#
+# Dependencies (install before first run):
+#   mc (MinIO client), schelk, cpupower, taskset, stdbuf, python3, curl,
+#   make, uv, pzstd, jq, Rust toolchain (cargo/rustup)
+#
+# The script delegates to the existing bench-reth-*.sh scripts in the reth
+# repo for the actual build, snapshot, and run steps.
+set -euo pipefail
+
+# ── PATH ──────────────────────────────────────────────────────────────
+# Ensure cargo and user-local bins (mc, uv) are visible
+export PATH="$HOME/.local/bin:$HOME/.cargo/bin:$PATH"
+
+# ── Defaults ──────────────────────────────────────────────────────────
+RETH_REPO="${RETH_REPO:-$HOME/reth}"
+BLOCKS=500
+WARMUP=100
+CORES=0
+SAMPLY=false
+TRACY="off"
+TRACY_FILTER="debug"
+TUNE=true
+BASELINE_REF=""
+FEATURE_REF=""
+
+# ── Parse arguments ──────────────────────────────────────────────────
+usage() {
+  cat <<EOF
+Usage: $(basename "$0") <baseline-ref> <feature-ref> [options]
+
+Options:
+  --blocks N         Number of blocks to benchmark (default: 500)
+  --warmup N         Number of warmup blocks (default: 100)
+  --cores N          Limit reth to N CPU cores (default: 0 = all)
+  --samply           Enable samply profiling
+  --tracy MODE       Tracy profiling: off, on, full (default: off)
+                       on   = tracing only (lower overhead)
+                       full = tracing + CPU sampling (higher overhead)
+  --tracy-filter F   Tracy tracing filter (default: debug)
+  --no-tune          Skip system tuning
+EOF
+  exit 1
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --blocks)       BLOCKS="$2"; shift 2 ;;
+    --warmup)       WARMUP="$2"; shift 2 ;;
+    --cores)        CORES="$2"; shift 2 ;;
+    --samply)       SAMPLY=true; shift ;;
+    --tracy)        TRACY="$2"; shift 2 ;;
+    --tracy-filter) TRACY_FILTER="$2"; shift 2 ;;
+    --no-tune)      TUNE=false; shift ;;
+    --help|-h)  usage ;;
+    -*)         echo "Unknown option: $1"; usage ;;
+    *)
+      if [ -z "$BASELINE_REF" ]; then
+        BASELINE_REF="$1"
+      elif [ -z "$FEATURE_REF" ]; then
+        FEATURE_REF="$1"
+      else
+        echo "Unexpected argument: $1"; usage
+      fi
+      shift
+      ;;
+  esac
+done
+
+if [ -z "$BASELINE_REF" ] || [ -z "$FEATURE_REF" ]; then
+  echo "Error: both <baseline-ref> and <feature-ref> are required."
+  usage
+fi
+
+# Validate --tracy value
+case "$TRACY" in
+  off|on|full) ;;
+  *) echo "Error: --tracy must be off, on, or full (got: $TRACY)"; usage ;;
+esac
+
+# Samply + tracy=full are mutually exclusive (both use perf sampling)
+if [ "$SAMPLY" = "true" ] && [ "$TRACY" = "full" ]; then
+  echo "Warning: samply and tracy=full both use perf sampling; downgrading tracy to 'on'."
+  TRACY="on"
+fi
+
+# ── Check dependencies ───────────────────────────────────────────────
+missing=()
+for cmd in mc schelk cpupower taskset stdbuf python3 curl make uv pzstd jq cargo; do
+  command -v "$cmd" &>/dev/null || missing+=("$cmd")
+done
+if [ ${#missing[@]} -gt 0 ]; then
+  echo "Error: missing required tools: ${missing[*]}"
+  echo "See the CI 'Install dependencies' step in .github/workflows/bench.yml for install instructions."
+  exit 1
+fi
+
+if [ "$TRACY" != "off" ]; then
+  if ! command -v tracy-capture &>/dev/null; then
+    echo "Error: tracy-capture is required for --tracy $TRACY"
+    exit 1
+  fi
+fi
+
+# Ensure tools that run via sudo are in a sudo-visible path.
+# The bench scripts use `sudo schelk` / `sudo samply` but cargo installs
+# them to ~/.cargo/bin which sudo's secure_path doesn't include.
+for cmd in schelk samply; do
+  if command -v "$cmd" &>/dev/null && ! sudo sh -c "command -v $cmd" &>/dev/null; then
+    echo "Installing $cmd to /usr/local/bin (needed for sudo)..."
+    sudo install "$(command -v "$cmd")" /usr/local/bin/
+  fi
+done
+
+if [ ! -d "$RETH_REPO/.git" ]; then
+  echo "Error: RETH_REPO=$RETH_REPO is not a git repository."
+  echo "Set RETH_REPO or clone reth to ~/reth"
+  exit 1
+fi
+
+# ── Resolve paths ────────────────────────────────────────────────────
+SELF_DIR="$(cd "$(dirname "$0")" && pwd)"
+SCRIPTS_DIR="${RETH_REPO}/.github/scripts"
+BENCH_WORK_DIR="${RETH_REPO}/../bench-work-$(date +%Y%m%d-%H%M%S)"
+BASELINE_SRC="${RETH_REPO}/../reth-baseline"
+FEATURE_SRC="${RETH_REPO}/../reth-feature"
+
+mkdir -p "$BENCH_WORK_DIR"
+BENCH_WORK_DIR="$(cd "$BENCH_WORK_DIR" && pwd)"
+
+# ── Global cleanup trap (restores system tuning on any exit) ─────────
+TUNING_APPLIED=false
+CSTATE_PID=
+METRICS_PROXY_PID=
+cleanup_global() {
+  [ -n "$METRICS_PROXY_PID" ] && kill "$METRICS_PROXY_PID" 2>/dev/null || true
+  if [ "$TUNING_APPLIED" = true ]; then
+    echo
+    echo "▸ Restoring system settings..."
+    [ -n "$CSTATE_PID" ] && kill "$CSTATE_PID" 2>/dev/null || true
+    sudo systemctl start irqbalance cron atd 2>/dev/null || true
+    echo "  System settings restored."
+  fi
+}
+trap cleanup_global EXIT
+
+echo "═══════════════════════════════════════════════════════════"
+echo "  reth local benchmark"
+echo "═══════════════════════════════════════════════════════════"
+echo "  Baseline ref : $BASELINE_REF"
+echo "  Feature ref  : $FEATURE_REF"
+echo "  Blocks       : $BLOCKS"
+echo "  Warmup       : $WARMUP"
+echo "  Cores        : $CORES"
+echo "  Samply       : $SAMPLY"
+echo "  Tracy        : $TRACY"
+echo "  Tracy filter : $TRACY_FILTER"
+echo "  System tune  : $TUNE"
+echo "  Work dir     : $BENCH_WORK_DIR"
+echo "  Reth repo    : $RETH_REPO"
+echo "═══════════════════════════════════════════════════════════"
+echo
+
+# Enable sccache if available (matches CI's RUSTC_WRAPPER=sccache)
+if command -v sccache &>/dev/null; then
+  export RUSTC_WRAPPER="sccache"
+fi
+
+# Export env vars expected by the bench-reth-*.sh scripts
+export BENCH_BLOCKS="$BLOCKS"
+export BENCH_WARMUP_BLOCKS="$WARMUP"
+export BENCH_CORES="$CORES"
+export BENCH_SAMPLY="$SAMPLY"
+export BENCH_TRACY="$TRACY"
+export BENCH_TRACY_FILTER="$TRACY_FILTER"
+export BENCH_WORK_DIR
+export SCHELK_MOUNT="${SCHELK_MOUNT:-/reth-bench}"
+export BENCH_RPC_URL="${BENCH_RPC_URL:-https://ethereum.reth.rs/rpc}"
+export BENCH_METRICS_ADDR="127.0.0.1:9100"
+
+# ── Step 1: Resolve refs to full SHAs ────────────────────────────────
+echo "▸ Resolving git refs..."
+cd "$RETH_REPO"
+
+resolve_ref() {
+  local ref="$1"
+  git fetch origin "$ref" --quiet 2>/dev/null || true
+  git rev-parse "$ref" 2>/dev/null \
+    || git rev-parse "origin/$ref" 2>/dev/null \
+    || { echo "Error: cannot resolve ref '$ref'"; exit 1; }
+}
+
+BASELINE_SHA="$(resolve_ref "$BASELINE_REF")"
+FEATURE_SHA="$(resolve_ref "$FEATURE_REF")"
+echo "  Baseline SHA : $BASELINE_SHA"
+echo "  Feature SHA  : $FEATURE_SHA"
+echo
+
+# ── Step 2: Prepare source directories ───────────────────────────────
+echo "▸ Preparing source directories..."
+
+prepare_source() {
+  local src_dir="$1" ref="$2"
+  if [ -d "$src_dir" ]; then
+    git -C "$src_dir" fetch origin "$ref" 2>/dev/null || true
+  else
+    git clone --recurse-submodules "$RETH_REPO" "$src_dir"
+  fi
+  git -C "$src_dir" checkout "$ref" --force
+  git -C "$src_dir" submodule update --init --recursive
+}
+
+prepare_source "$BASELINE_SRC" "$BASELINE_SHA"
+prepare_source "$FEATURE_SRC" "$FEATURE_SHA"
+BASELINE_SRC="$(cd "$BASELINE_SRC" && pwd)"
+FEATURE_SRC="$(cd "$FEATURE_SRC" && pwd)"
+echo "  Baseline src : $BASELINE_SRC"
+echo "  Feature src  : $FEATURE_SRC"
+echo
+
+# ── Step 3: Check / download snapshot ────────────────────────────────
+echo "▸ Checking snapshot..."
+cd "$RETH_REPO"
+SNAPSHOT_NEEDED=false
+if ! "${SCRIPTS_DIR}/bench-reth-snapshot.sh" --check; then
+  SNAPSHOT_NEEDED=true
+  echo "  Snapshot needs update."
+else
+  echo "  Snapshot is up-to-date."
+fi
+echo
+
+# ── Step 4: Build binaries (+ snapshot download) in parallel ─────────
+echo "▸ Building binaries (parallel)..."
+cd "$RETH_REPO"
+
+FAIL=0
+
+"${SCRIPTS_DIR}/bench-reth-build.sh" baseline "$BASELINE_SRC" "$BASELINE_SHA" &
+PID_BASELINE=$!
+
+"${SCRIPTS_DIR}/bench-reth-build.sh" feature "$FEATURE_SRC" "$FEATURE_SHA" &
+PID_FEATURE=$!
+
+PID_SNAPSHOT=
+if [ "$SNAPSHOT_NEEDED" = "true" ]; then
+  echo "  Also downloading snapshot in parallel..."
+  "${SCRIPTS_DIR}/bench-reth-snapshot.sh" &
+  PID_SNAPSHOT=$!
+fi
+
+wait $PID_BASELINE || FAIL=1
+wait $PID_FEATURE  || FAIL=1
+[ -n "$PID_SNAPSHOT" ] && { wait $PID_SNAPSHOT || FAIL=1; }
+
+if [ $FAIL -ne 0 ]; then
+  echo "Error: one or more parallel tasks failed (builds / snapshot)"
+  exit 1
+fi
+echo "  Binaries built successfully."
+echo
+
+# ── Step 5: System tuning (optional) ────────────────────────────────
+if [ "$TUNE" = "true" ]; then
+  echo "▸ Applying system tuning..."
+
+  sudo cpupower frequency-set -g performance 2>/dev/null || true
+
+  # Disable turbo boost (Intel + AMD)
+  echo 1 | sudo tee /sys/devices/system/cpu/intel_pstate/no_turbo 2>/dev/null || true
+  echo 0 | sudo tee /sys/devices/system/cpu/cpufreq/boost 2>/dev/null || true
+
+  sudo swapoff -a 2>/dev/null || true
+  echo 0 | sudo tee /proc/sys/kernel/randomize_va_space 2>/dev/null || true
+
+  # Disable SMT (hyperthreading)
+  for cpu in /sys/devices/system/cpu/cpu*/topology/thread_siblings_list; do
+    [ -f "$cpu" ] || continue
+    first=$(cut -d, -f1 < "$cpu" | cut -d- -f1)
+    current=$(echo "$cpu" | grep -o 'cpu[0-9]*' | grep -o '[0-9]*')
+    if [ "$current" != "$first" ]; then
+      echo 0 | sudo tee "/sys/devices/system/cpu/cpu${current}/online" 2>/dev/null || true
+    fi
+  done
+  echo "  Online CPUs: $(nproc)"
+
+  # Disable transparent huge pages
+  for p in /sys/kernel/mm/transparent_hugepage /sys/kernel/mm/transparent_hugepages; do
+    if [ -d "$p" ]; then
+      echo never | sudo tee "$p/enabled" 2>/dev/null || true
+      echo never | sudo tee "$p/defrag" 2>/dev/null || true
+      break
+    fi
+  done
+
+  # Prevent deep C-states
+  sudo sh -c 'exec 3<>/dev/cpu_dma_latency; echo -ne "\x00\x00\x00\x00" >&3; sleep infinity' &
+  CSTATE_PID=$!
+
+  # Pin IRQs to core 0
+  for irq in /proc/irq/*/smp_affinity_list; do
+    echo 0 | sudo tee "$irq" 2>/dev/null || true
+  done
+
+  # Stop noisy background services
+  sudo systemctl stop irqbalance cron atd unattended-upgrades snapd 2>/dev/null || true
+
+  TUNING_APPLIED=true
+
+  # Log environment for reproducibility (matches CI)
+  echo "  === Benchmark environment ==="
+  echo "  Kernel : $(uname -r)"
+  lscpu | grep -E 'Model name|CPU\(s\)|MHz|NUMA' | sed 's/^/  /'
+  echo "  Governor : $(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 2>/dev/null || echo unknown)"
+  echo "  Freq     : $(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq 2>/dev/null || echo unknown)"
+  echo "  THP      : $(cat /sys/kernel/mm/transparent_hugepage/enabled 2>/dev/null || cat /sys/kernel/mm/transparent_hugepages/enabled 2>/dev/null || echo unknown)"
+  free -h | sed 's/^/  /'
+  echo "  System tuning applied."
+  echo
+fi
+
+# ── Step 5b: Tracefs mount (tracy=full only) ─────────────────────────
+if [ "$TRACY" = "full" ] && [ "$(uname)" = "Linux" ]; then
+  echo "▸ Mounting tracefs for Tracy full mode..."
+  sudo mount -t tracefs tracefs /sys/kernel/tracing -o mode=755 2>/dev/null || true
+fi
+
+# ── Tracy upload & viewer helpers ────────────────────────────────────
+TRACY_VIEWER_BASE="${TRACY_VIEWER_BASE:-}"
+
+tracy_viewer_url() {
+  local profile_url="$1"
+  if [ -z "$TRACY_VIEWER_BASE" ]; then
+    echo ""
+    return
+  fi
+  local encoded
+  encoded=$(python3 -c "import urllib.parse, sys; print(urllib.parse.quote(sys.argv[1], safe=''))" "$profile_url")
+  echo "${TRACY_VIEWER_BASE}?profile_url=${encoded}"
+}
+
+upload_tracy() {
+  local label="$1" output_dir="$2" sha="$3"
+  local tracy_file="$output_dir/tracy-profile.tracy"
+
+  if [ ! -f "$tracy_file" ]; then
+    echo "  Tracy: no profile found, skipping upload."
+    return
+  fi
+
+  local timestamp short_sha remote_name bucket mc_alias
+  timestamp=$(date +%Y%m%d-%H%M%S)
+  short_sha="${sha:0:7}"
+  remote_name="${label}-${short_sha}-${timestamp}.tracy"
+  bucket="${TRACY_BUCKET:-tracy-profiles}"
+  mc_alias="${MC_ALIAS:-minio}"
+  local minio_base="${TRACY_MINIO_URL:-http://minio.minio.svc.cluster.local:9000}"
+
+  echo "  Tracy: uploading profile..."
+  if mc cp "$tracy_file" "${mc_alias}/${bucket}/${remote_name}"; then
+    local url="${minio_base}/${bucket}/${remote_name}"
+    echo "$url" > "$output_dir/tracy_url.txt"
+    local viewer
+    viewer=$(tracy_viewer_url "$url")
+    if [ -n "$viewer" ]; then
+      echo "$viewer" > "$output_dir/tracy_viewer_url.txt"
+      echo "  Tracy: uploaded → $viewer"
+    else
+      echo "  Tracy: uploaded → $url"
+    fi
+  else
+    echo "  Tracy: upload failed (non-fatal)."
+  fi
+
+  # Delete large profile to free disk
+  rm -f "$tracy_file"
+}
+
+# ── Step 6: Pre-flight cleanup ───────────────────────────────────────
+echo "▸ Pre-flight cleanup..."
+pkill -f bench-metrics-proxy 2>/dev/null || true
+sudo pkill -9 reth 2>/dev/null || true
+sleep 1
+if mountpoint -q "$SCHELK_MOUNT" 2>/dev/null; then
+  sudo umount -l "$SCHELK_MOUNT" 2>/dev/null || true
+  sudo schelk recover -y 2>/dev/null || true
+fi
+echo
+
+# ── Step 7: Interleaved benchmark runs (B-F-F-B) ────────────────────
+# This ordering reduces systematic bias from thermal drift and cache warming.
+BASELINE_BIN="${BASELINE_SRC}/target/profiling/reth"
+FEATURE_BIN="${FEATURE_SRC}/target/profiling/reth"
+
+# Start metrics proxy (reth → label injection → Prometheus)
+LABELS_FILE="/tmp/bench-metrics-labels.json"
+echo '{}' > "$LABELS_FILE"
+METRICS_SUBNET="${METRICS_SUBNET:-10.10.0.0/24}"
+METRICS_PORT="${METRICS_PORT:-9090}"
+python3 "${SELF_DIR}/bench-metrics-proxy.py" \
+  --labels "$LABELS_FILE" \
+  --upstream "http://${BENCH_METRICS_ADDR}/" \
+  --subnet "$METRICS_SUBNET" \
+  --port "$METRICS_PORT" &
+METRICS_PROXY_PID=$!
+echo "▸ Metrics proxy started (PID $METRICS_PROXY_PID) on subnet ${METRICS_SUBNET}, port ${METRICS_PORT}"
+
+# Unique benchmark ID: local-<timestamp> for local runs, ci-<run_id> for CI
+BENCH_ID="local-$(basename "$BENCH_WORK_DIR" | sed 's/bench-work-//')"
+# Reference epoch: shared time origin so all runs overlay in Grafana.
+# The proxy maps each run's elapsed time onto this common origin.
+BENCH_REFERENCE_EPOCH=$(date +%s)
+
+write_labels() {
+  local run_label="$1" run_type="$2" ref="$3" sha="$4"
+  LAST_RUN_START=$(date +%s)
+  cat > "$LABELS_FILE" <<-EOF
+	{"benchmark_run":"${run_label}","run_type":"${run_type}","git_ref":"${ref}","bench_sha":"${sha}","benchmark_id":"${BENCH_ID}","run_start_epoch":"${LAST_RUN_START}","reference_epoch":"${BENCH_REFERENCE_EPOCH}"}
+	EOF
+}
+
+run_bench() {
+  local label="$1" binary="$2" output_dir="$3"
+  echo "▸ Running benchmark: ${label}..."
+  cd "$RETH_REPO"
+  if command -v taskset &>/dev/null; then
+    taskset -c 0 "${SCRIPTS_DIR}/bench-reth-run.sh" "$label" "$binary" "$output_dir"
+  else
+    "${SCRIPTS_DIR}/bench-reth-run.sh" "$label" "$binary" "$output_dir"
+  fi
+  echo "  ✓ ${label} complete."
+  echo
+}
+
+write_labels "baseline-1" "baseline" "$BASELINE_REF" "$BASELINE_SHA"
+run_bench "baseline-1" "$BASELINE_BIN" "$BENCH_WORK_DIR/baseline-1"
+
+write_labels "feature-1" "feature" "$FEATURE_REF" "$FEATURE_SHA"
+run_bench "feature-1"  "$FEATURE_BIN"  "$BENCH_WORK_DIR/feature-1"
+
+write_labels "feature-2" "feature" "$FEATURE_REF" "$FEATURE_SHA"
+run_bench "feature-2"  "$FEATURE_BIN"  "$BENCH_WORK_DIR/feature-2"
+
+write_labels "baseline-2" "baseline" "$BASELINE_REF" "$BASELINE_SHA"
+run_bench "baseline-2" "$BASELINE_BIN" "$BENCH_WORK_DIR/baseline-2"
+
+# ── Compute Grafana URL ──────────────────────────────────────────────
+GRAFANA_BASE_URL="https://tempoxyz.grafana.net/d/reth-bench-ghr/reth-bench-ghr"
+GRAFANA_DATASOURCE="ef57fux92e9z4e"
+LAST_RUN_DURATION=$(( $(date +%s) - LAST_RUN_START ))
+FROM_MS=$(( BENCH_REFERENCE_EPOCH * 1000 ))
+TO_MS=$(( (BENCH_REFERENCE_EPOCH + LAST_RUN_DURATION) * 1000 ))
+GRAFANA_URL="${GRAFANA_BASE_URL}?orgId=1&from=${FROM_MS}&to=${TO_MS}&timezone=browser&var-datasource=${GRAFANA_DATASOURCE}&var-job=reth-bench&var-benchmark_id=${BENCH_ID}&var-benchmark_run=\$__all"
+
+# ── Step 8: Scan logs for errors ─────────────────────────────────────
+echo "▸ Scanning logs for errors..."
+ERRORS_FILE="$BENCH_WORK_DIR/errors.md"
+found_errors=false
+for run_dir in baseline-1 feature-1 feature-2 baseline-2; do
+  LOG="$BENCH_WORK_DIR/$run_dir/node.log"
+  [ -f "$LOG" ] || continue
+  panics=$(grep -c -E 'panicked at' "$LOG" 2>/dev/null || true)
+  errors=$(grep -c ' ERROR ' "$LOG" 2>/dev/null || true)
+  if [ "$panics" -gt 0 ] || [ "$errors" -gt 0 ]; then
+    if [ "$found_errors" = false ]; then
+      printf '### ⚠️ Node Errors\n\n' >> "$ERRORS_FILE"
+      found_errors=true
+    fi
+    printf '<details><summary><b>%s</b>: %d panic(s), %d error(s)</summary>\n\n' \
+      "$run_dir" "$panics" "$errors" >> "$ERRORS_FILE"
+    if [ "$panics" -gt 0 ]; then
+      printf '**Panics:**\n```\n' >> "$ERRORS_FILE"
+      grep -E 'panicked at' "$LOG" | head -10 >> "$ERRORS_FILE"
+      printf '```\n' >> "$ERRORS_FILE"
+    fi
+    if [ "$errors" -gt 0 ]; then
+      printf '**Errors (first 20):**\n```\n' >> "$ERRORS_FILE"
+      grep ' ERROR ' "$LOG" | head -20 >> "$ERRORS_FILE"
+      printf '```\n' >> "$ERRORS_FILE"
+    fi
+    printf '\n</details>\n\n' >> "$ERRORS_FILE"
+  fi
+done
+if [ "$found_errors" = true ]; then
+  echo "  ⚠ Errors found — see $ERRORS_FILE"
+else
+  echo "  No errors found."
+fi
+echo
+
+# ── Step 9: Parse results ───────────────────────────────────────────
+echo "▸ Parsing results..."
+cd "$RETH_REPO"
+
+SUMMARY_ARGS=(
+  --output-summary "$BENCH_WORK_DIR/summary.json"
+  --output-markdown "$BENCH_WORK_DIR/comment.md"
+  --repo "paradigmxyz/reth"
+  --baseline-ref "$BASELINE_SHA"
+  --baseline-name "$BASELINE_REF"
+  --feature-name "$FEATURE_REF"
+  --feature-ref "$FEATURE_SHA"
+  --baseline-csv "$BENCH_WORK_DIR/baseline-1/combined_latency.csv" "$BENCH_WORK_DIR/baseline-2/combined_latency.csv"
+  --feature-csv "$BENCH_WORK_DIR/feature-1/combined_latency.csv" "$BENCH_WORK_DIR/feature-2/combined_latency.csv"
+  --gas-csv "$BENCH_WORK_DIR/feature-1/total_gas.csv"
+  --grafana-url "$GRAFANA_URL"
+)
+
+python3 "${SCRIPTS_DIR}/bench-reth-summary.py" "${SUMMARY_ARGS[@]}"
+echo
+
+# ── Step 10: Generate charts ─────────────────────────────────────────
+echo "▸ Generating charts..."
+CHART_ARGS=(
+  --output-dir "$BENCH_WORK_DIR/charts"
+  --feature "$BENCH_WORK_DIR/feature-1/combined_latency.csv" "$BENCH_WORK_DIR/feature-2/combined_latency.csv"
+  --baseline "$BENCH_WORK_DIR/baseline-1/combined_latency.csv" "$BENCH_WORK_DIR/baseline-2/combined_latency.csv"
+  --baseline-name "$BASELINE_REF"
+  --feature-name "$FEATURE_REF"
+)
+
+if python3 -c "import matplotlib" 2>/dev/null; then
+  python3 "${SCRIPTS_DIR}/bench-reth-charts.py" "${CHART_ARGS[@]}"
+elif command -v uv &>/dev/null; then
+  uv run --with matplotlib python3 "${SCRIPTS_DIR}/bench-reth-charts.py" "${CHART_ARGS[@]}"
+else
+  echo "  Warning: matplotlib not available, skipping chart generation."
+fi
+echo
+
+# ── Step 11: Upload Tracy profiles ────────────────────────────────────
+if [ "$TRACY" != "off" ]; then
+  echo "▸ Uploading Tracy profiles..."
+  upload_tracy "baseline-1" "$BENCH_WORK_DIR/baseline-1" "$BASELINE_SHA"
+  upload_tracy "feature-1"  "$BENCH_WORK_DIR/feature-1"  "$FEATURE_SHA"
+  upload_tracy "feature-2"  "$BENCH_WORK_DIR/feature-2"  "$FEATURE_SHA"
+  upload_tracy "baseline-2" "$BENCH_WORK_DIR/baseline-2" "$BASELINE_SHA"
+  echo
+fi
+
+# ── Done (system restore happens via EXIT trap) ─────────────────────
+echo "═══════════════════════════════════════════════════════════"
+echo "  Benchmark complete!"
+echo "═══════════════════════════════════════════════════════════"
+echo "  Results  : $BENCH_WORK_DIR/summary.json"
+echo "  Markdown : $BENCH_WORK_DIR/comment.md"
+echo "  Charts   : $BENCH_WORK_DIR/charts/"
+if [ -f "$ERRORS_FILE" ]; then
+  echo "  Errors   : $ERRORS_FILE"
+fi
+echo "  Grafana  : $GRAFANA_URL"
+if [ "$TRACY" != "off" ]; then
+  echo "  ─── Tracy Profiles ───"
+  for run_dir in baseline-1 feature-1 feature-2 baseline-2; do
+    url_file="$BENCH_WORK_DIR/$run_dir/tracy_viewer_url.txt"
+    if [ -f "$url_file" ]; then
+      echo "  $run_dir : $(cat "$url_file")"
+    fi
+  done
+fi
+echo "═══════════════════════════════════════════════════════════"

.github/scripts/bench-reth-run.sh

@@ -6,6 +6,13 @@
 # Usage: bench-reth-run.sh <label> <binary> <output-dir>
 #
 # Required env: SCHELK_MOUNT, BENCH_RPC_URL, BENCH_BLOCKS, BENCH_WARMUP_BLOCKS
+# Optional env: BENCH_BIG_BLOCKS (true/false), BENCH_WORK_DIR (for big blocks path)
+#               BENCH_RETH_NEW_PAYLOAD (true/false, default true)
+#               BENCH_WAIT_TIME (duration like 500ms, default empty)
+#               BENCH_BASELINE_ARGS (extra reth node args for baseline runs)
+#               BENCH_FEATURE_ARGS (extra reth node args for feature runs)
+#               BENCH_OTLP_TRACES_ENDPOINT (OTLP HTTP endpoint for traces, e.g. https://host/insert/opentelemetry/v1/traces)
+#               BENCH_OTLP_LOGS_ENDPOINT (OTLP HTTP endpoint for logs, e.g. https://host/insert/opentelemetry/v1/logs)
 set -euo pipefail
 
 LABEL="$1"
@@ -17,6 +24,24 @@ LOG="${OUTPUT_DIR}/node.log"
 
 cleanup() {
   kill "$TAIL_PID" 2>/dev/null || true
+  # Stop tracy-capture first (SIGINT makes it disconnect and flush to disk)
+  # Must happen before killing reth, otherwise reth keeps streaming data.
+  if [ -n "${TRACY_PID:-}" ] && kill -0 "$TRACY_PID" 2>/dev/null; then
+    echo "Stopping tracy-capture..."
+    kill -INT "$TRACY_PID" 2>/dev/null || true
+    for i in $(seq 1 30); do
+      kill -0 "$TRACY_PID" 2>/dev/null || break
+      if [ $((i % 10)) -eq 0 ]; then
+        echo "Waiting for tracy-capture to finish writing... (${i}s)"
+      fi
+      sleep 1
+    done
+    if kill -0 "$TRACY_PID" 2>/dev/null; then
+      echo "tracy-capture still running after 30s, killing..."
+      kill -9 "$TRACY_PID" 2>/dev/null || true
+    fi
+    wait "$TRACY_PID" 2>/dev/null || true
+  fi
   if [ -n "${RETH_PID:-}" ] && sudo kill -0 "$RETH_PID" 2>/dev/null; then
     if [ "${BENCH_SAMPLY:-false}" = "true" ]; then
       # Send SIGINT to the inner reth process by exact name (not -f which
@@ -53,8 +78,14 @@ cleanup() {
   fi
 }
 TAIL_PID=
+TRACY_PID=
 trap cleanup EXIT
 
+# Clean up stale schelk state from a previous cancelled run.
+# If schelk thinks it's still mounted (e.g. a cancelled run skipped cleanup),
+# recover first to reset state.
+sudo schelk recover -y -k || true
+
 # Mount
 sudo schelk mount -y
 sync
@@ -73,6 +104,8 @@ if [ "${BENCH_CORES:-0}" -gt 0 ] && [ "$BENCH_CORES" -lt "$MAX_RETH" ]; then
 fi
 RETH_CPUS="1-${MAX_RETH}"
 
+BIG_BLOCKS="${BENCH_BIG_BLOCKS:-false}"
+
 RETH_ARGS=(
   node
   --datadir "$DATADIR"
@@ -87,16 +120,60 @@ RETH_ARGS=(
   --no-persist-peers
 )
 
+# Big blocks mode requires the testing API and skip-invalid-transactions
+if [ "$BIG_BLOCKS" = "true" ]; then
+  RETH_ARGS+=(--http.api eth,net,web3,reth,testing --testing.skip-invalid-transactions)
+fi
+
+# Append per-label extra node args (baseline or feature)
+EXTRA_NODE_ARGS=""
+case "$LABEL" in
+  baseline*) EXTRA_NODE_ARGS="${BENCH_BASELINE_ARGS:-}" ;;
+  feature*)  EXTRA_NODE_ARGS="${BENCH_FEATURE_ARGS:-}" ;;
+esac
+if [ -n "$EXTRA_NODE_ARGS" ]; then
+  # Word-split the string into individual args
+  # shellcheck disable=SC2206
+  RETH_ARGS+=($EXTRA_NODE_ARGS)
+fi
+
+if [ -n "${BENCH_METRICS_ADDR:-}" ]; then
+  RETH_ARGS+=(--metrics "$BENCH_METRICS_ADDR")
+fi
+
+# OTLP traces and logs export
+if [ -n "${BENCH_OTLP_TRACES_ENDPOINT:-}" ]; then
+  RETH_ARGS+=(--tracing-otlp="${BENCH_OTLP_TRACES_ENDPOINT}" --tracing-otlp.service-name=reth-bench)
+fi
+if [ -n "${BENCH_OTLP_LOGS_ENDPOINT:-}" ]; then
+  RETH_ARGS+=(--logs-otlp="${BENCH_OTLP_LOGS_ENDPOINT}")
+fi
+
+# Tracy profiling: add --log.tracy flags and set environment
+if [ "${BENCH_TRACY:-off}" != "off" ]; then
+  RETH_ARGS+=(--log.tracy --log.tracy.filter "${BENCH_TRACY_FILTER:-debug}")
+  if [ "${BENCH_TRACY}" = "on" ]; then
+    export TRACY_NO_SYS_TRACE=1
+  elif [ "${BENCH_TRACY}" = "full" ]; then
+    export TRACY_SAMPLING_HZ="${BENCH_TRACY_SAMPLING_HZ:-1}"
+  fi
+fi
+
+SUDO_ENV=()
+if [ -n "${OTEL_RESOURCE_ATTRIBUTES:-}" ]; then
+  SUDO_ENV+=("OTEL_RESOURCE_ATTRIBUTES=${OTEL_RESOURCE_ATTRIBUTES}")
+fi
+
 if [ "${BENCH_SAMPLY:-false}" = "true" ]; then
   RETH_ARGS+=(--log.samply)
   SAMPLY="$(which samply)"
-  sudo taskset -c "$RETH_CPUS" nice -n -20 \
+  sudo env "${SUDO_ENV[@]}" taskset -c "$RETH_CPUS" nice -n -20 \
     "$SAMPLY" record --save-only --presymbolicate --rate 10000 \
     --output "$OUTPUT_DIR/samply-profile.json.gz" \
     -- "$BINARY" "${RETH_ARGS[@]}" \
     > "$LOG" 2>&1 &
 else
-  sudo taskset -c "$RETH_CPUS" nice -n -20 "$BINARY" "${RETH_ARGS[@]}" \
+  sudo env "${SUDO_ENV[@]}" taskset -c "$RETH_CPUS" nice -n -20 "$BINARY" "${RETH_ARGS[@]}" \
     > "$LOG" 2>&1 &
 fi
 
@@ -124,21 +201,65 @@ done
 # files are not root-owned (avoids EACCES on next checkout).
 BENCH_NICE="sudo nice -n -20 sudo -u $(id -un)"
 
-# Warmup
-$BENCH_NICE "$RETH_BENCH" new-payload-fcu \
-  --rpc-url "$BENCH_RPC_URL" \
-  --engine-rpc-url http://127.0.0.1:8551 \
-  --jwt-secret "$DATADIR/jwt.hex" \
-  --advance "${BENCH_WARMUP_BLOCKS:-50}" \
-  --reth-new-payload 2>&1 | sed -u "s/^/[bench] /"
+# Build optional flags
+EXTRA_BENCH_ARGS=()
+if [ "${BENCH_RETH_NEW_PAYLOAD:-true}" != "false" ]; then
+  EXTRA_BENCH_ARGS+=(--reth-new-payload)
+fi
+if [ -n "${BENCH_WAIT_TIME:-}" ]; then
+  EXTRA_BENCH_ARGS+=(--wait-time "$BENCH_WAIT_TIME")
+fi
 
-# Benchmark
-$BENCH_NICE "$RETH_BENCH" new-payload-fcu \
-  --rpc-url "$BENCH_RPC_URL" \
-  --engine-rpc-url http://127.0.0.1:8551 \
-  --jwt-secret "$DATADIR/jwt.hex" \
-  --advance "$BENCH_BLOCKS" \
-  --reth-new-payload \
-  --output "$OUTPUT_DIR" 2>&1 | sed -u "s/^/[bench] /"
+if [ "$BIG_BLOCKS" = "true" ]; then
+  # Big blocks mode: replay pre-generated payloads with gas ramp
+  BIG_BLOCKS_DIR="${BENCH_WORK_DIR}/big-blocks"
+  # Count gas ramp blocks for reporting
+  GAS_RAMP_COUNT=$(find "$BIG_BLOCKS_DIR/gas-ramp-dir" -name '*.json' | wc -l)
+  echo "$GAS_RAMP_COUNT" > "$OUTPUT_DIR/gas_ramp_blocks.txt"
+  echo "Gas ramp blocks: $GAS_RAMP_COUNT"
+
+  # Start tracy-capture so profile only covers the benchmark
+  if [ "${BENCH_TRACY:-off}" != "off" ]; then
+    echo "Starting tracy-capture..."
+    tracy-capture -f -o "$OUTPUT_DIR/tracy-profile.tracy" &
+    TRACY_PID=$!
+    sleep 0.5  # give tracy-capture time to connect
+  fi
+
+  echo "Running big blocks benchmark (replay-payloads)..."
+  $BENCH_NICE "$RETH_BENCH" replay-payloads \
+    "${EXTRA_BENCH_ARGS[@]}" \
+    --gas-ramp-dir "$BIG_BLOCKS_DIR/gas-ramp-dir" \
+    --payload-dir "$BIG_BLOCKS_DIR/payloads" \
+    --engine-rpc-url http://127.0.0.1:8551 \
+    --jwt-secret "$DATADIR/jwt.hex" \
+    --output "$OUTPUT_DIR" 2>&1 | sed -u "s/^/[bench] /"
+else
+  # Standard mode: warmup + new-payload-fcu
+  # Warmup
+  $BENCH_NICE "$RETH_BENCH" new-payload-fcu \
+    --rpc-url "$BENCH_RPC_URL" \
+    --engine-rpc-url http://127.0.0.1:8551 \
+    --jwt-secret "$DATADIR/jwt.hex" \
+    --advance "${BENCH_WARMUP_BLOCKS:-50}" \
+    "${EXTRA_BENCH_ARGS[@]}" 2>&1 | sed -u "s/^/[bench] /"
+
+  # Start tracy-capture after warmup so profile only covers the benchmark
+  if [ "${BENCH_TRACY:-off}" != "off" ]; then
+    echo "Starting tracy-capture..."
+    tracy-capture -f -o "$OUTPUT_DIR/tracy-profile.tracy" &
+    TRACY_PID=$!
+    sleep 0.5  # give tracy-capture time to connect
+  fi
+
+  # Benchmark
+  $BENCH_NICE "$RETH_BENCH" new-payload-fcu \
+    --rpc-url "$BENCH_RPC_URL" \
+    --engine-rpc-url http://127.0.0.1:8551 \
+    --jwt-secret "$DATADIR/jwt.hex" \
+    --advance "$BENCH_BLOCKS" \
+    "${EXTRA_BENCH_ARGS[@]}" \
+    --output "$OUTPUT_DIR" 2>&1 | sed -u "s/^/[bench] /"
+fi
 
 # cleanup runs via trap

.github/scripts/bench-reth-summary.py

@@ -107,6 +107,10 @@ def compute_stats(combined: list[dict]) -> dict:
             mgas_s_values.append(r["gas_used"] / lat_s / 1_000_000)
     mean_mgas_s = sum(mgas_s_values) / len(mgas_s_values) if mgas_s_values else 0
 
+    total_latencies_ms = [r["total_latency_us"] / 1_000 for r in combined]
+    wall_clock_s = sum(total_latencies_ms) / 1_000
+    mean_total_lat_ms = sum(total_latencies_ms) / n
+
     return {
         "n": n,
         "mean_ms": mean_lat,
@@ -115,6 +119,8 @@ def compute_stats(combined: list[dict]) -> dict:
         "p90_ms": percentile(sorted_lat, 90),
         "p99_ms": percentile(sorted_lat, 99),
         "mean_mgas_s": mean_mgas_s,
+        "wall_clock_s": wall_clock_s,
+        "mean_total_lat_ms": mean_total_lat_ms,
     }
 
 
@@ -139,13 +145,14 @@ def compute_wait_stats(combined: list[dict], field: str) -> dict:
 
 def _paired_data(
     baseline: list[dict], feature: list[dict]
-) -> tuple[list[tuple[float, float]], list[float], list[float]]:
+) -> tuple[list[tuple[float, float]], list[float], list[float], list[float]]:
     """Match blocks and return paired latencies and per-block diffs.
 
     Returns:
         pairs: list of (baseline_ms, feature_ms) tuples
         lat_diffs_ms: list of feature − baseline latency diffs in ms
         mgas_diffs: list of feature − baseline Mgas/s diffs
+        total_lat_diffs_ms: list of feature − baseline total latency diffs in ms
     """
     baseline_by_block = {r["block_number"]: r for r in baseline}
     feature_by_block = {r["block_number"]: r for r in feature}
@@ -154,6 +161,7 @@ def _paired_data(
     pairs = []
     lat_diffs_ms = []
     mgas_diffs = []
+    total_lat_diffs_ms = []
     for bn in common_blocks:
         b = baseline_by_block[bn]
         f = feature_by_block[bn]
@@ -168,7 +176,10 @@ def _paired_data(
                 f["gas_used"] / f_lat_s / 1_000_000
                 - b["gas_used"] / b_lat_s / 1_000_000
             )
-    return pairs, lat_diffs_ms, mgas_diffs
+        total_lat_diffs_ms.append(
+            f["total_latency_us"] / 1_000 - b["total_latency_us"] / 1_000
+        )
+    return pairs, lat_diffs_ms, mgas_diffs, total_lat_diffs_ms
 
 
 def compute_paired_stats(
@@ -183,12 +194,14 @@ def compute_paired_stats(
     all_pairs = []
     all_lat_diffs = []
     all_mgas_diffs = []
+    all_total_lat_diffs = []
     blocks_per_pair = []
     for baseline, feature in zip(baseline_runs, feature_runs):
-        pairs, lat_diffs, mgas_diffs = _paired_data(baseline, feature)
+        pairs, lat_diffs, mgas_diffs, total_lat_diffs = _paired_data(baseline, feature)
         all_pairs.extend(pairs)
         all_lat_diffs.extend(lat_diffs)
         all_mgas_diffs.extend(mgas_diffs)
+        all_total_lat_diffs.extend(total_lat_diffs)
         blocks_per_pair.append(len(pairs))
 
     if not all_lat_diffs:
@@ -227,6 +240,11 @@ def compute_paired_stats(
     mgas_se = std_mgas_diff / math.sqrt(len(all_mgas_diffs)) if all_mgas_diffs else 0.0
     mgas_ci = T_CRITICAL * mgas_se
 
+    mean_total_diff = sum(all_total_lat_diffs) / len(all_total_lat_diffs) if all_total_lat_diffs else 0.0
+    std_total_diff = stddev(all_total_lat_diffs, mean_total_diff) if len(all_total_lat_diffs) > 1 else 0.0
+    total_se = std_total_diff / math.sqrt(len(all_total_lat_diffs)) if all_total_lat_diffs else 0.0
+    wall_clock_ci_ms = T_CRITICAL * total_se
+
     return {
         "n": n,
         "mean_diff_ms": mean_diff,
@@ -239,6 +257,7 @@ def compute_paired_stats(
         "p99_ci_ms": (p99_boot[hi] - p99_boot[lo]) / 2,
         "mean_mgas_diff": mean_mgas_diff,
         "mgas_ci": mgas_ci,
+        "wall_clock_ci_ms": wall_clock_ci_ms,
         "blocks": max(blocks_per_pair),
     }
 
@@ -267,6 +286,10 @@ def fmt_mgas(v: float) -> str:
     return f"{v:.2f}"
 
 
+def fmt_s(v: float) -> str:
+    return f"{v:.2f}s"
+
+
 def significance(pct: float, ci_pct: float, lower_is_better: bool) -> str:
     """Return significance label: 'good', 'bad', or 'neutral'."""
     significant = abs(pct) > ci_pct
@@ -304,6 +327,7 @@ def compute_changes(
         ("p90", "p90_ms", "p90_ci_ms", "p90_ms", True),
         ("p99", "p99_ms", "p99_ci_ms", "p99_ms", True),
         ("mgas_s", "mean_mgas_s", "mgas_ci", "mean_mgas_s", False),
+        ("wall_clock", "wall_clock_s", "wall_clock_ci_ms", "mean_total_lat_ms", True),
     ]
     changes = {}
     for name, stat_key, ci_key, base_key, lower_is_better in metrics:
@@ -326,6 +350,7 @@ def generate_comparison_table(
     baseline_name: str,
     feature_name: str,
     feature_sha: str,
+    big_blocks: bool = False,
 ) -> str:
     """Generate a markdown comparison table between baseline and feature."""
     n = paired["blocks"]
@@ -335,6 +360,7 @@ def generate_comparison_table(
 
     mean_pct = pct(run1["mean_ms"], run2["mean_ms"])
     gas_pct = pct(run1["mean_mgas_s"], run2["mean_mgas_s"])
+    wall_pct = pct(run1["wall_clock_s"], run2["wall_clock_s"])
 
     p50_pct = pct(run1["p50_ms"], run2["p50_ms"])
     p90_pct = pct(run1["p90_ms"], run2["p90_ms"])
@@ -348,6 +374,7 @@ def generate_comparison_table(
     # CI as a percentage of baseline mean
     lat_ci_pct = paired["ci_ms"] / run1["mean_ms"] * 100.0 if run1["mean_ms"] > 0 else 0.0
     mgas_ci_pct = paired["mgas_ci"] / run1["mean_mgas_s"] * 100.0 if run1["mean_mgas_s"] > 0 else 0.0
+    wall_ci_pct = paired["wall_clock_ci_ms"] / run1["mean_total_lat_ms"] * 100.0 if run1["mean_total_lat_ms"] > 0 else 0.0
 
     base_url = f"https://github.com/{repo}/commit"
     baseline_label = f"[`{baseline_name}`]({base_url}/{baseline_ref})"
@@ -362,8 +389,9 @@ def generate_comparison_table(
         f"| P90 | {fmt_ms(run1['p90_ms'])} | {fmt_ms(run2['p90_ms'])} | {change_str(p90_pct, p90_ci_pct, lower_is_better=True)} |",
         f"| P99 | {fmt_ms(run1['p99_ms'])} | {fmt_ms(run2['p99_ms'])} | {change_str(p99_pct, p99_ci_pct, lower_is_better=True)} |",
         f"| Mgas/s | {fmt_mgas(run1['mean_mgas_s'])} | {fmt_mgas(run2['mean_mgas_s'])} | {change_str(gas_pct, mgas_ci_pct, lower_is_better=False)} |",
+        f"| Wall Clock | {fmt_s(run1['wall_clock_s'])} | {fmt_s(run2['wall_clock_s'])} | {change_str(wall_pct, wall_ci_pct, lower_is_better=True)} |",
         "",
-        f"*{n} blocks*",
+        f"*{n} {'big blocks' if big_blocks else 'blocks'}*",
     ]
     return "\n".join(lines)
 
@@ -394,6 +422,7 @@ def generate_markdown(
     summary: dict, comparison_table: str,
     wait_time_tables: list[str] | None = None,
     behind_baseline: int = 0, repo: str = "", baseline_ref: str = "", baseline_name: str = "",
+    grafana_url: str | None = None,
 ) -> str:
     """Generate a markdown comment body."""
     lines = ["## Benchmark Results", ""]
@@ -413,6 +442,9 @@ def generate_markdown(
                 lines.append(table)
                 lines.append("")
         lines.append("</details>")
+    if grafana_url:
+        lines.append("")
+        lines.append(f"**[Grafana Dashboard]({grafana_url})**")
     return "\n".join(lines)
 
 
@@ -439,6 +471,9 @@ def main():
     parser.add_argument("--feature-name", "--branch-name", default=None, help="Feature branch name")
     parser.add_argument("--feature-ref", "--branch-sha", "--feature-sha", default=None, help="Feature commit SHA")
     parser.add_argument("--behind-baseline", "--behind-main", type=int, default=0, help="Commits behind baseline")
+    parser.add_argument("--big-blocks", action="store_true", default=False, help="Big blocks mode")
+    parser.add_argument("--gas-ramp-blocks", type=int, default=0, help="Number of gas ramp blocks (big blocks mode)")
+    parser.add_argument("--grafana-url", default=None, help="Grafana dashboard URL for this benchmark run")
     args = parser.parse_args()
 
     if len(args.baseline_csv) != len(args.feature_csv):
@@ -487,6 +522,7 @@ def main():
         baseline_name=baseline_name,
         feature_name=feature_name,
         feature_sha=feature_sha,
+        big_blocks=args.big_blocks,
     )
     print(f"Generated comparison ({paired_stats['n']} paired blocks, "
           f"mean diff {paired_stats['mean_diff_ms']:+.3f}ms ± {paired_stats['ci_ms']:.3f}ms)")
@@ -517,6 +553,8 @@ def main():
 
     summary = {
         "blocks": paired_stats["blocks"],
+        "big_blocks": args.big_blocks,
+        "gas_ramp_blocks": args.gas_ramp_blocks,
         "baseline": {
             "name": baseline_name,
             "ref": baseline_ref,
@@ -542,6 +580,7 @@ def main():
         repo=args.repo,
         baseline_ref=baseline_ref,
         baseline_name=baseline_name,
+        grafana_url=args.grafana_url,
     )
 
     with open(args.output_markdown, "w") as f:

.github/scripts/bench-slack-notify.js

@@ -7,6 +7,8 @@
 //   BENCH_PR               – PR number (may be empty)
 //   BENCH_ACTOR            – GitHub user who triggered the bench
 //   BENCH_JOB_URL          – URL to the Actions job page
+//   BENCH_BASELINE_ARGS    – Extra CLI args for the baseline reth node
+//   BENCH_FEATURE_ARGS     – Extra CLI args for the feature reth node
 //   BENCH_SAMPLY           – 'true' if samply profiling was enabled
 //
 // Usage from actions/github-script:
@@ -68,6 +70,7 @@ function buildSuccessBlocks({ summary, prNumber, actor, actorSlackId, jobUrl, re
 
   function fmtMs(v) { return v.toFixed(2) + 'ms'; }
   function fmtMgas(v) { return v.toFixed(2); }
+  function fmtS(v) { return v.toFixed(2) + 's'; }
   function fmtChange(ch) {
     if (!ch.pct && !ch.ci_pct) return ' ';
     const pctStr = `${ch.pct >= 0 ? '+' : ''}${ch.pct.toFixed(2)}%`;
@@ -117,12 +120,27 @@ function buildSuccessBlocks({ summary, prNumber, actor, actorSlackId, jobUrl, re
   if (fl1) featureLine += ` | <${fl1}|Samply 1>`;
   if (fl2) featureLine += ` | <${fl2}|Samply 2>`;
 
-  const warmup = summary.warmup_blocks || process.env.BENCH_WARMUP_BLOCKS || '';
-  const countsLine = warmup
-    ? `*Warmup:* ${warmup} | *Blocks:* ${summary.blocks}`
-    : `*Blocks:* ${summary.blocks}`;
+  const cores = process.env.BENCH_CORES || '0';
+  const countsParts = [];
+  if (summary.big_blocks) {
+    const gasRamp = summary.gas_ramp_blocks || 0;
+    if (gasRamp > 0) countsParts.push(`*Gas Ramp:* ${gasRamp}`);
+    countsParts.push(`*Big Blocks:* ${summary.blocks}`);
+  } else {
+    const warmup = summary.warmup_blocks || process.env.BENCH_WARMUP_BLOCKS || '';
+    if (warmup) countsParts.push(`*Warmup:* ${warmup}`);
+    countsParts.push(`*Blocks:* ${summary.blocks}`);
+  }
+  if (cores !== '0') countsParts.push(`*Cores:* ${cores}`);
+  const countsLine = countsParts.join(' | ');
 
-  const sectionText = [metaParts.join(' | '), '', baselineLine, featureLine, countsLine].join('\n');
+  const baselineArgs = process.env.BENCH_BASELINE_ARGS || '';
+  const featureArgs = process.env.BENCH_FEATURE_ARGS || '';
+  const argsLines = [];
+  if (baselineArgs) argsLines.push(`*Baseline Args:* \`${baselineArgs}\``);
+  if (featureArgs) argsLines.push(`*Feature Args:* \`${featureArgs}\``);
+
+  const sectionText = [metaParts.join(' | '), '', baselineLine, featureLine, ...argsLines, countsLine].join('\n');
 
   // Action buttons
   const diffUrl = `https://github.com/${repo}/compare/${summary.baseline.ref}...${summary.feature.ref}`;
@@ -166,6 +184,7 @@ function buildSuccessBlocks({ summary, prNumber, actor, actorSlackId, jobUrl, re
         [cell('P90'),      cell(fmtMs(b.p90_ms)),       cell(fmtMs(f.p90_ms)),       cell(fmtChange(c.p90))],
         [cell('P99'),      cell(fmtMs(b.p99_ms)),       cell(fmtMs(f.p99_ms)),       cell(fmtChange(c.p99))],
         [cell('Mgas/s'),   cell(fmtMgas(b.mean_mgas_s)), cell(fmtMgas(f.mean_mgas_s)), cell(fmtChange(c.mgas_s))],
+        [cell('Wall Clock'), cell(fmtS(b.wall_clock_s)), cell(fmtS(f.wall_clock_s)), cell(fmtChange(c.wall_clock))],
       ],
     },
     {

.github/scripts/bench-slack-users.json

@@ -9,5 +9,16 @@
   "gakonst": "U092SEPDM40",
   "Rjected": "U09F6SCKRGT",
   "DaniPopes": "U09FAT8EK2A",
-  "emmajam": "U0A34UN92HW"
+  "emmajam": "U0A34UN92HW",
+  "onbjerg": "U09FB0UK5AA",
+  "fgimenez": "U09G3GP7CSU",
+  "rakita": "U09FB3Z2M7Y",
+  "jxom": "U09F72MG083",
+  "tmm": "U0AD0U8E88N",
+  "pepyakin": "U0A7HKMGEHJ",
+  "grandizzy": "U09F8DBDDRT",
+  "SuperFluffy": "U095BKHB2Q4",
+  "kamsz": "U0A2563UBRD",
+  "zerosnacks": "U09FARPMN74",
+  "samczsun": "U096R14E4H3"
 }

.github/scripts/build_pgo_bolt.sh

@@ -0,0 +1,414 @@
+#!/usr/bin/env bash
+#
+# Full PGO+BOLT optimized build for reth using real reth-bench workloads.
+#
+# Phases:
+#   1. Build PGO-instrumented reth, run reth-bench → collect PGO profiles
+#   2. Build BOLT-instrumented reth (with PGO), run reth-bench → collect BOLT profiles
+#   3. Build final PGO+BOLT optimized binary
+#
+# Required environment variables:
+#   DATADIR    - Path to reth datadir (must already contain chain data)
+#   RPC_URL    - Source RPC URL for reth-bench to fetch payloads from
+#
+# Optional environment variables:
+#   PGO_BLOCKS      - Number of blocks for PGO profiling (default: 20)
+#   BOLT_BLOCKS     - Number of blocks for BOLT profiling (default: 20)
+#   SKIP_BOLT       - Temporarily skip BOLT phases (default: false)
+#   STRIP_SYMBOLS   - Strip debug symbols from output binary (default: true)
+#   COLLECT_PGO_ONLY - Stop after producing merged.profdata (default: false)
+#   PGO_PROFDATA    - Path to pre-collected merged.profdata (optional)
+#   PROFILE         - Cargo profile (default: maxperf-symbols)
+#   FEATURES        - Cargo features (default: jemalloc,asm-keccak,min-debug-logs)
+#   TARGET          - Target triple (default: auto-detected)
+#   EXTRA_RUSTFLAGS - Additional RUSTFLAGS (e.g. -C target-cpu=x86-64-v3)
+#
+# Output:
+#   target/$PROFILE_DIR/reth  — final optimized binary
+set -euo pipefail
+
+gha_section_start() {
+    local title="$1"
+    if [ -n "${GITHUB_ACTIONS:-}" ]; then
+        echo "::group::$title"
+    else
+        echo ""
+        echo "=== $title ==="
+    fi
+}
+
+gha_section_end() {
+    if [ -n "${GITHUB_ACTIONS:-}" ]; then
+        echo "::endgroup::"
+    fi
+}
+
+cd "$(dirname "$0")/../.."
+
+# ── Configuration ──────────────────────────────────────────────────────────────
+PGO_BLOCKS="${PGO_BLOCKS:-20}"
+BOLT_BLOCKS="${BOLT_BLOCKS:-20}"
+SKIP_BOLT="${SKIP_BOLT:-false}"
+STRIP_SYMBOLS="${STRIP_SYMBOLS:-true}"
+COLLECT_PGO_ONLY="${COLLECT_PGO_ONLY:-false}"
+PROFILE="${PROFILE:-maxperf-symbols}"
+FEATURES="${FEATURES:-jemalloc,asm-keccak,min-debug-logs}"
+TARGET="${TARGET:-$(rustc -Vv | grep host | cut -d' ' -f2)}"
+BASE_RUSTFLAGS="${RUSTFLAGS:-}"
+EXTRA_RUSTFLAGS="${EXTRA_RUSTFLAGS:-}"
+COMBINED_RUSTFLAGS="$BASE_RUSTFLAGS $EXTRA_RUSTFLAGS"
+PGO_PROFDATA="${PGO_PROFDATA:-}"
+DATADIR="${DATADIR:-}"
+RPC_URL="${RPC_URL:-}"
+
+SKIP_BOLT_BOOL=false
+if [[ "${SKIP_BOLT,,}" == "true" || "$SKIP_BOLT" == "1" ]]; then
+    SKIP_BOLT_BOOL=true
+fi
+
+STRIP_SYMBOLS_BOOL=false
+if [[ "${STRIP_SYMBOLS,,}" == "true" || "$STRIP_SYMBOLS" == "1" ]]; then
+    STRIP_SYMBOLS_BOOL=true
+fi
+
+COLLECT_PGO_ONLY_BOOL=false
+if [[ "${COLLECT_PGO_ONLY,,}" == "true" || "$COLLECT_PGO_ONLY" == "1" ]]; then
+    COLLECT_PGO_ONLY_BOOL=true
+fi
+
+USE_PRECOLLECTED_PGO=false
+if [ -n "$PGO_PROFDATA" ]; then
+    if [ ! -f "$PGO_PROFDATA" ]; then
+        echo "error: PGO_PROFDATA points to a missing file: $PGO_PROFDATA"
+        exit 1
+    fi
+    USE_PRECOLLECTED_PGO=true
+fi
+
+NEEDS_BENCH_WORKLOAD=true
+if [ "$USE_PRECOLLECTED_PGO" = true ] && [ "$SKIP_BOLT_BOOL" = true ]; then
+    NEEDS_BENCH_WORKLOAD=false
+fi
+
+if [ "$NEEDS_BENCH_WORKLOAD" = true ]; then
+    : "${DATADIR:?DATADIR must be set to the reth data directory}"
+    : "${RPC_URL:?RPC_URL must be set}"
+fi
+
+if [[ "$PROFILE" == dev ]]; then
+    PROFILE_DIR=debug
+else
+    PROFILE_DIR=$PROFILE
+fi
+
+MANIFEST_PATH="bin/reth"
+
+LLVM_VERSION=$(rustc -Vv | grep -oP 'LLVM version: \K\d+')
+PGO_DIR="$PWD/target/pgo-profiles"
+BOLT_DIR="$PWD/target/bolt-profiles"
+CARGO_ARGS=(--profile "$PROFILE" --features "$FEATURES" --manifest-path "$MANIFEST_PATH/Cargo.toml" --bin "reth" --locked)
+
+# Enable debug symbols for BOLT (requires symbols to reorder code).
+# Strip them at the end.
+PROFILE_UPPER=$(echo "$PROFILE" | tr '[:lower:]-' '[:upper:]_')
+export "CARGO_PROFILE_${PROFILE_UPPER}_STRIP=debuginfo"
+
+gha_section_start "Full PGO+BOLT Build"
+echo "Binary:      reth"
+echo "Manifest:    $MANIFEST_PATH"
+echo "Target:      $TARGET"
+echo "Profile:     $PROFILE"
+echo "Features:    $FEATURES"
+echo "LLVM:        $LLVM_VERSION"
+echo "PGO blocks:  $PGO_BLOCKS"
+echo "BOLT blocks: $BOLT_BLOCKS"
+echo "Skip BOLT:   $SKIP_BOLT"
+echo "Strip symbols: $STRIP_SYMBOLS"
+echo "Collect only: $COLLECT_PGO_ONLY"
+echo "PGO profdata: ${PGO_PROFDATA:-<collect with reth-bench>}"
+echo "RUSTFLAGS:   ${BASE_RUSTFLAGS:-<unset>}"
+echo "EXTRA_RUSTFLAGS: ${EXTRA_RUSTFLAGS:-<unset>}"
+if [ "$NEEDS_BENCH_WORKLOAD" = true ]; then
+    echo "Datadir:     $DATADIR"
+    echo "RPC URL:     $RPC_URL"
+else
+    echo "Datadir:     <not required>"
+    echo "RPC URL:     <not required>"
+fi
+gha_section_end
+
+# ── Prerequisites ──────────────────────────────────────────────────────────────
+gha_section_start "Installing prerequisites"
+rustup component add llvm-tools-preview
+
+LLVM_PROFDATA=$(find "$(rustc --print sysroot)" -name llvm-profdata -type f | head -1)
+if [ -z "$LLVM_PROFDATA" ]; then
+    echo "error: llvm-profdata not found"
+    exit 1
+fi
+
+install_bolt() {
+    if command -v llvm-bolt &>/dev/null; then
+        echo "BOLT already installed"
+        return
+    fi
+    echo "Installing BOLT from apt.llvm.org..."
+    wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc >/dev/null
+    CODENAME=$(lsb_release -cs)
+    echo "deb http://apt.llvm.org/$CODENAME/ llvm-toolchain-$CODENAME-$LLVM_VERSION main" | sudo tee /etc/apt/sources.list.d/llvm.list >/dev/null
+    sudo apt-get update -qq
+    sudo apt-get install -y -qq "bolt-$LLVM_VERSION"
+    sudo ln -sf "/usr/bin/llvm-bolt-$LLVM_VERSION" /usr/local/bin/llvm-bolt
+    sudo ln -sf "/usr/bin/merge-fdata-$LLVM_VERSION" /usr/local/bin/merge-fdata
+}
+if [ "$SKIP_BOLT_BOOL" = true ]; then
+    echo "Skipping BOLT installation (SKIP_BOLT=$SKIP_BOLT)"
+else
+    install_bolt
+fi
+gha_section_end
+
+if [ "$NEEDS_BENCH_WORKLOAD" = true ]; then
+    # Build reth-bench once (non-instrumented) — reused for both phases.
+    gha_section_start "Building reth-bench"
+    RUSTFLAGS="$COMBINED_RUSTFLAGS" \
+        cargo build --profile "$PROFILE" --features "$FEATURES" \
+        --manifest-path bin/reth-bench/Cargo.toml --bin reth-bench --locked
+    RETH_BENCH_BIN="$(find target -name reth-bench -type f -executable | head -1)"
+    echo "reth-bench: $RETH_BENCH_BIN"
+    gha_section_end
+else
+    gha_section_start "Building reth-bench"
+    echo "Skipping reth-bench build (pre-collected PGO with SKIP_BOLT=true)"
+    gha_section_end
+fi
+
+# ── Helpers ────────────────────────────────────────────────────────────────────
+RETH_PID=
+cleanup() {
+    if [ -n "${RETH_PID:-}" ] && kill -0 "$RETH_PID" 2>/dev/null; then
+        echo "Stopping reth (pid $RETH_PID)..."
+        sudo kill "$RETH_PID" 2>/dev/null || true
+        for i in $(seq 1 60); do
+            sudo kill -0 "$RETH_PID" 2>/dev/null || break
+            if [ $((i % 10)) -eq 0 ]; then
+                echo "  waiting... (${i}s)"
+            fi
+            sleep 1
+        done
+        sudo kill -9 "$RETH_PID" 2>/dev/null || true
+    fi
+}
+trap cleanup EXIT
+
+# Start reth, wait for RPC, run reth-bench, then stop reth.
+# Arguments: $1 = reth binary path, $2 = number of blocks, $3 = log label
+run_bench_workload() {
+    local reth_bin="$1" blocks="$2" label="$3"
+    local http_port=8545 authrpc_port=8551
+
+    echo "--- Starting reth ($label) ---"
+    sudo "$reth_bin" node \
+        --datadir "$DATADIR" \
+        --log.file.directory "/tmp/reth-${label}-logs" \
+        --engine.accept-execution-requests-hash \
+        --http --http.port "$http_port" \
+        --authrpc.port "$authrpc_port" \
+        --disable-discovery --no-persist-peers \
+        > "/tmp/reth-${label}.log" 2>&1 &
+    RETH_PID=$!
+
+    echo "Waiting for reth RPC..."
+    for i in $(seq 1 120); do
+        if curl -sf "http://127.0.0.1:$http_port" -X POST \
+            -H 'Content-Type: application/json' \
+            -d '{"jsonrpc":"2.0","method":"eth_blockNumber","params":[],"id":1}' \
+            > /dev/null 2>&1; then
+            echo "reth is ready after ${i}s"
+            break
+        fi
+        if [ "$i" -eq 120 ]; then
+            echo "error: reth failed to start within 120s"
+            cat "/tmp/reth-${label}.log"
+            exit 1
+        fi
+        sleep 1
+    done
+
+    echo "Running reth-bench ($blocks blocks)..."
+    "$RETH_BENCH_BIN" new-payload-fcu \
+        --rpc-url "$RPC_URL" \
+        --engine-rpc-url "http://127.0.0.1:$authrpc_port" \
+        --jwt-secret "$DATADIR/jwt.hex" \
+        --advance "$blocks" \
+        --reth-new-payload 2>&1 | sed -u "s/^/[$label] /"
+
+    echo "Stopping reth ($label)..."
+    sudo kill "$RETH_PID" 2>/dev/null || true
+    for i in $(seq 1 60); do
+        sudo kill -0 "$RETH_PID" 2>/dev/null || break
+        sleep 1
+    done
+    sudo kill -9 "$RETH_PID" 2>/dev/null || true
+    RETH_PID=
+}
+
+publish_binary() {
+    local source_bin="$1"
+    for out in "target/$TARGET/$PROFILE_DIR" "target/$PROFILE_DIR"; do
+        local destination="$out/reth"
+        mkdir -p "$out"
+        # Skip copying when source and destination resolve to the same inode.
+        if [ -e "$destination" ] && [ "$source_bin" -ef "$destination" ]; then
+            continue
+        fi
+        cp "$source_bin" "$destination"
+    done
+}
+
+if [ "$USE_PRECOLLECTED_PGO" = true ]; then
+    gha_section_start "Phase 1: Using Pre-Collected PGO Profile"
+    rm -rf "$PGO_DIR"
+    mkdir -p "$PGO_DIR"
+    cp "$PGO_PROFDATA" "$PGO_DIR/merged.profdata"
+    echo "Using pre-collected profile: $PGO_PROFDATA"
+    echo "PGO profile: $PGO_DIR/merged.profdata ($(ls -lh "$PGO_DIR/merged.profdata" | awk '{print $5}'))"
+    gha_section_end
+else
+    # ── Phase 1: PGO profile collection ───────────────────────────────────────
+    gha_section_start "Phase 1: PGO Profile Collection"
+
+    rm -rf "$PGO_DIR"
+    mkdir -p "$PGO_DIR"
+
+    echo "Building PGO-instrumented binary..."
+    RUSTFLAGS="-Cprofile-generate=$PGO_DIR -Crelocation-model=pic $COMBINED_RUSTFLAGS" \
+        cargo build "${CARGO_ARGS[@]}" --target "$TARGET"
+
+    PGO_RETH_BIN="$PWD/target/$TARGET/$PROFILE_DIR/reth"
+    echo "Instrumented binary: $PGO_RETH_BIN ($(ls -lh "$PGO_RETH_BIN" | awk '{print $5}'))"
+
+    run_bench_workload "$PGO_RETH_BIN" "$PGO_BLOCKS" "pgo"
+
+    # Fix ownership if reth ran as root.
+    sudo chown -R "$(id -un):$(id -gn)" "$PGO_DIR" 2>/dev/null || true
+
+    # Merge PGO profiles.
+    echo "Merging PGO profiles..."
+    PROFRAW_COUNT=$(find "$PGO_DIR" -name '*.profraw' | wc -l)
+    echo "Found $PROFRAW_COUNT .profraw files"
+    if [ "$PROFRAW_COUNT" -eq 0 ]; then
+        echo "error: no .profraw files — instrumented binary did not produce profiles"
+        exit 1
+    fi
+    "$LLVM_PROFDATA" merge -o "$PGO_DIR/merged.profdata" "$PGO_DIR"/*.profraw
+    echo "PGO profile: $PGO_DIR/merged.profdata ($(ls -lh "$PGO_DIR/merged.profdata" | awk '{print $5}'))"
+    gha_section_end
+fi
+
+if [ "$COLLECT_PGO_ONLY_BOOL" = true ]; then
+    gha_section_start "PGO Collection Complete"
+    echo "COLLECT_PGO_ONLY=true, skipping PGO/BOLT optimized binary build"
+    echo "Profile: $PGO_DIR/merged.profdata"
+    gha_section_end
+    exit 0
+fi
+
+if [ "$SKIP_BOLT_BOOL" = true ]; then
+    gha_section_start "BOLT Phase Skipped"
+    echo "SKIP_BOLT=$SKIP_BOLT, building PGO-only binary"
+    echo "Building PGO-optimized binary..."
+    RUSTFLAGS="-Cprofile-use=$PGO_DIR/merged.profdata $COMBINED_RUSTFLAGS" \
+        cargo build "${CARGO_ARGS[@]}" --target "$TARGET"
+
+    BUILT_BIN="$PWD/target/$TARGET/$PROFILE_DIR/reth"
+    if [ "$STRIP_SYMBOLS_BOOL" = true ]; then
+        echo "Stripping debug symbols..."
+        strip "$BUILT_BIN"
+    else
+        echo "Skipping strip (STRIP_SYMBOLS=$STRIP_SYMBOLS)"
+    fi
+    publish_binary "$BUILT_BIN"
+    gha_section_end
+else
+    # ── Phase 2: BOLT profile collection (with PGO) ──────────────────────────
+    gha_section_start "Phase 2: BOLT Profile Collection (with PGO)"
+
+    rm -rf "$BOLT_DIR"
+    mkdir -p "$BOLT_DIR"
+
+    echo "Building BOLT-instrumented binary with PGO..."
+    # --emit-relocs preserves relocation entries in the binary, required by llvm-bolt -instrument
+    RUSTFLAGS="-Cprofile-use=$PGO_DIR/merged.profdata -Clink-arg=-Wl,--emit-relocs $COMBINED_RUSTFLAGS" \
+        cargo build "${CARGO_ARGS[@]}" --target "$TARGET"
+
+    # Instrument with BOLT
+    BUILT_BIN="$PWD/target/$TARGET/$PROFILE_DIR/reth"
+    BOLT_INSTRUMENTED_BIN="$BUILT_BIN-bolt-instrumented"
+
+    echo "Instrumenting binary with BOLT..."
+    # --skip-funcs: skip compiler-generated drop_in_place functions that BOLT can't handle
+    # as split functions in relocation mode (triggered by --emit-relocs)
+    llvm-bolt "$BUILT_BIN" \
+        -instrument \
+        --instrumentation-file-append-pid \
+        --instrumentation-file="$BOLT_DIR/prof" \
+        --skip-funcs='.*drop_in_place.*' \
+        -o "$BOLT_INSTRUMENTED_BIN"
+    echo "BOLT-instrumented binary: $BOLT_INSTRUMENTED_BIN ($(ls -lh "$BOLT_INSTRUMENTED_BIN" | awk '{print $5}'))"
+
+    run_bench_workload "$BOLT_INSTRUMENTED_BIN" "$BOLT_BLOCKS" "bolt"
+
+    # Fix ownership for BOLT profiles
+    sudo chown -R "$(id -un):$(id -gn)" "$BOLT_DIR" 2>/dev/null || true
+
+    # Merge BOLT profiles
+    echo "Merging BOLT profiles..."
+    FDATA_COUNT=$(find "$BOLT_DIR" -name '*.fdata' | wc -l)
+    echo "Found $FDATA_COUNT .fdata files"
+    if [ "$FDATA_COUNT" -eq 0 ]; then
+        echo "error: no .fdata files — BOLT-instrumented binary did not produce profiles"
+        exit 1
+    fi
+    merge-fdata "$BOLT_DIR"/*.fdata > "$BOLT_DIR/merged.fdata"
+    echo "BOLT profile: $BOLT_DIR/merged.fdata ($(ls -lh "$BOLT_DIR/merged.fdata" | awk '{print $5}'))"
+    gha_section_end
+
+    # ── Phase 3: Final optimized build ───────────────────────────────────────
+    gha_section_start "Phase 3: Final PGO+BOLT Optimized Build"
+
+    echo "Building PGO-optimized binary..."
+    # --emit-relocs preserves relocation entries in the binary, required by llvm-bolt for code reordering
+    RUSTFLAGS="-Cprofile-use=$PGO_DIR/merged.profdata -Clink-arg=-Wl,--emit-relocs $COMBINED_RUSTFLAGS" \
+        cargo build "${CARGO_ARGS[@]}" --target "$TARGET"
+
+    BUILT_BIN="$PWD/target/$TARGET/$PROFILE_DIR/reth"
+    OPTIMIZED_BIN="$BUILT_BIN-bolt-optimized"
+
+    echo "Optimizing with BOLT..."
+    llvm-bolt "$BUILT_BIN" \
+        -o "$OPTIMIZED_BIN" \
+        --data "$BOLT_DIR/merged.fdata" \
+        -reorder-blocks=ext-tsp \
+        -reorder-functions=cdsort \
+        -split-functions \
+        -split-all-cold \
+        -dyno-stats \
+        -icf=1 \
+        -use-gnu-stack \
+        --skip-funcs='.*drop_in_place.*'
+
+    if [ "$STRIP_SYMBOLS_BOOL" = true ]; then
+        echo "Stripping debug symbols..."
+        strip "$OPTIMIZED_BIN"
+    else
+        echo "Skipping strip (STRIP_SYMBOLS=$STRIP_SYMBOLS)"
+    fi
+    publish_binary "$OPTIMIZED_BIN"
+    gha_section_end
+fi
+
+gha_section_start "Build Complete"
+ls -lh "target/$PROFILE_DIR/reth"
+echo "Output: target/$PROFILE_DIR/reth"
+gha_section_end

.github/scripts/hive/expected_failures.yaml

@@ -16,28 +16,11 @@ rpc-compat:
   # syncing mode, the test expects syncing to be false on start
   - eth_syncing/check-syncing (reth)
 
-# no fix due to https://github.com/paradigmxyz/reth/issues/8732
-engine-withdrawals:
-  - Withdrawals Fork On Genesis (Paris) (reth)
-  - Withdrawals Fork on Block 1 (Paris) (reth)
-  - Withdrawals Fork on Block 2 (Paris) (reth)
-  - Withdrawals Fork on Block 3 (Paris) (reth)
-  - Withdraw to a single account (Paris) (reth)
-  - Withdraw to two accounts (Paris) (reth)
-  - Withdraw many accounts (Paris) (reth)
-  - Withdraw zero amount (Paris) (reth)
-  - Empty Withdrawals (Paris) (reth)
-  - Corrupted Block Hash Payload (INVALID) (Paris) (reth)
-  - Withdrawals Fork on Canonical Block 8 / Side Block 7 - 10 Block Re-Org (Paris) (reth)
+engine-withdrawals: [ ]
 
 engine-api: [ ]
 
-# no fix due to https://github.com/paradigmxyz/reth/issues/8732
-engine-cancun:
-  - Invalid PayloadAttributes, Missing BeaconRoot, Syncing=True (Cancun) (reth)
-  # the test fails with older versions of the code for which it passed before, probably related to changes
-  # in hive or its dependencies
-  - Blob Transaction Ordering, Multiple Clients (Cancun) (reth)
+engine-cancun: [ ]
 
 sync: [ ]
 
@@ -49,7 +32,7 @@ engine-auth: [ ]
 #   The test artificially creates an empty account with storage, then tests EIP-7610's behavior.
 #   On mainnet, ~25 such accounts exist as contract addresses (derived from keccak(prefix, caller,
 #   nonce/salt), not from public keys). No private key exists for contract addresses. To trigger
-#   this with EIP-7702, you'd need to recover a private key from one of the already deployed contract addresses - mathematically impossible. 
+#   this with EIP-7702, you'd need to recover a private key from one of the already deployed contract addresses - mathematically impossible.
 #
 # tests/paris/eip7610_create_collision/test_initcollision.py::test_init_collision_*
 #   Requires hash collision on create2 address to target already deployed accounts with storage.

.github/scripts/hive/ignored_tests.yaml

@@ -11,17 +11,6 @@
 #
 # When a test should no longer be ignored, remove it from this list.
 
-# flaky
-engine-withdrawals:
-  - Withdrawals Fork on Block 1 - 8 Block Re-Org NewPayload (Paris) (reth)
-  - Withdrawals Fork on Block 8 - 10 Block Re-Org NewPayload (Paris) (reth)
-  - Withdrawals Fork on Canonical Block 8 / Side Block 7 - 10 Block Re-Org (Paris) (reth)
-  # P2P sync timing issue in hive Docker environment: secondary client returns SYNCING but
-  # peer discovery/connection doesn't complete within the timeout when running with
-  # --sim.parallelism 16. Not a correctness bug, purely a CI timing issue.
-  - Sync after 2 blocks - Withdrawals on Block 2 - Multiple Withdrawal Accounts (Paris) (reth)
-  - Sync after 2 blocks - Withdrawals on Block 2 - Multiple Withdrawal Accounts - No Transactions (Paris) (reth)
-  - Sync after 128 blocks - Withdrawals on Block 2 - Multiple Withdrawal Accounts (Paris) (reth)
 engine-cancun:
   - Transaction Re-Org, New Payload on Revert Back (Cancun) (reth)
   - Transaction Re-Org, Re-Org to Different Block (Cancun) (reth)

.github/workflows/bench.yml

@@ -7,16 +7,12 @@
 # same block range (snapshot recovered between runs) to compare performance.
 
 on:
-  # TODO: Disabled temporarily for https://github.com/CodSpeedHQ/runner/issues/55
-  # merge_group:
-  push:
-    branches: [main]
   issue_comment:
-    types: [created, edited]
+    types: [created]
   workflow_dispatch:
     inputs:
       blocks:
-        description: "Number of blocks to benchmark"
+        description: "Number of blocks to benchmark (or 'big' for big blocks mode)"
         required: false
         default: "500"
         type: string
@@ -35,16 +31,46 @@ on:
         required: false
         default: ""
         type: string
+      wait_time:
+        description: "Fixed wait time between blocks (e.g. 500ms, 1s)"
+        required: false
+        default: ""
+        type: string
+      baseline_args:
+        description: "Extra CLI args for the baseline reth node"
+        required: false
+        default: ""
+        type: string
+      feature_args:
+        description: "Extra CLI args for the feature reth node"
+        required: false
+        default: ""
+        type: string
       samply:
         description: "Enable samply profiling"
         required: false
         default: "false"
         type: boolean
+      reth_newPayload:
+        description: "Use reth_newPayload RPC (server-side timing)"
+        required: false
+        default: "true"
+        type: boolean
       cores:
         description: "Limit reth to N CPU cores (0 = all available)"
         required: false
         default: "0"
         type: string
+      no_slack:
+        description: "Suppress Slack notifications for benchmark results"
+        required: false
+        default: "true"
+        type: boolean
+      abba:
+        description: "Run ABBA (BFFB) interleaved order; false = single AB pass"
+        required: false
+        default: "true"
+        type: boolean
 
 env:
   CARGO_TERM_COLOR: always
@@ -60,46 +86,6 @@ permissions:
   pull-requests: write
 
 jobs:
-  codspeed:
-    if: github.event_name == 'push'
-    runs-on: depot-ubuntu-latest
-    concurrency:
-      group: bench-codspeed-${{ github.head_ref || github.run_id }}
-      cancel-in-progress: true
-    strategy:
-      matrix:
-        partition: [1, 2]
-        total_partitions: [2]
-        include:
-          - partition: 1
-            crates: "-p reth-primitives -p reth-trie-common -p reth-trie-sparse"
-          - partition: 2
-            crates: "-p reth-trie"
-    name: codspeed (${{ matrix.partition }}/${{ matrix.total_partitions }})
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: true
-          ref: ${{ github.event_name == 'issue_comment' && format('refs/pull/{0}/merge', github.event.issue.number) || '' }}
-      - uses: rui314/setup-mold@v1
-      - uses: dtolnay/rust-toolchain@stable
-      - uses: mozilla-actions/sccache-action@v0.0.9
-      - uses: Swatinem/rust-cache@v2
-        with:
-          cache-on-failure: true
-      - name: Install cargo-codspeed
-        uses: taiki-e/install-action@v2
-        with:
-          tool: cargo-codspeed
-      - name: Build the benchmark target(s)
-        run: cargo codspeed build --profile profiling --features test-utils ${{ matrix.crates }}
-      - name: Run the benchmarks
-        uses: CodSpeedHQ/action@v4
-        with:
-          run: cargo codspeed run ${{ matrix.crates }}
-          mode: instrumentation
-          token: ${{ secrets.CODSPEED_TOKEN }}
-
   reth-bench-ack:
     if: |
       (github.event_name == 'issue_comment' && github.event.issue.pull_request && (startsWith(github.event.comment.body, '@decofe bench') || startsWith(github.event.comment.body, 'derek bench'))) ||
@@ -116,7 +102,14 @@ jobs:
       baseline-name: ${{ steps.args.outputs.baseline-name }}
       feature-name: ${{ steps.args.outputs.feature-name }}
       samply: ${{ steps.args.outputs.samply }}
+      no-slack: ${{ steps.args.outputs.no-slack }}
       cores: ${{ steps.args.outputs.cores }}
+      big-blocks: ${{ steps.args.outputs.big-blocks }}
+      reth-new-payload: ${{ steps.args.outputs.reth-new-payload }}
+      wait-time: ${{ steps.args.outputs.wait-time }}
+      baseline-args: ${{ steps.args.outputs.baseline-args }}
+      feature-args: ${{ steps.args.outputs.feature-args }}
+      abba: ${{ steps.args.outputs.abba }}
       comment-id: ${{ steps.ack.outputs.comment-id }}
     steps:
       - name: Check org membership
@@ -144,7 +137,7 @@ jobs:
         with:
           github-token: ${{ secrets.DEREK_PAT }}
           script: |
-            let pr, actor, blocks, warmup, baseline, feature, samply, cores;
+            let pr, actor, blocks, warmup, baseline, feature, samply, cores, bigBlocks;
 
             if (context.eventName === 'workflow_dispatch') {
               actor = '${{ github.actor }}';
@@ -153,7 +146,14 @@ jobs:
               baseline = '${{ github.event.inputs.baseline }}';
               feature = '${{ github.event.inputs.feature }}';
               samply = '${{ github.event.inputs.samply }}' === 'true' ? 'true' : 'false';
+              var noSlack = '${{ github.event.inputs.no_slack }}' !== 'false' ? 'true' : 'false';
               cores = '${{ github.event.inputs.cores }}' || '0';
+              bigBlocks = blocks === 'big' ? 'true' : 'false';
+              var rethNewPayload = '${{ github.event.inputs.reth_newPayload }}' !== 'false' ? 'true' : 'false';
+              var abba = '${{ github.event.inputs.abba }}' !== 'false' ? 'true' : 'false';
+              var waitTime = '${{ github.event.inputs.wait_time }}' || '';
+              var baselineNodeArgs = '${{ github.event.inputs.baseline_args }}' || '';
+              var featureNodeArgs = '${{ github.event.inputs.feature_args }}' || '';
 
               // Find PR for the selected branch
               const branch = '${{ github.ref_name }}';
@@ -173,37 +173,75 @@ jobs:
               actor = context.payload.comment.user.login;
 
               const body = context.payload.comment.body.trim();
-              const intArgs = new Set(['blocks', 'warmup', 'cores']);
+              const intArgs = new Set(['warmup', 'cores']);
+              const intOrKeywordArgs = new Map([['blocks', new Set(['big'])]]);
               const refArgs = new Set(['baseline', 'feature']);
-              const boolArgs = new Set(['samply']);
-              const defaults = { blocks: '500', warmup: '100', baseline: '', feature: '', samply: 'false', cores: '0' };
+              const boolArgs = new Set(['samply', 'no-slack']);
+              const boolDefaultTrue = new Set(['reth_newPayload', 'abba']);
+              const durationArgs = new Set(['wait-time']);
+              const stringArgs = new Set(['baseline-args', 'feature-args']);
+              const defaults = { blocks: '500', warmup: '100', baseline: '', feature: '', samply: 'false', 'no-slack': 'false', cores: '0', reth_newPayload: 'true', abba: 'true', 'wait-time': '', 'baseline-args': '', 'feature-args': '' };
               const unknown = [];
               const invalid = [];
               const args = body.replace(/^(?:@decofe|derek) bench\s*/, '');
-              for (const part of args.split(/\s+/).filter(Boolean)) {
+              // Parse args, handling quoted values like key="value with spaces"
+              const parts = [];
+              const argRegex = /(\S+?="[^"]*"|\S+?='[^']*'|\S+)/g;
+              let m;
+              while ((m = argRegex.exec(args)) !== null) parts.push(m[1]);
+              for (const part of parts) {
                 const eq = part.indexOf('=');
                 if (eq === -1) {
                   if (boolArgs.has(part)) {
                     defaults[part] = 'true';
+                  } else if (boolDefaultTrue.has(part)) {
+                    defaults[part] = 'true';
                   } else {
                     unknown.push(part);
                   }
                   continue;
                 }
                 const key = part.slice(0, eq);
-                const value = part.slice(eq + 1);
-                if (intArgs.has(key)) {
+                let value = part.slice(eq + 1);
+                // Strip surrounding quotes
+                if ((value.startsWith('"') && value.endsWith('"')) || (value.startsWith("'") && value.endsWith("'"))) {
+                  value = value.slice(1, -1);
+                }
+                if (boolDefaultTrue.has(key)) {
+                  if (value === 'true' || value === 'false') {
+                    defaults[key] = value;
+                  } else {
+                    invalid.push(`\`${key}=${value}\` (must be true or false)`);
+                  }
+                } else if (durationArgs.has(key)) {
+                  if (/^\d+(ms|s|m)$/.test(value)) {
+                    defaults[key] = value;
+                  } else {
+                    invalid.push(`\`${key}=${value}\` (must be a duration like 500ms, 1s, 2m)`);
+                  }
+                } else if (intArgs.has(key)) {
                   if (!/^\d+$/.test(value)) {
                     invalid.push(`\`${key}=${value}\` (must be a positive integer)`);
                   } else {
                     defaults[key] = value;
                   }
+                } else if (intOrKeywordArgs.has(key)) {
+                  const keywords = intOrKeywordArgs.get(key);
+                  if (keywords.has(value)) {
+                    defaults[key] = value;
+                  } else if (/^\d+$/.test(value)) {
+                    defaults[key] = value;
+                  } else {
+                    invalid.push(`\`${key}=${value}\` (must be a positive integer or one of: ${[...keywords].join(', ')})`);
+                  }
                 } else if (refArgs.has(key)) {
                   if (!value) {
                     invalid.push(`\`${key}=\` (must be a git ref)`);
                   } else {
                     defaults[key] = value;
                   }
+                } else if (stringArgs.has(key)) {
+                  defaults[key] = value;
                 } else {
                   unknown.push(key);
                 }
@@ -212,7 +250,7 @@ jobs:
               if (unknown.length) errors.push(`Unknown argument(s): \`${unknown.join('`, `')}\``);
               if (invalid.length) errors.push(`Invalid value(s): ${invalid.join(', ')}`);
               if (errors.length) {
-                const msg = `❌ **Invalid bench command**\n\n${errors.join('\n')}\n\n**Usage:** \`@decofe bench [blocks=N] [warmup=N] [baseline=REF] [feature=REF] [samply] [cores=N]\``;
+                const msg = `❌ **Invalid bench command**\n\n${errors.join('\n')}\n\n**Usage:** \`@decofe bench [blocks=N|big] [warmup=N] [baseline=REF] [feature=REF] [samply] [no-slack] [cores=N] [reth_newPayload=true|false] [abba=true|false] [wait-time=DURATION] [baseline-args="..."] [feature-args="..."]\``;
                 await github.rest.issues.createComment({
                   owner: context.repo.owner,
                   repo: context.repo.repo,
@@ -227,7 +265,14 @@ jobs:
               baseline = defaults.baseline;
               feature = defaults.feature;
               samply = defaults.samply;
+              var noSlack = defaults['no-slack'];
               cores = defaults.cores;
+              bigBlocks = blocks === 'big' ? 'true' : 'false';
+              var rethNewPayload = defaults.reth_newPayload;
+              var abba = defaults.abba;
+              var waitTime = defaults['wait-time'];
+              var baselineNodeArgs = defaults['baseline-args'];
+              var featureNodeArgs = defaults['feature-args'];
             }
 
             // Resolve display names for baseline/feature
@@ -255,7 +300,14 @@ jobs:
             core.setOutput('baseline-name', baselineName);
             core.setOutput('feature-name', featureName);
             core.setOutput('samply', samply);
+            core.setOutput('no-slack', noSlack);
             core.setOutput('cores', cores);
+            core.setOutput('big-blocks', bigBlocks);
+            core.setOutput('reth-new-payload', rethNewPayload);
+            core.setOutput('wait-time', waitTime);
+            core.setOutput('baseline-args', baselineNodeArgs);
+            core.setOutput('feature-args', featureNodeArgs);
+            core.setOutput('abba', abba);
 
       - name: Acknowledge request
         id: ack
@@ -295,7 +347,6 @@ jobs:
                 });
                 allRuns.push(...r);
               }
-              // Only count runs that trigger reth-bench (not push-triggered codspeed runs)
               const benchRuns = allRuns.filter(r => r.event === 'issue_comment' || r.event === 'workflow_dispatch');
               const thisRun = benchRuns.find(r => r.id === context.runId);
               const thisCreatedAt = thisRun ? new Date(thisRun.created_at) : new Date();
@@ -314,10 +365,24 @@ jobs:
             const baseline = '${{ steps.args.outputs.baseline-name }}';
             const feature = '${{ steps.args.outputs.feature-name }}';
             const samply = '${{ steps.args.outputs.samply }}' === 'true';
+            const noSlack = '${{ steps.args.outputs.no-slack }}' === 'true';
+            const bigBlocks = '${{ steps.args.outputs.big-blocks }}' === 'true';
             const samplyNote = samply ? ', samply: `enabled`' : '';
+            const noSlackNote = noSlack ? ', no-slack' : '';
             const cores = '${{ steps.args.outputs.cores }}';
             const coresNote = cores && cores !== '0' ? `, cores: \`${cores}\`` : '';
-            const config = `**Config:** ${blocks} blocks, ${warmup} warmup blocks, baseline: \`${baseline}\`, feature: \`${feature}\`${samplyNote}${coresNote}`;
+            const rethNP = '${{ steps.args.outputs.reth-new-payload }}' !== 'false';
+            const rethNPNote = !rethNP ? ', reth_newPayload: `disabled`' : '';
+            const abbaEnabled = '${{ steps.args.outputs.abba }}' !== 'false';
+            const abbaNote = !abbaEnabled ? ', abba: `disabled`' : '';
+            const waitTimeVal = '${{ steps.args.outputs.wait-time }}';
+            const waitTimeNote = waitTimeVal ? `, wait-time: \`${waitTimeVal}\`` : '';
+            const baselineArgsVal = '${{ steps.args.outputs.baseline-args }}';
+            const baselineArgsNote = baselineArgsVal ? `, baseline-args: \`${baselineArgsVal}\`` : '';
+            const featureArgsVal = '${{ steps.args.outputs.feature-args }}';
+            const featureArgsNote = featureArgsVal ? `, feature-args: \`${featureArgsVal}\`` : '';
+            const blocksDesc = bigBlocks ? 'blocks: `big`' : `${blocks} blocks, ${warmup} warmup blocks`;
+            const config = `**Config:** ${blocksDesc}, baseline: \`${baseline}\`, feature: \`${feature}\`${samplyNote}${noSlackNote}${coresNote}${rethNPNote}${abbaNote}${waitTimeNote}${baselineArgsNote}${featureArgsNote}`;
 
             const { data: comment } = await github.rest.issues.createComment({
               owner: context.repo.owner,
@@ -342,10 +407,24 @@ jobs:
             const baseline = '${{ steps.args.outputs.baseline-name }}';
             const feature = '${{ steps.args.outputs.feature-name }}';
             const samply = '${{ steps.args.outputs.samply }}' === 'true';
+            const noSlack = '${{ steps.args.outputs.no-slack }}' === 'true';
+            const bigBlocks = '${{ steps.args.outputs.big-blocks }}' === 'true';
             const samplyNote = samply ? ', samply: `enabled`' : '';
+            const noSlackNote = noSlack ? ', no-slack' : '';
             const cores = '${{ steps.args.outputs.cores }}';
             const coresNote = cores && cores !== '0' ? `, cores: \`${cores}\`` : '';
-            const config = `**Config:** ${blocks} blocks, ${warmup} warmup blocks, baseline: \`${baseline}\`, feature: \`${feature}\`${samplyNote}${coresNote}`;
+            const rethNP = '${{ steps.args.outputs.reth-new-payload }}' !== 'false';
+            const rethNPNote = !rethNP ? ', reth_newPayload: `disabled`' : '';
+            const abbaEnabled = '${{ steps.args.outputs.abba }}' !== 'false';
+            const abbaNote = !abbaEnabled ? ', abba: `disabled`' : '';
+            const waitTimeVal = '${{ steps.args.outputs.wait-time }}';
+            const waitTimeNote = waitTimeVal ? `, wait-time: \`${waitTimeVal}\`` : '';
+            const baselineArgsVal = '${{ steps.args.outputs.baseline-args }}';
+            const baselineArgsNote = baselineArgsVal ? `, baseline-args: \`${baselineArgsVal}\`` : '';
+            const featureArgsVal = '${{ steps.args.outputs.feature-args }}';
+            const featureArgsNote = featureArgsVal ? `, feature-args: \`${featureArgsVal}\`` : '';
+            const blocksDesc = bigBlocks ? 'blocks: `big`' : `${blocks} blocks, ${warmup} warmup blocks`;
+            const config = `**Config:** ${blocksDesc}, baseline: \`${baseline}\`, feature: \`${feature}\`${samplyNote}${noSlackNote}${coresNote}${rethNPNote}${abbaNote}${waitTimeNote}${baselineArgsNote}${featureArgsNote}`;
             const runUrl = `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
 
             const numRunners = parseInt(process.env.BENCH_RUNNERS) || 1;
@@ -409,8 +488,21 @@ jobs:
       BENCH_WARMUP_BLOCKS: ${{ needs.reth-bench-ack.outputs.warmup }}
       BENCH_SAMPLY: ${{ needs.reth-bench-ack.outputs.samply }}
       BENCH_CORES: ${{ needs.reth-bench-ack.outputs.cores }}
+      BENCH_BIG_BLOCKS: ${{ needs.reth-bench-ack.outputs.big-blocks }}
+      BENCH_RETH_NEW_PAYLOAD: ${{ needs.reth-bench-ack.outputs.reth-new-payload }}
+      BENCH_WAIT_TIME: ${{ needs.reth-bench-ack.outputs.wait-time }}
+      BENCH_BASELINE_ARGS: ${{ needs.reth-bench-ack.outputs.baseline-args }}
+      BENCH_FEATURE_ARGS: ${{ needs.reth-bench-ack.outputs.feature-args }}
+      BENCH_ABBA: ${{ needs.reth-bench-ack.outputs.abba }}
       BENCH_COMMENT_ID: ${{ needs.reth-bench-ack.outputs.comment-id }}
+      BENCH_NO_SLACK: ${{ needs.reth-bench-ack.outputs.no-slack }}
+      BENCH_METRICS_ADDR: "127.0.0.1:9100"
+      BENCH_OTLP_TRACES_ENDPOINT: ${{ secrets.BENCH_OTLP_TRACES_ENDPOINT }}
+      BENCH_OTLP_LOGS_ENDPOINT: ${{ secrets.BENCH_OTLP_LOGS_ENDPOINT }}
     steps:
+      - name: Clean up previous bench-work
+        run: sudo rm -rf "$BENCH_WORK_DIR" 2>/dev/null || true
+
       - name: Resolve checkout ref
         id: checkout-ref
         uses: actions/github-script@v8
@@ -425,13 +517,11 @@ jobs:
               repo: context.repo.repo,
               pull_number: parseInt(process.env.BENCH_PR),
             });
-            // For closed/merged PRs, the merge ref doesn't exist — use head SHA
-            if (pr.state !== 'open') {
-              core.info(`PR #${process.env.BENCH_PR} is ${pr.state}, using head SHA ${pr.head.sha}`);
-              core.setOutput('ref', pr.head.sha);
-            } else {
-              core.setOutput('ref', `refs/pull/${process.env.BENCH_PR}/merge`);
-            }
+            // Always use head SHA — the merge ref (refs/pull/N/merge) may not
+            // exist if the PR has conflicts, was force-pushed, or was
+            // merged/closed between this step and checkout.
+            core.info(`PR #${process.env.BENCH_PR} (${pr.state}), using head SHA ${pr.head.sha}`);
+            core.setOutput('ref', pr.head.sha);
 
       - uses: actions/checkout@v6
         with:
@@ -459,10 +549,24 @@ jobs:
             const baseline = '${{ needs.reth-bench-ack.outputs.baseline-name }}';
             const feature = '${{ needs.reth-bench-ack.outputs.feature-name }}';
             const samply = process.env.BENCH_SAMPLY === 'true';
+            const noSlack = process.env.BENCH_NO_SLACK === 'true';
+            const bigBlocks = process.env.BENCH_BIG_BLOCKS === 'true';
             const samplyNote = samply ? ', samply: `enabled`' : '';
+            const noSlackNote = noSlack ? ', no-slack' : '';
             const cores = process.env.BENCH_CORES || '0';
             const coresNote = cores && cores !== '0' ? `, cores: \`${cores}\`` : '';
-            core.exportVariable('BENCH_CONFIG', `**Config:** ${blocks} blocks, ${warmup} warmup blocks, baseline: \`${baseline}\`, feature: \`${feature}\`${samplyNote}${coresNote}`);
+            const rethNP = (process.env.BENCH_RETH_NEW_PAYLOAD || 'true') !== 'false';
+            const rethNPNote = !rethNP ? ', reth_newPayload: `disabled`' : '';
+            const abbaEnabled = (process.env.BENCH_ABBA || 'true') !== 'false';
+            const abbaNote = !abbaEnabled ? ', abba: `disabled`' : '';
+            const waitTimeVal = process.env.BENCH_WAIT_TIME || '';
+            const waitTimeNote = waitTimeVal ? `, wait-time: \`${waitTimeVal}\`` : '';
+            const baselineArgsVal = process.env.BENCH_BASELINE_ARGS || '';
+            const baselineArgsNote = baselineArgsVal ? `, baseline-args: \`${baselineArgsVal}\`` : '';
+            const featureArgsVal = process.env.BENCH_FEATURE_ARGS || '';
+            const featureArgsNote = featureArgsVal ? `, feature-args: \`${featureArgsVal}\`` : '';
+            const blocksDesc = bigBlocks ? 'blocks: `big`' : `${blocks} blocks, ${warmup} warmup blocks`;
+            core.exportVariable('BENCH_CONFIG', `**Config:** ${blocksDesc}, baseline: \`${baseline}\`, feature: \`${feature}\`${samplyNote}${noSlackNote}${coresNote}${rethNPNote}${abbaNote}${waitTimeNote}${baselineArgsNote}${featureArgsNote}`);
 
             const { buildBody } = require('./.github/scripts/bench-update-status.js');
             await github.rest.issues.updateComment({
@@ -722,6 +826,45 @@ jobs:
           rm -rf "$BENCH_WORK_DIR"
           mkdir -p "$BENCH_WORK_DIR"
 
+      - name: Download big blocks
+        if: env.BENCH_BIG_BLOCKS == 'true'
+        run: |
+          set -euo pipefail
+          MC="mc --config-dir /home/ubuntu/.mc"
+          BUCKET="minio/reth-snapshots/reth-1-minimal-nightly-previous-big-blocks.tar.zst"
+          BIG_BLOCKS_DIR="${BENCH_WORK_DIR}/big-blocks"
+          rm -rf "$BIG_BLOCKS_DIR"; mkdir -p "$BIG_BLOCKS_DIR"
+          echo "Downloading big blocks from $BUCKET..."
+          $MC cat "$BUCKET" | pzstd -d -p 6 | tar -xf - -C "$BIG_BLOCKS_DIR"
+          echo "Big blocks downloaded to $BIG_BLOCKS_DIR"
+          # Verify expected directory structure
+          if [ ! -d "$BIG_BLOCKS_DIR/gas-ramp-dir" ] || [ ! -d "$BIG_BLOCKS_DIR/payloads" ]; then
+            echo "::error::Big blocks archive missing expected gas-ramp-dir/ or payloads/ directories"
+            ls -laR "$BIG_BLOCKS_DIR"
+            exit 1
+          fi
+          echo "Payload files: $(find "$BIG_BLOCKS_DIR/payloads" -name '*.json' | wc -l)"
+
+      - name: Start metrics proxy
+        run: |
+          BENCH_ID="ci-${{ github.run_id }}"
+          BENCH_REFERENCE_EPOCH=$(date +%s)
+          echo "BENCH_ID=${BENCH_ID}" >> "$GITHUB_ENV"
+          echo "BENCH_REFERENCE_EPOCH=${BENCH_REFERENCE_EPOCH}" >> "$GITHUB_ENV"
+
+          LABELS_FILE="/tmp/bench-metrics-labels.json"
+          echo '{}' > "$LABELS_FILE"
+          echo "BENCH_LABELS_FILE=${LABELS_FILE}" >> "$GITHUB_ENV"
+
+          python3 .github/scripts/bench-metrics-proxy.py \
+            --labels "$LABELS_FILE" \
+            --upstream "http://${BENCH_METRICS_ADDR}/" \
+            --subnet 10.10.0.0/24 \
+            --port 9090 &
+          PROXY_PID=$!
+          echo "BENCH_METRICS_PROXY_PID=${PROXY_PID}" >> "$GITHUB_ENV"
+          echo "Metrics proxy started (PID $PROXY_PID)"
+
       - name: Update status (running benchmarks)
         if: success() && env.BENCH_COMMENT_ID
         uses: actions/github-script@v8
@@ -735,19 +878,62 @@ jobs:
       # thermal drift and cache warming.
       - name: "Run benchmark: baseline (1/2)"
         id: run-baseline-1
-        run: taskset -c 0 .github/scripts/bench-reth-run.sh baseline ../reth-baseline/target/profiling/reth "$BENCH_WORK_DIR/baseline-1"
+        env:
+          BASELINE_REF: ${{ steps.refs.outputs.baseline-ref }}
+          OTEL_RESOURCE_ATTRIBUTES: "benchmark_id=${{ env.BENCH_ID }},benchmark_run=baseline-1,run_type=baseline,git_ref=${{ steps.refs.outputs.baseline-ref }}"
+        run: |
+          cat > "$BENCH_LABELS_FILE" <<LABELS
+          {"benchmark_run":"baseline-1","run_type":"baseline","git_ref":"${BASELINE_REF}","bench_sha":"${BASELINE_REF}","benchmark_id":"${BENCH_ID}","run_start_epoch":"$(date +%s)","reference_epoch":"${BENCH_REFERENCE_EPOCH}"}
+          LABELS
+          taskset -c 0 .github/scripts/bench-reth-run.sh baseline ../reth-baseline/target/profiling/reth "$BENCH_WORK_DIR/baseline-1"
 
       - name: "Run benchmark: feature (1/2)"
         id: run-feature-1
-        run: taskset -c 0 .github/scripts/bench-reth-run.sh feature ../reth-feature/target/profiling/reth "$BENCH_WORK_DIR/feature-1"
+        env:
+          FEATURE_REF: ${{ steps.refs.outputs.feature-ref }}
+          OTEL_RESOURCE_ATTRIBUTES: "benchmark_id=${{ env.BENCH_ID }},benchmark_run=feature-1,run_type=feature,git_ref=${{ steps.refs.outputs.feature-ref }}"
+        run: |
+          cat > "$BENCH_LABELS_FILE" <<LABELS
+          {"benchmark_run":"feature-1","run_type":"feature","git_ref":"${FEATURE_REF}","bench_sha":"${FEATURE_REF}","benchmark_id":"${BENCH_ID}","run_start_epoch":"$(date +%s)","reference_epoch":"${BENCH_REFERENCE_EPOCH}"}
+          LABELS
+          taskset -c 0 .github/scripts/bench-reth-run.sh feature ../reth-feature/target/profiling/reth "$BENCH_WORK_DIR/feature-1"
 
       - name: "Run benchmark: feature (2/2)"
         id: run-feature-2
-        run: taskset -c 0 .github/scripts/bench-reth-run.sh feature ../reth-feature/target/profiling/reth "$BENCH_WORK_DIR/feature-2"
+        env:
+          FEATURE_REF: ${{ steps.refs.outputs.feature-ref }}
+          OTEL_RESOURCE_ATTRIBUTES: "benchmark_id=${{ env.BENCH_ID }},benchmark_run=feature-2,run_type=feature,git_ref=${{ steps.refs.outputs.feature-ref }}"
+        run: |
+          cat > "$BENCH_LABELS_FILE" <<LABELS
+          {"benchmark_run":"feature-2","run_type":"feature","git_ref":"${FEATURE_REF}","bench_sha":"${FEATURE_REF}","benchmark_id":"${BENCH_ID}","run_start_epoch":"$(date +%s)","reference_epoch":"${BENCH_REFERENCE_EPOCH}"}
+          LABELS
+          taskset -c 0 .github/scripts/bench-reth-run.sh feature ../reth-feature/target/profiling/reth "$BENCH_WORK_DIR/feature-2"
 
       - name: "Run benchmark: baseline (2/2)"
         id: run-baseline-2
-        run: taskset -c 0 .github/scripts/bench-reth-run.sh baseline ../reth-baseline/target/profiling/reth "$BENCH_WORK_DIR/baseline-2"
+        env:
+          BASELINE_REF: ${{ steps.refs.outputs.baseline-ref }}
+          OTEL_RESOURCE_ATTRIBUTES: "benchmark_id=${{ env.BENCH_ID }},benchmark_run=baseline-2,run_type=baseline,git_ref=${{ steps.refs.outputs.baseline-ref }}"
+        run: |
+          LAST_RUN_START=$(date +%s)
+          echo "BENCH_LAST_RUN_START=${LAST_RUN_START}" >> "$GITHUB_ENV"
+          cat > "$BENCH_LABELS_FILE" <<LABELS
+          {"benchmark_run":"baseline-2","run_type":"baseline","git_ref":"${BASELINE_REF}","bench_sha":"${BASELINE_REF}","benchmark_id":"${BENCH_ID}","run_start_epoch":"${LAST_RUN_START}","reference_epoch":"${BENCH_REFERENCE_EPOCH}"}
+          LABELS
+          taskset -c 0 .github/scripts/bench-reth-run.sh baseline ../reth-baseline/target/profiling/reth "$BENCH_WORK_DIR/baseline-2"
+
+      - name: Stop metrics proxy & generate Grafana URL
+        id: metrics
+        if: "!cancelled()"
+        run: |
+          kill "$BENCH_METRICS_PROXY_PID" 2>/dev/null || true
+
+          LAST_RUN_DURATION=$(( $(date +%s) - BENCH_LAST_RUN_START ))
+          FROM_MS=$(( BENCH_REFERENCE_EPOCH * 1000 ))
+          TO_MS=$(( (BENCH_REFERENCE_EPOCH + LAST_RUN_DURATION) * 1000 ))
+          GRAFANA_URL="https://tempoxyz.grafana.net/d/reth-bench-ghr/reth-bench-ghr?orgId=1&from=${FROM_MS}&to=${TO_MS}&timezone=browser&var-datasource=ef57fux92e9z4e&var-job=reth-bench&var-benchmark_id=${BENCH_ID}&var-benchmark_run=\$__all"
+          echo "grafana-url=${GRAFANA_URL}" >> "$GITHUB_OUTPUT"
+          echo "Grafana URL: ${GRAFANA_URL}"
 
       - name: Scan logs for errors
         if: "!cancelled()"
@@ -849,12 +1035,30 @@ jobs:
           SUMMARY_ARGS="$SUMMARY_ARGS --baseline-name ${BASELINE_NAME}"
           SUMMARY_ARGS="$SUMMARY_ARGS --feature-name ${FEATURE_NAME}"
           SUMMARY_ARGS="$SUMMARY_ARGS --feature-ref ${FEATURE_REF}"
-          SUMMARY_ARGS="$SUMMARY_ARGS --baseline-csv $BENCH_WORK_DIR/baseline-1/combined_latency.csv $BENCH_WORK_DIR/baseline-2/combined_latency.csv"
-          SUMMARY_ARGS="$SUMMARY_ARGS --feature-csv $BENCH_WORK_DIR/feature-1/combined_latency.csv $BENCH_WORK_DIR/feature-2/combined_latency.csv"
+          BASELINE_CSVS="$BENCH_WORK_DIR/baseline-1/combined_latency.csv"
+          FEATURE_CSVS="$BENCH_WORK_DIR/feature-1/combined_latency.csv"
+          if [ "${BENCH_ABBA:-true}" = "true" ]; then
+            BASELINE_CSVS="$BASELINE_CSVS $BENCH_WORK_DIR/baseline-2/combined_latency.csv"
+            FEATURE_CSVS="$FEATURE_CSVS $BENCH_WORK_DIR/feature-2/combined_latency.csv"
+          fi
+          SUMMARY_ARGS="$SUMMARY_ARGS --baseline-csv $BASELINE_CSVS"
+          SUMMARY_ARGS="$SUMMARY_ARGS --feature-csv $FEATURE_CSVS"
           SUMMARY_ARGS="$SUMMARY_ARGS --gas-csv $BENCH_WORK_DIR/feature-1/total_gas.csv"
           if [ "$BEHIND_BASELINE" -gt 0 ]; then
             SUMMARY_ARGS="$SUMMARY_ARGS --behind-baseline $BEHIND_BASELINE"
           fi
+          if [ "${BENCH_BIG_BLOCKS:-false}" = "true" ]; then
+            SUMMARY_ARGS="$SUMMARY_ARGS --big-blocks"
+            # Read gas ramp blocks count from first baseline run (same for all runs)
+            GAS_RAMP_FILE="$BENCH_WORK_DIR/baseline-1/gas_ramp_blocks.txt"
+            if [ -f "$GAS_RAMP_FILE" ]; then
+              SUMMARY_ARGS="$SUMMARY_ARGS --gas-ramp-blocks $(cat "$GAS_RAMP_FILE" | tr -d '[:space:]')"
+            fi
+          fi
+          GRAFANA_URL='${{ steps.metrics.outputs.grafana-url }}'
+          if [ -n "$GRAFANA_URL" ]; then
+            SUMMARY_ARGS="$SUMMARY_ARGS --grafana-url $GRAFANA_URL"
+          fi
           # shellcheck disable=SC2086
           python3 .github/scripts/bench-reth-summary.py $SUMMARY_ARGS
 
@@ -865,8 +1069,14 @@ jobs:
           FEATURE_NAME: ${{ steps.refs.outputs.feature-name }}
         run: |
           CHART_ARGS="--output-dir $BENCH_WORK_DIR/charts"
-          CHART_ARGS="$CHART_ARGS --feature $BENCH_WORK_DIR/feature-1/combined_latency.csv $BENCH_WORK_DIR/feature-2/combined_latency.csv"
-          CHART_ARGS="$CHART_ARGS --baseline $BENCH_WORK_DIR/baseline-1/combined_latency.csv $BENCH_WORK_DIR/baseline-2/combined_latency.csv"
+          FEATURE_CSVS="$BENCH_WORK_DIR/feature-1/combined_latency.csv"
+          BASELINE_CSVS="$BENCH_WORK_DIR/baseline-1/combined_latency.csv"
+          if [ "${BENCH_ABBA:-true}" = "true" ]; then
+            FEATURE_CSVS="$FEATURE_CSVS $BENCH_WORK_DIR/feature-2/combined_latency.csv"
+            BASELINE_CSVS="$BASELINE_CSVS $BENCH_WORK_DIR/baseline-2/combined_latency.csv"
+          fi
+          CHART_ARGS="$CHART_ARGS --feature $FEATURE_CSVS"
+          CHART_ARGS="$CHART_ARGS --baseline $BASELINE_CSVS"
           CHART_ARGS="$CHART_ARGS --baseline-name ${BASELINE_NAME}"
           CHART_ARGS="$CHART_ARGS --feature-name ${FEATURE_NAME}"
           # shellcheck disable=SC2086
@@ -874,7 +1084,7 @@ jobs:
 
       - name: Upload results
         if: "!cancelled()"
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         with:
           name: bench-reth-results
           path: ${{ env.BENCH_WORK_DIR }}
@@ -906,7 +1116,7 @@ jobs:
           rm -rf "${TMP_DIR}"
 
       - name: Compare & comment
-        if: success()
+        if: success() && env.BENCH_COMMENT_ID
         uses: actions/github-script@v8
         with:
           github-token: ${{ secrets.DEREK_PAT }}
@@ -942,7 +1152,8 @@ jobs:
 
             // Samply profile links (URLs point directly to Firefox Profiler)
             if (process.env.BENCH_SAMPLY === 'true') {
-              const runs = ['baseline-1', 'feature-1', 'feature-2', 'baseline-2'];
+              const abba = (process.env.BENCH_ABBA || 'true') !== 'false';
+              const runs = abba ? ['baseline-1', 'feature-1', 'feature-2', 'baseline-2'] : ['baseline-1', 'feature-1'];
               const links = [];
               for (const run of runs) {
                 try {
@@ -957,6 +1168,12 @@ jobs:
               }
             }
 
+            // Grafana dashboard link
+            const grafanaUrl = '${{ steps.metrics.outputs.grafana-url }}';
+            if (grafanaUrl) {
+              comment += `\n\n### Grafana Dashboard\n\n[View real-time metrics](${grafanaUrl})\n`;
+            }
+
             // Node errors (panics / ERROR logs)
             try {
               const errors = fs.readFileSync(process.env.BENCH_WORK_DIR + '/errors.md', 'utf8');
@@ -982,7 +1199,7 @@ jobs:
             }
 
       - name: Send Slack notification (success)
-        if: success()
+        if: success() && env.BENCH_NO_SLACK != 'true'
         uses: actions/github-script@v8
         env:
           SLACK_BENCH_BOT_TOKEN: ${{ secrets.SLACK_BENCH_BOT_TOKEN }}
@@ -998,12 +1215,13 @@ jobs:
         with:
           github-token: ${{ secrets.DEREK_PAT }}
           script: |
+            const abba = (process.env.BENCH_ABBA || 'true') !== 'false';
             const steps_status = [
               ['building binaries${{ steps.snapshot-check.outputs.needed == 'true' && ' & downloading snapshot' || '' }}', '${{ steps.build.outcome }}'],
               ['running baseline benchmark (1/2)', '${{ steps.run-baseline-1.outcome }}'],
               ['running feature benchmark (1/2)', '${{ steps.run-feature-1.outcome }}'],
-              ['running feature benchmark (2/2)', '${{ steps.run-feature-2.outcome }}'],
-              ['running baseline benchmark (2/2)', '${{ steps.run-baseline-2.outcome }}'],
+              ...(abba ? [['running feature benchmark (2/2)', '${{ steps.run-feature-2.outcome }}']] : []),
+              ...(abba ? [['running baseline benchmark (2/2)', '${{ steps.run-baseline-2.outcome }}']] : []),
             ];
             const failed = steps_status.find(([, o]) => o === 'failure');
             const failedStep = failed ? failed[0] : 'unknown step';
@@ -1032,12 +1250,13 @@ jobs:
           SLACK_BENCH_CHANNEL: ${{ secrets.SLACK_BENCH_CHANNEL }}
         with:
           script: |
+            const abba = (process.env.BENCH_ABBA || 'true') !== 'false';
             const steps_status = [
               ['building binaries${{ steps.snapshot-check.outputs.needed == 'true' && ' & downloading snapshot' || '' }}', '${{ steps.build.outcome }}'],
               ['running baseline benchmark (1/2)', '${{ steps.run-baseline-1.outcome }}'],
               ['running feature benchmark (1/2)', '${{ steps.run-feature-1.outcome }}'],
-              ['running feature benchmark (2/2)', '${{ steps.run-feature-2.outcome }}'],
-              ['running baseline benchmark (2/2)', '${{ steps.run-baseline-2.outcome }}'],
+              ...(abba ? [['running feature benchmark (2/2)', '${{ steps.run-feature-2.outcome }}']] : []),
+              ...(abba ? [['running baseline benchmark (2/2)', '${{ steps.run-baseline-2.outcome }}']] : []),
             ];
             const failed = steps_status.find(([, o]) => o === 'failure');
             const failedStep = failed ? failed[0] : 'unknown step';

.github/workflows/docker-test.yml

@@ -76,7 +76,7 @@ jobs:
             *.dockerfile=Dockerfile
 
       - name: Upload reth image
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         with:
           name: ${{ inputs.artifact_name }}
           path: ./artifacts

.github/workflows/docker.yml

@@ -28,12 +28,30 @@ on:
         required: false
         type: boolean
         default: false
+      disable_pgo:
+        description: "Disable PGO profiling entirely"
+        required: false
+        type: boolean
+        default: false
+      pgo_blocks:
+        description: "Number of blocks to execute for PGO profiling"
+        required: false
+        type: string
+        default: "20"
 
 jobs:
+  collect-pgo-profile:
+    if: github.repository == 'paradigmxyz/reth' && !(github.event_name == 'workflow_dispatch' && inputs.disable_pgo)
+    uses: ./.github/workflows/pgo-profile.yml
+    with:
+      pgo_blocks: ${{ github.event_name == 'workflow_dispatch' && inputs.pgo_blocks || '20' }}
+    secrets: inherit
+
   build:
-    if: github.repository == 'paradigmxyz/reth'
+    if: github.repository == 'paradigmxyz/reth' && !failure() && !cancelled()
     name: Build Docker images
     runs-on: ubuntu-24.04
+    needs: collect-pgo-profile
     permissions:
       packages: write
       contents: read
@@ -45,7 +63,7 @@ jobs:
         uses: depot/setup-action@v1
 
       - name: Log in to GHCR
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
@@ -58,6 +76,30 @@ jobs:
           echo "describe=$(git describe --always --tags)" >> "$GITHUB_OUTPUT"
           echo "dirty=false" >> "$GITHUB_OUTPUT"
 
+      - name: Download pre-collected PGO profile
+        if: ${{ !(github.event_name == 'workflow_dispatch' && inputs.disable_pgo) }}
+        uses: actions/download-artifact@v7
+        with:
+          name: pgo-profdata
+          path: dist
+
+      - name: Configure PGO build args
+        id: pgo
+        run: |
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]] && [[ "${{ inputs.disable_pgo }}" == "true" ]]; then
+            echo "use_pgo_bolt=false" >> "$GITHUB_OUTPUT"
+            echo "pgo_profdata=" >> "$GITHUB_OUTPUT"
+            echo "PGO disabled via workflow input"
+          else
+            if [ ! -f dist/merged.profdata ]; then
+              echo "::error::Expected dist/merged.profdata from collect-pgo-profile job"
+              exit 1
+            fi
+            echo "use_pgo_bolt=true" >> "$GITHUB_OUTPUT"
+            echo "pgo_profdata=dist/merged.profdata" >> "$GITHUB_OUTPUT"
+            echo "Using pre-collected PGO profile from collect-pgo-profile job"
+          fi
+
       - name: Determine build parameters
         id: params
         run: |
@@ -107,6 +149,9 @@ jobs:
           push: ${{ !(github.event_name == 'workflow_dispatch' && inputs.dry_run) }}
           set: |
             ${{ steps.params.outputs.ethereum_set }}
+            *.args.USE_PGO_BOLT=${{ steps.pgo.outputs.use_pgo_bolt }}
+            *.args.PGO_PROFDATA=${{ steps.pgo.outputs.pgo_profdata }}
+            *.args.STRIP_SYMBOLS=false
 
       - name: Verify image architectures
         env:

.github/workflows/hive.yml

@@ -75,7 +75,7 @@ jobs:
           chmod +x hive
 
       - name: Upload hive assets
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         with:
           name: hive_assets
           path: ./hive_assets
@@ -198,13 +198,13 @@ jobs:
           fetch-depth: 0
 
       - name: Download hive assets
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v8
         with:
           name: hive_assets
           path: /tmp
 
       - name: Download reth image
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v8
         with:
           name: reth-${{ matrix.storage }}
           path: /tmp

.github/workflows/kurtosis.yml

@@ -40,7 +40,7 @@ jobs:
           fetch-depth: 0
 
       - name: Download reth image
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v8
         with:
           name: artifacts
           path: /tmp

.github/workflows/pgo-profile.yml

@@ -0,0 +1,107 @@
+name: pgo-profile
+
+on:
+  workflow_call:
+    inputs:
+      pgo_blocks:
+        description: "Number of blocks to execute for PGO profiling"
+        required: false
+        type: string
+        default: "20"
+  workflow_dispatch:
+    inputs:
+      pgo_blocks:
+        description: "Number of blocks to execute for PGO profiling"
+        required: false
+        type: string
+        default: "20"
+
+jobs:
+  collect:
+    name: collect PGO profiles
+    runs-on: [self-hosted, Linux, X64]
+    timeout-minutes: 180
+    env:
+      SCHELK_MOUNT: /reth-bench
+      BENCH_RPC_URL: https://ethereum.reth.rs/rpc
+      RUSTC_WRAPPER: "sccache"
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: true
+      - uses: rui314/setup-mold@v1
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          target: x86_64-unknown-linux-gnu
+      - uses: mozilla-actions/sccache-action@v0.0.9
+        continue-on-error: true
+      - uses: Swatinem/rust-cache@v2
+        with:
+          cache-on-failure: true
+
+      - name: Install dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -y --no-install-recommends \
+            dmsetup lsb-release wget linux-tools-"$(uname -r)" || \
+            sudo apt-get install -y --no-install-recommends linux-tools-generic
+
+      - name: Download snapshot if needed
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          BENCH_REPO: ${{ github.repository }}
+        run: |
+          if ! .github/scripts/bench-reth-snapshot.sh --check; then
+            echo "Snapshot outdated or missing, downloading..."
+            .github/scripts/bench-reth-snapshot.sh
+          fi
+
+      - name: Mount snapshot
+        run: |
+          sudo pkill -9 reth || true
+          sleep 1
+          if mountpoint -q "$SCHELK_MOUNT"; then
+            sudo umount -l "$SCHELK_MOUNT" || true
+            sudo schelk recover -y || true
+          fi
+          sudo schelk mount -y
+          sync
+          sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'
+
+      - name: Collect PGO profile
+        run: |
+          DATADIR="$SCHELK_MOUNT/datadir" \
+          RPC_URL="$BENCH_RPC_URL" \
+          PGO_BLOCKS="${{ inputs.pgo_blocks || '20' }}" \
+          BOLT_BLOCKS="${{ inputs.pgo_blocks || '20' }}" \
+          COLLECT_PGO_ONLY=true \
+          SKIP_BOLT=true \
+          PROFILE=maxperf-symbols \
+          FEATURES="jemalloc,asm-keccak,min-debug-logs" \
+          TARGET=x86_64-unknown-linux-gnu \
+          EXTRA_RUSTFLAGS="-C target-cpu=x86-64-v3 -C target-feature=+pclmulqdq" \
+            .github/scripts/build_pgo_bolt.sh
+
+      - name: Show PGO profile stats
+        run: |
+          LLVM_PROFDATA=$(find "$(rustc --print sysroot)" -name llvm-profdata -type f | head -1)
+          if [ -z "$LLVM_PROFDATA" ]; then
+            echo "::error::llvm-profdata not found in rust toolchain"
+            exit 1
+          fi
+          "$LLVM_PROFDATA" show --detailed-summary --topn=20 target/pgo-profiles/merged.profdata
+
+      - name: Upload PGO profile
+        uses: actions/upload-artifact@v7
+        with:
+          name: pgo-profdata
+          path: target/pgo-profiles/merged.profdata
+          retention-days: 1
+
+      - name: Recover snapshot
+        if: always()
+        run: |
+          if mountpoint -q "$SCHELK_MOUNT"; then
+            sudo umount -l "$SCHELK_MOUNT" || true
+            sudo schelk recover -y || true
+          fi

.github/workflows/pr-audit.yml

@@ -0,0 +1,30 @@
+name: Pull request audit
+
+on:
+  pull_request:
+    types: [labeled]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    if: github.event.label.name == 'cyclops'
+    steps:
+      - name: Publish event
+        run: |
+          set -euo pipefail
+
+          echo "${{ secrets.EVENTS_KEY }}" > ${{ runner.temp }}/key
+          echo "${{ secrets.EVENTS_CERT }}" > ${{ runner.temp }}/cert
+
+          curl -sf -o /dev/null -X POST ${{ secrets.EVENTS_ARGS }} \
+            -H "Content-Type: application/json" \
+            --key ${{ runner.temp }}/key \
+            --cert ${{ runner.temp }}/cert \
+            -d '{
+              "repository": "${{ github.repository }}",
+              "event": "pr_audit",
+              "data": {
+                "pr_number": ${{ github.event.pull_request.number }},
+                "sha": "${{ github.event.pull_request.head.sha }}"
+              }
+            }'

.github/workflows/release-reproducible.yml

@@ -52,7 +52,7 @@ jobs:
         uses: docker/setup-buildx-action@v3
 
       - name: Log in to GitHub Container Registry
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
         with:
           registry: ghcr.io
           username: ${{ github.actor }}

.github/workflows/release.yml

@@ -13,6 +13,10 @@ on:
         description: "Enable dry run mode (builds artifacts but skips uploads and release creation)"
         type: boolean
         default: false
+      pgo_blocks:
+        description: "Number of blocks to execute for PGO profiling on self-hosted runner"
+        type: string
+        default: "20"
 
 env:
   REPO_NAME: ${{ github.repository_owner }}/reth
@@ -37,7 +41,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Extract version
-        run: echo "VERSION=${GITHUB_REF_NAME}" >> $GITHUB_OUTPUT
+        run: echo "VERSION=${GITHUB_REF_NAME//\//-}" >> $GITHUB_OUTPUT
         id: extract_version
     outputs:
       VERSION: ${{ steps.extract_version.outputs.VERSION }}
@@ -69,22 +73,22 @@ jobs:
       fail-fast: true
       matrix:
         configs:
-          - target: x86_64-unknown-linux-gnu
-            os: ubuntu-24.04
-            profile: maxperf
-            allow_fail: false
           - target: aarch64-unknown-linux-gnu
             os: ubuntu-24.04-arm
             profile: maxperf
             allow_fail: false
+            rustflags: ""
+            native: true
           - target: x86_64-apple-darwin
             os: macos-14
             profile: maxperf
             allow_fail: false
+            rustflags: "-C target-cpu=x86-64-v3 -C target-feature=+pclmulqdq"
           - target: aarch64-apple-darwin
             os: macos-14
             profile: maxperf
             allow_fail: false
+            rustflags: ""
         build:
           - command: build
             binary: reth
@@ -96,6 +100,7 @@ jobs:
           target: ${{ matrix.configs.target }}
       - uses: mozilla-actions/sccache-action@v0.0.9
       - name: Install cross main
+        if: ${{ !matrix.configs.native }}
         id: cross_main
         run: |
           cargo install cross --locked --git https://github.com/cross-rs/cross
@@ -110,7 +115,12 @@ jobs:
           echo "MACOSX_DEPLOYMENT_TARGET=$(xcrun -sdk macosx --show-sdk-platform-version)" >> $GITHUB_ENV
 
       - name: Build Reth
-        run: make PROFILE=${{ matrix.configs.profile }} ${{ matrix.build.command }}-${{ matrix.configs.target }}
+        run: |
+          if [ "${{ matrix.configs.native }}" = "true" ]; then
+            make PROFILE=${{ matrix.configs.profile }} EXTRA_RUSTFLAGS="${{ matrix.configs.rustflags }}" ${{ matrix.build.command }}-native-${{ matrix.configs.target }}
+          else
+            make PROFILE=${{ matrix.configs.profile }} EXTRA_RUSTFLAGS="${{ matrix.configs.rustflags }}" ${{ matrix.build.command }}-${{ matrix.configs.target }}
+          fi
       - name: Move binary
         run: |
           mkdir artifacts
@@ -131,22 +141,102 @@ jobs:
 
       - name: Upload artifact
         if: ${{ github.event.inputs.dry_run != 'true' }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         with:
           name: ${{ matrix.build.binary }}-${{ needs.extract-version.outputs.VERSION }}-${{ matrix.configs.target }}.tar.gz
           path: ${{ matrix.build.binary }}-${{ needs.extract-version.outputs.VERSION }}-${{ matrix.configs.target }}.tar.gz
 
       - name: Upload signature
         if: ${{ github.event.inputs.dry_run != 'true' }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         with:
           name: ${{ matrix.build.binary }}-${{ needs.extract-version.outputs.VERSION }}-${{ matrix.configs.target }}.tar.gz.asc
           path: ${{ matrix.build.binary }}-${{ needs.extract-version.outputs.VERSION }}-${{ matrix.configs.target }}.tar.gz.asc
 
+  collect-pgo-profile:
+    uses: ./.github/workflows/pgo-profile.yml
+    with:
+      pgo_blocks: ${{ github.event_name == 'workflow_dispatch' && inputs.pgo_blocks || '20' }}
+    secrets: inherit
+
+  build-pgo:
+    name: build release (x86_64-linux PGO+BOLT)
+    runs-on: [self-hosted, Linux, X64]
+    needs: [extract-version, collect-pgo-profile]
+    timeout-minutes: 120
+    env:
+      RUSTC_WRAPPER: "sccache"
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: true
+      - uses: rui314/setup-mold@v1
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          target: x86_64-unknown-linux-gnu
+      - uses: mozilla-actions/sccache-action@v0.0.9
+        continue-on-error: true
+      - uses: Swatinem/rust-cache@v2
+        with:
+          cache-on-failure: true
+
+      - name: Download pre-collected PGO profile
+        uses: actions/download-artifact@v7
+        with:
+          name: pgo-profdata
+          path: dist
+
+      - name: Verify PGO profile artifact
+        run: |
+          test -f dist/merged.profdata
+          ls -lh dist/merged.profdata
+
+      - name: Build Reth with PGO+BOLT
+        run: |
+          SKIP_BOLT=true \
+          PGO_PROFDATA="$PWD/dist/merged.profdata" \
+          PROFILE=maxperf-symbols \
+          FEATURES="jemalloc,asm-keccak,min-debug-logs" \
+          TARGET=x86_64-unknown-linux-gnu \
+          EXTRA_RUSTFLAGS="-C target-cpu=x86-64-v3 -C target-feature=+pclmulqdq" \
+            .github/scripts/build_pgo_bolt.sh
+
+      - name: Move binary
+        run: |
+          mkdir artifacts
+          mv target/maxperf-symbols/reth ./artifacts
+
+      - name: Configure GPG and create artifacts
+        env:
+          GPG_SIGNING_KEY: ${{ secrets.GPG_SIGNING_KEY }}
+          GPG_PASSPHRASE: ${{ secrets.GPG_PASSPHRASE }}
+        run: |
+          export GPG_TTY=$(tty)
+          echo -n "$GPG_SIGNING_KEY" | base64 --decode | gpg --batch --import
+          cd artifacts
+          tar -czf reth-${{ needs.extract-version.outputs.VERSION }}-x86_64-unknown-linux-gnu.tar.gz reth*
+          echo "$GPG_PASSPHRASE" | gpg --passphrase-fd 0 --pinentry-mode loopback --batch -ab reth-${{ needs.extract-version.outputs.VERSION }}-x86_64-unknown-linux-gnu.tar.gz
+          mv *tar.gz* ..
+        shell: bash
+
+      - name: Upload artifact
+        if: ${{ github.event.inputs.dry_run != 'true' }}
+        uses: actions/upload-artifact@v6
+        with:
+          name: reth-${{ needs.extract-version.outputs.VERSION }}-x86_64-unknown-linux-gnu.tar.gz
+          path: reth-${{ needs.extract-version.outputs.VERSION }}-x86_64-unknown-linux-gnu.tar.gz
+
+      - name: Upload signature
+        if: ${{ github.event.inputs.dry_run != 'true' }}
+        uses: actions/upload-artifact@v6
+        with:
+          name: reth-${{ needs.extract-version.outputs.VERSION }}-x86_64-unknown-linux-gnu.tar.gz.asc
+          path: reth-${{ needs.extract-version.outputs.VERSION }}-x86_64-unknown-linux-gnu.tar.gz.asc
+
   draft-release:
     name: draft release
     runs-on: ubuntu-latest
-    needs: [build, extract-version]
+    needs: [build, build-pgo, extract-version]
     if: ${{ github.event.inputs.dry_run != 'true' }}
     env:
       VERSION: ${{ needs.extract-version.outputs.VERSION }}
@@ -160,7 +250,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Download artifacts
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v8
       - name: Generate full changelog
         id: changelog
         run: |

.github/workflows/reproducible-build.yml

@@ -43,7 +43,7 @@ jobs:
           echo "Binaries SHA256 on ${{ matrix.machine }}: $(cat checksum.sha256)"
 
       - name: Upload the hash
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         with:
           name: checksum-${{ matrix.machine }}
           path: |
@@ -56,12 +56,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download artifacts from machine-1
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v8
         with:
           name: checksum-machine-1
           path: machine-1/
       - name: Download artifacts from machine-2
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v8
         with:
           name: checksum-machine-2
           path: machine-2/

.github/workflows/stage.yml

@@ -51,15 +51,12 @@ jobs:
       - name: Run execution stage
         run: |
           reth stage run execution --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints
-      - name: Run account-hashing stage
-        run: |
-          reth stage run account-hashing --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints
-      - name: Run storage hashing stage
-        run: |
-          reth stage run storage-hashing --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints
-      - name: Run hashing stage
-        run: |
-          reth stage run hashing --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints
+      # NOTE: account-hashing, storage-hashing, and hashing stages are omitted.
+      # With storage v2 (now default), these stages are no-ops because the
+      # execution stage writes directly to HashedAccounts/HashedStorages.
+      # Running them here is harmful: `stage run` unwinds before executing,
+      # and the unwind reverts the hashed state that execution wrote, but
+      # the no-op execute never restores it — causing merkle to fail.
       - name: Run merkle stage
         run: |
           reth stage run merkle --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints

CLAUDE.md

@@ -191,6 +191,78 @@ The `book` CI job (`.github/workflows/lint.yml`) enforces this by regenerating t
 
 ### Opening PRs against <https://github.com/paradigmxyz/reth>
 
+#### Titles
+
+Use [Conventional Commits](https://www.conventionalcommits.org/) with an optional scope:
+
+```
+<type>(<scope>): <short description>
+```
+
+**Types**: `feat`, `fix`, `perf`, `refactor`, `docs`, `test`, `chore`
+
+**Scope** (optional): crate or area, e.g. `evm`, `trie`, `rpc`, `engine`, `net`
+
+Examples:
+- `fix(rpc): correct gas estimation for ERC-20 transfers`
+- `perf: batch trie updates to reduce cursor overhead`
+- `feat(engine): add new_payload_interval metric`
+
+#### Descriptions
+
+Keep it short. Say what changed and why — nothing more.
+
+**Do:**
+- Write 1–3 sentences summarizing the change
+- Explain _why_ if the diff doesn't make it obvious
+- Link related issues or EIPs
+- Include benchmark numbers for perf changes
+
+**Don't:**
+- List every file changed — that's what the diff is for
+- Repeat the title in the body
+- Add "Files changed" or "Changes" sections
+- Write walls of text that go stale when the diff is updated
+- Use filler like "This PR introduces...", "comprehensive", "robust", "enhance", "leverage"
+
+**Template:**
+
+```
+Closes #<issue>
+
+<what changed, 1-3 sentences>
+
+<why, if not obvious from the diff>
+```
+
+**Good example:**
+
+```
+Closes #16800
+
+Adds fallback for external IP resolution so node startup doesn't fail
+when STUN is unreachable. Falls back to the configured default.
+```
+
+**Bad example:**
+
+```
+## Summary
+This PR introduces comprehensive improvements to the IP resolution system.
+
+## Changes
+- Modified `crates/net/discv4/src/lib.rs` to add fallback
+- Modified `crates/net/discv4/src/config.rs` to add default IP
+- Added tests in `crates/net/discv4/src/tests/ip.rs`
+
+## Files Changed
+- crates/net/discv4/src/lib.rs
+- crates/net/discv4/src/config.rs
+- crates/net/discv4/src/tests/ip.rs
+```
+
+#### Labels and CI
+
 Label PRs appropriately, first check the available labels and then apply the relevant ones:
 * when changes are RPC related, add A-rpc label
 * when changes are docs related, add C-docs label

Cargo.toml

@@ -1,5 +1,5 @@
 [workspace.package]
-version = "1.11.1"
+version = "1.11.3"
 edition = "2024"
 rust-version = "1.93"
 license = "MIT OR Apache-2.0"
@@ -170,6 +170,7 @@ rust.rust_2018_idioms = { level = "deny", priority = -1 }
 rust.unreachable_pub = "warn"
 rust.unused_must_use = "deny"
 rust.rust_2024_incompatible_pat = "warn"
+rust.unexpected_cfgs = { level = "warn", check-cfg = ['cfg(tokio_unstable)'] }
 rustdoc.all = "warn"
 # rust.unnameable-types = "warn"
 
@@ -436,15 +437,15 @@ reth-trie-sparse = { path = "crates/trie/sparse", default-features = false }
 reth-zstd-compressors = { path = "crates/storage/zstd-compressors", default-features = false }
 
 # revm
-revm = { version = "34.0.0", default-features = false }
-revm-bytecode = { version = "8.0.0", default-features = false }
-revm-database = { version = "10.0.0", default-features = false }
-revm-state = { version = "9.0.0", default-features = false }
-revm-primitives = { version = "22.0.0", default-features = false }
-revm-interpreter = { version = "32.0.0", default-features = false }
-revm-database-interface = { version = "9.0.0", default-features = false }
-op-revm = { version = "15.0.0", default-features = false }
-revm-inspectors = "0.34.2"
+revm = { version = "36.0.0", default-features = false }
+revm-bytecode = { version = "9.0.0", default-features = false }
+revm-database = { version = "12.0.0", default-features = false }
+revm-state = { version = "10.0.0", default-features = false }
+revm-primitives = { version = "22.1.0", default-features = false }
+revm-interpreter = { version = "34.0.0", default-features = false }
+revm-database-interface = { version = "10.0.0", default-features = false }
+op-revm = { version = "17.0.0", default-features = false }
+revm-inspectors = "0.36.0"
 
 # eth
 alloy-dyn-abi = "1.5.6"
@@ -454,7 +455,7 @@ alloy-sol-types = { version = "1.5.6", default-features = false }
 alloy-chains = { version = "0.2.5", default-features = false }
 alloy-eip2124 = { version = "0.2.0", default-features = false }
 alloy-eip7928 = { version = "0.3.0", default-features = false }
-alloy-evm = { version = "0.27.2", default-features = false }
+alloy-evm = { version = "0.29.2", default-features = false }
 alloy-rlp = { version = "0.3.13", default-features = false, features = ["core-net"] }
 alloy-trie = { version = "0.9.4", default-features = false }
 
@@ -489,14 +490,9 @@ alloy-transport-ipc = { version = "1.7.3", default-features = false }
 alloy-transport-ws = { version = "1.7.3", default-features = false }
 
 # op
-alloy-op-evm = { version = "0.27.2", default-features = false }
-alloy-op-hardforks = "0.4.4"
-op-alloy-rpc-types = { version = "0.23.1", default-features = false }
-op-alloy-rpc-types-engine = { version = "0.23.1", default-features = false }
-op-alloy-network = { version = "0.23.1", default-features = false }
-op-alloy-consensus = { version = "0.23.1", default-features = false }
-op-alloy-rpc-jsonrpsee = { version = "0.23.1", default-features = false }
-op-alloy-flz = { version = "0.13.1", default-features = false }
+op-alloy-rpc-types = { version = "0.24.0", default-features = false }
+op-alloy-rpc-types-engine = { version = "0.24.0", default-features = false }
+op-alloy-consensus = { version = "0.24.0", default-features = false }
 
 # misc
 either = { version = "1.15.0", default-features = false }
@@ -508,6 +504,7 @@ bincode = "1.3"
 bitflags = "2.4"
 boyer-moore-magiclen = "0.2.16"
 bytes = { version = "1.11.1", default-features = false }
+blake3 = "1.8"
 brotli = "8"
 cfg-if = "1.0"
 clap = "4"
@@ -523,6 +520,7 @@ humantime = "2.1"
 humantime-serde = "1.1"
 itertools = { version = "0.14", default-features = false }
 linked_hash_set = "0.1"
+libc = "0.2"
 lz4 = "1.28.1"
 modular-bitfield = "0.13.1"
 notify = { version = "8.0.0", default-features = false, features = ["macos_fsevent"] }
@@ -541,6 +539,8 @@ serde_json = { version = "1.0", default-features = false, features = ["alloc"] }
 serde_with = { version = "3", default-features = false, features = ["macros"] }
 sha2 = { version = "0.10", default-features = false }
 shlex = "1.3"
+# https://github.com/orlp/slotmap/pull/148
+slotmap = { git = "https://github.com/DaniPopes/slotmap.git", branch = "dani/shrink-methods" }
 smallvec = "1"
 strum = { version = "0.27", default-features = false }
 strum_macros = "0.27"
@@ -665,6 +665,7 @@ cipher = "0.4.3"
 comfy-table = "7.0"
 concat-kdf = "0.1.0"
 crossbeam-channel = "0.5.13"
+crossbeam-queue = "0.3"
 crossbeam-utils = "0.8"
 crossterm = "0.29.0"
 csv = "1.3.0"
@@ -741,10 +742,8 @@ ipnet = "2.11"
 # alloy-transport-ws = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
 
 # op-alloy-consensus = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
-# op-alloy-network = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
 # op-alloy-rpc-types = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
 # op-alloy-rpc-types-engine = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
-# op-alloy-rpc-jsonrpsee = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
 #
 # revm-inspectors = { git = "https://github.com/paradigmxyz/revm-inspectors", rev = "1207e33" }
 #
@@ -754,10 +753,6 @@ ipnet = "2.11"
 # jsonrpsee-http-client = { git = "https://github.com/paradigmxyz/jsonrpsee", branch = "matt/make-rpc-service-pub" }
 # jsonrpsee-types = { git = "https://github.com/paradigmxyz/jsonrpsee", branch = "matt/make-rpc-service-pub" }
 
-# alloy-evm = { git = "https://github.com/alloy-rs/evm", rev = "df124c0" }
-# alloy-op-evm = { git = "https://github.com/alloy-rs/evm", rev = "df124c0" }
+# alloy-evm = { git = "https://github.com/alloy-rs/evm", rev = "9bc2dba" }
 
 # revm-inspectors = { git = "https://github.com/paradigmxyz/revm-inspectors", rev = "3020ea8" }
-
-# alloy-evm = { git = "https://github.com/alloy-rs/evm", rev = "072c248" }
-# alloy-op-evm = { git = "https://github.com/alloy-rs/evm", rev = "072c248" }

Dockerfile.depot

@@ -1,8 +1,10 @@
 # syntax=docker/dockerfile:1
 
 # Dockerfile for reth, optimized for Depot builds
+# Supports PGO+BOLT optimization for maximum performance
 # Usage:
 #   reth: --build-arg BINARY=reth
+#   PGO+BOLT: --build-arg USE_PGO_BOLT=true (Linux x86_64/aarch64 only)
 
 FROM rust:1.93 AS builder
 WORKDIR /app
@@ -43,6 +45,18 @@ ENV VERGEN_GIT_SHA=$VERGEN_GIT_SHA
 ENV VERGEN_GIT_DESCRIBE=$VERGEN_GIT_DESCRIBE
 ENV VERGEN_GIT_DIRTY=$VERGEN_GIT_DIRTY
 
+# Enable PGO+BOLT optimization (Linux only)
+ARG USE_PGO_BOLT=false
+ENV USE_PGO_BOLT=$USE_PGO_BOLT
+
+# Optional path to a pre-collected merged.profdata file in build context.
+ARG PGO_PROFDATA=""
+ENV PGO_PROFDATA=$PGO_PROFDATA
+
+# Whether to strip debug symbols from PGO-built binaries.
+ARG STRIP_SYMBOLS=true
+ENV STRIP_SYMBOLS=$STRIP_SYMBOLS
+
 # Build application
 # Platform-specific RUSTFLAGS: amd64 uses x86-64-v3 (Haswell+) with pclmulqdq for rocksdb
 ARG TARGETPLATFORM
@@ -53,12 +67,21 @@ RUN --mount=type=secret,id=DEPOT_TOKEN,env=SCCACHE_WEBDAV_TOKEN \
     --mount=type=cache,target=$SCCACHE_DIR,sharing=shared \
     export RUSTC_WRAPPER=sccache SCCACHE_WEBDAV_ENDPOINT=https://cache.depot.dev SCCACHE_DIR=/sccache && \
     sccache --start-server && \
-    if [ -n "$RUSTFLAGS" ]; then \
-        export RUSTFLAGS="$RUSTFLAGS"; \
-    elif [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
-        export RUSTFLAGS="-C target-cpu=x86-64-v3 -C target-feature=+pclmulqdq"; \
+    if [ "$USE_PGO_BOLT" = "true" ] && [ "$TARGETPLATFORM" = "linux/amd64" ] && [ -n "$PGO_PROFDATA" ] && [ -f "$PGO_PROFDATA" ]; then \
+        apt-get update && apt-get install -y -qq lsb-release wget sudo && \
+        BINARY="$BINARY" PROFILE="$BUILD_PROFILE" FEATURES="$FEATURES" SKIP_BOLT=true STRIP_SYMBOLS="$STRIP_SYMBOLS" PGO_PROFDATA="$PGO_PROFDATA" \
+            ./.github/scripts/build_pgo_bolt.sh; \
+    else \
+        if [ "$USE_PGO_BOLT" = "true" ]; then \
+            echo "PGO requested but pre-collected profile missing at '${PGO_PROFDATA:-<unset>}' - falling back to non-PGO build"; \
+        fi; \
+        if [ -n "$RUSTFLAGS" ]; then \
+            export RUSTFLAGS="$RUSTFLAGS"; \
+        elif [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
+            export RUSTFLAGS="-C target-cpu=x86-64-v3 -C target-feature=+pclmulqdq"; \
+        fi && \
+        cargo build --profile $BUILD_PROFILE --features "$FEATURES" --locked --bin $BINARY --manifest-path $MANIFEST_PATH/Cargo.toml; \
     fi && \
-    cargo build --profile $BUILD_PROFILE --features "$FEATURES" --locked --bin $BINARY --manifest-path $MANIFEST_PATH/Cargo.toml && \
     sccache --show-stats
 
 # Copy binary to a known location (ARG not resolved in COPY)

Makefile

@@ -17,6 +17,9 @@ FEATURES ?=
 # Cargo profile for builds. Default is for local builds, CI uses an override.
 PROFILE ?= release
 
+# Extra RUSTFLAGS to append to build targets (e.g., "-C target-cpu=x86-64-v3")
+EXTRA_RUSTFLAGS ?=
+
 # Extra flags for Cargo
 CARGO_INSTALL_EXTRA_FLAGS ?=
 
@@ -74,7 +77,7 @@ build-debug: ## Build the reth binary into `target/debug` directory.
 	cargo build --bin reth --features "$(FEATURES)"
 # Builds the reth binary natively.
 build-native-%:
-	cargo build --bin reth --target $* --features "$(FEATURES)" --profile "$(PROFILE)"
+	$(if $(EXTRA_RUSTFLAGS),RUSTFLAGS="$(EXTRA_RUSTFLAGS)") cargo build --bin reth --target $* --features "$(FEATURES)" --profile "$(PROFILE)"
 
 # The following commands use `cross` to build a cross-compile.
 #
@@ -92,11 +95,12 @@ build-native-%:
 # on other systems. JEMALLOC_SYS_WITH_LG_PAGE=16 tells jemalloc to use 64-KiB
 # pages. See: https://github.com/paradigmxyz/reth/issues/6742
 build-aarch64-unknown-linux-gnu: export JEMALLOC_SYS_WITH_LG_PAGE=16
+build-native-aarch64-unknown-linux-gnu: export JEMALLOC_SYS_WITH_LG_PAGE=16
 
 # Note: The additional rustc compiler flags are for intrinsics needed by MDBX.
 # See: https://github.com/cross-rs/cross/wiki/FAQ#undefined-reference-with-build-std
 build-%:
-	RUSTFLAGS="-C link-arg=-lgcc -Clink-arg=-static-libgcc" \
+	RUSTFLAGS="-C link-arg=-lgcc -Clink-arg=-static-libgcc $(EXTRA_RUSTFLAGS)" \
 		cross build --bin reth --target $* --features "$(FEATURES)" --profile "$(PROFILE)"
 
 # Unfortunately we can't easily use cross to build for Darwin because of licensing issues.

bin/reth-bench/src/bench/context.rs

@@ -7,7 +7,7 @@ use alloy_primitives::address;
 use alloy_provider::{network::AnyNetwork, Provider, RootProvider};
 use alloy_rpc_client::ClientBuilder;
 use alloy_rpc_types_engine::JwtSecret;
-use alloy_transport::layers::RetryBackoffLayer;
+use alloy_transport::layers::{RateLimitRetryPolicy, RetryBackoffLayer};
 use reqwest::Url;
 use reth_node_core::args::BenchmarkArgs;
 use tracing::info;
@@ -31,6 +31,8 @@ pub(crate) struct BenchContext {
     pub(crate) is_optimism: bool,
     /// Whether to use `reth_newPayload` endpoint instead of `engine_newPayload*`.
     pub(crate) use_reth_namespace: bool,
+    /// Whether to fetch and replay RLP-encoded blocks.
+    pub(crate) rlp_blocks: bool,
 }
 
 impl BenchContext {
@@ -51,9 +53,15 @@ impl BenchContext {
             }
         }
 
-        // set up alloy client for blocks
+        // set up alloy client for blocks, retrying on 429/503 (default) and 502
+        let retry_policy =
+            RateLimitRetryPolicy::default().or(|err: &alloy_transport::TransportError| -> bool {
+                err.as_transport_err()
+                    .and_then(|t| t.as_http_error())
+                    .is_some_and(|e| e.status == 502)
+            });
         let client = ClientBuilder::default()
-            .layer(RetryBackoffLayer::new(10, 800, u64::MAX))
+            .layer(RetryBackoffLayer::new_with_policy(10, 800, u64::MAX, retry_policy))
             .http(rpc_url.parse()?);
         let block_provider = RootProvider::<AnyNetwork>::new(client);
 
@@ -86,9 +94,11 @@ impl BenchContext {
 
         // Computes the block range for the benchmark.
         //
-        // - If `--advance` is provided, fetches the latest block and sets:
+        // - If `--advance` is provided, fetches the latest block from the engine and sets:
         //     - `from = head + 1`
         //     - `to = head + advance`
+        // - If only `--to` is provided, fetches the latest block from the engine and sets:
+        //     - `from = head`
         // - Otherwise, uses the values from `--from` and `--to`.
         let (from, to) = if let Some(advance) = bench_args.advance {
             if advance == 0 {
@@ -101,6 +111,14 @@ impl BenchContext {
                 .ok_or_else(|| eyre::eyre!("Failed to fetch latest block for --advance"))?;
             let head_number = head_block.header.number;
             (Some(head_number), Some(head_number + advance))
+        } else if bench_args.from.is_none() && bench_args.to.is_some() {
+            let head_block = auth_provider
+                .get_block_by_number(BlockNumberOrTag::Latest)
+                .await?
+                .ok_or_else(|| eyre::eyre!("Failed to fetch latest block from engine"))?;
+            let head_number = head_block.header.number;
+            info!(target: "reth-bench", "No --from provided, derived from engine head: {}", head_number);
+            (Some(head_number), bench_args.to)
         } else {
             (bench_args.from, bench_args.to)
         };
@@ -112,7 +130,7 @@ impl BenchContext {
             .full()
             .await?
             .ok_or_else(|| eyre::eyre!("Failed to fetch latest block from RPC"))?;
-        let mut benchmark_mode = BenchMode::new(from, to, latest_block.into_inner().number())?;
+        let mut benchmark_mode = BenchMode::new(from, to, latest_block.into_inner().number());
 
         let first_block = match benchmark_mode {
             BenchMode::Continuous(start) => {
@@ -142,7 +160,8 @@ impl BenchContext {
         };
 
         let next_block = first_block.header.number + 1;
-        let use_reth_namespace = bench_args.reth_new_payload;
+        let rlp_blocks = bench_args.rlp_blocks;
+        let use_reth_namespace = bench_args.reth_new_payload || rlp_blocks;
         Ok(Self {
             auth_provider,
             block_provider,
@@ -150,6 +169,7 @@ impl BenchContext {
             next_block,
             is_optimism,
             use_reth_namespace,
+            rlp_blocks,
         })
     }
 }

bin/reth-bench/src/bench/gas_limit_ramp.rs

@@ -21,6 +21,7 @@ use reth_chainspec::ChainSpec;
 use reth_cli_runner::CliContext;
 use reth_ethereum_primitives::TransactionSigned;
 use reth_primitives_traits::constants::{GAS_LIMIT_BOUND_DIVISOR, MAXIMUM_GAS_LIMIT_BLOCK};
+use reth_rpc_api::RethNewPayloadInput;
 use std::{path::PathBuf, time::Instant};
 use tracing::info;
 
@@ -184,34 +185,32 @@ impl Command {
                 Some(new_payload_version),
             )?;
 
+            let (version, params) = if self.reth_new_payload {
+                (None, serde_json::to_value((RethNewPayloadInput::ExecutionData(execution_data),))?)
+            } else {
+                (Some(version), params)
+            };
+
             // Save payload to file with version info for replay
             let payload_path =
                 self.output.join(format!("payload_block_{}.json", block.header.number));
             let file = GasRampPayloadFile {
-                version: version as u8,
+                version: version.map(|v| v as u8),
                 block_hash,
                 params: params.clone(),
-                execution_data: Some(execution_data.clone()),
             };
             let payload_json = serde_json::to_string_pretty(&file)?;
             std::fs::write(&payload_path, &payload_json)?;
             info!(target: "reth-bench", block_number = block.header.number, path = %payload_path.display(), "Saved payload");
 
-            let reth_data = self.reth_new_payload.then_some(execution_data);
-            let _ = call_new_payload_with_reth(&provider, version, params, reth_data).await?;
+            let _ = call_new_payload_with_reth(&provider, version, params).await?;
 
             let forkchoice_state = ForkchoiceState {
                 head_block_hash: block_hash,
                 safe_block_hash: block_hash,
                 finalized_block_hash: block_hash,
             };
-            call_forkchoice_updated_with_reth(
-                &provider,
-                version,
-                forkchoice_state,
-                self.reth_new_payload,
-            )
-            .await?;
+            call_forkchoice_updated_with_reth(&provider, version, forkchoice_state).await?;
 
             parent_header = block.header;
             parent_hash = block_hash;

bin/reth-bench/src/bench/new_payload_fcu.rs

@@ -25,7 +25,7 @@ use crate::{
         block_to_new_payload, call_forkchoice_updated_with_reth, call_new_payload_with_reth,
     },
 };
-use alloy_provider::Provider;
+use alloy_provider::{ext::DebugApi, Provider};
 use alloy_rpc_types_engine::ForkchoiceState;
 use clap::Parser;
 use eyre::{Context, OptionExt};
@@ -154,6 +154,7 @@ impl Command {
             mut next_block,
             is_optimism,
             use_reth_namespace,
+            rlp_blocks,
         } = BenchContext::new(&self.benchmark, self.rpc_url).await?;
 
         let total_blocks = benchmark_mode.total_blocks();
@@ -186,6 +187,21 @@ impl Command {
                     }
                 };
 
+                let rlp = if rlp_blocks {
+                    let rlp = match block_provider.debug_get_raw_block(next_block.into()).await {
+                        Ok(rlp) => rlp,
+                        Err(e) => {
+                            tracing::error!(target: "reth-bench", "Failed to fetch raw block {next_block}: {e}");
+                            let _ = error_sender
+                                .send(eyre::eyre!("Failed to fetch raw block {next_block}: {e}"));
+                            break;
+                        }
+                    };
+                    Some(rlp)
+                } else {
+                    None
+                };
+
                 let head_block_hash = block.header.hash;
                 let safe_block_hash = block_provider
                     .get_block_by_number(block.header.number.saturating_sub(32).into());
@@ -207,7 +223,7 @@ impl Command {
 
                 next_block += 1;
                 if let Err(e) = sender
-                    .send((block, head_block_hash, safe_block_hash, finalized_block_hash))
+                    .send((block, head_block_hash, safe_block_hash, finalized_block_hash, rlp))
                     .await
                 {
                     tracing::error!(target: "reth-bench", "Failed to send block data: {e}");
@@ -221,7 +237,7 @@ impl Command {
         let total_benchmark_duration = Instant::now();
         let mut total_wait_time = Duration::ZERO;
 
-        while let Some((block, head, safe, finalized)) = {
+        while let Some((block, head, safe, finalized, rlp)) = {
             let wait_start = Instant::now();
             let result = receiver.recv().await;
             total_wait_time += wait_start.elapsed();
@@ -240,11 +256,11 @@ impl Command {
                 finalized_block_hash: finalized,
             };
 
-            let (version, params, execution_data) = block_to_new_payload(block, is_optimism)?;
+            let (version, params) =
+                block_to_new_payload(block, is_optimism, rlp, use_reth_namespace)?;
             let start = Instant::now();
-            let reth_data = use_reth_namespace.then_some(execution_data);
             let server_timings =
-                call_new_payload_with_reth(&auth_provider, version, params, reth_data).await?;
+                call_new_payload_with_reth(&auth_provider, version, params).await?;
 
             let np_latency =
                 server_timings.as_ref().map(|t| t.latency).unwrap_or_else(|| start.elapsed());
@@ -263,13 +279,7 @@ impl Command {
             };
 
             let fcu_start = Instant::now();
-            call_forkchoice_updated_with_reth(
-                &auth_provider,
-                version,
-                forkchoice_state,
-                use_reth_namespace,
-            )
-            .await?;
+            call_forkchoice_updated_with_reth(&auth_provider, version, forkchoice_state).await?;
             let fcu_latency = fcu_start.elapsed();
 
             let total_latency = if server_timings.is_some() {

bin/reth-bench/src/bench/new_payload_only.rs

@@ -11,7 +11,7 @@ use crate::{
     },
     valid_payload::{block_to_new_payload, call_new_payload_with_reth},
 };
-use alloy_provider::Provider;
+use alloy_provider::{ext::DebugApi, Provider};
 use clap::Parser;
 use csv::Writer;
 use eyre::{Context, OptionExt};
@@ -51,6 +51,7 @@ impl Command {
             mut next_block,
             is_optimism,
             use_reth_namespace,
+            rlp_blocks,
         } = BenchContext::new(&self.benchmark, self.rpc_url).await?;
 
         let total_blocks = benchmark_mode.total_blocks();
@@ -83,8 +84,21 @@ impl Command {
                     }
                 };
 
+                let rlp = if rlp_blocks {
+                    let Ok(rlp) = block_provider.debug_get_raw_block(next_block.into()).await
+                    else {
+                        tracing::error!(target: "reth-bench", "Failed to fetch raw block {next_block}");
+                        let _ = error_sender
+                            .send(eyre::eyre!("Failed to fetch raw block {next_block}"));
+                        break;
+                    };
+                    Some(rlp)
+                } else {
+                    None
+                };
+
                 next_block += 1;
-                if let Err(e) = sender.send(block).await {
+                if let Err(e) = sender.send((block, rlp)).await {
                     tracing::error!(target: "reth-bench", "Failed to send block data: {e}");
                     break;
                 }
@@ -96,7 +110,7 @@ impl Command {
         let total_benchmark_duration = Instant::now();
         let mut total_wait_time = Duration::ZERO;
 
-        while let Some(block) = {
+        while let Some((block, rlp)) = {
             let wait_start = Instant::now();
             let result = receiver.recv().await;
             total_wait_time += wait_start.elapsed();
@@ -108,12 +122,12 @@ impl Command {
 
             debug!(target: "reth-bench", number=?block.header.number, "Sending payload to engine");
 
-            let (version, params, execution_data) = block_to_new_payload(block, is_optimism)?;
+            let (version, params) =
+                block_to_new_payload(block, is_optimism, rlp, use_reth_namespace)?;
 
             let start = Instant::now();
-            let reth_data = use_reth_namespace.then_some(execution_data);
             let server_timings =
-                call_new_payload_with_reth(&auth_provider, version, params, reth_data).await?;
+                call_new_payload_with_reth(&auth_provider, version, params).await?;
 
             let latency =
                 server_timings.as_ref().map(|t| t.latency).unwrap_or_else(|| start.elapsed());

bin/reth-bench/src/bench/output.rs

@@ -22,14 +22,14 @@ pub(crate) const NEW_PAYLOAD_OUTPUT_SUFFIX: &str = "new_payload_latency.csv";
 #[derive(Debug, Serialize, Deserialize)]
 pub(crate) struct GasRampPayloadFile {
     /// Engine API version (1-5).
-    pub(crate) version: u8,
+    ///
+    /// `None` indicates that `reth_newPayload` should be used.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub(crate) version: Option<u8>,
     /// The block hash for FCU.
     pub(crate) block_hash: B256,
     /// The params to pass to newPayload.
     pub(crate) params: serde_json::Value,
-    /// The execution data for `reth_newPayload`.
-    #[serde(skip_serializing_if = "Option::is_none", default)]
-    pub(crate) execution_data: Option<alloy_rpc_types_engine::ExecutionData>,
 }
 
 /// This represents the results of a single `newPayload` call in the benchmark, containing the gas
@@ -114,16 +114,27 @@ impl CombinedResult {
 
 impl std::fmt::Display for CombinedResult {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        let np = &self.new_payload_result;
         write!(
             f,
             "Block {} processed at {:.4} Ggas/s, used {} total gas. Combined: {:.4} Ggas/s. fcu: {:?}, newPayload: {:?}",
             self.block_number,
-            self.new_payload_result.gas_per_second() / GIGAGAS as f64,
-            self.new_payload_result.gas_used,
+            np.gas_per_second() / GIGAGAS as f64,
+            np.gas_used,
             self.combined_gas_per_second() / GIGAGAS as f64,
             self.fcu_latency,
-            self.new_payload_result.latency
-        )
+            np.latency,
+        )?;
+        if !np.execution_cache_wait.is_zero() {
+            write!(f, ", execution cache wait: {:?}", np.execution_cache_wait)?;
+        }
+        if !np.sparse_trie_wait.is_zero() {
+            write!(f, ", trie cache wait: {:?}", np.sparse_trie_wait)?;
+        }
+        if let Some(d) = np.persistence_wait {
+            write!(f, ", persistence wait: {d:?}")?;
+        }
+        Ok(())
     }
 }
 

bin/reth-bench/src/bench/replay_payloads.rs

@@ -38,6 +38,7 @@ use eyre::Context;
 use reth_cli_runner::CliContext;
 use reth_engine_primitives::config::DEFAULT_PERSISTENCE_THRESHOLD;
 use reth_node_api::EngineApiMessageVersion;
+use reth_rpc_api::RethNewPayloadInput;
 use std::{
     path::PathBuf,
     time::{Duration, Instant},
@@ -161,7 +162,9 @@ struct GasRampPayload {
     /// Block number from filename.
     block_number: u64,
     /// Engine API version for newPayload.
-    version: EngineApiMessageVersion,
+    ///
+    /// `None` indicates that `reth_newPayload` should be used.
+    version: Option<EngineApiMessageVersion>,
     /// The file contents.
     file: GasRampPayloadFile,
 }
@@ -273,13 +276,10 @@ impl Command {
                 "Executing gas ramp payload (newPayload + FCU)"
             );
 
-            let reth_data =
-                if self.reth_new_payload { payload.file.execution_data.clone() } else { None };
             let _ = call_new_payload_with_reth(
                 &auth_provider,
                 payload.version,
                 payload.file.params.clone(),
-                reth_data,
             )
             .await?;
 
@@ -288,20 +288,10 @@ impl Command {
                 safe_block_hash: parent_hash,
                 finalized_block_hash: parent_hash,
             };
-            call_forkchoice_updated_with_reth(
-                &auth_provider,
-                payload.version,
-                fcu_state,
-                self.reth_new_payload,
-            )
-            .await?;
+            call_forkchoice_updated_with_reth(&auth_provider, payload.version, fcu_state).await?;
 
             info!(target: "reth-bench", gas_ramp_payload = i + 1, "Gas ramp payload executed successfully");
 
-            if let Some(w) = &mut waiter {
-                w.on_block(payload.block_number).await?;
-            }
-
             parent_hash = payload.file.block_hash;
         }
 
@@ -342,31 +332,34 @@ impl Command {
                 "Sending newPayload"
             );
 
-            let params = serde_json::to_value((
-                execution_payload.clone(),
-                Vec::<B256>::new(),
-                B256::ZERO,
-                envelope.execution_requests.to_vec(),
-            ))?;
+            let (version, params) = if self.reth_new_payload {
+                let reth_data = ExecutionData {
+                    payload: execution_payload.clone().into(),
+                    sidecar: ExecutionPayloadSidecar::v4(
+                        CancunPayloadFields {
+                            versioned_hashes: Vec::new(),
+                            parent_beacon_block_root: B256::ZERO,
+                        },
+                        PraguePayloadFields {
+                            requests: envelope.execution_requests.clone().into(),
+                        },
+                    ),
+                };
+                (None, serde_json::to_value((RethNewPayloadInput::ExecutionData(reth_data),))?)
+            } else {
+                (
+                    Some(EngineApiMessageVersion::V4),
+                    serde_json::to_value((
+                        execution_payload.clone(),
+                        Vec::<B256>::new(),
+                        B256::ZERO,
+                        envelope.execution_requests.to_vec(),
+                    ))?,
+                )
+            };
 
-            let reth_data = self.reth_new_payload.then(|| ExecutionData {
-                payload: execution_payload.clone().into(),
-                sidecar: ExecutionPayloadSidecar::v4(
-                    CancunPayloadFields {
-                        versioned_hashes: Vec::new(),
-                        parent_beacon_block_root: B256::ZERO,
-                    },
-                    PraguePayloadFields { requests: envelope.execution_requests.clone().into() },
-                ),
-            });
-
-            let server_timings = call_new_payload_with_reth(
-                &auth_provider,
-                EngineApiMessageVersion::V4,
-                params,
-                reth_data,
-            )
-            .await?;
+            let server_timings =
+                call_new_payload_with_reth(&auth_provider, version, params).await?;
 
             let np_latency =
                 server_timings.as_ref().map(|t| t.latency).unwrap_or_else(|| start.elapsed());
@@ -391,13 +384,7 @@ impl Command {
             };
 
             let fcu_start = Instant::now();
-            call_forkchoice_updated_with_reth(
-                &auth_provider,
-                EngineApiMessageVersion::V4,
-                fcu_state,
-                self.reth_new_payload,
-            )
-            .await?;
+            call_forkchoice_updated_with_reth(&auth_provider, version, fcu_state).await?;
             let fcu_latency = fcu_start.elapsed();
 
             let total_latency =
@@ -558,13 +545,18 @@ impl Command {
             let file: GasRampPayloadFile = serde_json::from_str(&content)
                 .wrap_err_with(|| format!("Failed to parse {:?}", path))?;
 
-            let version = match file.version {
-                1 => EngineApiMessageVersion::V1,
-                2 => EngineApiMessageVersion::V2,
-                3 => EngineApiMessageVersion::V3,
-                4 => EngineApiMessageVersion::V4,
-                5 => EngineApiMessageVersion::V5,
-                v => return Err(eyre::eyre!("Invalid version {} in {:?}", v, path)),
+            let version = if let Some(version) = file.version {
+                match version {
+                    1 => EngineApiMessageVersion::V1,
+                    2 => EngineApiMessageVersion::V2,
+                    3 => EngineApiMessageVersion::V3,
+                    4 => EngineApiMessageVersion::V4,
+                    5 => EngineApiMessageVersion::V5,
+                    v => return Err(eyre::eyre!("Invalid version {} in {:?}", v, path)),
+                }
+                .into()
+            } else {
+                None
             };
 
             info!(

bin/reth-bench/src/bench_mode.rs

@@ -34,17 +34,16 @@ impl BenchMode {
     }
 
     /// Create a [`BenchMode`] from optional `from` and `to` fields.
-    pub fn new(from: Option<u64>, to: Option<u64>, latest_block: u64) -> Result<Self, eyre::Error> {
+    ///
+    /// If only `--to` is provided, `from` is derived as `latest_block + 1`.
+    pub const fn new(from: Option<u64>, to: Option<u64>, latest_block: u64) -> Self {
         // If neither `--from` nor `--to` are provided, we will run the benchmark continuously,
         // starting at the latest block.
         match (from, to) {
-            (Some(from), Some(to)) => Ok(Self::Range(from..=to)),
-            (None, None) => Ok(Self::Continuous(latest_block)),
-            (Some(start), None) => Ok(Self::Continuous(start)),
-            _ => {
-                // both or neither are allowed, everything else is ambiguous
-                Err(eyre::eyre!("`from` and `to` must be provided together, or not at all."))
-            }
+            (Some(from), Some(to)) => Self::Range(from..=to),
+            (None, None) => Self::Continuous(latest_block),
+            (Some(start), None) => Self::Continuous(start),
+            (None, Some(to)) => Self::Range(latest_block + 1..=to),
         }
     }
 }

bin/reth-bench/src/valid_payload.rs

@@ -3,7 +3,7 @@
 //! before sending additional calls.
 
 use alloy_eips::eip7685::Requests;
-use alloy_primitives::B256;
+use alloy_primitives::{Bytes, B256};
 use alloy_provider::{ext::EngineApi, network::AnyRpcBlock, Network, Provider};
 use alloy_rpc_types_engine::{
     ExecutionData, ExecutionPayload, ExecutionPayloadInputV2, ExecutionPayloadSidecar,
@@ -12,6 +12,7 @@ use alloy_rpc_types_engine::{
 use alloy_transport::TransportResult;
 use op_alloy_rpc_types_engine::OpExecutionPayloadV4;
 use reth_node_api::EngineApiMessageVersion;
+use reth_rpc_api::RethNewPayloadInput;
 use serde::Deserialize;
 use std::time::Duration;
 use tracing::{debug, error};
@@ -169,7 +170,15 @@ where
 pub(crate) fn block_to_new_payload(
     block: AnyRpcBlock,
     is_optimism: bool,
-) -> eyre::Result<(EngineApiMessageVersion, serde_json::Value, ExecutionData)> {
+    rlp: Option<Bytes>,
+    reth_new_payload: bool,
+) -> eyre::Result<(Option<EngineApiMessageVersion>, serde_json::Value)> {
+    if let Some(rlp) = rlp {
+        return Ok((
+            None,
+            serde_json::to_value((RethNewPayloadInput::<ExecutionData>::BlockRlp(rlp),))?,
+        ));
+    }
     let block = block
         .into_inner()
         .map_header(|header| header.map(|h| h.into_header_with_defaults()))
@@ -181,7 +190,14 @@ pub(crate) fn block_to_new_payload(
 
     // Convert to execution payload
     let (payload, sidecar) = ExecutionPayload::from_block_slow(&block);
-    payload_to_new_payload(payload, sidecar, is_optimism, block.withdrawals_root, None)
+    let (version, params, execution_data) =
+        payload_to_new_payload(payload, sidecar, is_optimism, block.withdrawals_root, None)?;
+
+    if reth_new_payload {
+        Ok((None, serde_json::to_value((RethNewPayloadInput::ExecutionData(execution_data),))?))
+    } else {
+        Ok((Some(version), params))
+    }
 }
 
 /// Converts an execution payload and sidecar into versioned engine API params and an
@@ -219,8 +235,8 @@ pub(crate) fn payload_to_new_payload(
                         ))?,
                     )
                 } else {
-                    // Extract actual Requests from RequestsOrHash
-                    let requests = prague.requests.requests_hash();
+                    // Preserve the original RequestsOrHash payload for engine_newPayloadV4.
+                    let requests = prague.requests.clone();
                     (
                         version,
                         serde_json::to_value((
@@ -266,17 +282,15 @@ pub(crate) fn payload_to_new_payload(
 #[allow(dead_code)]
 pub(crate) async fn call_new_payload<N: Network, P: Provider<N>>(
     provider: P,
-    version: EngineApiMessageVersion,
+    version: Option<EngineApiMessageVersion>,
     params: serde_json::Value,
-) -> TransportResult<Option<NewPayloadTimingBreakdown>> {
-    call_new_payload_with_reth(provider, version, params, None).await
+) -> eyre::Result<Option<NewPayloadTimingBreakdown>> {
+    call_new_payload_with_reth(provider, version, params).await
 }
 
 /// Response from `reth_newPayload` endpoint, which includes server-measured latency.
 #[derive(Debug, Deserialize)]
 struct RethPayloadStatus {
-    #[serde(flatten)]
-    status: PayloadStatus,
     latency_us: u64,
     #[serde(default)]
     persistence_wait_us: Option<u64>,
@@ -300,72 +314,50 @@ pub(crate) struct NewPayloadTimingBreakdown {
 }
 
 /// Calls either `engine_newPayload*` or `reth_newPayload` depending on whether
-/// `reth_execution_data` is provided.
+/// `version` is provided.
 ///
-/// When `reth_execution_data` is `Some`, uses the `reth_newPayload` endpoint which takes
-/// `ExecutionData` directly and waits for persistence and cache updates to complete.
+/// When `version` is `None`, uses `reth_newPayload` endpoint with provided params.
 ///
 /// Returns the server-reported timing breakdown when using the reth namespace, or `None` for
 /// the standard engine namespace.
 pub(crate) async fn call_new_payload_with_reth<N: Network, P: Provider<N>>(
     provider: P,
-    version: EngineApiMessageVersion,
+    version: Option<EngineApiMessageVersion>,
     params: serde_json::Value,
-    reth_execution_data: Option<ExecutionData>,
-) -> TransportResult<Option<NewPayloadTimingBreakdown>> {
-    if let Some(execution_data) = reth_execution_data {
-        let method = "reth_newPayload";
-        let reth_params = serde_json::to_value((execution_data.clone(),))
-            .expect("ExecutionData serialization cannot fail");
+) -> eyre::Result<Option<NewPayloadTimingBreakdown>> {
+    let method = version.map(|v| v.method_name()).unwrap_or("reth_newPayload");
 
-        debug!(target: "reth-bench", method, "Sending newPayload");
+    debug!(target: "reth-bench", method, "Sending newPayload");
 
-        let mut resp: RethPayloadStatus = provider.client().request(method, &reth_params).await?;
+    let resp = loop {
+        let resp: serde_json::Value = provider.client().request(method, &params).await?;
+        let status = PayloadStatus::deserialize(&resp)?;
 
-        while !resp.status.is_valid() {
-            if resp.status.is_invalid() {
-                error!(target: "reth-bench", status=?resp.status, "Invalid {method}");
-                return Err(alloy_json_rpc::RpcError::LocalUsageError(Box::new(
-                    std::io::Error::other(format!("Invalid {method}: {:?}", resp.status)),
-                )))
-            }
-            if resp.status.is_syncing() {
-                return Err(alloy_json_rpc::RpcError::UnsupportedFeature(
-                    "invalid range: no canonical state found for parent of requested block",
-                ))
-            }
-            resp = provider.client().request(method, &reth_params).await?;
+        if status.is_valid() {
+            break resp;
         }
-
-        Ok(Some(NewPayloadTimingBreakdown {
-            latency: Duration::from_micros(resp.latency_us),
-            persistence_wait: resp.persistence_wait_us.map(Duration::from_micros),
-            execution_cache_wait: Duration::from_micros(resp.execution_cache_wait_us),
-            sparse_trie_wait: Duration::from_micros(resp.sparse_trie_wait_us),
-        }))
-    } else {
-        let method = version.method_name();
-
-        debug!(target: "reth-bench", method, "Sending newPayload");
-
-        let mut status: PayloadStatus = provider.client().request(method, &params).await?;
-
-        while !status.is_valid() {
-            if status.is_invalid() {
-                error!(target: "reth-bench", ?status, ?params, "Invalid {method}",);
-                return Err(alloy_json_rpc::RpcError::LocalUsageError(Box::new(
-                    std::io::Error::other(format!("Invalid {method}: {status:?}")),
-                )))
-            }
-            if status.is_syncing() {
-                return Err(alloy_json_rpc::RpcError::UnsupportedFeature(
-                    "invalid range: no canonical state found for parent of requested block",
-                ))
-            }
-            status = provider.client().request(method, &params).await?;
+        if status.is_invalid() {
+            return Err(eyre::eyre!("Invalid {method}: {status:?}"));
         }
-        Ok(None)
+        if status.is_syncing() {
+            return Err(eyre::eyre!(
+                "invalid range: no canonical state found for parent of requested block"
+            ));
+        }
+    };
+
+    if version.is_some() {
+        return Ok(None);
     }
+
+    let resp: RethPayloadStatus = serde_json::from_value(resp)?;
+
+    Ok(Some(NewPayloadTimingBreakdown {
+        latency: Duration::from_micros(resp.latency_us),
+        persistence_wait: resp.persistence_wait_us.map(Duration::from_micros),
+        execution_cache_wait: Duration::from_micros(resp.execution_cache_wait_us),
+        sparse_trie_wait: Duration::from_micros(resp.sparse_trie_wait_us),
+    }))
 }
 
 /// Calls the correct `engine_forkchoiceUpdated` method depending on the given
@@ -403,20 +395,25 @@ pub(crate) async fn call_forkchoice_updated_with_reth<
     P: Provider<N> + EngineApiValidWaitExt<N>,
 >(
     provider: P,
-    message_version: EngineApiMessageVersion,
+    message_version: Option<EngineApiMessageVersion>,
     forkchoice_state: ForkchoiceState,
-    use_reth: bool,
 ) -> TransportResult<ForkchoiceUpdated> {
-    if use_reth {
+    if let Some(message_version) = message_version {
+        call_forkchoice_updated(provider, message_version, forkchoice_state, None).await
+    } else {
         let method = "reth_forkchoiceUpdated";
         let reth_params = serde_json::to_value((forkchoice_state,))
             .expect("ForkchoiceState serialization cannot fail");
 
         debug!(target: "reth-bench", method, "Sending forkchoiceUpdated");
 
-        let mut resp: ForkchoiceUpdated = provider.client().request(method, &reth_params).await?;
+        loop {
+            let resp: ForkchoiceUpdated = provider.client().request(method, &reth_params).await?;
+
+            if resp.is_valid() {
+                break Ok(resp)
+            }
 
-        while !resp.is_valid() {
             if resp.is_invalid() {
                 error!(target: "reth-bench", ?resp, "Invalid {method}");
                 return Err(alloy_json_rpc::RpcError::LocalUsageError(Box::new(
@@ -428,11 +425,6 @@ pub(crate) async fn call_forkchoice_updated_with_reth<
                     "invalid range: no canonical state found for parent of requested block",
                 ))
             }
-            resp = provider.client().request(method, &reth_params).await?;
         }
-
-        Ok(resp)
-    } else {
-        call_forkchoice_updated(provider, message_version, forkchoice_state, None).await
     }
 }

crates/chain-state/Cargo.toml

@@ -56,7 +56,6 @@ alloy-signer.workspace = true
 alloy-signer-local.workspace = true
 rand.workspace = true
 revm-state.workspace = true
-criterion.workspace = true
 
 [features]
 serde = [
@@ -86,8 +85,3 @@ test-utils = [
     "reth-ethereum-primitives/test-utils",
 ]
 rayon = ["dep:rayon"]
-
-[[bench]]
-name = "canonical_hashes_range"
-harness = false
-required-features = ["test-utils"]

crates/chain-state/benches/canonical_hashes_range.rs

@@ -1,96 +0,0 @@
-#![allow(missing_docs)]
-
-use criterion::{black_box, criterion_group, criterion_main, Criterion};
-use reth_chain_state::{
-    test_utils::TestBlockBuilder, ExecutedBlock, MemoryOverlayStateProviderRef,
-};
-use reth_ethereum_primitives::EthPrimitives;
-use reth_storage_api::{noop::NoopProvider, BlockHashReader};
-
-criterion_group!(benches, bench_canonical_hashes_range);
-criterion_main!(benches);
-
-fn bench_canonical_hashes_range(c: &mut Criterion) {
-    let mut group = c.benchmark_group("canonical_hashes_range");
-
-    let scenarios = [("small", 10), ("medium", 100), ("large", 1000)];
-
-    for (name, num_blocks) in scenarios {
-        group.bench_function(format!("{}_blocks_{}", name, num_blocks), |b| {
-            let (provider, blocks) = setup_provider_with_blocks(num_blocks);
-            let start_block = blocks[0].recovered_block().number;
-            let end_block = blocks[num_blocks / 2].recovered_block().number;
-
-            b.iter(|| {
-                black_box(
-                    provider
-                        .canonical_hashes_range(black_box(start_block), black_box(end_block))
-                        .unwrap(),
-                )
-            })
-        });
-    }
-
-    let (provider, blocks) = setup_provider_with_blocks(500);
-    let base_block = blocks[100].recovered_block().number;
-
-    let range_sizes = [1, 10, 50, 100, 250];
-    for range_size in range_sizes {
-        group.bench_function(format!("range_size_{}", range_size), |b| {
-            let end_block = base_block + range_size;
-
-            b.iter(|| {
-                black_box(
-                    provider
-                        .canonical_hashes_range(black_box(base_block), black_box(end_block))
-                        .unwrap(),
-                )
-            })
-        });
-    }
-
-    // Benchmark edge cases
-    group.bench_function("no_in_memory_matches", |b| {
-        let (provider, blocks) = setup_provider_with_blocks(100);
-        let first_block = blocks[0].recovered_block().number;
-        let start_block = first_block - 50;
-        let end_block = first_block - 10;
-
-        b.iter(|| {
-            black_box(
-                provider
-                    .canonical_hashes_range(black_box(start_block), black_box(end_block))
-                    .unwrap(),
-            )
-        })
-    });
-
-    group.bench_function("all_in_memory_matches", |b| {
-        let (provider, blocks) = setup_provider_with_blocks(100);
-        let first_block = blocks[0].recovered_block().number;
-        let last_block = blocks[blocks.len() - 1].recovered_block().number;
-
-        b.iter(|| {
-            black_box(
-                provider
-                    .canonical_hashes_range(black_box(first_block), black_box(last_block + 1))
-                    .unwrap(),
-            )
-        })
-    });
-
-    group.finish();
-}
-
-fn setup_provider_with_blocks(
-    num_blocks: usize,
-) -> (MemoryOverlayStateProviderRef<'static, EthPrimitives>, Vec<ExecutedBlock<EthPrimitives>>) {
-    let mut builder = TestBlockBuilder::<EthPrimitives>::default();
-
-    let blocks: Vec<_> = builder.get_executed_blocks(1000..1000 + num_blocks as u64).collect();
-
-    let historical = Box::new(NoopProvider::default());
-    let provider = MemoryOverlayStateProviderRef::new(historical, blocks.clone());
-
-    (provider, blocks)
-}

crates/chain-state/src/deferred_trie.rs

@@ -9,7 +9,7 @@ use std::{
     fmt,
     sync::{Arc, LazyLock},
 };
-use tracing::instrument;
+use tracing::{debug_span, instrument};
 
 /// Shared handle to asynchronously populated trie data.
 ///
@@ -163,6 +163,8 @@ impl DeferredTrieData {
         anchor_hash: B256,
         ancestors: &[Self],
     ) -> ComputedTrieData {
+        let _span = debug_span!(target: "engine::tree::deferred_trie", "sort_inputs").entered();
+
         #[cfg(feature = "rayon")]
         let (sorted_hashed_state, sorted_trie_updates) = rayon::join(
             || match Arc::try_unwrap(hashed_state) {
@@ -187,6 +189,10 @@ impl DeferredTrieData {
             },
         );
 
+        drop(_span);
+
+        let _span = debug_span!(target: "engine::tree::deferred_trie", "build_overlay").entered();
+
         // Reuse parent's overlay if available and anchors match.
         // We can only reuse the parent's overlay if it was built on top of the same
         // persisted anchor. If the anchor has changed (e.g., due to persistence),
@@ -205,6 +211,9 @@ impl DeferredTrieData {
                         Arc::clone(&trie_input.state),
                         Default::default(), // prefix_sets are per-block, not cumulative
                     );
+                    let _span =
+                        debug_span!(target: "engine::tree::deferred_trie", "extend_overlay")
+                            .entered();
                     // Only trigger COW clone if there's actually data to add.
                     #[cfg(feature = "rayon")]
                     {
@@ -272,6 +281,7 @@ impl DeferredTrieData {
         sorted_hashed_state: &HashedPostStateSorted,
         sorted_trie_updates: &TrieUpdatesSorted,
     ) -> TrieInputSorted {
+        let _span = debug_span!(target: "engine::tree::deferred_trie", "merge_ancestors", num_ancestors = ancestors.len()).entered();
         let mut overlay = TrieInputSorted::default();
 
         let state_mut = Arc::make_mut(&mut overlay.state);

crates/chain-state/src/execution_stats.rs

@@ -0,0 +1,69 @@
+//! Execution timing statistics for detailed block logging.
+//!
+//! This module provides types for collecting and passing execution timing statistics
+//! through the block processing pipeline, enabling unified detailed block logging after
+//! database commit.
+
+use std::time::Duration;
+
+use alloy_primitives::B256;
+
+/// Statistics collected during block execution for cross-client performance analysis.
+///
+/// These statistics are populated during block validation and carried through to
+/// persistence, where they are used to emit a single unified log entry that includes
+/// complete timing information (including commit time).
+#[derive(Debug, Clone, Default)]
+pub struct ExecutionTimingStats {
+    /// Block number
+    pub block_number: u64,
+    /// Block hash
+    pub block_hash: B256,
+    /// Total gas used by the block
+    pub gas_used: u64,
+    /// Number of transactions in the block
+    pub tx_count: usize,
+    /// Time spent executing transactions (includes state reads)
+    pub execution_duration: Duration,
+    /// Time spent fetching state during execution (subset of `execution_duration`, includes cache
+    /// hits)
+    pub state_read_duration: Duration,
+    /// Time spent computing state root hash
+    pub state_hash_duration: Duration,
+    /// Number of accounts read during execution
+    pub accounts_read: usize,
+    /// Number of storage slots read (SLOAD operations)
+    pub storage_read: usize,
+    /// Number of code reads (EXTCODE* operations)
+    pub code_read: usize,
+    /// Total bytes of code read
+    pub code_bytes_read: usize,
+    /// Number of accounts changed (balance/nonce updates)
+    pub accounts_changed: usize,
+    /// Number of accounts deleted (SELFDESTRUCT)
+    pub accounts_deleted: usize,
+    /// Number of storage slots changed (SSTORE operations)
+    pub storage_slots_changed: usize,
+    /// Number of storage slots deleted (set to zero)
+    pub storage_slots_deleted: usize,
+    /// Number of bytecodes created/changed (contract deployments)
+    pub bytecodes_changed: usize,
+    /// Total bytes of code written
+    pub code_bytes_written: usize,
+    /// Number of EIP-7702 delegations set
+    pub eip7702_delegations_set: usize,
+    /// Number of EIP-7702 delegations cleared
+    pub eip7702_delegations_cleared: usize,
+    /// Account cache hits
+    pub account_cache_hits: usize,
+    /// Account cache misses
+    pub account_cache_misses: usize,
+    /// Storage cache hits
+    pub storage_cache_hits: usize,
+    /// Storage cache misses
+    pub storage_cache_misses: usize,
+    /// Code cache hits
+    pub code_cache_hits: usize,
+    /// Code cache misses
+    pub code_cache_misses: usize,
+}

crates/chain-state/src/lib.rs

@@ -8,6 +8,9 @@
 #![cfg_attr(not(test), warn(unused_crate_dependencies))]
 #![cfg_attr(docsrs, feature(doc_cfg))]
 
+mod execution_stats;
+pub use execution_stats::ExecutionTimingStats;
+
 mod in_memory;
 pub use in_memory::*;
 

crates/chainspec/src/spec.rs

@@ -855,15 +855,9 @@ impl From<Genesis> for ChainSpec {
                             // those networks we use the activation
                             // blocks of those networks
                             match genesis.config.chain_id {
-                                1 => {
-                                    if ttd == MAINNET_PARIS_TTD {
-                                        return Some(MAINNET_PARIS_BLOCK)
-                                    }
-                                }
-                                11155111 => {
-                                    if ttd == SEPOLIA_PARIS_TTD {
-                                        return Some(SEPOLIA_PARIS_BLOCK)
-                                    }
+                                1 if ttd == MAINNET_PARIS_TTD => return Some(MAINNET_PARIS_BLOCK),
+                                11155111 if ttd == SEPOLIA_PARIS_TTD => {
+                                    return Some(SEPOLIA_PARIS_BLOCK)
                                 }
                                 _ => {}
                             };

crates/cli/cli/src/lib.rs

@@ -21,7 +21,7 @@ use crate::chainspec::ChainSpecParser;
 ///
 /// This trait is supposed to be implemented by the main struct of the CLI.
 ///
-/// It provides commonly used functionality for running commands and information about the CL, such
+/// It provides commonly used functionality for running commands and information about the CLI, such
 /// as the name and version.
 pub trait RethCli: Sized {
     /// The associated `ChainSpecParser` type

crates/cli/commands/Cargo.toml

@@ -46,7 +46,7 @@ reth-prune.workspace = true
 reth-prune-types.workspace = true
 reth-revm.workspace = true
 reth-stages.workspace = true
-reth-stages-types = { workspace = true, optional = true }
+reth-stages-types.workspace = true
 reth-static-file-types = { workspace = true, features = ["clap"] }
 reth-static-file.workspace = true
 reth-tasks.workspace = true
@@ -87,6 +87,8 @@ tokio-stream.workspace = true
 reqwest.workspace = true
 url.workspace = true
 metrics.workspace = true
+blake3.workspace = true
+rayon.workspace = true
 
 # io
 fdlimit.workspace = true
@@ -127,7 +129,7 @@ arbitrary = [
     "reth-trie-common?/test-utils",
     "reth-codecs/arbitrary",
     "reth-prune-types/arbitrary",
-    "reth-stages-types?/arbitrary",
+    "reth-stages-types/arbitrary",
     "reth-trie-common?/arbitrary",
     "alloy-consensus/arbitrary",
     "reth-primitives-traits/arbitrary",

crates/cli/commands/src/common.rs

@@ -73,17 +73,12 @@ pub struct EnvironmentArgs<C: ChainSpecParser> {
 }
 
 impl<C: ChainSpecParser> EnvironmentArgs<C> {
-    /// Returns the effective storage settings derived from `--storage.v2`.
+    /// Returns the storage settings for new database initialization.
     ///
-    /// The base storage mode is determined by `--storage.v2`:
-    /// - When `--storage.v2` is set: uses [`StorageSettings::v2()`] defaults
-    /// - Otherwise: uses [`StorageSettings::base()`] defaults
+    /// Always returns [`StorageSettings::v2()`] — v2 is the default for all new
+    /// databases. Existing databases use the settings persisted in their metadata.
     pub fn storage_settings(&self) -> StorageSettings {
-        if self.storage.v2 {
-            StorageSettings::v2()
-        } else {
-            StorageSettings::base()
-        }
+        StorageSettings::v2()
     }
 
     /// Initializes environment according to [`AccessRights`] and returns an instance of

crates/cli/commands/src/db/mod.rs

@@ -19,6 +19,7 @@ mod list;
 mod prune_checkpoints;
 mod repair_trie;
 mod settings;
+mod stage_checkpoints;
 mod state;
 mod static_file_header;
 mod stats;
@@ -70,6 +71,8 @@ pub enum Subcommands {
     Settings(settings::Command),
     /// View or set prune checkpoints
     PruneCheckpoints(prune_checkpoints::Command),
+    // View or set stage checkpoints
+    StageCheckpoints(stage_checkpoints::Command),
     /// Gets storage size information for an account
     AccountStorage(account_storage::Command),
     /// Gets account state and storage at a specific block
@@ -99,14 +102,14 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> Command<C>
         let static_files_path = data_dir.static_files();
         let exex_wal_path = data_dir.exex_wal();
 
-        // ensure the provided datadir exist
+        // ensure the provided datadir exists
         eyre::ensure!(
             data_dir.data_dir().is_dir(),
             "Datadir does not exist: {:?}",
             data_dir.data_dir()
         );
 
-        // ensure the provided database exist
+        // ensure the provided database exists
         eyre::ensure!(db_path.is_dir(), "Database does not exist: {:?}", db_path);
 
         match self.command {
@@ -213,6 +216,11 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> Command<C>
                     command.execute(&tool)?;
                 });
             }
+            Subcommands::StageCheckpoints(command) => {
+                db_exec!(self.env, tool, N, command.access_rights(), {
+                    command.execute(&tool)?;
+                });
+            }
             Subcommands::AccountStorage(command) => {
                 db_exec!(self.env, tool, N, AccessRights::RO, {
                     command.execute(&tool)?;

crates/cli/commands/src/db/stage_checkpoints.rs

@@ -0,0 +1,297 @@
+//! `reth db stage-checkpoints` command for viewing and setting stage checkpoint values.
+
+use clap::{Args, Parser, Subcommand, ValueEnum};
+use reth_db_common::DbTool;
+use reth_provider::{
+    providers::ProviderNodeTypes, DBProvider, DatabaseProviderFactory, StageCheckpointReader,
+    StageCheckpointWriter,
+};
+use reth_stages::StageId;
+
+use crate::common::AccessRights;
+
+/// `reth db stage-checkpoints` subcommand
+#[derive(Debug, Parser)]
+pub struct Command {
+    #[command(subcommand)]
+    command: Subcommands,
+}
+
+impl Command {
+    /// Returns database access rights required for the command.
+    pub fn access_rights(&self) -> AccessRights {
+        match &self.command {
+            Subcommands::Get { .. } => AccessRights::RO,
+            Subcommands::Set(_) => AccessRights::RW,
+        }
+    }
+
+    /// Execute the command
+    pub fn execute<N: ProviderNodeTypes>(self, tool: &DbTool<N>) -> eyre::Result<()> {
+        match self.command {
+            Subcommands::Get { stage } => Self::get(tool, stage),
+            Subcommands::Set(args) => Self::set(tool, args),
+        }
+    }
+
+    fn get<N: ProviderNodeTypes>(tool: &DbTool<N>, stage: Option<StageArg>) -> eyre::Result<()> {
+        let provider = tool.provider_factory.provider()?;
+
+        match stage {
+            Some(stage) => {
+                let stage_id = stage.into();
+                let checkpoint = provider.get_stage_checkpoint(stage_id)?;
+                println!("{stage_id}: {checkpoint:?}");
+            }
+            None => {
+                let mut checkpoints = provider.get_all_checkpoints()?;
+                checkpoints.sort_by(|a, b| a.0.cmp(&b.0));
+                for (stage, checkpoint) in checkpoints {
+                    println!("{stage}: {checkpoint:?}");
+                }
+            }
+        }
+
+        Ok(())
+    }
+
+    fn set<N: ProviderNodeTypes>(tool: &DbTool<N>, args: SetArgs) -> eyre::Result<()> {
+        let stage_id: StageId = args.stage.into();
+        let provider_rw = tool.provider_factory.database_provider_rw()?;
+
+        let previous = provider_rw.get_stage_checkpoint(stage_id)?;
+        let mut checkpoint = previous.unwrap_or_default();
+        checkpoint.block_number = args.block_number;
+
+        if args.clear_stage_unit {
+            checkpoint.stage_checkpoint = None;
+        }
+
+        provider_rw.save_stage_checkpoint(stage_id, checkpoint)?;
+
+        provider_rw.commit()?;
+
+        println!("Updated checkpoint for {stage_id}: {checkpoint:?}");
+
+        Ok(())
+    }
+}
+
+#[derive(Debug, Subcommand)]
+enum Subcommands {
+    /// Get stage checkpoint(s) from database.
+    Get {
+        /// Specific stage to query. If omitted, shows all stages.
+        #[arg(long, value_enum)]
+        stage: Option<StageArg>,
+    },
+    /// Set a stage checkpoint.
+    Set(SetArgs),
+}
+
+/// Arguments for the `set` subcommand.
+#[derive(Debug, Args)]
+pub struct SetArgs {
+    /// Stage to update.
+    #[arg(long, value_enum)]
+    stage: StageArg,
+
+    /// Block number to set as stage checkpoint.
+    #[arg(long)]
+    block_number: u64,
+
+    /// Clear stage-specific unit checkpoint payload.
+    #[arg(long)]
+    clear_stage_unit: bool,
+}
+
+/// CLI-friendly stage names.
+#[derive(Debug, Clone, Copy, ValueEnum)]
+#[clap(rename_all = "kebab-case")]
+pub enum StageArg {
+    Era,
+    Headers,
+    Bodies,
+    SenderRecovery,
+    Execution,
+    PruneSenderRecovery,
+    MerkleUnwind,
+    AccountHashing,
+    StorageHashing,
+    MerkleExecute,
+    TransactionLookup,
+    IndexStorageHistory,
+    IndexAccountHistory,
+    Prune,
+    Finish,
+}
+
+impl From<StageArg> for StageId {
+    fn from(arg: StageArg) -> Self {
+        match arg {
+            StageArg::Era => Self::Era,
+            StageArg::Headers => Self::Headers,
+            StageArg::Bodies => Self::Bodies,
+            StageArg::SenderRecovery => Self::SenderRecovery,
+            StageArg::Execution => Self::Execution,
+            StageArg::PruneSenderRecovery => Self::PruneSenderRecovery,
+            StageArg::MerkleUnwind => Self::MerkleUnwind,
+            StageArg::AccountHashing => Self::AccountHashing,
+            StageArg::StorageHashing => Self::StorageHashing,
+            StageArg::MerkleExecute => Self::MerkleExecute,
+            StageArg::TransactionLookup => Self::TransactionLookup,
+            StageArg::IndexStorageHistory => Self::IndexStorageHistory,
+            StageArg::IndexAccountHistory => Self::IndexAccountHistory,
+            StageArg::Prune => Self::Prune,
+            StageArg::Finish => Self::Finish,
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use clap::Parser;
+    use reth_provider::{
+        test_utils::create_test_provider_factory, DBProvider, DatabaseProviderFactory,
+        StageCheckpointReader, StageCheckpointWriter,
+    };
+    use reth_stages::StageCheckpoint;
+
+    #[test]
+    fn parse_set_args() {
+        let command = Command::parse_from([
+            "stage-checkpoints",
+            "set",
+            "--stage",
+            "headers",
+            "--block-number",
+            "123",
+        ]);
+
+        assert!(matches!(
+            command.command,
+            Subcommands::Set(SetArgs {
+                stage: StageArg::Headers,
+                block_number: 123,
+                clear_stage_unit: false,
+            })
+        ));
+    }
+
+    #[test]
+    fn set_overwrites_block_number() {
+        let provider_factory = create_test_provider_factory();
+        let tool = DbTool::new(provider_factory.clone()).expect("db tool");
+
+        {
+            let provider_rw = provider_factory.database_provider_rw().expect("rw provider");
+            provider_rw
+                .save_stage_checkpoint(StageId::Headers, StageCheckpoint::new(10))
+                .expect("save checkpoint");
+            provider_rw.commit().expect("commit initial checkpoint");
+        }
+
+        let command = Command {
+            command: Subcommands::Set(SetArgs {
+                stage: StageArg::Headers,
+                block_number: 42,
+                clear_stage_unit: false,
+            }),
+        };
+
+        command.execute(&tool).expect("execute command");
+
+        let provider = provider_factory.provider().expect("provider");
+        let checkpoint = provider
+            .get_stage_checkpoint(StageId::Headers)
+            .expect("get stage checkpoint")
+            .expect("missing stage checkpoint");
+
+        assert_eq!(checkpoint.block_number, 42);
+    }
+
+    #[test]
+    fn set_preserves_stage_unit_checkpoint_unless_cleared() {
+        let provider_factory = create_test_provider_factory();
+        let tool = DbTool::new(provider_factory.clone()).expect("db tool");
+
+        {
+            let provider_rw = provider_factory.database_provider_rw().expect("rw provider");
+            let checkpoint = StageCheckpoint::new(10).with_block_range(&StageId::Execution, 5, 10);
+            provider_rw
+                .save_stage_checkpoint(StageId::Execution, checkpoint)
+                .expect("save checkpoint");
+            provider_rw.commit().expect("commit initial checkpoint");
+        }
+
+        Command {
+            command: Subcommands::Set(SetArgs {
+                stage: StageArg::Execution,
+                block_number: 11,
+                clear_stage_unit: false,
+            }),
+        }
+        .execute(&tool)
+        .expect("execute command");
+
+        let provider = provider_factory.provider().expect("provider");
+        let checkpoint = provider
+            .get_stage_checkpoint(StageId::Execution)
+            .expect("get stage checkpoint")
+            .expect("missing stage checkpoint");
+        assert!(checkpoint.stage_checkpoint.is_some());
+
+        Command {
+            command: Subcommands::Set(SetArgs {
+                stage: StageArg::Execution,
+                block_number: 12,
+                clear_stage_unit: true,
+            }),
+        }
+        .execute(&tool)
+        .expect("execute command");
+
+        let checkpoint = provider_factory
+            .provider()
+            .expect("provider")
+            .get_stage_checkpoint(StageId::Execution)
+            .expect("get stage checkpoint")
+            .expect("missing stage checkpoint");
+        assert!(checkpoint.stage_checkpoint.is_none());
+    }
+
+    #[test]
+    fn set_preserves_checkpoint_progress() {
+        let provider_factory = create_test_provider_factory();
+        let tool = DbTool::new(provider_factory.clone()).expect("db tool");
+
+        {
+            let provider_rw = provider_factory.database_provider_rw().expect("rw provider");
+            provider_rw
+                .save_stage_checkpoint(StageId::MerkleExecute, StageCheckpoint::new(10))
+                .expect("save checkpoint");
+            provider_rw
+                .save_stage_checkpoint_progress(StageId::MerkleExecute, vec![1, 2, 3])
+                .expect("save progress");
+            provider_rw.commit().expect("commit initial checkpoint");
+        }
+
+        Command {
+            command: Subcommands::Set(SetArgs {
+                stage: StageArg::MerkleExecute,
+                block_number: 20,
+                clear_stage_unit: false,
+            }),
+        }
+        .execute(&tool)
+        .expect("execute command");
+
+        let provider = provider_factory.provider().expect("provider");
+        let progress = provider
+            .get_stage_checkpoint_progress(StageId::MerkleExecute)
+            .expect("get stage checkpoint progress");
+
+        assert_eq!(progress, Some(vec![1, 2, 3]));
+    }
+}

crates/cli/commands/src/db/state.rs

@@ -9,7 +9,7 @@ use reth_db_api::{
 };
 use reth_db_common::DbTool;
 use reth_node_builder::NodeTypesWithDB;
-use reth_provider::providers::ProviderNodeTypes;
+use reth_provider::{providers::ProviderNodeTypes, StaticFileProviderFactory};
 use reth_storage_api::{BlockNumReader, StateProvider, StorageSettingsCache};
 use reth_tasks::spawn_scoped_os_thread;
 use std::{
@@ -17,9 +17,9 @@ use std::{
     thread,
     time::{Duration, Instant},
 };
-use tracing::{error, info};
+use tracing::info;
 
-/// Log progress every 5 seconds
+/// Log progress every 30 seconds
 const LOG_INTERVAL: Duration = Duration::from_secs(30);
 
 /// The arguments for the `reth db state` command
@@ -152,17 +152,11 @@ impl Command {
         let mut storage_keys = BTreeSet::new();
 
         if history_in_rocksdb {
-            error!(
-                target: "reth::cli",
-                "Historical storage queries with RocksDB backend are not yet supported. \
-                 Use MDBX for storage history or query current state without --block."
-            );
-            return Ok(());
+            self.collect_staticfile_storage_keys(tool, address, &mut storage_keys)?;
+        } else {
+            self.collect_mdbx_storage_keys_parallel(tool, address, &mut storage_keys)?;
         }
 
-        // Collect keys from MDBX StorageChangeSets using parallel scanning
-        self.collect_mdbx_storage_keys_parallel(tool, address, &mut storage_keys)?;
-
         info!(
             target: "reth::cli",
             address = %address,
@@ -207,6 +201,63 @@ impl Command {
         Ok(())
     }
 
+    /// Collects storage keys from static file StorageChangeSets (storage_v2).
+    fn collect_staticfile_storage_keys<N: NodeTypesWithDB + ProviderNodeTypes>(
+        &self,
+        tool: &DbTool<N>,
+        address: Address,
+        keys: &mut BTreeSet<B256>,
+    ) -> eyre::Result<()> {
+        let tip = tool.provider_factory.provider()?.best_block_number()?;
+
+        if tip == 0 {
+            return Ok(());
+        }
+
+        info!(
+            target: "reth::cli",
+            address = %address,
+            tip,
+            "Scanning static file storage changesets"
+        );
+
+        let static_file_provider = tool.provider_factory.static_file_provider();
+        let walker = static_file_provider.walk_storage_changeset_range(0..=tip);
+
+        let mut total_scanned = 0usize;
+        let mut last_log = Instant::now();
+
+        for changeset_result in walker {
+            let (block_addr, storage_entry) = changeset_result?;
+            total_scanned += 1;
+
+            if block_addr.address() == address {
+                keys.insert(storage_entry.key);
+            }
+
+            if last_log.elapsed() >= LOG_INTERVAL {
+                info!(
+                    target: "reth::cli",
+                    address = %address,
+                    entries_scanned = total_scanned,
+                    unique_keys = keys.len(),
+                    "Scanning static file storage changesets"
+                );
+                last_log = Instant::now();
+            }
+        }
+
+        info!(
+            target: "reth::cli",
+            address = %address,
+            total_entries = total_scanned,
+            unique_keys = keys.len(),
+            "Finished static file storage changeset scan"
+        );
+
+        Ok(())
+    }
+
     /// Collects storage keys from MDBX StorageChangeSets using parallel block range scanning.
     fn collect_mdbx_storage_keys_parallel<N: NodeTypesWithDB + ProviderNodeTypes>(
         &self,

crates/cli/commands/src/db/tui.rs

@@ -297,21 +297,18 @@ where
     }
 
     match event {
-        Event::Key(key) => {
-            if key.kind == event::KeyEventKind::Press {
-                match key.code {
-                    KeyCode::Char('q') | KeyCode::Char('Q') => return Ok(true),
-                    KeyCode::Down => app.next(),
-                    KeyCode::Up => app.previous(),
-                    KeyCode::Right => app.next_page(),
-                    KeyCode::Left => app.previous_page(),
-                    KeyCode::Char('G') => {
-                        app.mode = ViewMode::GoToPage;
-                    }
-                    _ => {}
-                }
+        Event::Key(key) if key.kind == event::KeyEventKind::Press => match key.code {
+            KeyCode::Char('q') | KeyCode::Char('Q') => return Ok(true),
+            KeyCode::Down => app.next(),
+            KeyCode::Up => app.previous(),
+            KeyCode::Right => app.next_page(),
+            KeyCode::Left => app.previous_page(),
+            KeyCode::Char('G') => {
+                app.mode = ViewMode::GoToPage;
             }
-        }
+            _ => {}
+        },
+        Event::Key(_) => {}
         Event::Mouse(e) => match e.kind {
             MouseEventKind::ScrollDown => app.next(),
             MouseEventKind::ScrollUp => app.previous(),

crates/cli/commands/src/download.rs

@@ -1,630 +0,0 @@
-use crate::common::EnvironmentArgs;
-use clap::Parser;
-use eyre::Result;
-use lz4::Decoder;
-use reqwest::{blocking::Client as BlockingClient, header::RANGE, Client, StatusCode};
-use reth_chainspec::{EthChainSpec, EthereumHardforks};
-use reth_cli::chainspec::ChainSpecParser;
-use reth_fs_util as fs;
-use std::{
-    borrow::Cow,
-    fs::OpenOptions,
-    io::{self, BufWriter, Read, Write},
-    path::{Path, PathBuf},
-    sync::{Arc, OnceLock},
-    time::{Duration, Instant},
-};
-use tar::Archive;
-use tokio::task;
-use tracing::info;
-use url::Url;
-use zstd::stream::read::Decoder as ZstdDecoder;
-
-const BYTE_UNITS: [&str; 4] = ["B", "KB", "MB", "GB"];
-const MERKLE_BASE_URL: &str = "https://downloads.merkle.io";
-const EXTENSION_TAR_LZ4: &str = ".tar.lz4";
-const EXTENSION_TAR_ZSTD: &str = ".tar.zst";
-
-/// Global static download defaults
-static DOWNLOAD_DEFAULTS: OnceLock<DownloadDefaults> = OnceLock::new();
-
-/// Download configuration defaults
-///
-/// Global defaults can be set via [`DownloadDefaults::try_init`].
-#[derive(Debug, Clone)]
-pub struct DownloadDefaults {
-    /// List of available snapshot sources
-    pub available_snapshots: Vec<Cow<'static, str>>,
-    /// Default base URL for snapshots
-    pub default_base_url: Cow<'static, str>,
-    /// Default base URL for chain-aware snapshots.
-    ///
-    /// When set, the chain ID is appended to form the full URL: `{base_url}/{chain_id}`.
-    /// For example, given a base URL of `https://snapshots.example.com` and chain ID `1`,
-    /// the resulting URL would be `https://snapshots.example.com/1`.
-    ///
-    /// Falls back to [`default_base_url`](Self::default_base_url) when `None`.
-    pub default_chain_aware_base_url: Option<Cow<'static, str>>,
-    /// Optional custom long help text that overrides the generated help
-    pub long_help: Option<String>,
-}
-
-impl DownloadDefaults {
-    /// Initialize the global download defaults with this configuration
-    pub fn try_init(self) -> Result<(), Self> {
-        DOWNLOAD_DEFAULTS.set(self)
-    }
-
-    /// Get a reference to the global download defaults
-    pub fn get_global() -> &'static DownloadDefaults {
-        DOWNLOAD_DEFAULTS.get_or_init(DownloadDefaults::default_download_defaults)
-    }
-
-    /// Default download configuration with defaults from merkle.io and publicnode
-    pub fn default_download_defaults() -> Self {
-        Self {
-            available_snapshots: vec![
-                Cow::Borrowed("https://www.merkle.io/snapshots (default, mainnet archive)"),
-                Cow::Borrowed("https://publicnode.com/snapshots (full nodes & testnets)"),
-            ],
-            default_base_url: Cow::Borrowed(MERKLE_BASE_URL),
-            default_chain_aware_base_url: None,
-            long_help: None,
-        }
-    }
-
-    /// Generates the long help text for the download URL argument using these defaults.
-    ///
-    /// If a custom long_help is set, it will be returned. Otherwise, help text is generated
-    /// from the available_snapshots list.
-    pub fn long_help(&self) -> String {
-        if let Some(ref custom_help) = self.long_help {
-            return custom_help.clone();
-        }
-
-        let mut help = String::from(
-            "Specify a snapshot URL or let the command propose a default one.\n\nAvailable snapshot sources:\n",
-        );
-
-        for source in &self.available_snapshots {
-            help.push_str("- ");
-            help.push_str(source);
-            help.push('\n');
-        }
-
-        help.push_str(
-            "\nIf no URL is provided, the latest archive snapshot for the selected chain\nwill be proposed for download from ",
-        );
-        help.push_str(
-            self.default_chain_aware_base_url.as_deref().unwrap_or(&self.default_base_url),
-        );
-        help.push_str(
-            ".\n\nLocal file:// URLs are also supported for extracting snapshots from disk.",
-        );
-        help
-    }
-
-    /// Add a snapshot source to the list
-    pub fn with_snapshot(mut self, source: impl Into<Cow<'static, str>>) -> Self {
-        self.available_snapshots.push(source.into());
-        self
-    }
-
-    /// Replace all snapshot sources
-    pub fn with_snapshots(mut self, sources: Vec<Cow<'static, str>>) -> Self {
-        self.available_snapshots = sources;
-        self
-    }
-
-    /// Set the default base URL, e.g. `https://downloads.merkle.io`.
-    pub fn with_base_url(mut self, url: impl Into<Cow<'static, str>>) -> Self {
-        self.default_base_url = url.into();
-        self
-    }
-
-    /// Set the default chain-aware base URL.
-    pub fn with_chain_aware_base_url(mut self, url: impl Into<Cow<'static, str>>) -> Self {
-        self.default_chain_aware_base_url = Some(url.into());
-        self
-    }
-
-    /// Builder: Set custom long help text, overriding the generated help
-    pub fn with_long_help(mut self, help: impl Into<String>) -> Self {
-        self.long_help = Some(help.into());
-        self
-    }
-}
-
-impl Default for DownloadDefaults {
-    fn default() -> Self {
-        Self::default_download_defaults()
-    }
-}
-
-#[derive(Debug, Parser)]
-pub struct DownloadCommand<C: ChainSpecParser> {
-    #[command(flatten)]
-    env: EnvironmentArgs<C>,
-
-    /// Custom URL to download the snapshot from
-    #[arg(long, short, long_help = DownloadDefaults::get_global().long_help())]
-    url: Option<String>,
-}
-
-impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> DownloadCommand<C> {
-    pub async fn execute<N>(self) -> Result<()> {
-        let data_dir = self.env.datadir.resolve_datadir(self.env.chain.chain());
-        fs::create_dir_all(&data_dir)?;
-
-        let url = match self.url {
-            Some(url) => url,
-            None => {
-                let url = get_latest_snapshot_url(self.env.chain.chain().id()).await?;
-                info!(target: "reth::cli", "Using default snapshot URL: {}", url);
-                url
-            }
-        };
-
-        info!(target: "reth::cli",
-            chain = %self.env.chain.chain(),
-            dir = ?data_dir.data_dir(),
-            url = %url,
-            "Starting snapshot download and extraction"
-        );
-
-        stream_and_extract(&url, data_dir.data_dir()).await?;
-        info!(target: "reth::cli", "Snapshot downloaded and extracted successfully");
-
-        Ok(())
-    }
-}
-
-impl<C: ChainSpecParser> DownloadCommand<C> {
-    /// Returns the underlying chain being used to run this command
-    pub fn chain_spec(&self) -> Option<&Arc<C::ChainSpec>> {
-        Some(&self.env.chain)
-    }
-}
-
-// Monitor process status and display progress every 100ms
-// to avoid overwhelming stdout
-struct DownloadProgress {
-    downloaded: u64,
-    total_size: u64,
-    last_displayed: Instant,
-    started_at: Instant,
-}
-
-impl DownloadProgress {
-    /// Creates new progress tracker with given total size
-    fn new(total_size: u64) -> Self {
-        let now = Instant::now();
-        Self { downloaded: 0, total_size, last_displayed: now, started_at: now }
-    }
-
-    /// Converts bytes to human readable format (B, KB, MB, GB)
-    fn format_size(size: u64) -> String {
-        let mut size = size as f64;
-        let mut unit_index = 0;
-
-        while size >= 1024.0 && unit_index < BYTE_UNITS.len() - 1 {
-            size /= 1024.0;
-            unit_index += 1;
-        }
-
-        format!("{:.2} {}", size, BYTE_UNITS[unit_index])
-    }
-
-    /// Format duration as human readable string
-    fn format_duration(duration: Duration) -> String {
-        let secs = duration.as_secs();
-        if secs < 60 {
-            format!("{secs}s")
-        } else if secs < 3600 {
-            format!("{}m {}s", secs / 60, secs % 60)
-        } else {
-            format!("{}h {}m", secs / 3600, (secs % 3600) / 60)
-        }
-    }
-
-    /// Updates progress bar
-    fn update(&mut self, chunk_size: u64) -> Result<()> {
-        self.downloaded += chunk_size;
-
-        // Only update display at most 10 times per second for efficiency
-        if self.last_displayed.elapsed() >= Duration::from_millis(100) {
-            let formatted_downloaded = Self::format_size(self.downloaded);
-            let formatted_total = Self::format_size(self.total_size);
-            let progress = (self.downloaded as f64 / self.total_size as f64) * 100.0;
-
-            // Calculate ETA based on current speed
-            let elapsed = self.started_at.elapsed();
-            let eta = if self.downloaded > 0 {
-                let remaining = self.total_size.saturating_sub(self.downloaded);
-                let speed = self.downloaded as f64 / elapsed.as_secs_f64();
-                if speed > 0.0 {
-                    Duration::from_secs_f64(remaining as f64 / speed)
-                } else {
-                    Duration::ZERO
-                }
-            } else {
-                Duration::ZERO
-            };
-            let eta_str = Self::format_duration(eta);
-
-            // Pad with spaces to clear any previous longer line
-            print!(
-                "\rDownloading and extracting... {progress:.2}% ({formatted_downloaded} / {formatted_total}) ETA: {eta_str}     ",
-            );
-            io::stdout().flush()?;
-            self.last_displayed = Instant::now();
-        }
-
-        Ok(())
-    }
-}
-
-/// Adapter to track progress while reading
-struct ProgressReader<R> {
-    reader: R,
-    progress: DownloadProgress,
-}
-
-impl<R: Read> ProgressReader<R> {
-    fn new(reader: R, total_size: u64) -> Self {
-        Self { reader, progress: DownloadProgress::new(total_size) }
-    }
-}
-
-impl<R: Read> Read for ProgressReader<R> {
-    fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> {
-        let bytes = self.reader.read(buf)?;
-        if bytes > 0 &&
-            let Err(e) = self.progress.update(bytes as u64)
-        {
-            return Err(io::Error::other(e));
-        }
-        Ok(bytes)
-    }
-}
-
-/// Supported compression formats for snapshots
-#[derive(Debug, Clone, Copy)]
-enum CompressionFormat {
-    Lz4,
-    Zstd,
-}
-
-impl CompressionFormat {
-    /// Detect compression format from file extension
-    fn from_url(url: &str) -> Result<Self> {
-        let path =
-            Url::parse(url).map(|u| u.path().to_string()).unwrap_or_else(|_| url.to_string());
-
-        if path.ends_with(EXTENSION_TAR_LZ4) {
-            Ok(Self::Lz4)
-        } else if path.ends_with(EXTENSION_TAR_ZSTD) {
-            Ok(Self::Zstd)
-        } else {
-            Err(eyre::eyre!(
-                "Unsupported file format. Expected .tar.lz4 or .tar.zst, got: {}",
-                path
-            ))
-        }
-    }
-}
-
-/// Extracts a compressed tar archive to the target directory with progress tracking.
-fn extract_archive<R: Read>(
-    reader: R,
-    total_size: u64,
-    format: CompressionFormat,
-    target_dir: &Path,
-) -> Result<()> {
-    let progress_reader = ProgressReader::new(reader, total_size);
-
-    match format {
-        CompressionFormat::Lz4 => {
-            let decoder = Decoder::new(progress_reader)?;
-            Archive::new(decoder).unpack(target_dir)?;
-        }
-        CompressionFormat::Zstd => {
-            let decoder = ZstdDecoder::new(progress_reader)?;
-            Archive::new(decoder).unpack(target_dir)?;
-        }
-    }
-
-    info!(target: "reth::cli", "Extraction complete.");
-    Ok(())
-}
-
-/// Extracts a snapshot from a local file.
-fn extract_from_file(path: &Path, format: CompressionFormat, target_dir: &Path) -> Result<()> {
-    let file = std::fs::File::open(path)?;
-    let total_size = file.metadata()?.len();
-    extract_archive(file, total_size, format, target_dir)
-}
-
-const MAX_DOWNLOAD_RETRIES: u32 = 10;
-const RETRY_BACKOFF_SECS: u64 = 5;
-
-/// Wrapper that tracks download progress while writing data.
-/// Used with [`io::copy`] to display progress during downloads.
-struct ProgressWriter<W> {
-    inner: W,
-    progress: DownloadProgress,
-}
-
-impl<W: Write> Write for ProgressWriter<W> {
-    fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
-        let n = self.inner.write(buf)?;
-        let _ = self.progress.update(n as u64);
-        Ok(n)
-    }
-
-    fn flush(&mut self) -> io::Result<()> {
-        self.inner.flush()
-    }
-}
-
-/// Downloads a file with resume support using HTTP Range requests.
-/// Automatically retries on failure, resuming from where it left off.
-/// Returns the path to the downloaded file and its total size.
-fn resumable_download(url: &str, target_dir: &Path) -> Result<(PathBuf, u64)> {
-    let file_name = Url::parse(url)
-        .ok()
-        .and_then(|u| u.path_segments()?.next_back().map(|s| s.to_string()))
-        .unwrap_or_else(|| "snapshot.tar".to_string());
-
-    let final_path = target_dir.join(&file_name);
-    let part_path = target_dir.join(format!("{file_name}.part"));
-
-    let client = BlockingClient::builder().timeout(Duration::from_secs(30)).build()?;
-
-    let mut total_size: Option<u64> = None;
-    let mut last_error: Option<eyre::Error> = None;
-
-    let finalize_download = |size: u64| -> Result<(PathBuf, u64)> {
-        fs::rename(&part_path, &final_path)?;
-        info!(target: "reth::cli", "Download complete: {}", final_path.display());
-        Ok((final_path.clone(), size))
-    };
-
-    for attempt in 1..=MAX_DOWNLOAD_RETRIES {
-        let existing_size = fs::metadata(&part_path).map(|m| m.len()).unwrap_or(0);
-
-        if let Some(total) = total_size &&
-            existing_size >= total
-        {
-            return finalize_download(total);
-        }
-
-        if attempt > 1 {
-            info!(target: "reth::cli",
-                "Retry attempt {}/{} - resuming from {} bytes",
-                attempt, MAX_DOWNLOAD_RETRIES, existing_size
-            );
-        }
-
-        let mut request = client.get(url);
-        if existing_size > 0 {
-            request = request.header(RANGE, format!("bytes={existing_size}-"));
-            if attempt == 1 {
-                info!(target: "reth::cli", "Resuming download from {} bytes", existing_size);
-            }
-        }
-
-        let response = match request.send().and_then(|r| r.error_for_status()) {
-            Ok(r) => r,
-            Err(e) => {
-                last_error = Some(e.into());
-                if attempt < MAX_DOWNLOAD_RETRIES {
-                    info!(target: "reth::cli",
-                        "Download failed, retrying in {} seconds...", RETRY_BACKOFF_SECS
-                    );
-                    std::thread::sleep(Duration::from_secs(RETRY_BACKOFF_SECS));
-                }
-                continue;
-            }
-        };
-
-        let is_partial = response.status() == StatusCode::PARTIAL_CONTENT;
-
-        let size = if is_partial {
-            response
-                .headers()
-                .get("Content-Range")
-                .and_then(|v| v.to_str().ok())
-                .and_then(|v| v.split('/').next_back())
-                .and_then(|v| v.parse().ok())
-        } else {
-            response.content_length()
-        };
-
-        if total_size.is_none() {
-            total_size = size;
-        }
-
-        let current_total = total_size.ok_or_else(|| {
-            eyre::eyre!("Server did not provide Content-Length or Content-Range header")
-        })?;
-
-        let file = if is_partial && existing_size > 0 {
-            OpenOptions::new()
-                .append(true)
-                .open(&part_path)
-                .map_err(|e| fs::FsPathError::open(e, &part_path))?
-        } else {
-            fs::create_file(&part_path)?
-        };
-
-        let start_offset = if is_partial { existing_size } else { 0 };
-        let mut progress = DownloadProgress::new(current_total);
-        progress.downloaded = start_offset;
-
-        let mut writer = ProgressWriter { inner: BufWriter::new(file), progress };
-        let mut reader = response;
-
-        let copy_result = io::copy(&mut reader, &mut writer);
-        let flush_result = writer.inner.flush();
-        println!();
-
-        if let Err(e) = copy_result.and(flush_result) {
-            last_error = Some(e.into());
-            if attempt < MAX_DOWNLOAD_RETRIES {
-                info!(target: "reth::cli",
-                    "Download interrupted, retrying in {} seconds...", RETRY_BACKOFF_SECS
-                );
-                std::thread::sleep(Duration::from_secs(RETRY_BACKOFF_SECS));
-            }
-            continue;
-        }
-
-        return finalize_download(current_total);
-    }
-
-    Err(last_error
-        .unwrap_or_else(|| eyre::eyre!("Download failed after {} attempts", MAX_DOWNLOAD_RETRIES)))
-}
-
-/// Fetches the snapshot from a remote URL with resume support, then extracts it.
-fn download_and_extract(url: &str, format: CompressionFormat, target_dir: &Path) -> Result<()> {
-    let (downloaded_path, total_size) = resumable_download(url, target_dir)?;
-
-    info!(target: "reth::cli", "Extracting snapshot...");
-    let file = fs::open(&downloaded_path)?;
-    extract_archive(file, total_size, format, target_dir)?;
-
-    fs::remove_file(&downloaded_path)?;
-    info!(target: "reth::cli", "Removed downloaded archive");
-
-    Ok(())
-}
-
-/// Downloads and extracts a snapshot, blocking until finished.
-///
-/// Supports both `file://` URLs for local files and HTTP(S) URLs for remote downloads.
-fn blocking_download_and_extract(url: &str, target_dir: &Path) -> Result<()> {
-    let format = CompressionFormat::from_url(url)?;
-
-    if let Ok(parsed_url) = Url::parse(url) &&
-        parsed_url.scheme() == "file"
-    {
-        let file_path = parsed_url
-            .to_file_path()
-            .map_err(|_| eyre::eyre!("Invalid file:// URL path: {}", url))?;
-        extract_from_file(&file_path, format, target_dir)
-    } else {
-        download_and_extract(url, format, target_dir)
-    }
-}
-
-async fn stream_and_extract(url: &str, target_dir: &Path) -> Result<()> {
-    let target_dir = target_dir.to_path_buf();
-    let url = url.to_string();
-    task::spawn_blocking(move || blocking_download_and_extract(&url, &target_dir)).await??;
-
-    Ok(())
-}
-
-// Builds default URL for latest mainnet archive snapshot using configured defaults
-async fn get_latest_snapshot_url(chain_id: u64) -> Result<String> {
-    let defaults = DownloadDefaults::get_global();
-    let base_url = match &defaults.default_chain_aware_base_url {
-        Some(url) => format!("{url}/{chain_id}"),
-        None => defaults.default_base_url.to_string(),
-    };
-    let latest_url = format!("{base_url}/latest.txt");
-    let filename = Client::new()
-        .get(latest_url)
-        .send()
-        .await?
-        .error_for_status()?
-        .text()
-        .await?
-        .trim()
-        .to_string();
-
-    Ok(format!("{base_url}/{filename}"))
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_download_defaults_builder() {
-        let defaults = DownloadDefaults::default()
-            .with_snapshot("https://example.com/snapshots (example)")
-            .with_base_url("https://example.com");
-
-        assert_eq!(defaults.default_base_url, "https://example.com");
-        assert_eq!(defaults.available_snapshots.len(), 3); // 2 defaults + 1 added
-    }
-
-    #[test]
-    fn test_download_defaults_replace_snapshots() {
-        let defaults = DownloadDefaults::default().with_snapshots(vec![
-            Cow::Borrowed("https://custom1.com"),
-            Cow::Borrowed("https://custom2.com"),
-        ]);
-
-        assert_eq!(defaults.available_snapshots.len(), 2);
-        assert_eq!(defaults.available_snapshots[0], "https://custom1.com");
-    }
-
-    #[test]
-    fn test_long_help_generation() {
-        let defaults = DownloadDefaults::default();
-        let help = defaults.long_help();
-
-        assert!(help.contains("Available snapshot sources:"));
-        assert!(help.contains("merkle.io"));
-        assert!(help.contains("publicnode.com"));
-        assert!(help.contains("file://"));
-    }
-
-    #[test]
-    fn test_long_help_override() {
-        let custom_help = "This is custom help text for downloading snapshots.";
-        let defaults = DownloadDefaults::default().with_long_help(custom_help);
-
-        let help = defaults.long_help();
-        assert_eq!(help, custom_help);
-        assert!(!help.contains("Available snapshot sources:"));
-    }
-
-    #[test]
-    fn test_builder_chaining() {
-        let defaults = DownloadDefaults::default()
-            .with_base_url("https://custom.example.com")
-            .with_snapshot("https://snapshot1.com")
-            .with_snapshot("https://snapshot2.com")
-            .with_long_help("Custom help for snapshots");
-
-        assert_eq!(defaults.default_base_url, "https://custom.example.com");
-        assert_eq!(defaults.available_snapshots.len(), 4); // 2 defaults + 2 added
-        assert_eq!(defaults.long_help, Some("Custom help for snapshots".to_string()));
-    }
-
-    #[test]
-    fn test_compression_format_detection() {
-        assert!(matches!(
-            CompressionFormat::from_url("https://example.com/snapshot.tar.lz4"),
-            Ok(CompressionFormat::Lz4)
-        ));
-        assert!(matches!(
-            CompressionFormat::from_url("https://example.com/snapshot.tar.zst"),
-            Ok(CompressionFormat::Zstd)
-        ));
-        assert!(matches!(
-            CompressionFormat::from_url("file:///path/to/snapshot.tar.lz4"),
-            Ok(CompressionFormat::Lz4)
-        ));
-        assert!(matches!(
-            CompressionFormat::from_url("file:///path/to/snapshot.tar.zst"),
-            Ok(CompressionFormat::Zstd)
-        ));
-        assert!(CompressionFormat::from_url("https://example.com/snapshot.tar.gz").is_err());
-    }
-}

crates/cli/commands/src/download/config_gen.rs

@@ -0,0 +1,610 @@
+use crate::download::{
+    manifest::{ComponentManifest, ComponentSelection, SnapshotComponentType, SnapshotManifest},
+    SelectionPreset,
+};
+use reth_chainspec::{EthereumHardfork, EthereumHardforks};
+use reth_config::config::{BlocksPerFileConfig, Config, PruneConfig, StaticFilesConfig};
+use reth_db::tables;
+use reth_db_api::transaction::{DbTx, DbTxMut};
+use reth_node_core::args::DefaultPruningValues;
+use reth_prune_types::{PruneCheckpoint, PruneMode, PruneSegment};
+use reth_stages_types::StageCheckpoint;
+use std::{collections::BTreeMap, path::Path};
+use tracing::info;
+
+/// Minimum blocks to keep for receipts, matching `--minimal` prune settings.
+const MINIMUM_RECEIPTS_DISTANCE: u64 = 64;
+
+/// Minimum blocks to keep for history/bodies, matching `--minimal` prune settings
+/// (`MINIMUM_UNWIND_SAFE_DISTANCE`).
+const MINIMUM_HISTORY_DISTANCE: u64 = 10064;
+
+/// Writes a [`Config`] as TOML to `<data_dir>/reth.toml`.
+///
+/// If the file already exists, it is not overwritten. Returns `true` if the file was written.
+pub fn write_config(config: &Config, data_dir: &Path) -> eyre::Result<bool> {
+    let config_path = data_dir.join("reth.toml");
+
+    if config_path.exists() {
+        info!(target: "reth::cli",
+            path = ?config_path,
+            "reth.toml already exists, skipping config generation"
+        );
+        return Ok(false);
+    }
+
+    let toml_str = toml::to_string_pretty(config)?;
+    reth_fs_util::write(&config_path, toml_str)?;
+
+    info!(target: "reth::cli",
+        path = ?config_path,
+        "Generated reth.toml based on downloaded components"
+    );
+
+    Ok(true)
+}
+
+/// Writes prune checkpoints to the provided write transaction.
+pub(crate) fn write_prune_checkpoints_tx<Tx>(
+    tx: &Tx,
+    config: &Config,
+    snapshot_block: u64,
+) -> eyre::Result<()>
+where
+    Tx: DbTx + DbTxMut,
+{
+    let segments = &config.prune.segments;
+
+    // Collect (segment, mode) pairs for all configured prune segments
+    let checkpoints: Vec<(PruneSegment, PruneMode)> = [
+        (PruneSegment::SenderRecovery, segments.sender_recovery),
+        (PruneSegment::TransactionLookup, segments.transaction_lookup),
+        (PruneSegment::Receipts, segments.receipts),
+        (PruneSegment::AccountHistory, segments.account_history),
+        (PruneSegment::StorageHistory, segments.storage_history),
+        (PruneSegment::Bodies, segments.bodies_history),
+    ]
+    .into_iter()
+    .filter_map(|(segment, mode)| mode.map(|m| (segment, m)))
+    .collect();
+
+    if checkpoints.is_empty() {
+        return Ok(());
+    }
+
+    // Look up the last tx number for the snapshot block from BlockBodyIndices
+    let tx_number =
+        tx.get::<tables::BlockBodyIndices>(snapshot_block)?.map(|indices| indices.last_tx_num());
+
+    for (segment, prune_mode) in &checkpoints {
+        let checkpoint = PruneCheckpoint {
+            block_number: Some(snapshot_block),
+            tx_number,
+            prune_mode: *prune_mode,
+        };
+
+        tx.put::<tables::PruneCheckpoints>(*segment, checkpoint)?;
+
+        info!(target: "reth::cli",
+            segment = %segment,
+            block = snapshot_block,
+            tx = ?tx_number,
+            mode = ?prune_mode,
+            "Set prune checkpoint"
+        );
+    }
+
+    Ok(())
+}
+
+/// Stage IDs for index stages whose output is stored in RocksDB and is never
+/// distributed in snapshots.
+const INDEX_STAGE_IDS: [&str; 3] =
+    ["TransactionLookup", "IndexAccountHistory", "IndexStorageHistory"];
+
+/// Prune segments that correspond to the index stages.
+const INDEX_PRUNE_SEGMENTS: [PruneSegment; 3] =
+    [PruneSegment::TransactionLookup, PruneSegment::AccountHistory, PruneSegment::StorageHistory];
+
+/// Resets stage and prune checkpoints for stages whose output is not included
+/// in the snapshot inside an existing write transaction.
+///
+/// A snapshot's mdbx comes from a fully synced node, so it has stage checkpoints
+/// at the tip for `TransactionLookup`, `IndexAccountHistory`, and
+/// `IndexStorageHistory`. Since we don't distribute the rocksdb indices those
+/// stages produced, we must reset their checkpoints to block 0. Otherwise the
+/// pipeline would see "already done" and skip rebuilding entirely.
+///
+/// We intentionally do not reset `SenderRecovery`: sender static files are
+/// distributed for archive downloads, and non-archive downloads rely on the
+/// configured prune checkpoints for this segment.
+pub(crate) fn reset_index_stage_checkpoints_tx<Tx>(tx: &Tx) -> eyre::Result<()>
+where
+    Tx: DbTx + DbTxMut,
+{
+    for stage_id in INDEX_STAGE_IDS {
+        tx.put::<tables::StageCheckpoints>(stage_id.to_string(), StageCheckpoint::default())?;
+
+        // Also clear any stage-specific progress data
+        tx.delete::<tables::StageCheckpointProgresses>(stage_id.to_string(), None)?;
+
+        info!(target: "reth::cli", stage = stage_id, "Reset stage checkpoint to block 0");
+    }
+
+    // Clear corresponding prune checkpoints so the pruner doesn't inherit
+    // state from the source node
+    for segment in INDEX_PRUNE_SEGMENTS {
+        tx.delete::<tables::PruneCheckpoints>(segment, None)?;
+    }
+
+    Ok(())
+}
+
+/// Generates a [`Config`] from per-component range selections.
+///
+/// When all data components are selected as `All`, no pruning is configured (archive node).
+/// Otherwise, `--minimal` style pruning is applied for missing/partial components.
+pub(crate) fn config_for_selections(
+    selections: &BTreeMap<SnapshotComponentType, ComponentSelection>,
+    manifest: &SnapshotManifest,
+    preset: Option<SelectionPreset>,
+    chain_spec: Option<&impl EthereumHardforks>,
+) -> Config {
+    let selection_for = |ty| selections.get(&ty).copied().unwrap_or(ComponentSelection::None);
+
+    let tx_sel = selection_for(SnapshotComponentType::Transactions);
+    let senders_sel = selection_for(SnapshotComponentType::TransactionSenders);
+    let receipt_sel = selection_for(SnapshotComponentType::Receipts);
+    let account_cs_sel = selection_for(SnapshotComponentType::AccountChangesets);
+    let storage_cs_sel = selection_for(SnapshotComponentType::StorageChangesets);
+
+    // Archive node — all data components present, no pruning
+    let is_archive = [tx_sel, senders_sel, receipt_sel, account_cs_sel, storage_cs_sel]
+        .iter()
+        .all(|s| *s == ComponentSelection::All);
+
+    // Extract blocks_per_file from manifest for all component types
+    let blocks_per_file = |ty: SnapshotComponentType| -> Option<u64> {
+        match manifest.component(ty)? {
+            ComponentManifest::Chunked(c) => Some(c.blocks_per_file),
+            ComponentManifest::Single(_) => None,
+        }
+    };
+    let static_files = StaticFilesConfig {
+        blocks_per_file: BlocksPerFileConfig {
+            headers: blocks_per_file(SnapshotComponentType::Headers),
+            transactions: blocks_per_file(SnapshotComponentType::Transactions),
+            receipts: blocks_per_file(SnapshotComponentType::Receipts),
+            transaction_senders: blocks_per_file(SnapshotComponentType::TransactionSenders),
+            account_change_sets: blocks_per_file(SnapshotComponentType::AccountChangesets),
+            storage_change_sets: blocks_per_file(SnapshotComponentType::StorageChangesets),
+        },
+    };
+
+    if is_archive || matches!(preset, Some(SelectionPreset::Archive)) {
+        return Config { static_files, ..Default::default() };
+    }
+
+    if matches!(preset, Some(SelectionPreset::Full)) {
+        let defaults = DefaultPruningValues::get_global();
+        let mut segments = defaults.full_prune_modes.clone();
+
+        if defaults.full_bodies_history_use_pre_merge {
+            segments.bodies_history = chain_spec.and_then(|chain_spec| {
+                chain_spec
+                    .ethereum_fork_activation(EthereumHardfork::Paris)
+                    .block_number()
+                    .map(PruneMode::Before)
+            });
+        }
+
+        return Config {
+            prune: PruneConfig { block_interval: PruneConfig::default().block_interval, segments },
+            static_files,
+            ..Default::default()
+        };
+    }
+
+    let mut config = Config::default();
+    let mut prune = PruneConfig::default();
+
+    if senders_sel != ComponentSelection::All {
+        prune.segments.sender_recovery = Some(PruneMode::Full);
+    }
+    prune.segments.transaction_lookup = Some(PruneMode::Full);
+
+    if let Some(mode) = selection_to_prune_mode(tx_sel, Some(MINIMUM_HISTORY_DISTANCE)) {
+        prune.segments.bodies_history = Some(mode);
+    }
+
+    if let Some(mode) = selection_to_prune_mode(receipt_sel, Some(MINIMUM_RECEIPTS_DISTANCE)) {
+        prune.segments.receipts = Some(mode);
+    }
+
+    if let Some(mode) = selection_to_prune_mode(account_cs_sel, Some(MINIMUM_HISTORY_DISTANCE)) {
+        prune.segments.account_history = Some(mode);
+    }
+
+    if let Some(mode) = selection_to_prune_mode(storage_cs_sel, Some(MINIMUM_HISTORY_DISTANCE)) {
+        prune.segments.storage_history = Some(mode);
+    }
+
+    config.prune = prune;
+    config.static_files = static_files;
+    config
+}
+
+/// Converts a [`ComponentSelection`] to an optional [`PruneMode`].
+///
+/// `min_distance` enforces the minimum blocks required for this segment.
+/// When set, `None` and distances below the minimum are clamped to it
+/// instead of producing `PruneMode::Full` which reth would reject.
+fn selection_to_prune_mode(
+    sel: ComponentSelection,
+    min_distance: Option<u64>,
+) -> Option<PruneMode> {
+    match sel {
+        ComponentSelection::All => None,
+        ComponentSelection::Distance(d) => {
+            Some(PruneMode::Distance(min_distance.map_or(d, |min| d.max(min))))
+        }
+        ComponentSelection::None => Some(min_distance.map_or(PruneMode::Full, PruneMode::Distance)),
+    }
+}
+
+/// Human-readable prune config summary.
+pub(crate) fn describe_prune_config(config: &Config) -> Vec<String> {
+    let segments = &config.prune.segments;
+
+    [
+        ("sender_recovery", segments.sender_recovery),
+        ("transaction_lookup", segments.transaction_lookup),
+        ("bodies_history", segments.bodies_history),
+        ("receipts", segments.receipts),
+        ("account_history", segments.account_history),
+        ("storage_history", segments.storage_history),
+    ]
+    .into_iter()
+    .filter_map(|(name, mode)| mode.map(|m| format!("{name}={}", format_mode(&m))))
+    .collect()
+}
+
+fn format_mode(mode: &PruneMode) -> String {
+    match mode {
+        PruneMode::Full => "\"full\"".to_string(),
+        PruneMode::Distance(d) => format!("{{ distance = {d} }}"),
+        PruneMode::Before(b) => format!("{{ before = {b} }}"),
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use reth_db::Database;
+
+    /// Empty manifest for tests that only care about prune config.
+    fn empty_manifest() -> SnapshotManifest {
+        SnapshotManifest {
+            block: 0,
+            chain_id: 1,
+            storage_version: 2,
+            timestamp: 0,
+            base_url: None,
+            reth_version: None,
+            components: BTreeMap::new(),
+        }
+    }
+
+    #[test]
+    fn write_prune_checkpoints_sets_all_segments() {
+        let dir = tempfile::tempdir().unwrap();
+        let db = reth_db::init_db(dir.path(), reth_db::mdbx::DatabaseArguments::default()).unwrap();
+
+        let mut selections = BTreeMap::new();
+        selections.insert(SnapshotComponentType::State, ComponentSelection::All);
+        selections.insert(SnapshotComponentType::Headers, ComponentSelection::All);
+        let config = config_for_selections(
+            &selections,
+            &empty_manifest(),
+            None,
+            None::<&reth_chainspec::ChainSpec>,
+        );
+        let snapshot_block = 21_000_000;
+
+        {
+            let tx = db.tx_mut().unwrap();
+            write_prune_checkpoints_tx(&tx, &config, snapshot_block).unwrap();
+            tx.commit().unwrap();
+        }
+
+        // Verify all expected segments have checkpoints
+        let tx = db.tx().unwrap();
+        for segment in [
+            PruneSegment::SenderRecovery,
+            PruneSegment::TransactionLookup,
+            PruneSegment::Receipts,
+            PruneSegment::AccountHistory,
+            PruneSegment::StorageHistory,
+            PruneSegment::Bodies,
+        ] {
+            let checkpoint = tx
+                .get::<tables::PruneCheckpoints>(segment)
+                .unwrap()
+                .unwrap_or_else(|| panic!("expected checkpoint for {segment}"));
+            assert_eq!(checkpoint.block_number, Some(snapshot_block));
+            // No BlockBodyIndices in empty DB, so tx_number should be None
+            assert_eq!(checkpoint.tx_number, None);
+        }
+    }
+
+    #[test]
+    fn write_prune_checkpoints_archive_no_checkpoints() {
+        let dir = tempfile::tempdir().unwrap();
+        let db = reth_db::init_db(dir.path(), reth_db::mdbx::DatabaseArguments::default()).unwrap();
+
+        // Archive node — no pruning configured, so no checkpoints written
+        let mut selections = BTreeMap::new();
+        for ty in SnapshotComponentType::ALL {
+            selections.insert(ty, ComponentSelection::All);
+        }
+        let config = config_for_selections(
+            &selections,
+            &empty_manifest(),
+            None,
+            None::<&reth_chainspec::ChainSpec>,
+        );
+
+        {
+            let tx = db.tx_mut().unwrap();
+            write_prune_checkpoints_tx(&tx, &config, 21_000_000).unwrap();
+            tx.commit().unwrap();
+        }
+
+        let tx = db.tx().unwrap();
+        for segment in [PruneSegment::SenderRecovery, PruneSegment::TransactionLookup] {
+            assert!(
+                tx.get::<tables::PruneCheckpoints>(segment).unwrap().is_none(),
+                "expected no checkpoint for {segment} on archive node"
+            );
+        }
+    }
+
+    #[test]
+    fn selections_all_no_pruning() {
+        let mut selections = BTreeMap::new();
+        for ty in SnapshotComponentType::ALL {
+            selections.insert(ty, ComponentSelection::All);
+        }
+        let config = config_for_selections(
+            &selections,
+            &empty_manifest(),
+            None,
+            None::<&reth_chainspec::ChainSpec>,
+        );
+        // Archive node — nothing pruned
+        assert_eq!(config.prune.segments.transaction_lookup, None);
+        assert_eq!(config.prune.segments.sender_recovery, None);
+        assert_eq!(config.prune.segments.bodies_history, None);
+        assert_eq!(config.prune.segments.receipts, None);
+        assert_eq!(config.prune.segments.account_history, None);
+        assert_eq!(config.prune.segments.storage_history, None);
+    }
+
+    #[test]
+    fn selections_none_clamps_to_minimum_distance() {
+        let mut selections = BTreeMap::new();
+        selections.insert(SnapshotComponentType::State, ComponentSelection::All);
+        selections.insert(SnapshotComponentType::Headers, ComponentSelection::All);
+        let config = config_for_selections(
+            &selections,
+            &empty_manifest(),
+            None,
+            None::<&reth_chainspec::ChainSpec>,
+        );
+        assert_eq!(config.prune.segments.transaction_lookup, Some(PruneMode::Full));
+        assert_eq!(config.prune.segments.sender_recovery, Some(PruneMode::Full));
+        // All segments clamped to their minimum distances
+        assert_eq!(
+            config.prune.segments.bodies_history,
+            Some(PruneMode::Distance(MINIMUM_HISTORY_DISTANCE))
+        );
+        assert_eq!(
+            config.prune.segments.receipts,
+            Some(PruneMode::Distance(MINIMUM_RECEIPTS_DISTANCE))
+        );
+        assert_eq!(
+            config.prune.segments.account_history,
+            Some(PruneMode::Distance(MINIMUM_HISTORY_DISTANCE))
+        );
+        assert_eq!(
+            config.prune.segments.storage_history,
+            Some(PruneMode::Distance(MINIMUM_HISTORY_DISTANCE))
+        );
+    }
+
+    #[test]
+    fn selections_distance_maps_bodies_history() {
+        let mut selections = BTreeMap::new();
+        selections.insert(SnapshotComponentType::State, ComponentSelection::All);
+        selections.insert(SnapshotComponentType::Headers, ComponentSelection::All);
+        selections
+            .insert(SnapshotComponentType::Transactions, ComponentSelection::Distance(10_064));
+        selections.insert(SnapshotComponentType::Receipts, ComponentSelection::None);
+        selections
+            .insert(SnapshotComponentType::AccountChangesets, ComponentSelection::Distance(10_064));
+        selections
+            .insert(SnapshotComponentType::StorageChangesets, ComponentSelection::Distance(10_064));
+        let config = config_for_selections(
+            &selections,
+            &empty_manifest(),
+            None,
+            None::<&reth_chainspec::ChainSpec>,
+        );
+
+        assert_eq!(config.prune.segments.transaction_lookup, Some(PruneMode::Full));
+        assert_eq!(config.prune.segments.sender_recovery, Some(PruneMode::Full));
+        // Bodies follows tx selection
+        assert_eq!(config.prune.segments.bodies_history, Some(PruneMode::Distance(10_064)));
+        assert_eq!(
+            config.prune.segments.receipts,
+            Some(PruneMode::Distance(MINIMUM_RECEIPTS_DISTANCE))
+        );
+        assert_eq!(config.prune.segments.account_history, Some(PruneMode::Distance(10_064)));
+        assert_eq!(config.prune.segments.storage_history, Some(PruneMode::Distance(10_064)));
+    }
+
+    #[test]
+    fn full_preset_matches_default_full_prune_config() {
+        let mut selections = BTreeMap::new();
+        selections.insert(SnapshotComponentType::State, ComponentSelection::All);
+        selections.insert(SnapshotComponentType::Headers, ComponentSelection::All);
+        selections
+            .insert(SnapshotComponentType::Transactions, ComponentSelection::Distance(500_000));
+        selections.insert(SnapshotComponentType::Receipts, ComponentSelection::Distance(10_064));
+
+        let chain_spec = reth_chainspec::MAINNET.clone();
+        let config = config_for_selections(
+            &selections,
+            &empty_manifest(),
+            Some(SelectionPreset::Full),
+            Some(chain_spec.as_ref()),
+        );
+
+        assert_eq!(config.prune.segments.sender_recovery, Some(PruneMode::Full));
+        assert_eq!(config.prune.segments.transaction_lookup, None);
+        assert_eq!(
+            config.prune.segments.receipts,
+            Some(PruneMode::Distance(MINIMUM_HISTORY_DISTANCE))
+        );
+        assert_eq!(
+            config.prune.segments.account_history,
+            Some(PruneMode::Distance(MINIMUM_HISTORY_DISTANCE))
+        );
+        assert_eq!(
+            config.prune.segments.storage_history,
+            Some(PruneMode::Distance(MINIMUM_HISTORY_DISTANCE))
+        );
+
+        let paris_block = chain_spec
+            .ethereum_fork_activation(EthereumHardfork::Paris)
+            .block_number()
+            .expect("mainnet Paris block should be known");
+        assert_eq!(config.prune.segments.bodies_history, Some(PruneMode::Before(paris_block)));
+    }
+
+    #[test]
+    fn describe_selections_all_no_pruning() {
+        let mut selections = BTreeMap::new();
+        for ty in SnapshotComponentType::ALL {
+            selections.insert(ty, ComponentSelection::All);
+        }
+        let config = config_for_selections(
+            &selections,
+            &empty_manifest(),
+            None,
+            None::<&reth_chainspec::ChainSpec>,
+        );
+        let desc = describe_prune_config(&config);
+        // Archive node — no prune segments described
+        assert!(desc.is_empty());
+    }
+
+    #[test]
+    fn describe_selections_with_distances() {
+        let mut selections = BTreeMap::new();
+        selections.insert(SnapshotComponentType::State, ComponentSelection::All);
+        selections.insert(SnapshotComponentType::Headers, ComponentSelection::All);
+        selections
+            .insert(SnapshotComponentType::Transactions, ComponentSelection::Distance(10_064));
+        selections.insert(SnapshotComponentType::Receipts, ComponentSelection::None);
+        let config = config_for_selections(
+            &selections,
+            &empty_manifest(),
+            None,
+            None::<&reth_chainspec::ChainSpec>,
+        );
+        let desc = describe_prune_config(&config);
+        assert!(desc.contains(&"sender_recovery=\"full\"".to_string()));
+        // Bodies follows tx selection
+        assert!(desc.contains(&"bodies_history={ distance = 10064 }".to_string()));
+        assert!(desc.contains(&"receipts={ distance = 64 }".to_string()));
+    }
+
+    #[test]
+    fn reset_index_stage_checkpoints_clears_only_rocksdb_index_stages() {
+        let dir = tempfile::tempdir().unwrap();
+        let db = reth_db::init_db(dir.path(), reth_db::mdbx::DatabaseArguments::default()).unwrap();
+
+        // Simulate a fully synced node: set stage checkpoints at tip
+        let tip_checkpoint = StageCheckpoint::new(24_500_000);
+        {
+            let tx = db.tx_mut().unwrap();
+            for stage_id in INDEX_STAGE_IDS {
+                tx.put::<tables::StageCheckpoints>(stage_id.to_string(), tip_checkpoint).unwrap();
+            }
+            for segment in INDEX_PRUNE_SEGMENTS {
+                tx.put::<tables::PruneCheckpoints>(
+                    segment,
+                    PruneCheckpoint {
+                        block_number: Some(24_500_000),
+                        tx_number: None,
+                        prune_mode: PruneMode::Full,
+                    },
+                )
+                .unwrap();
+            }
+
+            // Sender recovery checkpoints should be preserved by reset.
+            tx.put::<tables::StageCheckpoints>("SenderRecovery".to_string(), tip_checkpoint)
+                .unwrap();
+            tx.put::<tables::PruneCheckpoints>(
+                PruneSegment::SenderRecovery,
+                PruneCheckpoint {
+                    block_number: Some(24_500_000),
+                    tx_number: None,
+                    prune_mode: PruneMode::Full,
+                },
+            )
+            .unwrap();
+            tx.commit().unwrap();
+        }
+
+        // Reset
+        {
+            let tx = db.tx_mut().unwrap();
+            reset_index_stage_checkpoints_tx(&tx).unwrap();
+            tx.commit().unwrap();
+        }
+
+        // Verify stage checkpoints are at block 0
+        let tx = db.tx().unwrap();
+        for stage_id in INDEX_STAGE_IDS {
+            let checkpoint = tx
+                .get::<tables::StageCheckpoints>(stage_id.to_string())
+                .unwrap()
+                .expect("checkpoint should exist");
+            assert_eq!(checkpoint.block_number, 0, "stage {stage_id} should be reset to block 0");
+        }
+
+        // Verify prune checkpoints are deleted
+        for segment in INDEX_PRUNE_SEGMENTS {
+            assert!(
+                tx.get::<tables::PruneCheckpoints>(segment).unwrap().is_none(),
+                "prune checkpoint for {segment} should be deleted"
+            );
+        }
+
+        // Verify sender checkpoints are left untouched.
+        let sender_stage_checkpoint = tx
+            .get::<tables::StageCheckpoints>("SenderRecovery".to_string())
+            .unwrap()
+            .expect("sender checkpoint should exist");
+        assert_eq!(sender_stage_checkpoint.block_number, tip_checkpoint.block_number);
+
+        let sender_prune_checkpoint = tx
+            .get::<tables::PruneCheckpoints>(PruneSegment::SenderRecovery)
+            .unwrap()
+            .expect("sender prune checkpoint should exist");
+        assert_eq!(sender_prune_checkpoint.block_number, Some(tip_checkpoint.block_number));
+    }
+}

crates/cli/commands/src/download/manifest_cmd.rs

@@ -0,0 +1,232 @@
+use crate::download::manifest::generate_manifest;
+use clap::Parser;
+use eyre::{Result, WrapErr};
+use reth_db::{mdbx::DatabaseArguments, open_db_read_only, tables, Database};
+use reth_db_api::transaction::DbTx;
+use reth_stages_types::StageId;
+use reth_static_file_types::DEFAULT_BLOCKS_PER_STATIC_FILE;
+use std::{path::PathBuf, time::Instant};
+use tracing::{info, warn};
+
+/// Generate modular chunk archives and a snapshot manifest from a source datadir.
+///
+/// Archive naming convention:
+///   - Chunked: `{component}-{start}-{end}.tar.zst` (e.g. `transactions-0-499999.tar.zst`)
+#[derive(Debug, Parser)]
+pub struct SnapshotManifestCommand {
+    /// Source datadir containing static files.
+    #[arg(long, short = 'd')]
+    source_datadir: PathBuf,
+
+    /// Optional base URL where archives will be hosted.
+    #[arg(long)]
+    base_url: Option<String>,
+
+    /// Output directory where chunk archives and manifest.json are written.
+    #[arg(long, short = 'o')]
+    output_dir: PathBuf,
+
+    /// Block number this snapshot was taken at.
+    ///
+    /// If omitted, this is inferred from the source datadir's `Finish` stage checkpoint.
+    #[arg(long)]
+    block: Option<u64>,
+
+    /// Chain ID.
+    #[arg(long, default_value = "1")]
+    chain_id: u64,
+
+    /// Blocks per archive file for chunked components.
+    ///
+    /// If omitted, this is inferred from header static file ranges in the source datadir.
+    #[arg(long)]
+    blocks_per_file: Option<u64>,
+}
+
+impl SnapshotManifestCommand {
+    pub fn execute(self) -> Result<()> {
+        let block = match self.block {
+            Some(block) => block,
+            None => infer_snapshot_block(&self.source_datadir)?,
+        };
+        let blocks_per_file = match self.blocks_per_file {
+            Some(blocks_per_file) => blocks_per_file,
+            None => infer_blocks_per_file(&self.source_datadir)?,
+        };
+
+        info!(target: "reth::cli",
+            dir = ?self.source_datadir,
+            output = ?self.output_dir,
+            block,
+            blocks_per_file,
+            "Packaging modular snapshot archives"
+        );
+        let start = Instant::now();
+        let manifest = generate_manifest(
+            &self.source_datadir,
+            &self.output_dir,
+            self.base_url.as_deref(),
+            block,
+            self.chain_id,
+            blocks_per_file,
+        )?;
+
+        let num_components = manifest.components.len();
+        let json = serde_json::to_string_pretty(&manifest)?;
+        let output = self.output_dir.join("manifest.json");
+        reth_fs_util::write(&output, &json)?;
+        info!(target: "reth::cli",
+            path = ?output,
+            components = num_components,
+            block = manifest.block,
+            elapsed = ?start.elapsed(),
+            "Manifest written"
+        );
+
+        Ok(())
+    }
+}
+
+fn infer_snapshot_block(source_datadir: &std::path::Path) -> Result<u64> {
+    if let Ok(block) = infer_snapshot_block_from_db(source_datadir) {
+        return Ok(block);
+    }
+
+    let block = infer_snapshot_block_from_headers(source_datadir)?;
+    warn!(
+        target: "reth::cli",
+        block,
+        "Could not read Finish stage checkpoint from source DB, using header static-file tip"
+    );
+    Ok(block)
+}
+
+fn infer_snapshot_block_from_db(source_datadir: &std::path::Path) -> Result<u64> {
+    let candidates = [source_datadir.join("db"), source_datadir.to_path_buf()];
+
+    for db_path in candidates {
+        if !db_path.exists() {
+            continue;
+        }
+
+        let db = match open_db_read_only(&db_path, DatabaseArguments::default()) {
+            Ok(db) => db,
+            Err(_) => continue,
+        };
+
+        let tx = db.tx()?;
+        if let Some(checkpoint) = tx.get::<tables::StageCheckpoints>(StageId::Finish.to_string())? {
+            return Ok(checkpoint.block_number);
+        }
+    }
+
+    eyre::bail!(
+        "Could not infer --block from source DB (Finish checkpoint missing); pass --block manually"
+    )
+}
+
+fn infer_snapshot_block_from_headers(source_datadir: &std::path::Path) -> Result<u64> {
+    let max_end = header_ranges(source_datadir)?
+        .into_iter()
+        .map(|(_, end)| end)
+        .max()
+        .ok_or_else(|| eyre::eyre!("No header static files found to infer --block"))?;
+    Ok(max_end)
+}
+
+fn infer_blocks_per_file(source_datadir: &std::path::Path) -> Result<u64> {
+    let mut inferred = None;
+    for (start, end) in header_ranges(source_datadir)? {
+        let span = end.saturating_sub(start).saturating_add(1);
+        if span == 0 {
+            continue;
+        }
+
+        if let Some(existing) = inferred {
+            if existing != span {
+                eyre::bail!(
+                    "Inconsistent header static file ranges; pass --blocks-per-file manually"
+                );
+            }
+        } else {
+            inferred = Some(span);
+        }
+    }
+
+    inferred.ok_or_else(|| {
+        eyre::eyre!(
+            "Could not infer --blocks-per-file from header static files; pass it manually (default is {DEFAULT_BLOCKS_PER_STATIC_FILE})"
+        )
+    })
+}
+
+fn header_ranges(source_datadir: &std::path::Path) -> Result<Vec<(u64, u64)>> {
+    let static_files_dir = source_datadir.join("static_files");
+    let static_files_dir =
+        if static_files_dir.exists() { static_files_dir } else { source_datadir.to_path_buf() };
+
+    let entries = std::fs::read_dir(&static_files_dir).wrap_err_with(|| {
+        format!("Failed to read static files directory: {}", static_files_dir.display())
+    })?;
+
+    let mut ranges = Vec::new();
+    for entry in entries {
+        let entry = entry?;
+        let file_name = entry.file_name();
+        let file_name = file_name.to_string_lossy();
+        if let Some(range) = parse_headers_range(&file_name) {
+            ranges.push(range);
+        }
+    }
+
+    Ok(ranges)
+}
+
+fn parse_headers_range(file_name: &str) -> Option<(u64, u64)> {
+    let remainder = file_name.strip_prefix("static_file_headers_")?;
+    let (start, end_with_suffix) = remainder.split_once('_')?;
+
+    let start = start.parse::<u64>().ok()?;
+    let end_digits: String = end_with_suffix.chars().take_while(|ch| ch.is_ascii_digit()).collect();
+    let end = end_digits.parse::<u64>().ok()?;
+
+    Some((start, end))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use tempfile::tempdir;
+
+    #[test]
+    fn parse_headers_range_works_with_suffixes() {
+        assert_eq!(parse_headers_range("static_file_headers_0_499999"), Some((0, 499_999)));
+        assert_eq!(
+            parse_headers_range("static_file_headers_500000_999999.jar"),
+            Some((500_000, 999_999))
+        );
+        assert_eq!(parse_headers_range("static_file_transactions_0_499999"), None);
+    }
+
+    #[test]
+    fn infer_blocks_per_file_from_header_ranges() {
+        let dir = tempdir().unwrap();
+        let sf = dir.path().join("static_files");
+        std::fs::create_dir_all(&sf).unwrap();
+        std::fs::write(sf.join("static_file_headers_0_499999"), []).unwrap();
+        std::fs::write(sf.join("static_file_headers_500000_999999.jar"), []).unwrap();
+
+        assert_eq!(infer_blocks_per_file(dir.path()).unwrap(), 500_000);
+    }
+
+    #[test]
+    fn infer_snapshot_block_from_headers_uses_max_end() {
+        let dir = tempdir().unwrap();
+        let sf = dir.path().join("static_files");
+        std::fs::create_dir_all(&sf).unwrap();
+        std::fs::write(sf.join("static_file_headers_0_499999"), []).unwrap();
+        std::fs::write(sf.join("static_file_headers_500000_999999"), []).unwrap();
+
+        assert_eq!(infer_snapshot_block_from_headers(dir.path()).unwrap(), 999_999);
+    }
+}

crates/cli/commands/src/download/tui.rs

@@ -0,0 +1,437 @@
+use crate::download::{
+    manifest::{ComponentSelection, SnapshotComponentType, SnapshotManifest},
+    DownloadProgress, SelectionPreset,
+};
+use crossterm::{
+    event::{self, Event, KeyCode},
+    execute,
+    terminal::{disable_raw_mode, enable_raw_mode, EnterAlternateScreen, LeaveAlternateScreen},
+};
+use ratatui::{
+    backend::CrosstermBackend,
+    layout::{Constraint, Direction, Layout},
+    style::{Color, Modifier, Style},
+    text::{Line, Span},
+    widgets::{Block, Borders, List, ListItem, ListState, Paragraph},
+    Frame, Terminal,
+};
+use std::{
+    collections::BTreeMap,
+    io,
+    time::{Duration, Instant},
+};
+
+/// Result of the interactive component selector.
+pub struct SelectorOutput {
+    /// User-confirmed selections with per-component ranges.
+    pub selections: BTreeMap<SnapshotComponentType, ComponentSelection>,
+    /// Last preset action used in the TUI, if any.
+    pub preset: Option<SelectionPreset>,
+}
+
+/// All distance presets. Groups filter this to only valid options.
+const DISTANCE_PRESETS: [ComponentSelection; 6] = [
+    ComponentSelection::None,
+    ComponentSelection::Distance(64),
+    ComponentSelection::Distance(10_064),
+    ComponentSelection::Distance(100_000),
+    ComponentSelection::Distance(1_000_000),
+    ComponentSelection::All,
+];
+
+/// Presets for components that require at least 64 blocks (receipts).
+const RECEIPTS_PRESETS: [ComponentSelection; 5] = [
+    ComponentSelection::Distance(64),
+    ComponentSelection::Distance(10_064),
+    ComponentSelection::Distance(100_000),
+    ComponentSelection::Distance(1_000_000),
+    ComponentSelection::All,
+];
+
+/// Presets for components that require at least 10064 blocks (account/storage history).
+const HISTORY_PRESETS: [ComponentSelection; 4] = [
+    ComponentSelection::Distance(10_064),
+    ComponentSelection::Distance(100_000),
+    ComponentSelection::Distance(1_000_000),
+    ComponentSelection::All,
+];
+
+/// A display group bundles one or more component types into a single TUI row.
+struct DisplayGroup {
+    /// Display name shown in the TUI.
+    name: &'static str,
+    /// Underlying component types this group controls.
+    types: Vec<SnapshotComponentType>,
+    /// Whether this group is required and locked to All.
+    required: bool,
+    /// Valid presets for this group. Components with minimum distance requirements
+    /// exclude presets that would produce invalid prune configs.
+    presets: &'static [ComponentSelection],
+}
+
+/// Build the display groups from available components in the manifest.
+fn build_groups(manifest: &SnapshotManifest) -> Vec<DisplayGroup> {
+    let has = |ty: SnapshotComponentType| manifest.component(ty).is_some();
+
+    let mut groups = Vec::new();
+
+    if has(SnapshotComponentType::State) {
+        groups.push(DisplayGroup {
+            name: "State (mdbx)",
+            types: vec![SnapshotComponentType::State],
+            required: true,
+            presets: &DISTANCE_PRESETS,
+        });
+    }
+
+    if has(SnapshotComponentType::Headers) {
+        groups.push(DisplayGroup {
+            name: "Headers",
+            types: vec![SnapshotComponentType::Headers],
+            required: true,
+            presets: &DISTANCE_PRESETS,
+        });
+    }
+
+    if has(SnapshotComponentType::Transactions) {
+        groups.push(DisplayGroup {
+            name: "Transactions",
+            types: vec![SnapshotComponentType::Transactions],
+            required: false,
+            presets: &HISTORY_PRESETS,
+        });
+    }
+
+    if has(SnapshotComponentType::Receipts) {
+        groups.push(DisplayGroup {
+            name: "Receipts",
+            types: vec![SnapshotComponentType::Receipts],
+            required: false,
+            presets: &RECEIPTS_PRESETS,
+        });
+    }
+
+    // Bundle account + storage changesets as "State History"
+    let has_acc = has(SnapshotComponentType::AccountChangesets);
+    let has_stor = has(SnapshotComponentType::StorageChangesets);
+    if has_acc || has_stor {
+        let mut types = Vec::new();
+        if has_acc {
+            types.push(SnapshotComponentType::AccountChangesets);
+        }
+        if has_stor {
+            types.push(SnapshotComponentType::StorageChangesets);
+        }
+        groups.push(DisplayGroup {
+            name: "State History",
+            types,
+            required: false,
+            presets: &HISTORY_PRESETS,
+        });
+    }
+
+    groups
+}
+
+struct SelectorApp {
+    manifest: SnapshotManifest,
+    full_preset: BTreeMap<SnapshotComponentType, ComponentSelection>,
+    /// Display groups shown in the TUI.
+    groups: Vec<DisplayGroup>,
+    /// Current selection for each group.
+    selections: Vec<ComponentSelection>,
+    /// Last preset action invoked by user.
+    preset: Option<SelectionPreset>,
+    /// Current cursor position.
+    cursor: usize,
+    /// List state for ratatui.
+    list_state: ListState,
+}
+
+impl SelectorApp {
+    fn new(
+        manifest: SnapshotManifest,
+        full_preset: BTreeMap<SnapshotComponentType, ComponentSelection>,
+    ) -> Self {
+        let groups = build_groups(&manifest);
+
+        // Default to the minimal preset (matches --minimal prune config)
+        let selections = groups.iter().map(|g| g.types[0].minimal_selection()).collect();
+
+        let mut list_state = ListState::default();
+        list_state.select(Some(0));
+
+        Self {
+            manifest,
+            full_preset,
+            groups,
+            selections,
+            preset: Some(SelectionPreset::Minimal),
+            cursor: 0,
+            list_state,
+        }
+    }
+
+    fn cycle_right(&mut self) {
+        if let Some(group) = self.groups.get(self.cursor) {
+            if group.required {
+                return;
+            }
+            let presets = group.presets;
+            let current = self.selections[self.cursor];
+            let idx = presets.iter().position(|p| *p == current).unwrap_or(0);
+            self.selections[self.cursor] = presets[(idx + 1) % presets.len()];
+            self.preset = None;
+        }
+    }
+
+    fn cycle_left(&mut self) {
+        if let Some(group) = self.groups.get(self.cursor) {
+            if group.required {
+                return;
+            }
+            let presets = group.presets;
+            let current = self.selections[self.cursor];
+            let idx = presets.iter().position(|p| *p == current).unwrap_or(0);
+            self.selections[self.cursor] = presets[(idx + presets.len() - 1) % presets.len()];
+            self.preset = None;
+        }
+    }
+
+    fn select_all(&mut self) {
+        for sel in &mut self.selections {
+            *sel = ComponentSelection::All;
+        }
+        self.preset = Some(SelectionPreset::Archive);
+    }
+
+    fn select_minimal(&mut self) {
+        for (i, group) in self.groups.iter().enumerate() {
+            self.selections[i] = group.types[0].minimal_selection();
+        }
+        self.preset = Some(SelectionPreset::Minimal);
+    }
+
+    fn select_full(&mut self) {
+        for (i, group) in self.groups.iter().enumerate() {
+            let mut selection = group.types[0].minimal_selection();
+            for ty in &group.types {
+                if let Some(sel) = self.full_preset.get(ty).copied() {
+                    selection = sel;
+                    break;
+                }
+            }
+            self.selections[i] = selection;
+        }
+        self.preset = Some(SelectionPreset::Full);
+    }
+
+    fn move_up(&mut self) {
+        if self.cursor > 0 {
+            self.cursor -= 1;
+        } else {
+            self.cursor = self.groups.len().saturating_sub(1);
+        }
+        self.list_state.select(Some(self.cursor));
+    }
+
+    fn move_down(&mut self) {
+        if self.cursor < self.groups.len() - 1 {
+            self.cursor += 1;
+        } else {
+            self.cursor = 0;
+        }
+        self.list_state.select(Some(self.cursor));
+    }
+
+    /// Build the flat component→selection map from grouped selections.
+    fn selection_map(&self) -> BTreeMap<SnapshotComponentType, ComponentSelection> {
+        let mut map = BTreeMap::new();
+        for (group, sel) in self.groups.iter().zip(&self.selections) {
+            for ty in &group.types {
+                map.insert(*ty, *sel);
+            }
+        }
+        map
+    }
+
+    /// Size for a single group, summing all component types in the group.
+    fn group_size(&self, group_idx: usize) -> u64 {
+        let sel = self.selections[group_idx];
+        let distance = match sel {
+            ComponentSelection::None => return 0,
+            ComponentSelection::All => None,
+            ComponentSelection::Distance(d) => Some(d),
+        };
+        self.groups[group_idx]
+            .types
+            .iter()
+            .map(|ty| self.manifest.size_for_distance(*ty, distance))
+            .sum()
+    }
+
+    fn total_selected_size(&self) -> u64 {
+        (0..self.groups.len()).map(|i| self.group_size(i)).sum()
+    }
+}
+
+/// Runs the interactive component selector TUI.
+pub fn run_selector(
+    manifest: SnapshotManifest,
+    full_preset: &BTreeMap<SnapshotComponentType, ComponentSelection>,
+) -> eyre::Result<SelectorOutput> {
+    enable_raw_mode()?;
+    let mut stdout = io::stdout();
+    execute!(stdout, EnterAlternateScreen)?;
+    let backend = CrosstermBackend::new(stdout);
+    let mut terminal = Terminal::new(backend)?;
+
+    let mut app = SelectorApp::new(manifest, full_preset.clone());
+    let result = event_loop(&mut terminal, &mut app);
+
+    disable_raw_mode()?;
+    execute!(terminal.backend_mut(), LeaveAlternateScreen)?;
+    terminal.show_cursor()?;
+
+    result
+}
+
+fn event_loop(
+    terminal: &mut Terminal<CrosstermBackend<io::Stdout>>,
+    app: &mut SelectorApp,
+) -> eyre::Result<SelectorOutput> {
+    let tick_rate = Duration::from_millis(100);
+    let mut last_tick = Instant::now();
+
+    loop {
+        terminal.draw(|f| render(f, app))?;
+
+        let timeout =
+            tick_rate.checked_sub(last_tick.elapsed()).unwrap_or_else(|| Duration::from_secs(0));
+
+        if crossterm::event::poll(timeout)? &&
+            let Event::Key(key) = event::read()? &&
+            key.kind == event::KeyEventKind::Press
+        {
+            match key.code {
+                KeyCode::Char('q') | KeyCode::Esc => {
+                    eyre::bail!("Download cancelled by user");
+                }
+                KeyCode::Enter => {
+                    return Ok(SelectorOutput {
+                        selections: app.selection_map(),
+                        preset: app.preset,
+                    });
+                }
+                KeyCode::Right | KeyCode::Char('l') | KeyCode::Char(' ') => app.cycle_right(),
+                KeyCode::Left | KeyCode::Char('h') => app.cycle_left(),
+                KeyCode::Char('a') => app.select_all(),
+                KeyCode::Char('f') => app.select_full(),
+                KeyCode::Char('m') => app.select_minimal(),
+                KeyCode::Up | KeyCode::Char('k') => app.move_up(),
+                KeyCode::Down | KeyCode::Char('j') => app.move_down(),
+                _ => {}
+            }
+        }
+
+        if last_tick.elapsed() >= tick_rate {
+            last_tick = Instant::now();
+        }
+    }
+}
+
+fn format_selection(sel: &ComponentSelection) -> String {
+    match sel {
+        ComponentSelection::All => "All".to_string(),
+        ComponentSelection::Distance(d) => format!("Last {d} blocks"),
+        ComponentSelection::None => "None".to_string(),
+    }
+}
+
+fn render(f: &mut Frame<'_>, app: &mut SelectorApp) {
+    let chunks = Layout::default()
+        .direction(Direction::Vertical)
+        .constraints([
+            Constraint::Length(3), // Header
+            Constraint::Min(8),    // Component list
+            Constraint::Length(3), // Footer
+        ])
+        .split(f.area());
+
+    // Header
+    let block_info = if app.manifest.block > 0 {
+        format!(" (block {})", app.manifest.block)
+    } else {
+        String::new()
+    };
+    let header = Paragraph::new(format!(" Select snapshot components to download{}", block_info))
+        .style(Style::default().fg(Color::Cyan).add_modifier(Modifier::BOLD))
+        .block(Block::default().borders(Borders::ALL).title("reth download"));
+    f.render_widget(header, chunks[0]);
+
+    // Component list
+    let items: Vec<ListItem<'_>> = app
+        .groups
+        .iter()
+        .enumerate()
+        .map(|(i, group)| {
+            let sel = &app.selections[i];
+            let sel_str = format_selection(sel);
+
+            let size = app.group_size(i);
+            let size_str =
+                if size > 0 { DownloadProgress::format_size(size) } else { String::new() };
+
+            let required = if group.required { " (required)" } else { "" };
+
+            let at_max = *sel == *group.presets.last().unwrap_or(&ComponentSelection::All);
+            let at_min = *sel == group.presets[0];
+            let arrows = if group.required {
+                "   "
+            } else if at_max {
+                "◂  "
+            } else if at_min {
+                "  ▸"
+            } else {
+                "◂ ▸"
+            };
+
+            let style = if group.required {
+                Style::default().fg(Color::DarkGray)
+            } else if matches!(sel, ComponentSelection::None) {
+                Style::default().fg(Color::White)
+            } else {
+                Style::default().fg(Color::Green)
+            };
+
+            ListItem::new(Line::from(vec![
+                Span::styled(format!(" {:<22}", group.name), style),
+                Span::styled(
+                    format!("{arrows} {:<12}", sel_str),
+                    style.add_modifier(Modifier::BOLD),
+                ),
+                Span::styled(format!("{:>10}", size_str), style.add_modifier(Modifier::DIM)),
+                Span::styled(required.to_string(), Style::default().fg(Color::DarkGray)),
+            ]))
+        })
+        .collect();
+
+    let total_str = DownloadProgress::format_size(app.total_selected_size());
+    let list = List::new(items)
+        .block(
+            Block::default()
+                .borders(Borders::ALL)
+                .title(format!("Components — Total: {total_str}")),
+        )
+        .highlight_style(Style::default().add_modifier(Modifier::BOLD).bg(Color::DarkGray))
+        .highlight_symbol("▸ ");
+    f.render_stateful_widget(list, chunks[1], &mut app.list_state);
+
+    // Footer
+    let footer = Paragraph::new(
+        " [←/→] adjust  [m] minimal  [f] full  [a] archive  [Enter] confirm  [Esc] cancel",
+    )
+    .style(Style::default().fg(Color::Cyan).add_modifier(Modifier::BOLD))
+    .block(Block::default().borders(Borders::ALL));
+    f.render_widget(footer, chunks[2]);
+}

crates/cli/commands/src/init_state/mod.rs

@@ -47,7 +47,7 @@ pub struct InitStateCommand<C: ChainSpecParser> {
     /// Specifies whether to initialize the state without relying on EVM historical data.
     ///
     /// When enabled, and before inserting the state, it creates a dummy chain up to the last EVM
-    /// block specified. It then, appends the first block provided block.
+    /// block specified. It then appends the first provided block.
     ///
     /// - **Note**: **Do not** import receipts and blocks beforehand, or this will fail or be
     ///   ignored.

crates/cli/commands/src/node.rs

@@ -125,12 +125,12 @@ pub struct NodeCommand<C: ChainSpecParser, Ext: clap::Args + fmt::Debug = NoArgs
 }
 
 impl<C: ChainSpecParser> NodeCommand<C> {
-    /// Parsers only the default CLI arguments
+    /// Parses only the default CLI arguments
     pub fn parse_args() -> Self {
         Self::parse()
     }
 
-    /// Parsers only the default [`NodeCommand`] arguments from the given iterator
+    /// Parses only the default [`NodeCommand`] arguments from the given iterator
     pub fn try_parse_args_from<I, T>(itr: I) -> Result<Self, clap::error::Error>
     where
         I: IntoIterator<Item = T>,

crates/cli/commands/src/re_execute.rs

@@ -95,6 +95,10 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + Hardforks + EthereumHardforks>
             }
         };
 
+        if min_block > max_block {
+            eyre::bail!("--from ({min_block}) is beyond --to ({max_block}), nothing to re-execute");
+        }
+
         let num_tasks = self.num_tasks.unwrap_or_else(|| {
             std::thread::available_parallelism().map(|n| n.get() as u64).unwrap_or(10)
         });

crates/cli/commands/src/stage/dump/merkle.rs

@@ -127,12 +127,14 @@ fn unwind_and_copy<N: ProviderNodeTypes>(
     AccountHashingStage {
         clean_threshold: u64::MAX,
         commit_threshold: u64::MAX,
+        commit_entries: u64::MAX,
         etl_config: EtlConfig::default(),
     }
     .execute(&provider, execute_input)?;
     StorageHashingStage {
         clean_threshold: u64::MAX,
         commit_threshold: u64::MAX,
+        commit_entries: u64::MAX,
         etl_config: EtlConfig::default(),
     }
     .execute(&provider, execute_input)?;

crates/cli/commands/src/stage/run.rs

@@ -107,7 +107,7 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + Hardforks + EthereumHardforks>
         Comp: CliNodeComponents<N>,
         F: FnOnce(Arc<C::ChainSpec>) -> Comp,
     {
-        // Quit early if the stages requires a commit and `--commit` is not provided.
+        // Quit early if the stage requires a commit and `--commit` is not provided.
         if self.requires_commit() && !self.commit {
             return Err(eyre::eyre!(
                 "The stage {} requires overwriting existing static files and must commit, but `--commit` was not provided. Please pass `--commit` and try again.",
@@ -282,14 +282,22 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + Hardforks + EthereumHardforks>
                 ),
                 StageEnum::AccountHashing => (
                     Box::new(AccountHashingStage::new(
-                        HashingConfig { clean_threshold: 1, commit_threshold: batch_size },
+                        HashingConfig {
+                            clean_threshold: 1,
+                            commit_threshold: batch_size,
+                            commit_entries: u64::MAX,
+                        },
                         etl_config,
                     )),
                     None,
                 ),
                 StageEnum::StorageHashing => (
                     Box::new(StorageHashingStage::new(
-                        HashingConfig { clean_threshold: 1, commit_threshold: batch_size },
+                        HashingConfig {
+                            clean_threshold: 1,
+                            commit_threshold: batch_size,
+                            commit_entries: u64::MAX,
+                        },
                         etl_config,
                     )),
                     None,

crates/cli/runner/src/lib.rs

@@ -71,7 +71,12 @@ impl CliRunner {
     ) -> Result<(), E>
     where
         F: Future<Output = Result<(), E>>,
-        E: Send + Sync + From<std::io::Error> + From<reth_tasks::PanickedTaskError> + 'static,
+        E: Send
+            + Sync
+            + std::fmt::Display
+            + From<std::io::Error>
+            + From<reth_tasks::PanickedTaskError>
+            + 'static,
     {
         let (context, task_manager_handle) = cli_context(&self.runtime);
 
@@ -81,8 +86,8 @@ impl CliRunner {
             run_until_ctrl_c(command(context)),
         ));
 
-        if command_res.is_err() {
-            error!(target: "reth::cli", "shutting down due to error");
+        if let Err(err) = &command_res {
+            error!(target: "reth::cli", %err, "shutting down due to error");
         } else {
             debug!(target: "reth::cli", "shutting down gracefully");
             // after the command has finished or exit signal was received we shutdown the
@@ -105,7 +110,12 @@ impl CliRunner {
     ) -> Result<(), E>
     where
         F: Future<Output = Result<(), E>> + Send + 'static,
-        E: Send + Sync + From<std::io::Error> + From<reth_tasks::PanickedTaskError> + 'static,
+        E: Send
+            + Sync
+            + std::fmt::Display
+            + From<std::io::Error>
+            + From<reth_tasks::PanickedTaskError>
+            + 'static,
     {
         let (context, task_manager_handle) = cli_context(&self.runtime);
 
@@ -122,8 +132,8 @@ impl CliRunner {
             ),
         ));
 
-        if command_res.is_err() {
-            error!(target: "reth::cli", "shutting down due to error");
+        if let Err(err) = &command_res {
+            error!(target: "reth::cli", %err, "shutting down due to error");
         } else {
             debug!(target: "reth::cli", "shutting down gracefully");
             self.runtime.graceful_shutdown_with_timeout(self.config.graceful_shutdown_timeout);

crates/config/src/config.rs

@@ -332,11 +332,15 @@ pub struct HashingConfig {
     pub clean_threshold: u64,
     /// The maximum number of entities to process before committing progress to the database.
     pub commit_threshold: u64,
+    /// The maximum number of changeset entries to process before committing progress. The stage
+    /// commits after either `commit_threshold` blocks or `commit_entries` entries, whichever
+    /// comes first. This bounds memory usage when blocks contain many state changes.
+    pub commit_entries: u64,
 }
 
 impl Default for HashingConfig {
     fn default() -> Self {
-        Self { clean_threshold: 500_000, commit_threshold: 100_000 }
+        Self { clean_threshold: 500_000, commit_threshold: 100_000, commit_entries: 30_000_000 }
     }
 }
 

crates/engine/primitives/Cargo.toml

@@ -39,6 +39,7 @@ thiserror.workspace = true
 
 [features]
 default = ["std"]
+trie-debug = []
 std = [
     "reth-execution-types/std",
     "reth-ethereum-primitives/std",

crates/engine/primitives/src/config.rs

@@ -9,26 +9,6 @@ pub const DEFAULT_PERSISTENCE_THRESHOLD: u64 = 2;
 /// How close to the canonical head we persist blocks.
 pub const DEFAULT_MEMORY_BLOCK_BUFFER_TARGET: u64 = 0;
 
-/// Returns the default number of storage worker threads based on available parallelism.
-fn default_storage_worker_count() -> usize {
-    #[cfg(feature = "std")]
-    {
-        std::thread::available_parallelism().map_or(8, |n| n.get() * 2)
-    }
-    #[cfg(not(feature = "std"))]
-    {
-        8
-    }
-}
-
-/// Returns the default number of account worker threads.
-///
-/// Account workers coordinate storage proof collection and account trie traversal.
-/// They are set to the same count as storage workers for simplicity.
-fn default_account_worker_count() -> usize {
-    default_storage_worker_count()
-}
-
 /// The size of proof targets chunk to spawn in one multiproof calculation.
 pub const DEFAULT_MULTIPROOF_TASK_CHUNK_SIZE: usize = 5;
 
@@ -46,10 +26,15 @@ pub const DEFAULT_RESERVED_CPU_CORES: usize = 1;
 /// Depth 4 means we keep roughly 16^4 = 65536 potential branch paths at most.
 pub const DEFAULT_SPARSE_TRIE_PRUNE_DEPTH: usize = 4;
 
-/// Default maximum number of storage tries to keep after pruning.
+/// Default LFU hot-slot capacity for sparse trie pruning.
 ///
-/// Storage tries beyond this limit are cleared (but allocations preserved).
-pub const DEFAULT_SPARSE_TRIE_MAX_STORAGE_TRIES: usize = 100;
+/// Limits the number of `(address, slot)` pairs retained across prune cycles.
+pub const DEFAULT_SPARSE_TRIE_MAX_HOT_SLOTS: usize = 1500;
+
+/// Default LFU hot-account capacity for sparse trie pruning.
+///
+/// Limits the number of account addresses retained across prune cycles.
+pub const DEFAULT_SPARSE_TRIE_MAX_HOT_ACCOUNTS: usize = 1000;
 
 /// Default timeout for the state root task before spawning a sequential fallback.
 pub const DEFAULT_STATE_ROOT_TASK_TIMEOUT: Duration = Duration::from_secs(1);
@@ -147,23 +132,32 @@ pub struct TreeConfig {
     always_process_payload_attributes_on_canonical_head: bool,
     /// Whether to unwind canonical header to ancestor during forkchoice updates.
     allow_unwind_canonical_header: bool,
-    /// Number of storage proof worker threads.
-    storage_worker_count: usize,
-    /// Number of account proof worker threads.
-    account_worker_count: usize,
     /// Whether to disable cache metrics recording (can be expensive with large cached state).
     disable_cache_metrics: bool,
     /// Depth for sparse trie pruning after state root computation.
     sparse_trie_prune_depth: usize,
-    /// Maximum number of storage tries to retain after pruning.
-    sparse_trie_max_storage_tries: usize,
+    /// LFU hot-slot capacity: max `(address, slot)` pairs retained across prune cycles.
+    sparse_trie_max_hot_slots: usize,
+    /// LFU hot-account capacity: max account addresses retained across prune cycles.
+    sparse_trie_max_hot_accounts: usize,
+    /// When set, blocks whose total processing time (execution + state reads + state root +
+    /// DB commit) exceeds this duration trigger a structured `warn!` log with detailed timing,
+    /// state-operation counts, and cache hit-rate metrics. `Duration::ZERO` logs every block.
+    slow_block_threshold: Option<Duration>,
     /// Whether to fully disable sparse trie cache pruning between blocks.
     disable_sparse_trie_cache_pruning: bool,
+    /// Whether to use the arena-based sparse trie implementation.
+    enable_arena_sparse_trie: bool,
     /// Timeout for the state root task before spawning a sequential fallback computation.
     /// If `Some`, after waiting this duration for the state root task, a sequential state root
     /// computation is spawned in parallel and whichever finishes first is used.
     /// If `None`, the timeout fallback is disabled.
     state_root_task_timeout: Option<Duration>,
+    /// Maximum random jitter applied before each proof computation (trie-debug only).
+    /// When set, each proof worker sleeps for a random duration up to this value
+    /// before starting a proof calculation.
+    #[cfg(feature = "trie-debug")]
+    proof_jitter: Option<Duration>,
 }
 
 impl Default for TreeConfig {
@@ -187,13 +181,16 @@ impl Default for TreeConfig {
             state_root_fallback: false,
             always_process_payload_attributes_on_canonical_head: false,
             allow_unwind_canonical_header: false,
-            storage_worker_count: default_storage_worker_count(),
-            account_worker_count: default_account_worker_count(),
             disable_cache_metrics: false,
             sparse_trie_prune_depth: DEFAULT_SPARSE_TRIE_PRUNE_DEPTH,
-            sparse_trie_max_storage_tries: DEFAULT_SPARSE_TRIE_MAX_STORAGE_TRIES,
+            sparse_trie_max_hot_slots: DEFAULT_SPARSE_TRIE_MAX_HOT_SLOTS,
+            sparse_trie_max_hot_accounts: DEFAULT_SPARSE_TRIE_MAX_HOT_ACCOUNTS,
+            slow_block_threshold: None,
             disable_sparse_trie_cache_pruning: false,
+            enable_arena_sparse_trie: false,
             state_root_task_timeout: Some(DEFAULT_STATE_ROOT_TASK_TIMEOUT),
+            #[cfg(feature = "trie-debug")]
+            proof_jitter: None,
         }
     }
 }
@@ -220,11 +217,11 @@ impl TreeConfig {
         state_root_fallback: bool,
         always_process_payload_attributes_on_canonical_head: bool,
         allow_unwind_canonical_header: bool,
-        storage_worker_count: usize,
-        account_worker_count: usize,
         disable_cache_metrics: bool,
         sparse_trie_prune_depth: usize,
-        sparse_trie_max_storage_tries: usize,
+        sparse_trie_max_hot_slots: usize,
+        sparse_trie_max_hot_accounts: usize,
+        slow_block_threshold: Option<Duration>,
         state_root_task_timeout: Option<Duration>,
     ) -> Self {
         Self {
@@ -246,13 +243,16 @@ impl TreeConfig {
             state_root_fallback,
             always_process_payload_attributes_on_canonical_head,
             allow_unwind_canonical_header,
-            storage_worker_count,
-            account_worker_count,
             disable_cache_metrics,
             sparse_trie_prune_depth,
-            sparse_trie_max_storage_tries,
+            sparse_trie_max_hot_slots,
+            sparse_trie_max_hot_accounts,
+            slow_block_threshold,
             disable_sparse_trie_cache_pruning: false,
+            enable_arena_sparse_trie: false,
             state_root_task_timeout,
+            #[cfg(feature = "trie-debug")]
+            proof_jitter: None,
         }
     }
 
@@ -479,42 +479,6 @@ impl TreeConfig {
         self.has_enough_parallelism && !self.legacy_state_root
     }
 
-    /// Return the number of storage proof worker threads.
-    pub const fn storage_worker_count(&self) -> usize {
-        self.storage_worker_count
-    }
-
-    /// Setter for the number of storage proof worker threads.
-    ///
-    /// No-op if it's [`None`].
-    pub const fn with_storage_worker_count_opt(
-        mut self,
-        storage_worker_count: Option<usize>,
-    ) -> Self {
-        if let Some(count) = storage_worker_count {
-            self.storage_worker_count = count;
-        }
-        self
-    }
-
-    /// Return the number of account proof worker threads.
-    pub const fn account_worker_count(&self) -> usize {
-        self.account_worker_count
-    }
-
-    /// Setter for the number of account proof worker threads.
-    ///
-    /// No-op if it's [`None`].
-    pub const fn with_account_worker_count_opt(
-        mut self,
-        account_worker_count: Option<usize>,
-    ) -> Self {
-        if let Some(count) = account_worker_count {
-            self.account_worker_count = count;
-        }
-        self
-    }
-
     /// Returns whether cache metrics recording is disabled.
     pub const fn disable_cache_metrics(&self) -> bool {
         self.disable_cache_metrics
@@ -537,14 +501,43 @@ impl TreeConfig {
         self
     }
 
-    /// Returns the maximum number of storage tries to retain after pruning.
-    pub const fn sparse_trie_max_storage_tries(&self) -> usize {
-        self.sparse_trie_max_storage_tries
+    /// Returns the LFU hot-slot capacity for sparse trie pruning.
+    pub const fn sparse_trie_max_hot_slots(&self) -> usize {
+        self.sparse_trie_max_hot_slots
     }
 
-    /// Setter for maximum storage tries to retain.
-    pub const fn with_sparse_trie_max_storage_tries(mut self, max_tries: usize) -> Self {
-        self.sparse_trie_max_storage_tries = max_tries;
+    /// Setter for LFU hot-slot capacity.
+    pub const fn with_sparse_trie_max_hot_slots(mut self, max_hot_slots: usize) -> Self {
+        self.sparse_trie_max_hot_slots = max_hot_slots;
+        self
+    }
+
+    /// Returns the LFU hot-account capacity for sparse trie pruning.
+    pub const fn sparse_trie_max_hot_accounts(&self) -> usize {
+        self.sparse_trie_max_hot_accounts
+    }
+
+    /// Setter for LFU hot-account capacity.
+    pub const fn with_sparse_trie_max_hot_accounts(mut self, max_hot_accounts: usize) -> Self {
+        self.sparse_trie_max_hot_accounts = max_hot_accounts;
+        self
+    }
+
+    /// Returns the slow block threshold, if configured.
+    ///
+    /// When `Some`, blocks whose total processing time exceeds this duration emit a structured
+    /// warning with timing, state-operation, and cache-hit-rate details. `Duration::ZERO` logs
+    /// every block.
+    pub const fn slow_block_threshold(&self) -> Option<Duration> {
+        self.slow_block_threshold
+    }
+
+    /// Setter for slow block threshold.
+    pub const fn with_slow_block_threshold(
+        mut self,
+        slow_block_threshold: Option<Duration>,
+    ) -> Self {
+        self.slow_block_threshold = slow_block_threshold;
         self
     }
 
@@ -559,6 +552,17 @@ impl TreeConfig {
         self
     }
 
+    /// Returns whether the arena-based sparse trie is enabled.
+    pub const fn enable_arena_sparse_trie(&self) -> bool {
+        self.enable_arena_sparse_trie
+    }
+
+    /// Setter for whether to enable the arena-based sparse trie.
+    pub const fn with_enable_arena_sparse_trie(mut self, value: bool) -> Self {
+        self.enable_arena_sparse_trie = value;
+        self
+    }
+
     /// Returns the state root task timeout.
     pub const fn state_root_task_timeout(&self) -> Option<Duration> {
         self.state_root_task_timeout
@@ -569,4 +573,17 @@ impl TreeConfig {
         self.state_root_task_timeout = timeout;
         self
     }
+
+    /// Returns the proof jitter duration, if configured (trie-debug only).
+    #[cfg(feature = "trie-debug")]
+    pub const fn proof_jitter(&self) -> Option<Duration> {
+        self.proof_jitter
+    }
+
+    /// Setter for proof jitter (trie-debug only).
+    #[cfg(feature = "trie-debug")]
+    pub const fn with_proof_jitter(mut self, proof_jitter: Option<Duration>) -> Self {
+        self.proof_jitter = proof_jitter;
+        self
+    }
 }

crates/engine/primitives/src/event.rs

@@ -9,7 +9,7 @@ use core::{
     fmt::{Display, Formatter, Result},
     time::Duration,
 };
-use reth_chain_state::ExecutedBlock;
+use reth_chain_state::{ExecutedBlock, ExecutionTimingStats};
 use reth_ethereum_primitives::EthPrimitives;
 use reth_primitives_traits::{NodePrimitives, SealedBlock, SealedHeader};
 
@@ -32,6 +32,8 @@ pub enum ConsensusEngineEvent<N: NodePrimitives = EthPrimitives> {
     CanonicalChainCommitted(Box<SealedHeader<N::BlockHeader>>, Duration),
     /// The consensus engine processed an invalid block.
     InvalidBlock(Box<SealedBlock<N::Block>>),
+    /// A slow block was detected after persistence, with its timing statistics.
+    SlowBlock(SlowBlockInfo),
 }
 
 impl<N: NodePrimitives> ConsensusEngineEvent<N> {
@@ -73,6 +75,25 @@ where
             Self::BlockReceived(num_hash) => {
                 write!(f, "BlockReceived({num_hash:?})")
             }
+            Self::SlowBlock(info) => {
+                write!(
+                    f,
+                    "SlowBlock(block={}, total={:?})",
+                    info.stats.block_number, info.total_duration
+                )
+            }
         }
     }
 }
+
+/// Information about a slow block detected after persistence.
+#[derive(Clone, Debug)]
+pub struct SlowBlockInfo {
+    /// The timing statistics for the slow block.
+    pub stats: Box<ExecutionTimingStats>,
+    /// The commit duration for the batch containing this block.
+    pub commit_duration: Duration,
+    /// The total duration (execution + `state_root` + commit).
+    /// Note: `state_read` is a subset of execution and is not added separately.
+    pub total_duration: Duration,
+}

crates/engine/tree/Cargo.toml

@@ -98,22 +98,12 @@ reth-e2e-test-utils.workspace = true
 revm-state.workspace = true
 
 assert_matches.workspace = true
-criterion.workspace = true
 eyre.workspace = true
 serde_json.workspace = true
-crossbeam-channel.workspace = true
 proptest.workspace = true
 rand.workspace = true
 rand_08.workspace = true
 
-[[bench]]
-name = "channel_perf"
-harness = false
-
-[[bench]]
-name = "state_root_task"
-harness = false
-
 [features]
 test-utils = [
     "reth-chain-state/test-utils",
@@ -143,7 +133,12 @@ test-utils = [
     "reth-evm-ethereum/test-utils",
     "reth-tasks/test-utils",
 ]
-trie-debug = ["reth-trie-sparse/trie-debug", "dep:serde_json"]
+trie-debug = [
+    "reth-trie-sparse/trie-debug",
+    "reth-trie-parallel/trie-debug",
+    "reth-engine-primitives/trie-debug",
+    "dep:serde_json",
+]
 rocksdb = [
     "reth-provider/rocksdb",
     "reth-prune/rocksdb",

crates/engine/tree/benches/channel_perf.rs

@@ -1,138 +0,0 @@
-//! Benchmark comparing `std::sync::mpsc` and `crossbeam` channels for `StateRootTask`.
-
-#![allow(missing_docs)]
-
-use alloy_primitives::{B256, U256};
-use criterion::{criterion_group, criterion_main, BatchSize, BenchmarkId, Criterion};
-use proptest::test_runner::TestRunner;
-use rand::Rng;
-use revm_primitives::{Address, HashMap};
-use revm_state::{Account, AccountInfo, AccountStatus, EvmState, EvmStorage, EvmStorageSlot};
-use std::{hint::black_box, thread};
-
-/// Creates a mock state with the specified number of accounts for benchmarking
-fn create_bench_state(num_accounts: usize) -> EvmState {
-    let mut runner = TestRunner::deterministic();
-    let mut rng = runner.rng().clone();
-    let mut state_changes = HashMap::default();
-
-    for i in 0..num_accounts {
-        let storage =
-            EvmStorage::from_iter([(U256::from(i), EvmStorageSlot::new(U256::from(i + 1), 0))]);
-
-        let account = Account {
-            info: AccountInfo {
-                balance: U256::from(100),
-                nonce: 10,
-                code_hash: B256::from_slice(&rng.random::<[u8; 32]>()),
-                code: Default::default(),
-                account_id: None,
-            },
-            original_info: Box::new(AccountInfo::default()),
-            storage,
-            status: AccountStatus::empty(),
-            transaction_id: 0,
-        };
-
-        let address = Address::with_last_byte(i as u8);
-        state_changes.insert(address, account);
-    }
-
-    state_changes
-}
-
-/// Simulated `StateRootTask` with `std::sync::mpsc`
-struct StdStateRootTask {
-    rx: std::sync::mpsc::Receiver<EvmState>,
-}
-
-impl StdStateRootTask {
-    const fn new(rx: std::sync::mpsc::Receiver<EvmState>) -> Self {
-        Self { rx }
-    }
-
-    fn run(self) {
-        while let Ok(state) = self.rx.recv() {
-            black_box(state);
-        }
-    }
-}
-
-/// Simulated `StateRootTask` with `crossbeam-channel`
-struct CrossbeamStateRootTask {
-    rx: crossbeam_channel::Receiver<EvmState>,
-}
-
-impl CrossbeamStateRootTask {
-    const fn new(rx: crossbeam_channel::Receiver<EvmState>) -> Self {
-        Self { rx }
-    }
-
-    fn run(self) {
-        while let Ok(state) = self.rx.recv() {
-            black_box(state);
-        }
-    }
-}
-
-/// Benchmarks the performance of different channel implementations for state streaming
-fn bench_state_stream(c: &mut Criterion) {
-    let mut group = c.benchmark_group("state_stream_channels");
-    group.sample_size(10);
-
-    for size in &[1, 10, 100] {
-        let bench_setup = || {
-            let states: Vec<_> = (0..100).map(|_| create_bench_state(*size)).collect();
-            states
-        };
-
-        group.bench_with_input(BenchmarkId::new("std_channel", size), size, |b, _| {
-            b.iter_batched(
-                bench_setup,
-                |states| {
-                    let (tx, rx) = std::sync::mpsc::channel();
-                    let task = StdStateRootTask::new(rx);
-
-                    let processor = thread::spawn(move || {
-                        task.run();
-                    });
-
-                    for state in states {
-                        tx.send(state).unwrap();
-                    }
-                    drop(tx);
-
-                    processor.join().unwrap();
-                },
-                BatchSize::LargeInput,
-            );
-        });
-
-        group.bench_with_input(BenchmarkId::new("crossbeam_channel", size), size, |b, _| {
-            b.iter_batched(
-                bench_setup,
-                |states| {
-                    let (tx, rx) = crossbeam_channel::unbounded();
-                    let task = CrossbeamStateRootTask::new(rx);
-
-                    let processor = thread::spawn(move || {
-                        task.run();
-                    });
-
-                    for state in states {
-                        tx.send(state).unwrap();
-                    }
-                    drop(tx);
-
-                    processor.join().unwrap();
-                },
-                BatchSize::LargeInput,
-            );
-        });
-    }
-
-    group.finish();
-}
-
-criterion_group!(benches, bench_state_stream);
-criterion_main!(benches);

crates/engine/tree/benches/state_root_task.rs

@@ -1,272 +0,0 @@
-//! Benchmark for `StateRootTask` complete workflow, including sending state
-//! updates using the incoming messages sender and waiting for the final result.
-
-#![allow(missing_docs)]
-
-use alloy_consensus::constants::KECCAK_EMPTY;
-use alloy_evm::block::StateChangeSource;
-use alloy_primitives::{Address, B256};
-use criterion::{criterion_group, criterion_main, BenchmarkId, Criterion};
-use proptest::test_runner::TestRunner;
-use rand::Rng;
-use reth_chainspec::ChainSpec;
-use reth_db_common::init::init_genesis;
-use reth_engine_tree::tree::{
-    precompile_cache::PrecompileCacheMap, ExecutionEnv, PayloadProcessor, StateProviderBuilder,
-    TreeConfig,
-};
-use reth_ethereum_primitives::TransactionSigned;
-use reth_evm::OnStateHook;
-use reth_evm_ethereum::EthEvmConfig;
-use reth_primitives_traits::{Account as RethAccount, Recovered, StorageEntry};
-use reth_provider::{
-    providers::{BlockchainProvider, OverlayStateProviderFactory},
-    test_utils::{create_test_provider_factory_with_chain_spec, MockNodeTypesWithDB},
-    AccountReader, ChainSpecProvider, HashingWriter, ProviderFactory,
-};
-use revm_primitives::{HashMap, U256};
-use revm_state::{Account as RevmAccount, AccountInfo, AccountStatus, EvmState, EvmStorageSlot};
-use std::{hint::black_box, sync::Arc};
-
-#[derive(Debug, Clone)]
-struct BenchParams {
-    num_accounts: usize,
-    updates_per_account: usize,
-    storage_slots_per_account: usize,
-    selfdestructs_per_update: usize,
-}
-
-/// Generates a series of random state updates with configurable accounts,
-/// storage, and self-destructs
-fn create_bench_state_updates(params: &BenchParams) -> Vec<EvmState> {
-    let mut runner = TestRunner::deterministic();
-    let mut rng = runner.rng().clone();
-    let all_addresses: Vec<Address> =
-        (0..params.num_accounts).map(|_| Address::random_with(&mut rng)).collect();
-    let mut updates = Vec::with_capacity(params.updates_per_account);
-
-    for _ in 0..params.updates_per_account {
-        let mut state_update = EvmState::default();
-        let num_accounts_in_update = rng.random_range(1..=params.num_accounts);
-
-        // regular updates for randomly selected accounts
-        for &address in &all_addresses[0..num_accounts_in_update] {
-            // randomly choose to self-destruct with probability
-            // (selfdestructs/accounts)
-            let is_selfdestruct = rng
-                .random_bool(params.selfdestructs_per_update as f64 / params.num_accounts as f64);
-
-            let account = if is_selfdestruct {
-                RevmAccount {
-                    info: AccountInfo::default(),
-                    storage: HashMap::default(),
-                    status: AccountStatus::SelfDestructed,
-                    transaction_id: 0,
-                    original_info: Box::new(AccountInfo::default()),
-                }
-            } else {
-                RevmAccount {
-                    info: AccountInfo {
-                        balance: U256::from(rng.random::<u64>()),
-                        nonce: rng.random::<u64>(),
-                        code_hash: KECCAK_EMPTY,
-                        code: Some(Default::default()),
-                        account_id: None,
-                    },
-                    storage: (0..rng.random_range(0..=params.storage_slots_per_account))
-                        .map(|_| {
-                            (
-                                U256::from(rng.random::<u64>()),
-                                EvmStorageSlot::new_changed(
-                                    U256::ZERO,
-                                    U256::from(rng.random::<u64>()),
-                                    0,
-                                ),
-                            )
-                        })
-                        .collect(),
-                    status: AccountStatus::Touched,
-                    original_info: Box::new(AccountInfo::default()),
-                    transaction_id: 0,
-                }
-            };
-
-            state_update.insert(address, account);
-        }
-
-        updates.push(state_update);
-    }
-
-    updates
-}
-
-fn convert_revm_to_reth_account(revm_account: &RevmAccount) -> Option<RethAccount> {
-    match revm_account.status {
-        AccountStatus::SelfDestructed => None,
-        _ => Some(RethAccount {
-            balance: revm_account.info.balance,
-            nonce: revm_account.info.nonce,
-            bytecode_hash: if revm_account.info.code_hash == KECCAK_EMPTY {
-                None
-            } else {
-                Some(revm_account.info.code_hash)
-            },
-        }),
-    }
-}
-
-/// Applies state updates to the provider, ensuring self-destructs only affect
-/// existing accounts
-fn setup_provider(
-    factory: &ProviderFactory<MockNodeTypesWithDB>,
-    state_updates: &[EvmState],
-) -> Result<(), Box<dyn std::error::Error>> {
-    for update in state_updates {
-        let provider_rw = factory.provider_rw()?;
-
-        let mut account_updates = Vec::with_capacity(update.len());
-
-        for (address, account) in update {
-            // only process self-destructs if account exists, always process
-            // other updates
-            let should_process = match account.status {
-                AccountStatus::SelfDestructed => {
-                    provider_rw.basic_account(address).ok().flatten().is_some()
-                }
-                _ => true,
-            };
-
-            if should_process {
-                account_updates.push((
-                    *address,
-                    convert_revm_to_reth_account(account),
-                    (account.status == AccountStatus::Touched).then(|| {
-                        account
-                            .storage
-                            .iter()
-                            .map(|(slot, value)| StorageEntry {
-                                key: B256::from(*slot),
-                                value: value.present_value,
-                            })
-                            .collect::<Vec<_>>()
-                    }),
-                ));
-            }
-        }
-
-        // update in the provider account and its storage (if available)
-        for (address, account, maybe_storage) in account_updates {
-            provider_rw.insert_account_for_hashing(std::iter::once((address, account)))?;
-            if let Some(storage) = maybe_storage {
-                provider_rw
-                    .insert_storage_for_hashing(std::iter::once((address, storage.into_iter())))?;
-            }
-        }
-
-        provider_rw.commit()?;
-    }
-
-    Ok(())
-}
-
-fn bench_state_root(c: &mut Criterion) {
-    reth_tracing::init_test_tracing();
-
-    let mut group = c.benchmark_group("state_root");
-
-    let scenarios = vec![
-        BenchParams {
-            num_accounts: 100,
-            updates_per_account: 5,
-            storage_slots_per_account: 10,
-            selfdestructs_per_update: 2,
-        },
-        BenchParams {
-            num_accounts: 1000,
-            updates_per_account: 10,
-            storage_slots_per_account: 20,
-            selfdestructs_per_update: 5,
-        },
-        BenchParams {
-            num_accounts: 500,
-            updates_per_account: 8,
-            storage_slots_per_account: 15,
-            selfdestructs_per_update: 20,
-        },
-    ];
-
-    for params in scenarios {
-        group.bench_with_input(
-            BenchmarkId::new(
-                "state_root_task",
-                format!(
-                    "accounts_{}_updates_{}_slots_{}_selfdestructs_{}",
-                    params.num_accounts,
-                    params.updates_per_account,
-                    params.storage_slots_per_account,
-                    params.selfdestructs_per_update
-                ),
-            ),
-            &params,
-            |b, params| {
-                b.iter_with_setup(
-                    || {
-                        let factory = create_test_provider_factory_with_chain_spec(Arc::new(
-                            ChainSpec::default(),
-                        ));
-                        let genesis_hash = init_genesis(&factory).unwrap();
-                        let state_updates = create_bench_state_updates(params);
-                        setup_provider(&factory, &state_updates).expect("failed to setup provider");
-
-                        let payload_processor = PayloadProcessor::new(
-                            reth_tasks::Runtime::test(),
-                            EthEvmConfig::new(factory.chain_spec()),
-                            &TreeConfig::default(),
-                            PrecompileCacheMap::default(),
-                        );
-                        let provider = BlockchainProvider::new(factory).unwrap();
-
-                        (genesis_hash, payload_processor, provider, state_updates)
-                    },
-                    |(genesis_hash, mut payload_processor, provider, state_updates)| {
-                        black_box({
-                            let mut handle = payload_processor.spawn(
-                                ExecutionEnv::test_default(),
-                                (
-                                    Vec::<
-                                        Result<
-                                            Recovered<TransactionSigned>,
-                                            core::convert::Infallible,
-                                        >,
-                                    >::new(),
-                                    std::convert::identity,
-                                ),
-                                StateProviderBuilder::new(provider.clone(), genesis_hash, None),
-                                OverlayStateProviderFactory::new(
-                                    provider,
-                                    reth_trie_db::ChangesetCache::new(),
-                                ),
-                                &TreeConfig::default(),
-                                None,
-                            );
-
-                            let mut state_hook = handle.state_hook();
-
-                            for (i, update) in state_updates.into_iter().enumerate() {
-                                state_hook.on_state(StateChangeSource::Transaction(i), &update);
-                            }
-                            drop(state_hook);
-
-                            handle.state_root().expect("task failed")
-                        });
-                    },
-                )
-            },
-        );
-    }
-
-    group.finish();
-}
-
-criterion_group!(benches, bench_state_root);
-criterion_main!(benches);

crates/engine/tree/src/launch.rs

@@ -64,6 +64,7 @@ pub fn build_engine_orchestrator<N, Client, S, V, C>(
     sync_metrics_tx: MetricEventsSender,
     evm_config: C,
     changeset_cache: ChangesetCache,
+    runtime: Runtime,
 ) -> ChainOrchestrator<
     EngineHandler<
         EngineApiRequestHandler<EngineApiRequest<N::Payload, N::Primitives>, N::Primitives>,
@@ -99,6 +100,7 @@ where
         evm_config,
         changeset_cache,
         use_hashed_state,
+        runtime,
     );
 
     let engine_handler = EngineApiRequestHandler::new(to_tree_tx, from_tree);

crates/engine/tree/src/persistence.rs

@@ -18,10 +18,20 @@ use std::{
         Arc,
     },
     thread::JoinHandle,
+    time::Duration,
 };
 use thiserror::Error;
 use tracing::{debug, error, instrument};
 
+/// Unified result of any persistence operation.
+#[derive(Debug)]
+pub struct PersistenceResult {
+    /// The last block that was persisted, if any.
+    pub last_block: Option<BlockNumHash>,
+    /// The commit duration, only available for save-blocks operations.
+    pub commit_duration: Option<Duration>,
+}
+
 /// Writes parts of reth's in memory tree state to the database and static files.
 ///
 /// This is meant to be a spawned service that listens for various incoming persistence operations,
@@ -86,18 +96,16 @@ where
         while let Ok(action) = self.incoming.recv() {
             match action {
                 PersistenceAction::RemoveBlocksAbove(new_tip_num, sender) => {
-                    let result = self.on_remove_blocks_above(new_tip_num)?;
+                    let last_block = self.on_remove_blocks_above(new_tip_num)?;
                     // send new sync metrics based on removed blocks
                     let _ =
                         self.sync_metrics_tx.send(MetricEvent::SyncHeight { height: new_tip_num });
-                    // we ignore the error because the caller may or may not care about the result
-                    let _ = sender.send(result);
+                    let _ = sender.send(PersistenceResult { last_block, commit_duration: None });
                 }
                 PersistenceAction::SaveBlocks(blocks, sender) => {
                     let result = self.on_save_blocks(blocks)?;
-                    let result_number = result.map(|r| r.number);
+                    let result_number = result.last_block.map(|b| b.number);
 
-                    // we ignore the error because the caller may or may not care about the result
                     let _ = sender.send(result);
 
                     if let Some(block_number) = result_number {
@@ -140,7 +148,7 @@ where
     fn on_save_blocks(
         &mut self,
         blocks: Vec<ExecutedBlock<N::Primitives>>,
-    ) -> Result<Option<BlockNumHash>, PersistenceError> {
+    ) -> Result<PersistenceResult, PersistenceError> {
         let first_block = blocks.first().map(|b| b.recovered_block.num_hash());
         let last_block = blocks.last().map(|b| b.recovered_block.num_hash());
         let block_count = blocks.len();
@@ -157,10 +165,16 @@ where
             provider_rw.save_blocks(blocks, SaveBlocksMode::Full)?;
 
             if let Some(finalized) = pending_finalized {
-                provider_rw.save_finalized_block_number(finalized)?;
+                provider_rw.save_finalized_block_number(finalized.min(last.number))?;
+                if finalized > last.number {
+                    self.pending_finalized_block = Some(finalized);
+                }
             }
             if let Some(safe) = pending_safe {
-                provider_rw.save_safe_block_number(safe)?;
+                provider_rw.save_safe_block_number(safe.min(last.number))?;
+                if safe > last.number {
+                    self.pending_safe_block = Some(safe);
+                }
             }
 
             if self.pruner.is_pruning_needed(last.number) {
@@ -175,10 +189,11 @@ where
 
         debug!(target: "engine::persistence", first=?first_block, last=?last_block, "Saved range of blocks");
 
+        let elapsed = start_time.elapsed();
         self.metrics.save_blocks_batch_size.record(block_count as f64);
-        self.metrics.save_blocks_duration_seconds.record(start_time.elapsed());
+        self.metrics.save_blocks_duration_seconds.record(elapsed);
 
-        Ok(last_block)
+        Ok(PersistenceResult { last_block, commit_duration: Some(elapsed) })
     }
 }
 
@@ -202,13 +217,13 @@ pub enum PersistenceAction<N: NodePrimitives = EthPrimitives> {
     ///
     /// First, header, transaction, and receipt-related data should be written to static files.
     /// Then the execution history-related data will be written to the database.
-    SaveBlocks(Vec<ExecutedBlock<N>>, CrossbeamSender<Option<BlockNumHash>>),
+    SaveBlocks(Vec<ExecutedBlock<N>>, CrossbeamSender<PersistenceResult>),
 
     /// Removes block data above the given block number from the database.
     ///
     /// This will first update checkpoints from the database, then remove actual block data from
     /// static files.
-    RemoveBlocksAbove(u64, CrossbeamSender<Option<BlockNumHash>>),
+    RemoveBlocksAbove(u64, CrossbeamSender<PersistenceResult>),
 
     /// Update the persisted finalized block on disk
     SaveFinalizedBlock(u64),
@@ -287,7 +302,7 @@ impl<T: NodePrimitives> PersistenceHandle<T> {
     pub fn save_blocks(
         &self,
         blocks: Vec<ExecutedBlock<T>>,
-        tx: CrossbeamSender<Option<BlockNumHash>>,
+        tx: CrossbeamSender<PersistenceResult>,
     ) -> Result<(), SendError<PersistenceAction<T>>> {
         self.send_action(PersistenceAction::SaveBlocks(blocks, tx))
     }
@@ -322,7 +337,7 @@ impl<T: NodePrimitives> PersistenceHandle<T> {
     pub fn remove_blocks_above(
         &self,
         block_num: u64,
-        tx: CrossbeamSender<Option<BlockNumHash>>,
+        tx: CrossbeamSender<PersistenceResult>,
     ) -> Result<(), SendError<PersistenceAction<T>>> {
         self.send_action(PersistenceAction::RemoveBlocksAbove(block_num, tx))
     }
@@ -382,8 +397,8 @@ mod tests {
 
         handle.save_blocks(blocks, tx).unwrap();
 
-        let hash = rx.recv().unwrap();
-        assert_eq!(hash, None);
+        let result = rx.recv().unwrap();
+        assert!(result.last_block.is_none());
     }
 
     #[test]
@@ -401,12 +416,9 @@ mod tests {
 
         handle.save_blocks(blocks, tx).unwrap();
 
-        let BlockNumHash { hash: actual_hash, number: _ } = rx
-            .recv_timeout(std::time::Duration::from_secs(10))
-            .expect("test timed out")
-            .expect("no hash returned");
+        let result = rx.recv_timeout(std::time::Duration::from_secs(10)).expect("test timed out");
 
-        assert_eq!(block_hash, actual_hash);
+        assert_eq!(block_hash, result.last_block.unwrap().hash);
     }
 
     #[test]
@@ -420,8 +432,8 @@ mod tests {
         let (tx, rx) = crossbeam_channel::bounded(1);
 
         handle.save_blocks(blocks, tx).unwrap();
-        let BlockNumHash { hash: actual_hash, number: _ } = rx.recv().unwrap().unwrap();
-        assert_eq!(last_hash, actual_hash);
+        let result = rx.recv().unwrap();
+        assert_eq!(last_hash, result.last_block.unwrap().hash);
     }
 
     #[test]
@@ -438,8 +450,8 @@ mod tests {
 
             handle.save_blocks(blocks, tx).unwrap();
 
-            let BlockNumHash { hash: actual_hash, number: _ } = rx.recv().unwrap().unwrap();
-            assert_eq!(last_hash, actual_hash);
+            let result = rx.recv().unwrap();
+            assert_eq!(last_hash, result.last_block.unwrap().hash);
         }
     }
 }

crates/engine/tree/src/tree/cached_state.rs

@@ -18,9 +18,7 @@ use reth_trie::{
     updates::TrieUpdates, AccountProof, HashedPostState, HashedStorage, MultiProof,
     MultiProofTargets, StorageMultiProof, StorageProof, TrieInput,
 };
-use revm_primitives::eip7907::MAX_CODE_SIZE;
 use std::{
-    mem::size_of,
     sync::{
         atomic::{AtomicU64, AtomicUsize, Ordering},
         Arc,
@@ -56,8 +54,17 @@ const fn fixed_cache_key_size_with_value<K>(value: usize) -> usize {
     raw_size.div_ceil(FIXED_CACHE_ALIGNMENT) * FIXED_CACHE_ALIGNMENT
 }
 
-/// Size in bytes of a single code cache entry.
-const CODE_CACHE_ENTRY_SIZE: usize = fixed_cache_key_size_with_value::<Address>(MAX_CODE_SIZE);
+/// Estimated average bytecode size for cache budget calculation.
+///
+/// The fixed-cache stores `Option<Bytecode>` inline (pointer-sized), but each cached contract
+/// also holds bytecode on the heap. For budget estimation we use 8 KiB, which is close to the
+/// observed mainnet average (~7 KiB). Using `MAX_CODE_SIZE` (48 KiB) overestimates by ~7x,
+/// yielding only 4096 entries for a 228 MB code-cache budget when 16384 fit comfortably.
+const ESTIMATED_AVG_CODE_SIZE: usize = 8 * 1024;
+
+/// Size in bytes of a single code cache entry (inline metadata + estimated heap).
+const CODE_CACHE_ENTRY_SIZE: usize =
+    fixed_cache_key_size_with_value::<Address>(ESTIMATED_AVG_CODE_SIZE);
 
 /// Size in bytes of a single storage cache entry.
 const STORAGE_CACHE_ENTRY_SIZE: usize =
@@ -94,6 +101,10 @@ pub struct CachedStateProvider<S, const PREWARM: bool = false> {
 
     /// Metrics for the cached state provider
     metrics: CachedStateMetrics,
+
+    /// Optional cache statistics for detailed block logging. Only tracked when slow block
+    /// threshold is configured.
+    cache_stats: Option<Arc<CacheStats>>,
 }
 
 impl<S> CachedStateProvider<S> {
@@ -104,7 +115,7 @@ impl<S> CachedStateProvider<S> {
         caches: ExecutionCache,
         metrics: CachedStateMetrics,
     ) -> Self {
-        Self { state_provider, caches, metrics }
+        Self { state_provider, caches, metrics, cache_stats: None }
     }
 }
 
@@ -115,14 +126,28 @@ impl<S> CachedStateProvider<S, true> {
         caches: ExecutionCache,
         metrics: CachedStateMetrics,
     ) -> Self {
-        Self { state_provider, caches, metrics }
+        Self { state_provider, caches, metrics, cache_stats: None }
     }
 }
 
-/// Metrics for the cached state provider, showing hits / misses / size for each cache.
-///
-/// This struct combines both the provider-level metrics (hits/misses tracked by the provider)
-/// and the fixed-cache internal stats (collisions, size, capacity).
+impl<S, const PREWARM: bool> CachedStateProvider<S, PREWARM> {
+    /// Enables cache statistics tracking for detailed block logging.
+    pub fn with_cache_stats(mut self, stats: Option<Arc<CacheStats>>) -> Self {
+        self.cache_stats = stats;
+        self
+    }
+}
+
+/// Represents the status of a key in the cache.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum CachedStatus<T> {
+    /// The key is not in the cache (or was invalidated). The value was recalculated.
+    NotCached(T),
+    /// The key exists in cache and has a specific value.
+    Cached(T),
+}
+
+/// Metrics for the cached state provider, showing hits / misses for each cache
 #[derive(Metrics, Clone)]
 #[metrics(scope = "sync.caching")]
 pub struct CachedStateMetrics {
@@ -211,6 +236,73 @@ impl CachedStateMetrics {
     }
 }
 
+/// Cache hit/miss statistics for detailed block logging.
+#[derive(Debug, Default)]
+pub struct CacheStats {
+    /// Account cache hits
+    account_hits: AtomicUsize,
+    /// Account cache misses
+    account_misses: AtomicUsize,
+    /// Storage cache hits
+    storage_hits: AtomicUsize,
+    /// Storage cache misses
+    storage_misses: AtomicUsize,
+    /// Code cache hits
+    code_hits: AtomicUsize,
+    /// Code cache misses
+    code_misses: AtomicUsize,
+}
+
+impl CacheStats {
+    pub(crate) fn record_account_hit(&self) {
+        self.account_hits.fetch_add(1, Ordering::Relaxed);
+    }
+
+    pub(crate) fn record_account_miss(&self) {
+        self.account_misses.fetch_add(1, Ordering::Relaxed);
+    }
+
+    pub(crate) fn account_hits(&self) -> usize {
+        self.account_hits.load(Ordering::Relaxed)
+    }
+
+    pub(crate) fn account_misses(&self) -> usize {
+        self.account_misses.load(Ordering::Relaxed)
+    }
+
+    pub(crate) fn record_storage_hit(&self) {
+        self.storage_hits.fetch_add(1, Ordering::Relaxed);
+    }
+
+    pub(crate) fn record_storage_miss(&self) {
+        self.storage_misses.fetch_add(1, Ordering::Relaxed);
+    }
+
+    pub(crate) fn storage_hits(&self) -> usize {
+        self.storage_hits.load(Ordering::Relaxed)
+    }
+
+    pub(crate) fn storage_misses(&self) -> usize {
+        self.storage_misses.load(Ordering::Relaxed)
+    }
+
+    pub(crate) fn record_code_hit(&self) {
+        self.code_hits.fetch_add(1, Ordering::Relaxed);
+    }
+
+    pub(crate) fn record_code_miss(&self) {
+        self.code_misses.fetch_add(1, Ordering::Relaxed);
+    }
+
+    pub(crate) fn code_hits(&self) -> usize {
+        self.code_hits.load(Ordering::Relaxed)
+    }
+
+    pub(crate) fn code_misses(&self) -> usize {
+        self.code_misses.load(Ordering::Relaxed)
+    }
+}
+
 /// A stats handler for fixed-cache that tracks collisions and size.
 ///
 /// Note: Hits and misses are tracked directly by the [`CachedStateProvider`] via
@@ -306,27 +398,36 @@ impl<S: AccountReader, const PREWARM: bool> AccountReader for CachedStateProvide
             match self.caches.get_or_try_insert_account_with(*address, || {
                 self.state_provider.basic_account(address)
             })? {
-                CachedStatus::NotCached(value) | CachedStatus::Cached(value) => Ok(value),
+                // During prewarm we only record stats (not prometheus metrics)
+                CachedStatus::NotCached(value) => {
+                    if let Some(stats) = &self.cache_stats {
+                        stats.record_account_miss();
+                    }
+                    Ok(value)
+                }
+                CachedStatus::Cached(value) => {
+                    if let Some(stats) = &self.cache_stats {
+                        stats.record_account_hit();
+                    }
+                    Ok(value)
+                }
             }
         } else if let Some(account) = self.caches.0.account_cache.get(address) {
             self.metrics.account_cache_hits.increment(1);
+            if let Some(stats) = &self.cache_stats {
+                stats.record_account_hit();
+            }
             Ok(account)
         } else {
             self.metrics.account_cache_misses.increment(1);
+            if let Some(stats) = &self.cache_stats {
+                stats.record_account_miss();
+            }
             self.state_provider.basic_account(address)
         }
     }
 }
 
-/// Represents the status of a key in the cache.
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub enum CachedStatus<T> {
-    /// The key is not in the cache (or was invalidated). The value was recalculated.
-    NotCached(T),
-    /// The key exists in cache and has a specific value.
-    Cached(T),
-}
-
 impl<S: StateProvider, const PREWARM: bool> StateProvider for CachedStateProvider<S, PREWARM> {
     fn storage(
         &self,
@@ -337,17 +438,31 @@ impl<S: StateProvider, const PREWARM: bool> StateProvider for CachedStateProvide
             match self.caches.get_or_try_insert_storage_with(account, storage_key, || {
                 self.state_provider.storage(account, storage_key).map(Option::unwrap_or_default)
             })? {
-                CachedStatus::NotCached(value) | CachedStatus::Cached(value) => {
-                    // The slot that was never written to is indistinguishable from a slot
-                    // explicitly set to zero. We return `None` in both cases.
+                // During prewarm we only record stats (not prometheus metrics)
+                CachedStatus::NotCached(value) => {
+                    if let Some(stats) = &self.cache_stats {
+                        stats.record_storage_miss();
+                    }
+                    Ok(Some(value).filter(|v| !v.is_zero()))
+                }
+                CachedStatus::Cached(value) => {
+                    if let Some(stats) = &self.cache_stats {
+                        stats.record_storage_hit();
+                    }
                     Ok(Some(value).filter(|v| !v.is_zero()))
                 }
             }
         } else if let Some(value) = self.caches.0.storage_cache.get(&(account, storage_key)) {
             self.metrics.storage_cache_hits.increment(1);
+            if let Some(stats) = &self.cache_stats {
+                stats.record_storage_hit();
+            }
             Ok(Some(value).filter(|v| !v.is_zero()))
         } else {
             self.metrics.storage_cache_misses.increment(1);
+            if let Some(stats) = &self.cache_stats {
+                stats.record_storage_miss();
+            }
             self.state_provider.storage(account, storage_key)
         }
     }
@@ -359,13 +474,31 @@ impl<S: BytecodeReader, const PREWARM: bool> BytecodeReader for CachedStateProvi
             match self.caches.get_or_try_insert_code_with(*code_hash, || {
                 self.state_provider.bytecode_by_hash(code_hash)
             })? {
-                CachedStatus::NotCached(code) | CachedStatus::Cached(code) => Ok(code),
+                // During prewarm we only record stats (not prometheus metrics)
+                CachedStatus::NotCached(code) => {
+                    if let Some(stats) = &self.cache_stats {
+                        stats.record_code_miss();
+                    }
+                    Ok(code)
+                }
+                CachedStatus::Cached(code) => {
+                    if let Some(stats) = &self.cache_stats {
+                        stats.record_code_hit();
+                    }
+                    Ok(code)
+                }
             }
         } else if let Some(code) = self.caches.0.code_cache.get(code_hash) {
             self.metrics.code_cache_hits.increment(1);
+            if let Some(stats) = &self.cache_stats {
+                stats.record_code_hit();
+            }
             Ok(code)
         } else {
             self.metrics.code_cache_misses.increment(1);
+            if let Some(stats) = &self.cache_stats {
+                stats.record_code_miss();
+            }
             self.state_provider.bytecode_by_hash(code_hash)
         }
     }
@@ -707,7 +840,8 @@ impl ExecutionCache {
                 }
 
                 self.0.account_cache.remove(addr);
-                continue
+                self.0.account_stats.decrement_size();
+                continue;
             }
 
             // If we have an account that was modified, but it has a `None` account info, some wild
@@ -837,8 +971,10 @@ impl SavedCache {
         self.caches.update_metrics(&self.metrics);
     }
 
-    /// Clears all caches, resetting them to empty state.
-    pub(crate) fn clear(&self) {
+    /// Clears all caches, resetting them to empty state,
+    /// and updates the hash of the block this cache belongs to.
+    pub(crate) fn clear_with_hash(&mut self, hash: B256) {
+        self.hash = hash;
         self.caches.clear();
     }
 }
@@ -1085,4 +1221,20 @@ mod tests {
         assert!(caches.0.account_cache.get(&addr1).is_none());
         assert!(caches.0.account_cache.get(&addr2).is_some());
     }
+
+    #[test]
+    fn test_code_cache_capacity_with_default_budget() {
+        // Default cross-block cache is 4 GB; code gets 5.56% = ~228 MB.
+        let total_cache_size = 4 * 1024 * 1024 * 1024; // 4 GB
+        let code_budget = (total_cache_size * 556) / 10000; // 228 MB
+
+        let capacity = ExecutionCache::bytes_to_entries(code_budget, CODE_CACHE_ENTRY_SIZE);
+
+        // With ESTIMATED_AVG_CODE_SIZE (8 KiB) we expect 16384 entries.
+        // If someone accidentally reverts to MAX_CODE_SIZE (48 KiB), this would drop to 4096.
+        assert_eq!(
+            capacity, 16384,
+            "code cache should have 16384 entries with default 4 GB budget"
+        );
+    }
 }

crates/engine/tree/src/tree/instrumented_state.rs

@@ -13,7 +13,10 @@ use reth_trie::{
     MultiProofTargets, StorageMultiProof, StorageProof, TrieInput,
 };
 use std::{
-    sync::atomic::{AtomicU64, Ordering},
+    sync::{
+        atomic::{AtomicU64, AtomicUsize, Ordering},
+        Arc,
+    },
     time::Duration,
 };
 
@@ -33,11 +36,6 @@ pub(crate) struct AtomicDuration {
 }
 
 impl AtomicDuration {
-    /// Returns a zero duration.
-    pub(crate) const fn zero() -> Self {
-        Self { nanos: AtomicU64::new(0) }
-    }
-
     /// Returns the duration as a [`Duration`]
     pub(crate) fn duration(&self) -> Duration {
         let nanos = self.nanos.load(Ordering::Relaxed);
@@ -63,18 +61,10 @@ impl AtomicDuration {
 pub struct InstrumentedStateProvider<S> {
     /// The state provider
     state_provider: S,
-
-    /// Metrics for the instrumented state provider
+    /// Prometheus metrics for the instrumented state provider
     metrics: StateProviderMetrics,
-
-    /// The total time we spend fetching storage over the lifetime of this state provider
-    total_storage_fetch_latency: AtomicDuration,
-
-    /// The total time we spend fetching code over the lifetime of this state provider
-    total_code_fetch_latency: AtomicDuration,
-
-    /// The total time we spend fetching accounts over the lifetime of this state provider
-    total_account_fetch_latency: AtomicDuration,
+    /// Shared fetch statistics, readable after the provider is consumed.
+    stats: Arc<StateProviderStats>,
 }
 
 impl<S> InstrumentedStateProvider<S>
@@ -87,58 +77,33 @@ where
         Self {
             state_provider,
             metrics: StateProviderMetrics::new_with_labels(&[("source", source)]),
-            total_storage_fetch_latency: AtomicDuration::zero(),
-            total_code_fetch_latency: AtomicDuration::zero(),
-            total_account_fetch_latency: AtomicDuration::zero(),
+            stats: Arc::new(StateProviderStats::default()),
         }
     }
-}
 
-impl<S> InstrumentedStateProvider<S> {
-    /// Records the latency for a storage fetch, and increments the duration counter for the storage
-    /// fetch.
-    fn record_storage_fetch(&self, latency: Duration) {
-        self.metrics.storage_fetch_latency.record(latency);
-        self.total_storage_fetch_latency.add_duration(latency);
-    }
-
-    /// Records the latency for a code fetch, and increments the duration counter for the code
-    /// fetch.
-    fn record_code_fetch(&self, latency: Duration) {
-        self.metrics.code_fetch_latency.record(latency);
-        self.total_code_fetch_latency.add_duration(latency);
-    }
-
-    /// Records the latency for an account fetch, and increments the duration counter for the
-    /// account fetch.
-    fn record_account_fetch(&self, latency: Duration) {
-        self.metrics.account_fetch_latency.record(latency);
-        self.total_account_fetch_latency.add_duration(latency);
-    }
-
-    /// Records the total latencies into their respective gauges and histograms.
-    pub(crate) fn record_total_latency(&self) {
-        let total_storage_fetch_latency = self.total_storage_fetch_latency.duration();
-        self.metrics.total_storage_fetch_latency.record(total_storage_fetch_latency);
-        self.metrics
-            .total_storage_fetch_latency_gauge
-            .set(total_storage_fetch_latency.as_secs_f64());
-
-        let total_code_fetch_latency = self.total_code_fetch_latency.duration();
-        self.metrics.total_code_fetch_latency.record(total_code_fetch_latency);
-        self.metrics.total_code_fetch_latency_gauge.set(total_code_fetch_latency.as_secs_f64());
-
-        let total_account_fetch_latency = self.total_account_fetch_latency.duration();
-        self.metrics.total_account_fetch_latency.record(total_account_fetch_latency);
-        self.metrics
-            .total_account_fetch_latency_gauge
-            .set(total_account_fetch_latency.as_secs_f64());
+    /// Returns a shared reference to the accumulated fetch statistics.
+    pub fn stats(&self) -> Arc<StateProviderStats> {
+        Arc::clone(&self.stats)
     }
 }
 
 impl<S> Drop for InstrumentedStateProvider<S> {
     fn drop(&mut self) {
-        self.record_total_latency();
+        let total_storage_fetch_latency = self.stats.total_storage_fetch_latency.duration();
+        self.metrics.total_storage_fetch_latency.record(total_storage_fetch_latency);
+        self.metrics
+            .total_storage_fetch_latency_gauge
+            .set(total_storage_fetch_latency.as_secs_f64());
+
+        let total_code_fetch_latency = self.stats.total_code_fetch_latency.duration();
+        self.metrics.total_code_fetch_latency.record(total_code_fetch_latency);
+        self.metrics.total_code_fetch_latency_gauge.set(total_code_fetch_latency.as_secs_f64());
+
+        let total_account_fetch_latency = self.stats.total_account_fetch_latency.duration();
+        self.metrics.total_account_fetch_latency.record(total_account_fetch_latency);
+        self.metrics
+            .total_account_fetch_latency_gauge
+            .set(total_account_fetch_latency.as_secs_f64());
     }
 }
 
@@ -183,7 +148,10 @@ impl<S: AccountReader> AccountReader for InstrumentedStateProvider<S> {
     fn basic_account(&self, address: &Address) -> ProviderResult<Option<Account>> {
         let start = Instant::now();
         let res = self.state_provider.basic_account(address);
-        self.record_account_fetch(start.elapsed());
+        let elapsed = start.elapsed();
+        self.metrics.account_fetch_latency.record(elapsed);
+        self.stats.total_account_fetches.fetch_add(1, Ordering::Relaxed);
+        self.stats.total_account_fetch_latency.add_duration(elapsed);
         res
     }
 }
@@ -196,7 +164,10 @@ impl<S: StateProvider> StateProvider for InstrumentedStateProvider<S> {
     ) -> ProviderResult<Option<StorageValue>> {
         let start = Instant::now();
         let res = self.state_provider.storage(account, storage_key);
-        self.record_storage_fetch(start.elapsed());
+        let elapsed = start.elapsed();
+        self.metrics.storage_fetch_latency.record(elapsed);
+        self.stats.total_storage_fetches.fetch_add(1, Ordering::Relaxed);
+        self.stats.total_storage_fetch_latency.add_duration(elapsed);
         res
     }
 }
@@ -205,7 +176,17 @@ impl<S: BytecodeReader> BytecodeReader for InstrumentedStateProvider<S> {
     fn bytecode_by_hash(&self, code_hash: &B256) -> ProviderResult<Option<Bytecode>> {
         let start = Instant::now();
         let res = self.state_provider.bytecode_by_hash(code_hash);
-        self.record_code_fetch(start.elapsed());
+        let elapsed = start.elapsed();
+        self.metrics.code_fetch_latency.record(elapsed);
+        self.stats.total_code_fetches.fetch_add(1, Ordering::Relaxed);
+        self.stats.total_code_fetch_latency.add_duration(elapsed);
+        self.stats.total_code_fetched_bytes.fetch_add(
+            res.as_ref()
+                .ok()
+                .and_then(|code| code.as_ref().map(|code| code.len()))
+                .unwrap_or_default(),
+            Ordering::Relaxed,
+        );
         res
     }
 }
@@ -308,3 +289,56 @@ impl<S: HashedPostStateProvider> HashedPostStateProvider for InstrumentedStatePr
         self.state_provider.hashed_post_state(bundle_state)
     }
 }
+
+/// Accumulated fetch statistics from an [`InstrumentedStateProvider`].
+///
+/// Shared via `Arc` so statistics can be read after the provider is consumed.
+#[derive(Debug, Default)]
+pub struct StateProviderStats {
+    total_storage_fetches: AtomicUsize,
+    total_storage_fetch_latency: AtomicDuration,
+
+    total_code_fetches: AtomicUsize,
+    total_code_fetch_latency: AtomicDuration,
+    total_code_fetched_bytes: AtomicUsize,
+
+    total_account_fetches: AtomicUsize,
+    total_account_fetch_latency: AtomicDuration,
+}
+
+impl StateProviderStats {
+    /// Returns total number of storage fetches.
+    pub fn total_storage_fetches(&self) -> usize {
+        self.total_storage_fetches.load(Ordering::Relaxed)
+    }
+
+    /// Returns total time spent on storage fetches.
+    pub fn total_storage_fetch_latency(&self) -> Duration {
+        self.total_storage_fetch_latency.duration()
+    }
+
+    /// Returns total number of code fetches.
+    pub fn total_code_fetches(&self) -> usize {
+        self.total_code_fetches.load(Ordering::Relaxed)
+    }
+
+    /// Returns total time spent on code fetches.
+    pub fn total_code_fetch_latency(&self) -> Duration {
+        self.total_code_fetch_latency.duration()
+    }
+
+    /// Returns total amount of code fetched, in bytes.
+    pub fn total_code_fetched_bytes(&self) -> usize {
+        self.total_code_fetched_bytes.load(Ordering::Relaxed)
+    }
+
+    /// Returns total number of account fetches.
+    pub fn total_account_fetches(&self) -> usize {
+        self.total_account_fetches.load(Ordering::Relaxed)
+    }
+
+    /// Returns total time spent on account fetches.
+    pub fn total_account_fetch_latency(&self) -> Duration {
+        self.total_account_fetch_latency.duration()
+    }
+}

crates/engine/tree/src/tree/mod.rs

@@ -13,13 +13,13 @@ use alloy_rpc_types_engine::{
 };
 use error::{InsertBlockError, InsertBlockFatalError};
 use reth_chain_state::{
-    CanonicalInMemoryState, ComputedTrieData, ExecutedBlock, MemoryOverlayStateProvider,
-    NewCanonicalChain,
+    CanonicalInMemoryState, ComputedTrieData, ExecutedBlock, ExecutionTimingStats,
+    MemoryOverlayStateProvider, NewCanonicalChain,
 };
 use reth_consensus::{Consensus, FullConsensus};
 use reth_engine_primitives::{
     BeaconEngineMessage, BeaconOnNewPayloadError, ConsensusEngineEvent, ExecutionPayload,
-    ForkchoiceStateTracker, NewPayloadTimings, OnForkChoiceUpdated,
+    ForkchoiceStateTracker, NewPayloadTimings, OnForkChoiceUpdated, SlowBlockInfo,
 };
 use reth_errors::{ConsensusError, ProviderResult};
 use reth_evm::ConfigureEvm;
@@ -42,7 +42,7 @@ use reth_tasks::{spawn_os_thread, utils::increase_thread_priority};
 use reth_trie_db::ChangesetCache;
 use revm::interpreter::debug_unreachable;
 use state::TreeState;
-use std::{fmt::Debug, ops, sync::Arc, time::Duration};
+use std::{collections::HashMap, fmt::Debug, ops, sync::Arc, time::Duration};
 
 use crossbeam_channel::{Receiver, Sender};
 use tokio::sync::{
@@ -65,7 +65,7 @@ pub mod precompile_cache;
 mod tests;
 mod trie_updates;
 
-use crate::tree::error::AdvancePersistenceError;
+use crate::{persistence::PersistenceResult, tree::error::AdvancePersistenceError};
 pub use block_buffer::BlockBuffer;
 pub use cached_state::{CachedStateMetrics, CachedStateProvider, ExecutionCache, SavedCache};
 pub use invalid_headers::InvalidHeaderCache;
@@ -273,9 +273,15 @@ where
     evm_config: C,
     /// Changeset cache for in-memory trie changesets
     changeset_cache: ChangesetCache,
+    /// Timing statistics for executed blocks, keyed by block hash.
+    /// Stored here (not in `ExecutedBlock`) to avoid leaking observability concerns into the block
+    /// type. Entries are removed when blocks are persisted or invalidated.
+    execution_timing_stats: HashMap<B256, Box<ExecutionTimingStats>>,
     /// Whether the node uses hashed state as canonical storage (v2 mode).
     /// Cached at construction to avoid threading `StorageSettingsCache` bounds everywhere.
     use_hashed_state: bool,
+    /// Task runtime for spawning blocking work on named, reusable threads.
+    runtime: reth_tasks::Runtime,
 }
 
 impl<N, P: Debug, T: PayloadTypes + Debug, V: Debug, C> std::fmt::Debug
@@ -301,7 +307,9 @@ where
             .field("engine_kind", &self.engine_kind)
             .field("evm_config", &self.evm_config)
             .field("changeset_cache", &self.changeset_cache)
+            .field("execution_timing_stats", &self.execution_timing_stats.len())
             .field("use_hashed_state", &self.use_hashed_state)
+            .field("runtime", &self.runtime)
             .finish()
     }
 }
@@ -342,6 +350,7 @@ where
         evm_config: C,
         changeset_cache: ChangesetCache,
         use_hashed_state: bool,
+        runtime: reth_tasks::Runtime,
     ) -> Self {
         let (incoming_tx, incoming) = crossbeam_channel::unbounded();
 
@@ -363,7 +372,9 @@ where
             engine_kind,
             evm_config,
             changeset_cache,
+            execution_timing_stats: HashMap::new(),
             use_hashed_state,
+            runtime,
         }
     }
 
@@ -385,6 +396,7 @@ where
         evm_config: C,
         changeset_cache: ChangesetCache,
         use_hashed_state: bool,
+        runtime: reth_tasks::Runtime,
     ) -> (Sender<FromEngine<EngineApiRequest<T, N>, N::Block>>, UnboundedReceiver<EngineApiEvent<N>>)
     {
         let best_block_number = provider.best_block_number().unwrap_or(0);
@@ -418,6 +430,7 @@ where
             evm_config,
             changeset_cache,
             use_hashed_state,
+            runtime,
         );
         let incoming = task.incoming_tx.clone();
         spawn_os_thread("engine", || {
@@ -427,6 +440,14 @@ where
         (incoming, outgoing)
     }
 
+    /// Returns a [`TreeOutcome`] indicating the forkchoice head is valid and canonical.
+    fn valid_outcome(state: ForkchoiceState) -> TreeOutcome<OnForkChoiceUpdated> {
+        TreeOutcome::new(OnForkChoiceUpdated::valid(PayloadStatus::new(
+            PayloadStatusEnum::Valid,
+            Some(state.head_block_hash),
+        )))
+    }
+
     /// Returns a new [`Sender`] to send messages to this type.
     pub fn sender(&self) -> Sender<FromEngine<EngineApiRequest<T, N>, N::Block>> {
         self.incoming_tx.clone()
@@ -488,8 +509,8 @@ where
                 recv(persistence_rx) -> result => {
                     // Don't put it back - consumed (oneshot-like behavior)
                     match result {
-                        Ok(value) => LoopEvent::PersistenceComplete {
-                            result: value,
+                        Ok(result) => LoopEvent::PersistenceComplete {
+                            result,
                             start_time,
                         },
                         Err(_) => LoopEvent::Disconnected,
@@ -1118,11 +1139,7 @@ where
         }
 
         // The head block is already canonical
-        let outcome = TreeOutcome::new(OnForkChoiceUpdated::valid(PayloadStatus::new(
-            PayloadStatusEnum::Valid,
-            Some(state.head_block_hash),
-        )));
-        Ok(Some(outcome))
+        Ok(Some(Self::valid_outcome(state)))
     }
 
     /// Applies chain update for the new head block and processes payload attributes.
@@ -1183,12 +1200,7 @@ where
 
             // The head block is already canonical and we're not processing payload attributes,
             // so we're not triggering a payload job and can return right away
-
-            let outcome = TreeOutcome::new(OnForkChoiceUpdated::valid(PayloadStatus::new(
-                PayloadStatusEnum::Valid,
-                Some(state.head_block_hash),
-            )));
-            return Ok(Some(outcome));
+            return Ok(Some(Self::valid_outcome(state)));
         }
 
         // Ensure we can apply a new chain update for the head block
@@ -1208,11 +1220,7 @@ where
                 return Ok(Some(TreeOutcome::new(updated)));
             }
 
-            let outcome = TreeOutcome::new(OnForkChoiceUpdated::valid(PayloadStatus::new(
-                PayloadStatusEnum::Valid,
-                Some(state.head_block_hash),
-            )));
-            return Ok(Some(outcome));
+            return Ok(Some(Self::valid_outcome(state)));
         }
 
         Ok(None)
@@ -1367,15 +1375,16 @@ where
     /// Handles a completed persistence task.
     fn on_persistence_complete(
         &mut self,
-        last_persisted_hash_num: Option<BlockNumHash>,
+        result: PersistenceResult,
         start_time: Instant,
     ) -> Result<(), AdvancePersistenceError> {
         self.metrics.engine.persistence_duration.record(start_time.elapsed());
 
+        let commit_duration = result.commit_duration;
         let Some(BlockNumHash {
             hash: last_persisted_block_hash,
             number: last_persisted_block_number,
-        }) = last_persisted_hash_num
+        }) = result.last_block
         else {
             // if this happened, then we persisted no blocks because we sent an empty vec of blocks
             warn!(target: "engine::tree", "Persistence task completed but did not persist any blocks");
@@ -1416,11 +1425,13 @@ where
         // Spawn a background task to trigger computation so it's ready when the next payload
         // arrives.
         if let Some(overlay) = self.state.tree_state.prepare_canonical_overlay() {
-            tokio::task::spawn_blocking(move || {
+            self.runtime.spawn_blocking_named("prepare-overlay", move || {
                 let _ = overlay.get();
             });
         }
 
+        self.purge_timing_stats(last_persisted_block_number, commit_duration);
+
         Ok(())
     }
 
@@ -1575,7 +1586,7 @@ where
                                 {
                                     let (persistence_tx, persistence_rx) =
                                         std::sync::mpsc::channel();
-                                    tokio::task::spawn_blocking(move || {
+                                    self.runtime.spawn_blocking_named("wait-persist", move || {
                                         let start = Instant::now();
                                         let result =
                                             rx.recv().expect("persistence state channel closed");
@@ -1726,6 +1737,7 @@ where
 
         // remove all buffered blocks below the backfill height
         self.state.buffer.remove_old_blocks(backfill_height);
+        self.purge_timing_stats(backfill_height, None);
         // we remove all entries because now we're synced to the backfill target and consider this
         // the canonical chain
         self.canonical_in_memory_state.clear_state();
@@ -1859,6 +1871,43 @@ where
         Ok(())
     }
 
+    /// Removes timing stats for blocks at or below `below_number`.
+    ///
+    /// No-op when detailed block logging is disabled (no stats are recorded in that case).
+    /// When `commit_duration` is provided and a slow block threshold is configured, checks
+    /// each removed block against the threshold and emits a [`ConsensusEngineEvent::SlowBlock`]
+    /// event for blocks that exceed it.
+    fn purge_timing_stats(&mut self, below_number: u64, commit_duration: Option<Duration>) {
+        let threshold = self.config.slow_block_threshold();
+        let check_slow = commit_duration.is_some() && threshold.is_some();
+
+        // Two-pass: collect keys first because emit_event borrows &mut self.
+        let keys_to_remove: Vec<B256> = self
+            .execution_timing_stats
+            .iter()
+            .filter(|(_, stats)| stats.block_number <= below_number)
+            .map(|(k, _)| *k)
+            .collect();
+
+        for key in keys_to_remove {
+            let stats = self.execution_timing_stats.remove(&key).expect("key just found");
+            if check_slow {
+                let commit_dur = commit_duration.expect("checked above");
+                // state_read_duration is already included in execution_duration
+                let total_duration =
+                    stats.execution_duration + stats.state_hash_duration + commit_dur;
+
+                if total_duration > threshold.expect("checked above") {
+                    self.emit_event(ConsensusEngineEvent::SlowBlock(SlowBlockInfo {
+                        stats,
+                        commit_duration: commit_dur,
+                        total_duration,
+                    }));
+                }
+            }
+        }
+    }
+
     /// Emits an outgoing event to the engine.
     fn emit_event(&mut self, event: impl Into<EngineApiEvent<N>>) {
         let event = event.into();
@@ -2101,16 +2150,16 @@ where
     /// Prepares the invalid payload response for the given hash, checking the
     /// database for the parent hash and populating the payload status with the latest valid hash
     /// according to the engine api spec.
-    fn prepare_invalid_response(&mut self, mut parent_hash: B256) -> ProviderResult<PayloadStatus> {
-        // Edge case: the `latestValid` field is the zero hash if the parent block is the terminal
-        // PoW block, which we need to identify by looking at the parent's block difficulty
-        if let Some(parent) = self.sealed_header_by_hash(parent_hash)? &&
-            !parent.difficulty().is_zero()
-        {
-            parent_hash = B256::ZERO;
-        }
+    fn prepare_invalid_response(&mut self, parent_hash: B256) -> ProviderResult<PayloadStatus> {
+        let valid_parent_hash = match self.sealed_header_by_hash(parent_hash)? {
+            // Edge case: the `latestValid` field is the zero hash if the parent block is the
+            // terminal PoW block, which we need to identify by looking at the parent's block
+            // difficulty
+            Some(parent) if !parent.difficulty().is_zero() => Some(B256::ZERO),
+            Some(_) => Some(parent_hash),
+            None => self.latest_valid_hash_for_invalid_payload(parent_hash)?,
+        };
 
-        let valid_parent_hash = self.latest_valid_hash_for_invalid_payload(parent_hash)?;
         Ok(PayloadStatus::from_status(PayloadStatusEnum::Invalid {
             validation_error: PayloadValidationError::LinksToRejectedPayload.to_string(),
         })
@@ -2171,18 +2220,26 @@ where
 
     /// Finds any invalid ancestor for the given payload.
     ///
-    /// This function walks up the chain of buffered ancestors from the payload's block
-    /// hash and checks if any ancestor is marked as invalid in the tree state.
+    /// This function first checks if the block itself is in the invalid headers cache (to
+    /// avoid re-executing a known-invalid block). Then it walks up the chain of buffered
+    /// ancestors and checks if any ancestor is marked as invalid.
     ///
     /// The check works by:
-    /// 1. Finding the lowest buffered ancestor for the given block hash
-    /// 2. If the ancestor is the same as the block hash itself, using the parent hash instead
-    /// 3. Checking if this ancestor is in the `invalid_headers` map
+    /// 1. Checking if the block hash itself is in the `invalid_headers` map
+    /// 2. Finding the lowest buffered ancestor for the given block hash
+    /// 3. If the ancestor is the same as the block hash itself, using the parent hash instead
+    /// 4. Checking if this ancestor is in the `invalid_headers` map
     ///
     /// Returns the invalid ancestor block info if found, or None if no invalid ancestor exists.
     fn find_invalid_ancestor(&mut self, payload: &T::ExecutionData) -> Option<BlockWithParent> {
         let parent_hash = payload.parent_hash();
         let block_hash = payload.block_hash();
+
+        // Check if the block itself is already known to be invalid, avoiding re-execution
+        if let Some(entry) = self.state.invalid_headers.get(&block_hash) {
+            return Some(entry);
+        }
+
         let mut lowest_buffered_ancestor = self.lowest_buffered_ancestor_or(block_hash);
         if lowest_buffered_ancestor == block_hash {
             lowest_buffered_ancestor = parent_hash;
@@ -2583,6 +2640,51 @@ where
         Some(TreeEvent::Download(request))
     }
 
+    /// Handles a downloaded block that was successfully inserted as valid.
+    ///
+    /// If the block matches the sync target head, returns [`TreeAction::MakeCanonical`].
+    /// If it matches a non-head sync target (safe or finalized), makes it canonical inline
+    /// and triggers a download for the remaining blocks towards the actual head.
+    /// Otherwise, tries to connect buffered blocks.
+    fn on_valid_downloaded_block(
+        &mut self,
+        block_num_hash: BlockNumHash,
+    ) -> Result<Option<TreeEvent>, InsertBlockFatalError> {
+        // check if we just inserted a block that's part of sync targets,
+        // i.e. head, safe, or finalized
+        if let Some(sync_target) = self.state.forkchoice_state_tracker.sync_target_state() &&
+            sync_target.contains(block_num_hash.hash)
+        {
+            debug!(target: "engine::tree", ?sync_target, "appended downloaded sync target block");
+
+            if sync_target.head_block_hash == block_num_hash.hash {
+                // we just inserted the sync target head block, make it canonical
+                return Ok(Some(TreeEvent::TreeAction(TreeAction::MakeCanonical {
+                    sync_target_head: block_num_hash.hash,
+                })))
+            }
+
+            // This block is part of the sync target (safe or finalized) but not the
+            // head. Make it canonical and try to connect any buffered children, then
+            // continue downloading towards the actual head if needed.
+            self.make_canonical(block_num_hash.hash)?;
+            self.try_connect_buffered_blocks(block_num_hash)?;
+
+            // Check if we've reached the sync target head after connecting buffered
+            // blocks (e.g. the head block may have already been buffered).
+            if self.state.tree_state.canonical_block_hash() != sync_target.head_block_hash {
+                let target = self.lowest_buffered_ancestor_or(sync_target.head_block_hash);
+                trace!(target: "engine::tree", %target, "sync target head not yet reached, downloading head block");
+                return Ok(Some(TreeEvent::Download(DownloadRequest::single_block(target))))
+            }
+
+            return Ok(None)
+        }
+        trace!(target: "engine::tree", "appended downloaded block");
+        self.try_connect_buffered_blocks(block_num_hash)?;
+        Ok(None)
+    }
+
     /// Invoked with a block downloaded from the network
     ///
     /// Returns an event with the appropriate action to take, such as:
@@ -2605,22 +2707,11 @@ where
 
         // try to append the block
         match self.insert_block(block) {
-            Ok(InsertPayloadOk::Inserted(BlockStatus::Valid)) => {
-                // check if we just inserted a block that's part of sync targets,
-                // i.e. head, safe, or finalized
-                if let Some(sync_target) = self.state.forkchoice_state_tracker.sync_target_state() &&
-                    sync_target.contains(block_num_hash.hash)
-                {
-                    debug!(target: "engine::tree", ?sync_target, "appended downloaded sync target block");
-
-                    // we just inserted a block that we know is part of the canonical chain, so we
-                    // can make it canonical
-                    return Ok(Some(TreeEvent::TreeAction(TreeAction::MakeCanonical {
-                        sync_target_head: block_num_hash.hash,
-                    })))
-                }
-                trace!(target: "engine::tree", "appended downloaded block");
-                self.try_connect_buffered_blocks(block_num_hash)?;
+            Ok(
+                InsertPayloadOk::Inserted(BlockStatus::Valid) |
+                InsertPayloadOk::AlreadySeen(BlockStatus::Valid),
+            ) => {
+                return self.on_valid_downloaded_block(block_num_hash);
             }
             Ok(InsertPayloadOk::Inserted(BlockStatus::Disconnected { head, missing_ancestor })) => {
                 // block is not connected to the canonical head, we need to download
@@ -2700,7 +2791,12 @@ where
         &mut self,
         block_id: BlockWithParent,
         input: Input,
-        execute: impl FnOnce(&mut V, Input, TreeCtx<'_, N>) -> Result<ExecutedBlock<N>, Err>,
+        execute: impl FnOnce(
+            &mut V,
+            Input,
+            TreeCtx<'_, N>,
+        )
+            -> Result<(ExecutedBlock<N>, Option<Box<ExecutionTimingStats>>), Err>,
         convert_to_block: impl FnOnce(&mut Self, Input) -> Result<SealedBlock<N::Block>, Err>,
     ) -> Result<InsertPayloadOk, Err>
     where
@@ -2770,7 +2866,12 @@ where
 
         let start = Instant::now();
 
-        let executed = execute(&mut self.payload_validator, input, ctx)?;
+        let (executed, timing_stats) = execute(&mut self.payload_validator, input, ctx)?;
+
+        // Store timing stats for detailed block logging after persistence
+        if let Some(stats) = timing_stats {
+            self.execution_timing_stats.insert(executed.recovered_block().hash(), stats);
+        }
 
         // if the parent is the canonical head, we can insert the block as the pending block
         if self.state.tree_state.canonical_block_hash() == executed.recovered_block().parent_hash()
@@ -3092,8 +3193,8 @@ where
     EngineMessage(FromEngine<EngineApiRequest<T, N>, N::Block>),
     /// A persistence task completed.
     PersistenceComplete {
-        /// The result of the persistence operation.
-        result: Option<BlockNumHash>,
+        /// The unified result of the persistence operation.
+        result: PersistenceResult,
         /// When the persistence operation started.
         start_time: Instant,
     },

crates/engine/tree/src/tree/payload_processor/mod.rs

@@ -39,12 +39,13 @@ use reth_trie_parallel::{
     root::ParallelStateRootError,
 };
 use reth_trie_sparse::{
-    ParallelSparseTrie, ParallelismThresholds, RevealableSparseTrie, SparseStateTrie,
+    ArenaParallelSparseTrie, ConfigurableSparseTrie, ParallelSparseTrie, ParallelismThresholds,
+    RevealableSparseTrie, SparseStateTrie,
 };
 use std::{
     ops::Not,
     sync::{
-        atomic::AtomicBool,
+        atomic::{AtomicBool, AtomicUsize},
         mpsc::{self, channel},
         Arc,
     },
@@ -64,9 +65,9 @@ use preserved_sparse_trie::{PreservedSparseTrie, SharedPreservedSparseTrie};
 /// Default parallelism thresholds to use with the [`ParallelSparseTrie`].
 ///
 /// These values were determined by performing benchmarks using gradually increasing values to judge
-/// the affects. Below 100 throughput would generally be equal or slightly less, while above 150 it
+/// the effects. Below 100 throughput would generally be equal or slightly less, while above 150 it
 /// would deteriorate to the point where PST might as well not be used.
-pub const PARALLEL_SPARSE_TRIE_PARALLELISM_THRESHOLDS: ParallelismThresholds =
+const PARALLEL_SPARSE_TRIE_PARALLELISM_THRESHOLDS: ParallelismThresholds =
     ParallelismThresholds { min_revealed_nodes: 100, min_updated_nodes: 100 };
 
 /// Default node capacity for shrinking the sparse trie. This is used to limit the number of trie
@@ -131,12 +132,14 @@ where
     /// re-use allocated memory. Stored with the block hash it was computed for to enable trie
     /// preservation across sequential payload validations.
     sparse_state_trie: SharedPreservedSparseTrie,
-    /// Sparse trie prune depth.
-    sparse_trie_prune_depth: usize,
-    /// Maximum storage tries to retain after pruning.
-    sparse_trie_max_storage_tries: usize,
+    /// LFU hot-slot capacity: max storage slots retained across prune cycles.
+    sparse_trie_max_hot_slots: usize,
+    /// LFU hot-account capacity: max account addresses retained across prune cycles.
+    sparse_trie_max_hot_accounts: usize,
     /// Whether sparse trie cache pruning is fully disabled.
     disable_sparse_trie_cache_pruning: bool,
+    /// Whether to use the arena-based sparse trie implementation.
+    enable_arena_sparse_trie: bool,
     /// Whether to disable cache metrics recording.
     disable_cache_metrics: bool,
 }
@@ -169,9 +172,10 @@ where
             precompile_cache_disabled: config.precompile_cache_disabled(),
             precompile_cache_map,
             sparse_state_trie: SharedPreservedSparseTrie::default(),
-            sparse_trie_prune_depth: config.sparse_trie_prune_depth(),
-            sparse_trie_max_storage_tries: config.sparse_trie_max_storage_tries(),
+            sparse_trie_max_hot_slots: config.sparse_trie_max_hot_slots(),
+            sparse_trie_max_hot_accounts: config.sparse_trie_max_hot_accounts(),
             disable_sparse_trie_cache_pruning: config.disable_sparse_trie_cache_pruning(),
+            enable_arena_sparse_trie: config.enable_arena_sparse_trie(),
             disable_cache_metrics: config.disable_cache_metrics(),
         }
     }
@@ -192,10 +196,10 @@ where
         let (execution_tx, execution_rx) = std::sync::mpsc::channel();
         let (sparse_trie_tx, sparse_trie_rx) = std::sync::mpsc::channel();
 
-        self.executor.spawn_blocking(move || {
+        self.executor.spawn_blocking_named("wait-exec-cache", move || {
             let _ = execution_tx.send(execution_cache.wait_for_availability());
         });
-        self.executor.spawn_blocking(move || {
+        self.executor.spawn_blocking_named("wait-sparse-tri", move || {
             let _ = sparse_trie_tx.send(sparse_trie.wait_for_availability());
         });
 
@@ -282,40 +286,19 @@ where
             self.spawn_tx_iterator(transactions, env.transaction_count);
 
         let span = Span::current();
-        let (to_multi_proof, from_multi_proof) = crossbeam_channel::unbounded();
 
-        let parent_state_root = env.parent_state_root;
-        let transaction_count = env.transaction_count;
-        let chunk_size = config.multiproof_chunk_size();
+        let state_root_handle = self.spawn_state_root(multiproof_provider_factory, &env, config);
         let prewarm_handle = self.spawn_caching_with(
             env,
             prewarm_rx,
             provider_builder,
-            Some(to_multi_proof.clone()),
+            Some(state_root_handle.to_multi_proof.clone()),
             bal,
         );
 
-        // Create and spawn the storage proof task.
-        let task_ctx = ProofTaskCtx::new(multiproof_provider_factory);
-        let halve_workers = transaction_count <= Self::SMALL_BLOCK_PROOF_WORKER_TX_THRESHOLD;
-        let proof_handle = ProofWorkerHandle::new(&self.executor, task_ctx, halve_workers);
-
-        // wire the sparse trie to the state root response receiver
-        let (state_root_tx, state_root_rx) = channel();
-
-        // Spawn the sparse trie task using any stored trie and parallel trie configuration.
-        self.spawn_sparse_trie_task(
-            proof_handle,
-            state_root_tx,
-            from_multi_proof,
-            parent_state_root,
-            chunk_size,
-        );
-
         PayloadHandle {
-            to_multi_proof: Some(to_multi_proof),
+            state_root_handle: Some(state_root_handle),
             prewarm_handle,
-            state_root: Some(state_root_rx),
             transactions: execution_rx,
             _span: span,
         }
@@ -339,14 +322,57 @@ where
             self.spawn_tx_iterator(transactions, env.transaction_count);
         let prewarm_handle = self.spawn_caching_with(env, prewarm_rx, provider_builder, None, bal);
         PayloadHandle {
-            to_multi_proof: None,
+            state_root_handle: None,
             prewarm_handle,
-            state_root: None,
             transactions: execution_rx,
             _span: Span::current(),
         }
     }
 
+    /// Spawns state root computation pipeline (multiproof + sparse trie tasks).
+    ///
+    /// The returned [`StateRootHandle`] provides:
+    /// - [`StateRootHandle::state_hook`] — an [`OnStateHook`] to stream state updates during
+    ///   execution.
+    /// - [`StateRootHandle::state_root`] — blocks until the state root is computed and returns the
+    ///   state root.
+    ///
+    /// The state hook **must** be dropped after execution to signal the end of state updates.
+    #[instrument(level = "debug", target = "engine::tree::payload_processor", skip_all)]
+    pub fn spawn_state_root<F>(
+        &mut self,
+        multiproof_provider_factory: F,
+        env: &ExecutionEnv<Evm>,
+        config: &TreeConfig,
+    ) -> StateRootHandle
+    where
+        F: DatabaseProviderROFactory<Provider: TrieCursorFactory + HashedCursorFactory>
+            + Clone
+            + Send
+            + Sync
+            + 'static,
+    {
+        let (to_multi_proof, from_multi_proof) = crossbeam_channel::unbounded();
+
+        let task_ctx = ProofTaskCtx::new(multiproof_provider_factory);
+        #[cfg(feature = "trie-debug")]
+        let task_ctx = task_ctx.with_proof_jitter(config.proof_jitter());
+        let halve_workers = env.transaction_count <= Self::SMALL_BLOCK_PROOF_WORKER_TX_THRESHOLD;
+        let proof_handle = ProofWorkerHandle::new(&self.executor, task_ctx, halve_workers);
+
+        let (state_root_tx, state_root_rx) = channel();
+
+        self.spawn_sparse_trie_task(
+            proof_handle,
+            state_root_tx,
+            from_multi_proof,
+            env.parent_state_root,
+            config.multiproof_chunk_size(),
+        );
+
+        StateRootHandle::new(to_multi_proof, state_root_rx)
+    }
+
     /// Transaction count threshold below which proof workers are halved, since fewer transactions
     /// produce fewer state changes and most workers would be idle overhead.
     const SMALL_BLOCK_PROOF_WORKER_TX_THRESHOLD: usize = 30;
@@ -409,6 +435,7 @@ where
             // few transactions are recovered sequentially and sent immediately before
             // entering the parallel iterator for the remainder.
             let prefetch = Self::PARALLEL_PREFETCH_COUNT.min(transaction_count);
+            let executor = self.executor.clone();
             self.executor.spawn_blocking_named("tx-iterator", move || {
                 let (transactions, convert) = transactions.into_parts();
                 let mut all: Vec<_> = transactions.into_iter().collect();
@@ -424,15 +451,15 @@ where
                     .map(|(i, tx)| {
                         let idx = i + prefetch;
                         let tx = convert.convert(tx);
+                        (idx, tx)
+                    })
+                    .for_each_ordered_in(executor.cpu_pool(), |(idx, tx)| {
                         let tx = tx.map(|tx| {
                             let (tx_env, tx) = tx.into_parts();
                             let tx = WithTxEnv { tx_env, tx: Arc::new(tx) };
                             let _ = prewarm_tx.send((idx, tx.clone()));
                             tx
                         });
-                        (idx, tx)
-                    })
-                    .for_each_ordered(|(idx, tx)| {
                         let _ = execute_tx.send(tx);
                         debug!(target: "engine::tree::payload_processor", idx, "yielded transaction");
                     });
@@ -465,6 +492,8 @@ where
 
         let saved_cache = self.disable_state_cache.not().then(|| self.cache_for(env.parent_hash));
 
+        let executed_tx_index = Arc::new(AtomicUsize::new(0));
+
         // configure prewarming
         let prewarm_ctx = PrewarmContext {
             env,
@@ -473,6 +502,7 @@ where
             provider: provider_builder,
             metrics: PrewarmMetrics::default(),
             terminate_execution: Arc::new(AtomicBool::new(false)),
+            executed_tx_index: Arc::clone(&executed_tx_index),
             precompile_cache_disabled: self.precompile_cache_disabled,
             precompile_cache_map: self.precompile_cache_map.clone(),
         };
@@ -498,7 +528,7 @@ where
             });
         }
 
-        CacheTaskHandle { saved_cache, to_prewarm_task: Some(to_prewarm_task) }
+        CacheTaskHandle { saved_cache, to_prewarm_task: Some(to_prewarm_task), executed_tx_index }
     }
 
     /// Returns the cache for the given parent hash.
@@ -534,14 +564,15 @@ where
     ) {
         let preserved_sparse_trie = self.sparse_state_trie.clone();
         let trie_metrics = self.trie_metrics.clone();
-        let prune_depth = self.sparse_trie_prune_depth;
-        let max_storage_tries = self.sparse_trie_max_storage_tries;
+        let max_hot_slots = self.sparse_trie_max_hot_slots;
+        let max_hot_accounts = self.sparse_trie_max_hot_accounts;
         let disable_cache_pruning = self.disable_sparse_trie_cache_pruning;
+        let enable_arena_sparse_trie = self.enable_arena_sparse_trie;
         let executor = self.executor.clone();
 
         let parent_span = Span::current();
         self.executor.spawn_blocking_named("sparse-trie", move || {
-            increase_thread_priority();
+            reth_tasks::once!(increase_thread_priority);
 
             let _enter = debug_span!(target: "engine::tree::payload_processor", parent: parent_span, "sparse_trie_task")
                 .entered();
@@ -556,30 +587,39 @@ where
                 .sparse_trie_cache_wait_duration_histogram
                 .record(start.elapsed().as_secs_f64());
 
-            let sparse_state_trie = preserved
+            let mut sparse_state_trie = preserved
                 .map(|preserved| preserved.into_trie_for(parent_state_root))
                 .unwrap_or_else(|| {
                     debug!(
                         target: "engine::tree::payload_processor",
                         "Creating new sparse trie - no preserved trie available"
                     );
-                    let default_trie = RevealableSparseTrie::blind_from(
-                        ParallelSparseTrie::default().with_parallelism_thresholds(
-                            PARALLEL_SPARSE_TRIE_PARALLELISM_THRESHOLDS,
-                        ),
-                    );
-                    SparseStateTrie::new()
+                    let default_trie = if enable_arena_sparse_trie {
+                        RevealableSparseTrie::blind_from(
+                            ConfigurableSparseTrie::Arena(ArenaParallelSparseTrie::default()),
+                        )
+                    } else {
+                        RevealableSparseTrie::blind_from(
+                            ConfigurableSparseTrie::HashMap(
+                                ParallelSparseTrie::default().with_parallelism_thresholds(
+                                    PARALLEL_SPARSE_TRIE_PARALLELISM_THRESHOLDS,
+                                ),
+                            ),
+                        )
+                    };
+                    SparseStateTrie::default()
                         .with_accounts_trie(default_trie.clone())
                         .with_default_storage_trie(default_trie)
                         .with_updates(true)
                 });
+            sparse_state_trie.set_hot_cache_capacities(max_hot_slots, max_hot_accounts);
 
             let mut task = SparseTrieCacheTask::new_with_trie(
                 &executor,
                 from_multi_proof,
                 proof_worker_handle,
                 trie_metrics.clone(),
-                sparse_state_trie.with_skip_proof_node_filtering(true),
+                sparse_state_trie,
                 chunk_size,
             );
 
@@ -606,9 +646,8 @@ where
                     SPARSE_TRIE_MAX_VALUES_SHRINK_CAPACITY,
                 );
                 guard.store(PreservedSparseTrie::cleared(trie));
-                // Drop guard before deferred to release lock before expensive deallocations
                 drop(guard);
-                drop(deferred);
+                executor.spawn_drop(deferred);
                 return;
             }
 
@@ -619,8 +658,8 @@ where
             let deferred = if let Some(result) = task_result {
                 let start = Instant::now();
                 let (trie, deferred) = task.into_trie_for_reuse(
-                    prune_depth,
-                    max_storage_tries,
+                    max_hot_slots,
+                    max_hot_accounts,
                     SPARSE_TRIE_MAX_NODES_SHRINK_CAPACITY,
                     SPARSE_TRIE_MAX_VALUES_SHRINK_CAPACITY,
                     disable_cache_pruning,
@@ -629,6 +668,12 @@ where
                 trie_metrics
                     .into_trie_for_reuse_duration_histogram
                     .record(start.elapsed().as_secs_f64());
+                trie_metrics
+                    .sparse_trie_retained_memory_bytes
+                    .set(trie.memory_size() as f64);
+                trie_metrics
+                    .sparse_trie_retained_storage_tries
+                    .set(trie.retained_storage_tries_count() as f64);
                 guard.store(PreservedSparseTrie::anchored(trie, result.state_root));
                 deferred
             } else {
@@ -643,9 +688,8 @@ where
                 guard.store(PreservedSparseTrie::cleared(trie));
                 deferred
             };
-            // Drop guard before deferred to release lock before expensive deallocations
             drop(guard);
-            drop(deferred);
+            executor.spawn_drop(deferred);
         });
     }
 
@@ -725,20 +769,79 @@ fn convert_serial<RawTx, Tx, TxEnv, InnerTx, Recovered, Err, C>(
     }
 }
 
+/// Handle to a background state root computation task.
+///
+/// Unlike [`PayloadHandle`], this does not include transaction iteration or cache prewarming.
+/// It only provides access to the state root computation via [`Self::state_hook`] and
+/// [`Self::state_root`].
+///
+/// Created by [`PayloadProcessor::spawn_state_root`].
+#[derive(Debug)]
+pub struct StateRootHandle {
+    /// Channel for evm state updates to the multiproof pipeline.
+    to_multi_proof: CrossbeamSender<MultiProofMessage>,
+    /// Receiver for the computed state root.
+    state_root_rx: Option<mpsc::Receiver<Result<StateRootComputeOutcome, ParallelStateRootError>>>,
+}
+
+impl StateRootHandle {
+    /// Creates a new state root handle.
+    pub const fn new(
+        to_multi_proof: CrossbeamSender<MultiProofMessage>,
+        state_root_rx: mpsc::Receiver<Result<StateRootComputeOutcome, ParallelStateRootError>>,
+    ) -> Self {
+        Self { to_multi_proof, state_root_rx: Some(state_root_rx) }
+    }
+
+    /// Returns a state hook that streams state updates to the background state root task.
+    ///
+    /// The hook must be dropped after execution completes to signal the end of state updates.
+    pub fn state_hook(&self) -> impl OnStateHook {
+        let to_multi_proof = StateHookSender::new(self.to_multi_proof.clone());
+
+        move |source: StateChangeSource, state: &EvmState| {
+            let _ =
+                to_multi_proof.send(MultiProofMessage::StateUpdate(source.into(), state.clone()));
+        }
+    }
+
+    /// Awaits the state root computation result.
+    ///
+    /// # Panics
+    ///
+    /// If called more than once.
+    pub fn state_root(&mut self) -> Result<StateRootComputeOutcome, ParallelStateRootError> {
+        self.state_root_rx
+            .take()
+            .expect("state_root already taken")
+            .recv()
+            .map_err(|_| ParallelStateRootError::Other("sparse trie task dropped".to_string()))?
+    }
+
+    /// Takes the state root receiver for use with custom waiting logic (e.g., timeouts).
+    ///
+    /// # Panics
+    ///
+    /// If called more than once.
+    pub const fn take_state_root_rx(
+        &mut self,
+    ) -> mpsc::Receiver<Result<StateRootComputeOutcome, ParallelStateRootError>> {
+        self.state_root_rx.take().expect("state_root already taken")
+    }
+}
+
 /// Handle to all the spawned tasks.
 ///
 /// Generic over `R` (receipt type) to allow sharing `Arc<ExecutionOutcome<R>>` with the
 /// caching task without cloning the expensive `BundleState`.
 #[derive(Debug)]
 pub struct PayloadHandle<Tx, Err, R> {
-    /// Channel for evm state updates
-    to_multi_proof: Option<CrossbeamSender<MultiProofMessage>>,
+    /// Handle to the background state root computation, if spawned.
+    state_root_handle: Option<StateRootHandle>,
     // must include the receiver of the state root wired to the sparse trie
     prewarm_handle: CacheTaskHandle<R>,
     /// Stream of block transactions
     transactions: mpsc::Receiver<Result<Tx, Err>>,
-    /// Receiver for the state root
-    state_root: Option<mpsc::Receiver<Result<StateRootComputeOutcome, ParallelStateRootError>>>,
     /// Span for tracing
     _span: Span,
 }
@@ -756,11 +859,7 @@ impl<Tx, Err, R: Send + Sync + 'static> PayloadHandle<Tx, Err, R> {
         skip_all
     )]
     pub fn state_root(&mut self) -> Result<StateRootComputeOutcome, ParallelStateRootError> {
-        self.state_root
-            .take()
-            .expect("state_root is None")
-            .recv()
-            .map_err(|_| ParallelStateRootError::Other("sparse trie task dropped".to_string()))?
+        self.state_root_handle.as_mut().expect("state_root_handle is None").state_root()
     }
 
     /// Takes the state root receiver out of the handle for use with custom waiting logic
@@ -772,21 +871,14 @@ impl<Tx, Err, R: Send + Sync + 'static> PayloadHandle<Tx, Err, R> {
     pub const fn take_state_root_rx(
         &mut self,
     ) -> mpsc::Receiver<Result<StateRootComputeOutcome, ParallelStateRootError>> {
-        self.state_root.take().expect("state_root is None")
+        self.state_root_handle.as_mut().expect("state_root_handle is None").take_state_root_rx()
     }
 
     /// Returns a state hook to be used to send state updates to this task.
     ///
     /// If a multiproof task is spawned the hook will notify it about new states.
-    pub fn state_hook(&self) -> impl OnStateHook {
-        // convert the channel into a `StateHookSender` that emits an event on drop
-        let to_multi_proof = self.to_multi_proof.clone().map(StateHookSender::new);
-
-        move |source: StateChangeSource, state: &EvmState| {
-            if let Some(sender) = &to_multi_proof {
-                let _ = sender.send(MultiProofMessage::StateUpdate(source.into(), state.clone()));
-            }
-        }
+    pub fn state_hook(&self) -> Option<impl OnStateHook> {
+        self.state_root_handle.as_ref().map(|handle| handle.state_hook())
     }
 
     /// Returns a clone of the caches used by prewarming
@@ -799,6 +891,14 @@ impl<Tx, Err, R: Send + Sync + 'static> PayloadHandle<Tx, Err, R> {
         self.prewarm_handle.saved_cache.as_ref().map(|cache| cache.metrics().clone())
     }
 
+    /// Returns a reference to the shared executed transaction index counter.
+    ///
+    /// The main execution loop should store `index + 1` after executing each transaction so that
+    /// prewarm workers can skip transactions that have already been processed.
+    pub const fn executed_tx_index(&self) -> &Arc<AtomicUsize> {
+        &self.prewarm_handle.executed_tx_index
+    }
+
     /// Terminates the pre-warming transaction processing.
     ///
     /// Note: This does not terminate the task yet.
@@ -822,9 +922,7 @@ impl<Tx, Err, R: Send + Sync + 'static> PayloadHandle<Tx, Err, R> {
 
     /// Returns iterator yielding transactions from the stream.
     pub fn iter_transactions(&mut self) -> impl Iterator<Item = Result<Tx, Err>> + '_ {
-        core::iter::repeat_with(|| self.transactions.recv())
-            .take_while(|res| res.is_ok())
-            .map(|res| res.unwrap())
+        self.transactions.iter()
     }
 }
 
@@ -838,6 +936,9 @@ pub struct CacheTaskHandle<R> {
     saved_cache: Option<SavedCache>,
     /// Channel to the spawned prewarm task if any
     to_prewarm_task: Option<std::sync::mpsc::Sender<PrewarmTaskEvent<R>>>,
+    /// Shared counter tracking the next transaction index to be executed by the main execution
+    /// loop. Prewarm workers skip transactions below this index.
+    executed_tx_index: Arc<AtomicUsize>,
 }
 
 impl<R: Send + Sync + 'static> CacheTaskHandle<R> {
@@ -925,7 +1026,7 @@ impl PayloadExecutionCache {
     #[instrument(level = "debug", target = "engine::tree::payload_processor", skip(self))]
     pub(crate) fn get_cache_for(&self, parent_hash: B256) -> Option<SavedCache> {
         let start = Instant::now();
-        let cache = self.inner.read();
+        let mut cache = self.inner.write();
 
         let elapsed = start.elapsed();
         self.metrics.execution_cache_wait_duration.record(elapsed.as_secs_f64());
@@ -933,7 +1034,7 @@ impl PayloadExecutionCache {
             warn!(blocked_for=?elapsed, "Blocked waiting for execution cache mutex");
         }
 
-        if let Some(c) = cache.as_ref() {
+        if let Some(c) = cache.as_mut() {
             let cached_hash = c.executed_block_hash();
             // Check that the cache hash matches the parent hash of the current block. It won't
             // match in case it's a fork block.
@@ -954,11 +1055,11 @@ impl PayloadExecutionCache {
             );
 
             if available {
-                // If the has is available (no other threads are using it), but has a mismatching
-                // parent hash, we can just clear it and keep using without re-creating from
-                // scratch.
                 if !hash_matches {
-                    c.clear();
+                    // Fork block: clear and update the hash on the ORIGINAL before cloning.
+                    // This prevents the canonical chain from matching on the stale hash
+                    // and picking up polluted data if the fork block fails.
+                    c.clear_with_hash(parent_hash);
                 }
                 return Some(c.clone())
             } else if hash_matches {
@@ -971,12 +1072,6 @@ impl PayloadExecutionCache {
         None
     }
 
-    /// Clears the tracked cache
-    #[expect(unused)]
-    pub(crate) fn clear(&self) {
-        self.inner.write().take();
-    }
-
     /// Waits until the execution cache becomes available for use.
     ///
     /// This acquires a write lock to ensure exclusive access, then immediately releases it.
@@ -1154,10 +1249,18 @@ mod tests {
 
         execution_cache.update_with_guard(|slot| *slot = Some(make_saved_cache(hash)));
 
-        // When the parent hash doesn't match, the cache is cleared and returned for reuse
+        // When the parent hash doesn't match (fork block), the cache is cleared,
+        // hash updated on the original, and clone returned for reuse
         let different_hash = B256::from([4u8; 32]);
         let cache = execution_cache.get_cache_for(different_hash);
-        assert!(cache.is_some(), "cache should be returned for reuse after clearing")
+        assert!(cache.is_some(), "cache should be returned for reuse after clearing");
+
+        drop(cache);
+
+        // The stored cache now has the fork block's parent hash.
+        // Canonical chain looking for original hash sees a mismatch → clears and reuses.
+        let original = execution_cache.get_cache_for(hash);
+        assert!(original.is_some(), "canonical chain gets cache back via mismatch+clear");
     }
 
     #[test]
@@ -1366,7 +1469,7 @@ mod tests {
             None, // No BAL for test
         );
 
-        let mut state_hook = handle.state_hook();
+        let mut state_hook = handle.state_hook().expect("state hook is None");
 
         for (i, update) in state_updates.into_iter().enumerate() {
             state_hook.on_state(StateChangeSource::Transaction(i), &update);
@@ -1381,4 +1484,61 @@ mod tests {
             "State root mismatch: task={root_from_task}, base={root_from_regular}"
         );
     }
+
+    /// Tests the full prewarm lifecycle for a fork block:
+    ///
+    /// 1. Cache is at canonical block 4.
+    /// 2. Fork block (parent = block 2) checks out the cache via `get_cache_for`, simulating what
+    ///    `PrewarmCacheTask` does when it receives a `SavedCache`.
+    /// 3. Prewarm populates the shared cache with fork-specific state.
+    /// 4. While the prewarm clone is alive, the cache is unavailable (`usage_guard` > 1).
+    /// 5. Prewarm drops without calling `save_cache` (fork block was invalid).
+    /// 6. Canonical block 5 (parent = block 4) must get a cache with correct hash and no stale fork
+    ///    data.
+    #[test]
+    fn fork_prewarm_dropped_without_save_does_not_corrupt_cache() {
+        let execution_cache = PayloadExecutionCache::default();
+
+        // Canonical chain at block 4.
+        let block4_hash = B256::from([4u8; 32]);
+        execution_cache.update_with_guard(|slot| *slot = Some(make_saved_cache(block4_hash)));
+
+        // Fork block arrives with parent = block 2. Prewarm task checks out the cache.
+        // This simulates PrewarmCacheTask receiving a SavedCache clone from get_cache_for.
+        let fork_parent = B256::from([2u8; 32]);
+        let prewarm_cache = execution_cache.get_cache_for(fork_parent);
+        assert!(prewarm_cache.is_some(), "prewarm should obtain cache for fork block");
+        let prewarm_cache = prewarm_cache.unwrap();
+        assert_eq!(prewarm_cache.executed_block_hash(), fork_parent);
+
+        // Prewarm populates cache with fork-specific state (ancestor data for block 2).
+        // Since ExecutionCache uses Arc<Inner>, this data is shared with the stored original.
+        let fork_addr = Address::from([0xBB; 20]);
+        let fork_key = B256::from([0xCC; 32]);
+        prewarm_cache.cache().insert_storage(fork_addr, fork_key, Some(U256::from(999)));
+
+        // While prewarm holds the clone, the usage_guard count > 1 → cache is in use.
+        let during_prewarm = execution_cache.get_cache_for(block4_hash);
+        assert!(
+            during_prewarm.is_none(),
+            "cache must be unavailable while prewarm holds a reference"
+        );
+
+        // Fork block fails — prewarm task drops without calling save_cache/update_with_guard.
+        drop(prewarm_cache);
+
+        // Canonical block 5 arrives (parent = block 4).
+        // Stored hash = fork_parent (our fix), so get_cache_for sees a mismatch,
+        // clears the stale fork data, and returns a cache with hash = block4_hash.
+        let block5_cache = execution_cache.get_cache_for(block4_hash);
+        assert!(
+            block5_cache.is_some(),
+            "canonical chain must get cache after fork prewarm is dropped"
+        );
+        assert_eq!(
+            block5_cache.as_ref().unwrap().executed_block_hash(),
+            block4_hash,
+            "cache must carry the canonical parent hash, not the fork parent"
+        );
+    }
 }

crates/engine/tree/src/tree/payload_processor/multiproof.rs

@@ -8,7 +8,7 @@ use metrics::{Gauge, Histogram};
 use reth_metrics::Metrics;
 use reth_revm::state::EvmState;
 use reth_trie::{HashedPostState, HashedStorage};
-use reth_trie_parallel::targets_v2::MultiProofTargetsV2;
+use reth_trie_common::MultiProofTargetsV2;
 use std::sync::Arc;
 use tracing::trace;
 
@@ -47,16 +47,6 @@ pub enum MultiProofMessage {
     PrefetchProofs(MultiProofTargetsV2),
     /// New state update from transaction execution with its source
     StateUpdate(Source, EvmState),
-    /// State update that can be applied to the sparse trie without any new proofs.
-    ///
-    /// It can be the case when all accounts and storage slots from the state update were already
-    /// fetched and revealed.
-    EmptyProof {
-        /// The index of this proof in the sequence of state updates
-        sequence_number: u64,
-        /// The state update that was used to calculate the proof
-        state: HashedPostState,
-    },
     /// Pre-hashed state update from BAL conversion that can be applied directly without proofs.
     HashedStateUpdate(HashedPostState),
     /// Block Access List (EIP-7928; BAL) containing complete state changes for the block.
@@ -77,10 +67,11 @@ pub enum MultiProofMessage {
 /// This should trigger once the block has been executed (after) the last state update has been
 /// sent. This triggers the exit condition of the multi proof task.
 #[derive(Deref, Debug)]
-pub(super) struct StateHookSender(CrossbeamSender<MultiProofMessage>);
+pub struct StateHookSender(CrossbeamSender<MultiProofMessage>);
 
 impl StateHookSender {
-    pub(crate) const fn new(inner: CrossbeamSender<MultiProofMessage>) -> Self {
+    /// Creates a new [`StateHookSender`] wrapping the given channel sender.
+    pub const fn new(inner: CrossbeamSender<MultiProofMessage>) -> Self {
         Self(inner)
     }
 }
@@ -127,41 +118,6 @@ pub(crate) fn evm_state_to_hashed_post_state(update: EvmState) -> HashedPostStat
 #[derive(Metrics, Clone)]
 #[metrics(scope = "tree.root")]
 pub(crate) struct MultiProofTaskMetrics {
-    /// Histogram of active storage workers processing proofs.
-    pub active_storage_workers_histogram: Histogram,
-    /// Histogram of active account workers processing proofs.
-    pub active_account_workers_histogram: Histogram,
-    /// Gauge for the maximum number of storage workers in the pool.
-    pub max_storage_workers: Gauge,
-    /// Gauge for the maximum number of account workers in the pool.
-    pub max_account_workers: Gauge,
-    /// Histogram of pending storage multiproofs in the queue.
-    pub pending_storage_multiproofs_histogram: Histogram,
-    /// Histogram of pending account multiproofs in the queue.
-    pub pending_account_multiproofs_histogram: Histogram,
-
-    /// Histogram of the number of prefetch proof target accounts.
-    pub prefetch_proof_targets_accounts_histogram: Histogram,
-    /// Histogram of the number of prefetch proof target storages.
-    pub prefetch_proof_targets_storages_histogram: Histogram,
-    /// Histogram of the number of prefetch proof target chunks.
-    pub prefetch_proof_chunks_histogram: Histogram,
-
-    /// Histogram of the number of state update proof target accounts.
-    pub state_update_proof_targets_accounts_histogram: Histogram,
-    /// Histogram of the number of state update proof target storages.
-    pub state_update_proof_targets_storages_histogram: Histogram,
-    /// Histogram of the number of state update proof target chunks.
-    pub state_update_proof_chunks_histogram: Histogram,
-
-    /// Histogram of prefetch proof batch sizes (number of messages merged).
-    pub prefetch_batch_size_histogram: Histogram,
-
-    /// Histogram of proof calculation durations.
-    pub proof_calculation_duration_histogram: Histogram,
-
-    /// Histogram of sparse trie update durations.
-    pub sparse_trie_update_duration_histogram: Histogram,
     /// Histogram of durations spent revealing multiproof results into the sparse trie.
     pub sparse_trie_reveal_multiproof_duration_histogram: Histogram,
     /// Histogram of durations spent coalescing multiple proof results from the channel.
@@ -174,21 +130,24 @@ pub(crate) struct MultiProofTaskMetrics {
     pub sparse_trie_final_update_duration_histogram: Histogram,
     /// Histogram of sparse trie total durations.
     pub sparse_trie_total_duration_histogram: Histogram,
-
-    /// Histogram of state updates received.
-    pub state_updates_received_histogram: Histogram,
-    /// Histogram of proofs processed.
-    pub proofs_processed_histogram: Histogram,
-    /// Histogram of total time spent in the multiproof task.
-    pub multiproof_task_total_duration_histogram: Histogram,
-    /// Total time spent waiting for the first state update or prefetch request.
-    pub first_update_wait_time_histogram: Histogram,
-    /// Total time spent waiting for the last proof result.
-    pub last_proof_wait_time_histogram: Histogram,
     /// Time spent preparing the sparse trie for reuse after state root computation.
     pub into_trie_for_reuse_duration_histogram: Histogram,
     /// Time spent waiting for preserved sparse trie cache to become available.
     pub sparse_trie_cache_wait_duration_histogram: Histogram,
+
+    /// Number of account leaf updates applied without needing a new proof (cache hits).
+    pub sparse_trie_account_cache_hits: Histogram,
+    /// Number of account leaf updates that required a new proof (cache misses).
+    pub sparse_trie_account_cache_misses: Histogram,
+    /// Number of storage leaf updates applied without needing a new proof (cache hits).
+    pub sparse_trie_storage_cache_hits: Histogram,
+    /// Number of storage leaf updates that required a new proof (cache misses).
+    pub sparse_trie_storage_cache_misses: Histogram,
+
+    /// Retained memory of the preserved sparse trie cache in bytes.
+    pub sparse_trie_retained_memory_bytes: Gauge,
+    /// Number of storage tries retained in the preserved sparse trie cache.
+    pub sparse_trie_retained_storage_tries: Gauge,
 }
 
 /// Dispatches work items as a single unit or in chunks based on target size and worker

crates/engine/tree/src/tree/payload_processor/preserved_sparse_trie.rs

@@ -2,12 +2,12 @@
 
 use alloy_primitives::B256;
 use parking_lot::Mutex;
-use reth_trie_sparse::SparseStateTrie;
+use reth_trie_sparse::{ConfigurableSparseTrie, SparseStateTrie};
 use std::{sync::Arc, time::Instant};
 use tracing::debug;
 
 /// Type alias for the sparse trie type used in preservation.
-pub(super) type SparseTrie = SparseStateTrie;
+pub(super) type SparseTrie = SparseStateTrie<ConfigurableSparseTrie, ConfigurableSparseTrie>;
 
 /// Shared handle to a preserved sparse trie that can be reused across payload validations.
 ///

crates/engine/tree/src/tree/payload_processor/prewarm.rs

@@ -33,9 +33,9 @@ use reth_provider::{
 };
 use reth_revm::{database::StateProviderDatabase, state::EvmState};
 use reth_tasks::{pool::WorkerPool, Runtime};
-use reth_trie_parallel::targets_v2::MultiProofTargetsV2;
+use reth_trie_common::{MultiProofTargetsV2, ProofV2Target};
 use std::sync::{
-    atomic::{AtomicBool, Ordering},
+    atomic::{AtomicBool, AtomicUsize, Ordering},
     mpsc::{self, channel, Receiver, Sender},
     Arc,
 };
@@ -149,7 +149,7 @@ where
                 });
 
                 while let Ok((index, tx)) = pending.recv() {
-                    if ctx.terminate_execution.load(Ordering::Relaxed) {
+                    if ctx.should_stop() {
                         trace!(
                             target: "engine::tree::payload_processor::prewarm",
                             "Termination requested, stopping transaction distribution"
@@ -157,6 +157,11 @@ where
                         break;
                     }
 
+                    // skip transactions already executed by the main loop
+                    if index < ctx.executed_tx_index.load(Ordering::Relaxed) {
+                        continue;
+                    }
+
                     tx_count += 1;
                     let parent_span = Span::current();
                     s.spawn(move |_| {
@@ -202,13 +207,18 @@ where
         Tx: ExecutableTxFor<Evm>,
     {
         WorkerPool::with_worker_mut(|worker| {
-            let Some((evm, metrics, terminate_execution)) =
+            let Some(evm) =
                 worker.get_or_init::<PrewarmEvmState<Evm>>(|| ctx.evm_for_ctx()).as_mut()
             else {
                 return;
             };
 
-            if terminate_execution.load(Ordering::Relaxed) {
+            if ctx.should_stop() {
+                return;
+            }
+
+            // skip if main execution has already processed this transaction
+            if index < ctx.executed_tx_index.load(Ordering::Relaxed) {
                 return;
             }
 
@@ -225,25 +235,25 @@ where
                         sender=%tx.signer(),
                         "Error when executing prewarm transaction",
                     );
-                    metrics.transaction_errors.increment(1);
+                    ctx.metrics.transaction_errors.increment(1);
                     return;
                 }
             };
-            metrics.execution_duration.record(start.elapsed());
+            ctx.metrics.execution_duration.record(start.elapsed());
 
-            if terminate_execution.load(Ordering::Relaxed) {
+            if ctx.should_stop() {
                 return;
             }
 
             if index > 0 {
                 let (targets, storage_targets) = multiproof_targets_from_state(res.state);
-                metrics.prefetch_storage_targets.record(storage_targets as f64);
+                ctx.metrics.prefetch_storage_targets.record(storage_targets as f64);
                 if let Some(to_multi_proof) = to_multi_proof {
                     let _ = to_multi_proof.send(MultiProofMessage::PrefetchProofs(targets));
                 }
             }
 
-            metrics.total_runtime.record(start.elapsed());
+            ctx.metrics.total_runtime.record(start.elapsed());
         });
     }
 
@@ -348,7 +358,7 @@ where
             bal.par_iter().for_each_init(
                 || (ctx.clone(), None::<CachedStateProvider<reth_provider::StateProviderBox>>),
                 |(ctx, provider), account| {
-                    if ctx.terminate_execution.load(Ordering::Relaxed) {
+                    if ctx.should_stop() {
                         return;
                     }
                     ctx.prefetch_bal_account(provider, account);
@@ -442,7 +452,7 @@ where
                 PrewarmTaskEvent::TerminateTransactionExecution => {
                     // stop tx processing
                     debug!(target: "engine::tree::prewarm", "Terminating prewarm execution");
-                    self.ctx.terminate_execution.store(true, Ordering::Relaxed);
+                    self.ctx.stop();
                 }
                 PrewarmTaskEvent::Terminate { execution_outcome, valid_block_rx } => {
                     trace!(target: "engine::tree::payload_processor::prewarm", "Received termination signal");
@@ -497,6 +507,10 @@ where
     pub metrics: PrewarmMetrics,
     /// An atomic bool that tells prewarm tasks to not start any more execution.
     pub terminate_execution: Arc<AtomicBool>,
+    /// Shared counter tracking the next transaction index to be executed by the main execution
+    /// loop. Prewarm workers skip transactions with `index < counter` since those have already
+    /// been executed.
+    pub executed_tx_index: Arc<AtomicUsize>,
     /// Whether the precompile cache is disabled.
     pub precompile_cache_disabled: bool,
     /// The precompile cache map.
@@ -505,11 +519,8 @@ where
 
 /// Per-thread EVM state initialised by [`PrewarmContext::evm_for_ctx`] and stored in
 /// [`WorkerPool`] workers via [`Worker::get_or_init`](reth_tasks::pool::Worker::get_or_init).
-type PrewarmEvmState<Evm> = Option<(
-    EvmFor<Evm, StateProviderDatabase<reth_provider::StateProviderBox>>,
-    PrewarmMetrics,
-    Arc<AtomicBool>,
-)>;
+type PrewarmEvmState<Evm> =
+    Option<EvmFor<Evm, StateProviderDatabase<reth_provider::StateProviderBox>>>;
 
 impl<N, P, Evm> PrewarmContext<N, P, Evm>
 where
@@ -517,7 +528,7 @@ where
     P: BlockReader + StateProviderFactory + StateReader + Clone + 'static,
     Evm: ConfigureEvm<Primitives = N> + 'static,
 {
-    /// Creates a per-thread EVM, metrics handle, and termination flag for prewarming.
+    /// Creates a per-thread EVM for prewarming.
     #[instrument(level = "debug", target = "engine::tree::payload_processor::prewarm", skip_all)]
     fn evm_for_ctx(&self) -> PrewarmEvmState<Evm> {
         let mut state_provider = match self.provider.build() {
@@ -558,7 +569,7 @@ where
 
         if !self.precompile_cache_disabled {
             // Only cache pure precompiles to avoid issues with stateful precompiles
-            evm.precompiles_mut().map_pure_precompiles(|address, precompile| {
+            evm.precompiles_mut().map_cacheable_precompiles(|address, precompile| {
                 CachedPrecompile::wrap(
                     precompile,
                     self.precompile_cache_map.cache_for_address(*address),
@@ -568,7 +579,19 @@ where
             });
         }
 
-        Some((evm, self.metrics.clone(), self.terminate_execution.clone()))
+        Some(evm)
+    }
+
+    /// Returns `true` if prewarming should stop.
+    #[inline]
+    pub fn should_stop(&self) -> bool {
+        self.terminate_execution.load(Ordering::Relaxed)
+    }
+
+    /// Signals all prewarm tasks to stop execution.
+    #[inline]
+    pub fn stop(&self) {
+        self.terminate_execution.store(true, Ordering::Relaxed);
     }
 
     /// Prefetches a single account and all its storage slots from the BAL into the cache.
@@ -620,8 +643,6 @@ where
 /// Returns a set of [`MultiProofTargetsV2`] and the total amount of storage targets, based on the
 /// given state.
 fn multiproof_targets_from_state(state: EvmState) -> (MultiProofTargetsV2, usize) {
-    use reth_trie::proof_v2;
-
     let mut targets = MultiProofTargetsV2::default();
     let mut storage_target_count = 0;
     for (addr, account) in state {
@@ -647,7 +668,7 @@ fn multiproof_targets_from_state(state: EvmState) -> (MultiProofTargetsV2, usize
             }
 
             let hashed_slot = keccak256(B256::new(key.to_be_bytes()));
-            storage_slots.push(proof_v2::Target::from(hashed_slot));
+            storage_slots.push(ProofV2Target::from(hashed_slot));
         }
 
         storage_target_count += storage_slots.len();

crates/engine/tree/src/tree/payload_processor/sparse_trie.rs

@@ -12,25 +12,25 @@ use crate::tree::{
 use alloy_primitives::B256;
 use alloy_rlp::{Decodable, Encodable};
 use crossbeam_channel::{Receiver as CrossbeamReceiver, Sender as CrossbeamSender};
-use rayon::iter::ParallelIterator;
-use reth_primitives_traits::{Account, FastInstant as Instant, ParallelBridgeBuffered};
+use rayon::iter::{IntoParallelIterator, ParallelIterator};
+use reth_primitives_traits::{Account, FastInstant as Instant};
 use reth_tasks::Runtime;
 use reth_trie::{
-    proof_v2::Target, updates::TrieUpdates, DecodedMultiProofV2, HashedPostState, TrieAccount,
-    EMPTY_ROOT_HASH, TRIE_ACCOUNT_RLP_MAX_SIZE,
+    updates::TrieUpdates, DecodedMultiProofV2, HashedPostState, TrieAccount, EMPTY_ROOT_HASH,
+    TRIE_ACCOUNT_RLP_MAX_SIZE,
 };
+use reth_trie_common::{MultiProofTargetsV2, ProofV2Target};
 use reth_trie_parallel::{
     proof_task::{
         AccountMultiproofInput, ProofResultContext, ProofResultMessage, ProofWorkerHandle,
     },
     root::ParallelStateRootError,
-    targets_v2::MultiProofTargetsV2,
 };
 #[cfg(feature = "trie-debug")]
 use reth_trie_sparse::debug_recorder::TrieDebugRecorder;
 use reth_trie_sparse::{
-    errors::SparseTrieResult, DeferredDrops, LeafUpdate, ParallelSparseTrie, SparseStateTrie,
-    SparseTrie,
+    errors::SparseTrieResult, ConfigurableSparseTrie, DeferredDrops, LeafUpdate,
+    RevealableSparseTrie, SparseStateTrie, SparseTrie,
 };
 use revm_primitives::{hash_map::Entry, B256Map};
 use tracing::{debug, debug_span, error, instrument, trace_span};
@@ -39,7 +39,7 @@ use tracing::{debug, debug_span, error, instrument, trace_span};
 const MAX_PENDING_UPDATES: usize = 100;
 
 /// Sparse trie task implementation that uses in-memory sparse trie data to schedule proof fetching.
-pub(super) struct SparseTrieCacheTask<A = ParallelSparseTrie, S = ParallelSparseTrie> {
+pub(super) struct SparseTrieCacheTask<A = ConfigurableSparseTrie, S = ConfigurableSparseTrie> {
     /// Sender for proof results.
     proof_result_tx: CrossbeamSender<ProofResultMessage>,
     /// Receiver for proof results directly from workers.
@@ -92,6 +92,14 @@ pub(super) struct SparseTrieCacheTask<A = ParallelSparseTrie, S = ParallelSparse
     account_rlp_buf: Vec<u8>,
     /// Whether the last state update has been received.
     finished_state_updates: bool,
+    /// Accumulated account leaf update cache hits.
+    account_cache_hits: u64,
+    /// Accumulated account leaf update cache misses.
+    account_cache_misses: u64,
+    /// Accumulated storage leaf update cache hits.
+    storage_cache_hits: u64,
+    /// Accumulated storage leaf update cache misses.
+    storage_cache_misses: u64,
     /// Pending proof targets queued for dispatch to proof workers.
     pending_targets: PendingTargets,
     /// Number of pending execution/prewarming updates received but not yet passed to
@@ -142,6 +150,10 @@ where
             fetched_storage_targets: Default::default(),
             account_rlp_buf: Vec::with_capacity(TRIE_ACCOUNT_RLP_MAX_SIZE),
             finished_state_updates: Default::default(),
+            account_cache_hits: 0,
+            account_cache_misses: 0,
+            storage_cache_hits: 0,
+            storage_cache_misses: 0,
             pending_targets: Default::default(),
             pending_updates: Default::default(),
             metrics,
@@ -167,9 +179,7 @@ where
                 MultiProofMessage::FinishedStateUpdates => {
                     SparseTrieTaskMessage::FinishedStateUpdates
                 }
-                MultiProofMessage::EmptyProof { .. } | MultiProofMessage::BlockAccessList(_) => {
-                    continue
-                }
+                MultiProofMessage::BlockAccessList(_) => continue,
                 MultiProofMessage::HashedStateUpdate(state) => {
                     SparseTrieTaskMessage::HashedState(state)
                 }
@@ -189,8 +199,8 @@ where
     /// benchmarking purposes.
     pub(super) fn into_trie_for_reuse(
         self,
-        prune_depth: usize,
-        max_storage_tries: usize,
+        max_hot_slots: usize,
+        max_hot_accounts: usize,
         max_nodes_capacity: usize,
         max_values_capacity: usize,
         disable_pruning: bool,
@@ -199,7 +209,7 @@ where
         let Self { mut trie, .. } = self;
         trie.commit_updates(updates);
         if !disable_pruning {
-            trie.prune(prune_depth, max_storage_tries);
+            trie.prune(max_hot_slots, max_hot_accounts);
             trie.shrink_to(max_nodes_capacity, max_values_capacity);
         }
         let deferred = trie.take_deferred_drops();
@@ -332,6 +342,15 @@ where
         self.metrics.sparse_trie_final_update_duration_histogram.record(end.duration_since(start));
         self.metrics.sparse_trie_total_duration_histogram.record(end.duration_since(now));
 
+        self.metrics.sparse_trie_account_cache_hits.record(self.account_cache_hits as f64);
+        self.metrics.sparse_trie_account_cache_misses.record(self.account_cache_misses as f64);
+        self.metrics.sparse_trie_storage_cache_hits.record(self.storage_cache_hits as f64);
+        self.metrics.sparse_trie_storage_cache_misses.record(self.storage_cache_misses as f64);
+        self.account_cache_hits = 0;
+        self.account_cache_misses = 0;
+        self.storage_cache_hits = 0;
+        self.storage_cache_misses = 0;
+
         Ok(StateRootComputeOutcome {
             state_root,
             trie_updates: Arc::new(trie_updates),
@@ -363,13 +382,13 @@ where
         }
 
         for (address, slots) in targets.storage_targets {
-            for slot in slots {
-                // Only touch storages that are not yet present in the updates set.
-                self.new_storage_updates
-                    .entry(address)
-                    .or_default()
-                    .entry(slot.key())
-                    .or_insert(LeafUpdate::Touched);
+            if !slots.is_empty() {
+                // Look up outer map once per address instead of once per slot.
+                let new_updates = self.new_storage_updates.entry(address).or_default();
+                for slot in slots {
+                    // Only touch storages that are not yet present in the updates set.
+                    new_updates.entry(slot.key()).or_insert(LeafUpdate::Touched);
+                }
             }
 
             // Touch corresponding account leaf to make sure its revealed in accounts trie for
@@ -386,19 +405,26 @@ where
     )]
     fn on_hashed_state_update(&mut self, hashed_state_update: HashedPostState) {
         for (address, storage) in hashed_state_update.storages {
-            for (slot, value) in storage.storage {
-                let encoded = if value.is_zero() {
-                    Vec::new()
-                } else {
-                    alloy_rlp::encode_fixed_size(&value).to_vec()
-                };
-                self.new_storage_updates
-                    .entry(address)
-                    .or_default()
-                    .insert(slot, LeafUpdate::Changed(encoded));
+            if !storage.storage.is_empty() {
+                // Look up outer maps once per address instead of once per slot.
+                let new_updates = self.new_storage_updates.entry(address).or_default();
+                let mut existing_updates = self.storage_updates.get_mut(&address);
 
-                // Remove an existing storage update if it exists.
-                self.storage_updates.get_mut(&address).and_then(|updates| updates.remove(&slot));
+                for (slot, value) in storage.storage {
+                    self.trie.record_slot_touch(address, slot);
+
+                    let encoded = if value.is_zero() {
+                        Vec::new()
+                    } else {
+                        alloy_rlp::encode_fixed_size(&value).to_vec()
+                    };
+                    new_updates.insert(slot, LeafUpdate::Changed(encoded));
+
+                    // Remove an existing storage update if it exists.
+                    if let Some(ref mut existing) = existing_updates {
+                        existing.remove(&slot);
+                    }
+                }
             }
 
             // Make sure account is tracked in `account_updates` so that it is revealed in accounts
@@ -411,6 +437,8 @@ where
         }
 
         for (address, account) in hashed_state_update.accounts {
+            self.trie.record_account_touch(address);
+
             // Track account as touched.
             //
             // This might overwrite an existing update, which is fine, because storage root from it
@@ -505,18 +533,22 @@ where
             let fetched = self.fetched_storage_targets.entry(*address).or_default();
             let mut targets = Vec::new();
 
+            let updates_len_before = updates.len();
             trie.update_leaves(updates, |path, min_len| match fetched.entry(path) {
                 Entry::Occupied(mut entry) => {
                     if min_len < *entry.get() {
                         entry.insert(min_len);
-                        targets.push(Target::new(path).with_min_len(min_len));
+                        targets.push(ProofV2Target::new(path).with_min_len(min_len));
                     }
                 }
                 Entry::Vacant(entry) => {
                     entry.insert(min_len);
-                    targets.push(Target::new(path).with_min_len(min_len));
+                    targets.push(ProofV2Target::new(path).with_min_len(min_len));
                 }
             })?;
+            let updates_len_after = updates.len();
+            self.storage_cache_hits += (updates_len_before - updates_len_after) as u64;
+            self.storage_cache_misses += updates_len_after as u64;
 
             if !targets.is_empty() {
                 self.pending_targets.extend_storage_targets(address, targets);
@@ -551,18 +583,76 @@ where
                     if min_len < *entry.get() {
                         entry.insert(min_len);
                         self.pending_targets
-                            .push_account_target(Target::new(target).with_min_len(min_len));
+                            .push_account_target(ProofV2Target::new(target).with_min_len(min_len));
                     }
                 }
                 Entry::Vacant(entry) => {
                     entry.insert(min_len);
                     self.pending_targets
-                        .push_account_target(Target::new(target).with_min_len(min_len));
+                        .push_account_target(ProofV2Target::new(target).with_min_len(min_len));
                 }
             }
         })?;
 
-        Ok(account_updates.len() < updates_len_before)
+        let updates_len_after = account_updates.len();
+        self.account_cache_hits += (updates_len_before - updates_len_after) as u64;
+        self.account_cache_misses += updates_len_after as u64;
+
+        Ok(updates_len_after < updates_len_before)
+    }
+
+    /// Computes storage roots for accounts whose storage updates are fully drained.
+    ///
+    /// For each storage trie T that:
+    /// 1. was modified in the current block,
+    /// 2. all the storage updates are fully drained,
+    /// 3. but the storage root hasn't been updated yet,
+    ///
+    /// we trigger state root computation on a rayon pool.
+    #[instrument(
+        level = "debug",
+        target = "engine::tree::payload_processor::sparse_trie",
+        skip_all
+    )]
+    fn compute_drained_storage_roots(&mut self) {
+        let addresses_to_compute_roots: Vec<_> = self
+            .storage_updates
+            .iter()
+            .filter_map(|(address, updates)| updates.is_empty().then_some(*address))
+            .collect();
+
+        struct SendStorageTriePtr<S>(*mut RevealableSparseTrie<S>);
+        // SAFETY: this wrapper only forwards the pointer across rayon; deref invariants are
+        // documented at the use site below.
+        unsafe impl<S: Send> Send for SendStorageTriePtr<S> {}
+
+        let mut tries_to_compute_roots: Vec<(B256, SendStorageTriePtr<S>)> =
+            Vec::with_capacity(addresses_to_compute_roots.len());
+        for address in addresses_to_compute_roots {
+            if let Some(trie) = self.trie.storage_tries_mut().get_mut(&address) &&
+                !trie.is_root_cached()
+            {
+                tries_to_compute_roots.push((address, SendStorageTriePtr(trie)));
+            }
+        }
+
+        let parent_span = tracing::Span::current();
+        tries_to_compute_roots.into_par_iter().for_each(|(address, SendStorageTriePtr(trie))| {
+            let _enter = debug_span!(
+                target: "engine::tree::payload_processor::sparse_trie",
+                parent: &parent_span,
+                "storage_root",
+                ?address
+            )
+            .entered();
+            // SAFETY:
+            // - pointers are created from `storage_tries_mut().get_mut(address)` above;
+            // - `addresses_to_compute_roots` comes from map iteration, so addresses are unique;
+            // - we do not insert/remove entries between pointer collection and use, so pointers
+            //   stay valid and map reallocation cannot occur;
+            // - each pointer is consumed by at most one rayon task, so no aliasing mutable access.
+            unsafe { (*trie).root().expect("updates are drained, trie should be revealed by now") };
+        });
     }
 
     /// Iterates through all storage tries for which all updates were processed, computes their
@@ -580,21 +670,7 @@ where
             return Ok(());
         }
 
-        let span = debug_span!("compute_storage_roots").entered();
-        self
-            .trie
-            .storage_tries_mut()
-            .iter_mut()
-            .filter(|(address, trie)| {
-                self.storage_updates.get(*address).is_some_and(|updates| updates.is_empty()) &&
-                    !trie.is_root_cached()
-            })
-            .par_bridge_buffered()
-            .for_each(|(address, trie)| {
-                let _enter = debug_span!(target: "engine::tree::payload_processor::sparse_trie", parent: &span, "storage_root", ?address).entered();
-                trie.root().expect("updates are drained, trie should be revealed by now");
-            });
-        drop(span);
+        self.compute_drained_storage_roots();
 
         loop {
             let span = debug_span!("promote_updates", promoted = tracing::field::Empty).entered();
@@ -734,13 +810,13 @@ impl PendingTargets {
     }
 
     /// Adds a target to the account targets.
-    fn push_account_target(&mut self, target: Target) {
+    fn push_account_target(&mut self, target: ProofV2Target) {
         self.targets.account_targets.push(target);
         self.len += 1;
     }
 
     /// Extends storage targets for the given address.
-    fn extend_storage_targets(&mut self, address: &B256, targets: Vec<Target>) {
+    fn extend_storage_targets(&mut self, address: &B256, targets: Vec<ProofV2Target>) {
         self.len += targets.len();
         self.targets.storage_targets.entry(*address).or_default().extend(targets);
     }
@@ -774,7 +850,7 @@ pub struct StateRootComputeOutcome {
 mod tests {
     use super::*;
     use alloy_primitives::{keccak256, Address, B256, U256};
-    use reth_trie_sparse::ParallelSparseTrie;
+    use reth_trie_sparse::ArenaParallelSparseTrie;
 
     #[test]
     fn test_run_hashing_task_hashed_state_update_forwards() {
@@ -797,7 +873,7 @@ mod tests {
         let expected_state = hashed_state.clone();
 
         let handle = std::thread::spawn(move || {
-            SparseTrieCacheTask::<ParallelSparseTrie, ParallelSparseTrie>::run_hashing_task(
+            SparseTrieCacheTask::<ArenaParallelSparseTrie, ArenaParallelSparseTrie>::run_hashing_task(
                 updates_rx,
                 hashed_state_tx,
             );

crates/engine/tree/src/tree/payload_validator.rs

@@ -1,9 +1,9 @@
 //! Types and traits for validating blocks and payloads.
 
 use crate::tree::{
-    cached_state::CachedStateProvider,
+    cached_state::{CacheStats, CachedStateProvider},
     error::{InsertBlockError, InsertBlockErrorKind, InsertPayloadError},
-    instrumented_state::InstrumentedStateProvider,
+    instrumented_state::{InstrumentedStateProvider, StateProviderStats},
     payload_processor::PayloadProcessor,
     precompile_cache::{CachedPrecompile, CachedPrecompileMetrics, PrecompileCacheMap},
     sparse_trie::StateRootComputeOutcome,
@@ -14,12 +14,14 @@ use alloy_consensus::transaction::{Either, TxHashRef};
 use alloy_eip7928::BlockAccessList;
 use alloy_eips::{eip1898::BlockWithParent, eip4895::Withdrawal, NumHash};
 use alloy_evm::Evm;
-use alloy_primitives::B256;
+use alloy_primitives::{map::B256Set, B256};
 #[cfg(feature = "trie-debug")]
 use reth_trie_sparse::debug_recorder::TrieDebugRecorder;
 
 use crate::tree::payload_processor::receipt_root_task::{IndexedReceipt, ReceiptRootTaskHandle};
-use reth_chain_state::{CanonicalInMemoryState, DeferredTrieData, ExecutedBlock, LazyOverlay};
+use reth_chain_state::{
+    CanonicalInMemoryState, DeferredTrieData, ExecutedBlock, ExecutionTimingStats, LazyOverlay,
+};
 use reth_consensus::{ConsensusError, FullConsensus, ReceiptRootBloom};
 use reth_engine_primitives::{
     ConfigureEngineEvm, ExecutableTxIterator, ExecutionPayload, InvalidBlockHook, PayloadValidator,
@@ -27,7 +29,7 @@ use reth_engine_primitives::{
 use reth_errors::{BlockExecutionError, ProviderResult};
 use reth_evm::{
     block::BlockExecutor, execute::ExecutableTxFor, ConfigureEvm, EvmEnvFor, ExecutionCtxFor,
-    SpecFor,
+    OnStateHook, SpecFor,
 };
 use reth_payload_primitives::{
     BuiltPayload, InvalidPayloadAttributesError, NewPayloadError, PayloadTypes,
@@ -42,21 +44,36 @@ use reth_provider::{
     ProviderError, PruneCheckpointReader, StageCheckpointReader, StateProvider,
     StateProviderFactory, StateReader, StorageChangeSetReader, StorageSettingsCache,
 };
-use reth_revm::db::{states::bundle_state::BundleRetention, State};
-use reth_trie::{updates::TrieUpdates, HashedPostState, StateRoot};
+use reth_revm::db::{states::bundle_state::BundleRetention, BundleAccount, State};
+use reth_trie::{trie_cursor::TrieCursorFactory, updates::TrieUpdates, HashedPostState, StateRoot};
 use reth_trie_db::ChangesetCache;
 use reth_trie_parallel::root::{ParallelStateRoot, ParallelStateRootError};
-use revm_primitives::Address;
+use revm_primitives::{Address, KECCAK_EMPTY};
 use std::{
     collections::HashMap,
     panic::{self, AssertUnwindSafe},
-    sync::{mpsc::RecvTimeoutError, Arc},
+    sync::{
+        atomic::{AtomicUsize, Ordering},
+        mpsc::RecvTimeoutError,
+        Arc,
+    },
+    time::Duration,
 };
 use tracing::{debug, debug_span, error, info, instrument, trace, warn, Span};
 
+/// Output of block or payload validation.
+pub type ValidationOutcome<N, E = InsertPayloadError<BlockTy<N>>> =
+    Result<(ExecutedBlock<N>, Option<Box<ExecutionTimingStats>>), E>;
+
 /// Handle to a [`HashedPostState`] computed on a background thread.
 type LazyHashedPostState = reth_tasks::LazyHandle<HashedPostState>;
 
+/// Result type for block validation with optional timing stats.
+type InsertPayloadResult<N> = Result<
+    (ExecutedBlock<N>, Option<Box<ExecutionTimingStats>>),
+    InsertPayloadError<<N as NodePrimitives>::Block>,
+>;
+
 /// Context providing access to tree state during validation.
 ///
 /// This context is provided to the [`EngineValidator`] and includes the state of the tree's
@@ -85,7 +102,9 @@ impl<'a, N: NodePrimitives> TreeCtx<'a, N> {
     ) -> Self {
         Self { state, canonical_in_memory_state }
     }
+}
 
+impl<'a, N: NodePrimitives> TreeCtx<'a, N> {
     /// Returns a reference to the engine tree state
     pub const fn state(&self) -> &EngineApiTreeState<N> {
         &*self.state
@@ -276,7 +295,7 @@ where
         input: BlockOrPayload<T>,
         execution_err: InsertBlockErrorKind,
         parent_block: &SealedHeader<N::BlockHeader>,
-    ) -> Result<ExecutedBlock<N>, InsertPayloadError<N::Block>>
+    ) -> InsertPayloadResult<N>
     where
         V: PayloadValidator<T, Block = N::Block>,
     {
@@ -329,7 +348,7 @@ where
         &mut self,
         input: BlockOrPayload<T>,
         mut ctx: TreeCtx<'_, N>,
-    ) -> ValidationOutcome<N, InsertPayloadError<N::Block>>
+    ) -> InsertPayloadResult<N>
     where
         V: PayloadValidator<T, Block = N::Block> + Clone,
         Evm: ConfigureEngineEvm<T::ExecutionData, Primitives = N>,
@@ -481,25 +500,39 @@ where
             block_access_list,
         ));
 
+        // Create optional cache stats for detailed block logging
+        let slow_block_enabled = self.config.slow_block_threshold().is_some();
+        let cache_stats = slow_block_enabled.then(|| Arc::new(CacheStats::default()));
+
         // Use cached state provider before executing, used in execution after prewarming threads
         // complete
         if let Some((caches, cache_metrics)) = handle.caches().zip(handle.cache_metrics()) {
-            state_provider =
-                Box::new(CachedStateProvider::new(state_provider, caches, cache_metrics));
+            state_provider = Box::new(
+                CachedStateProvider::new(state_provider, caches, cache_metrics)
+                    .with_cache_stats(cache_stats.clone()),
+            );
         };
 
-        if self.config.state_provider_metrics() {
-            state_provider = Box::new(InstrumentedStateProvider::new(state_provider, "engine"));
-        }
+        let state_provider_stats = if slow_block_enabled || self.config.state_provider_metrics() {
+            let instrumented_state_provider =
+                InstrumentedStateProvider::new(state_provider, "engine");
+            let stats = slow_block_enabled.then(|| instrumented_state_provider.stats());
+            state_provider = Box::new(instrumented_state_provider);
+            stats
+        } else {
+            None
+        };
 
         // Execute the block and handle any execution errors.
         // The receipt root task is spawned before execution and receives receipts incrementally
         // as transactions complete, allowing parallel computation during execution.
+        let execute_block_start = Instant::now();
         let (output, senders, receipt_root_rx) =
             match self.execute_block(state_provider, env, &input, &mut handle) {
                 Ok(output) => output,
                 Err(err) => return self.handle_execution_error(input, err, &parent_block),
             };
+        let execution_duration = execute_block_start.elapsed();
 
         // After executing the block we can stop prewarming transactions
         handle.stop_prewarming_execution();
@@ -732,18 +765,37 @@ where
             .into())
         }
 
+        let timing_stats = state_provider_stats.map(|stats| {
+            self.calculate_timing_stats(
+                &block,
+                stats,
+                cache_stats,
+                &output,
+                execution_duration,
+                root_elapsed,
+            )
+        });
+
         if let Some(valid_block_tx) = valid_block_tx {
             let _ = valid_block_tx.send(());
         }
 
-        Ok(self.spawn_deferred_trie_task(
+        // Create the overlay provider NOW, while we're on the engine loop thread and trie changeset
+        // eviction cannot race with us. If we deferred this to the background task, persistence
+        // could advance and evict changeset cache entries between factory creation and the task
+        // actually running, causing expensive DB fallback computations when building the overlay.
+        let changeset_provider =
+            ensure_ok_post_block!(overlay_factory.database_provider_ro(), block);
+
+        let executed_block = self.spawn_deferred_trie_task(
             block,
             output,
             &ctx,
             hashed_state,
             trie_output,
-            overlay_factory,
-        ))
+            changeset_provider,
+        );
+        Ok((executed_block, timing_stats))
     }
 
     /// Return sealed block header from database or in-memory state by hash.
@@ -821,7 +873,6 @@ where
             State::builder()
                 .with_database(StateProviderDatabase::new(state_provider))
                 .with_bundle_update()
-                .without_state_clear()
                 .build()
         });
 
@@ -838,19 +889,21 @@ where
 
         if !self.config.precompile_cache_disabled() {
             let _span = debug_span!(target: "engine::tree", "setup_precompile_cache").entered();
-            executor.evm_mut().precompiles_mut().map_pure_precompiles(|address, precompile| {
-                let metrics = self
-                    .precompile_cache_metrics
-                    .entry(*address)
-                    .or_insert_with(|| CachedPrecompileMetrics::new_with_address(*address))
-                    .clone();
-                CachedPrecompile::wrap(
-                    precompile,
-                    self.precompile_cache_map.cache_for_address(*address),
-                    spec_id,
-                    Some(metrics),
-                )
-            });
+            executor.evm_mut().precompiles_mut().map_cacheable_precompiles(
+                |address, precompile| {
+                    let metrics = self
+                        .precompile_cache_metrics
+                        .entry(*address)
+                        .or_insert_with(|| CachedPrecompileMetrics::new_with_address(*address))
+                        .clone();
+                    CachedPrecompile::wrap(
+                        precompile,
+                        self.precompile_cache_map.cache_for_address(*address),
+                        spec_id,
+                        Some(metrics),
+                    )
+                },
+            );
         }
 
         // Spawn background task to compute receipt root and logs bloom incrementally.
@@ -864,7 +917,10 @@ where
             .spawn_blocking_named("receipt-root", move || task_handle.run(receipts_len));
 
         let transaction_count = input.transaction_count();
-        let executor = executor.with_state_hook(Some(Box::new(handle.state_hook())));
+        let executed_tx_index = Arc::clone(handle.executed_tx_index());
+        let executor = executor.with_state_hook(
+            handle.state_hook().map(|hook| Box::new(hook) as Box<dyn OnStateHook>),
+        );
 
         let execution_start = Instant::now();
 
@@ -874,6 +930,7 @@ where
             transaction_count,
             handle.iter_transactions(),
             &receipt_tx,
+            &executed_tx_index,
         )?;
         drop(receipt_tx);
 
@@ -893,8 +950,8 @@ where
         let execution_duration = execution_start.elapsed();
         self.metrics.record_block_execution(&output, execution_duration);
         self.metrics.record_block_execution_gas_bucket(output.result.gas_used, execution_duration);
-
         debug!(target: "engine::tree::payload_validator", elapsed = ?execution_duration, "Executed block");
+
         Ok((output, senders, result_rx))
     }
 
@@ -913,6 +970,7 @@ where
         transaction_count: usize,
         transactions: impl Iterator<Item = Result<Tx, Err>>,
         receipt_tx: &crossbeam_channel::Sender<IndexedReceipt<N::Receipt>>,
+        executed_tx_index: &AtomicUsize,
     ) -> Result<(E, Vec<Address>), BlockExecutionError>
     where
         E: BlockExecutor<Receipt = N::Receipt>,
@@ -951,6 +1009,7 @@ where
             let _enter = debug_span!(
                 target: "engine::tree",
                 "execute tx",
+                tx_index = senders.len() - 1,
             )
             .entered();
             trace!(target: "engine::tree", "Executing transaction");
@@ -959,6 +1018,9 @@ where
             executor.execute_transaction(tx)?;
             self.metrics.record_transaction_execution(tx_start.elapsed());
 
+            // advance the shared counter so prewarm workers skip already-executed txs
+            executed_tx_index.store(senders.len(), Ordering::Relaxed);
+
             let current_len = executor.receipts().len();
             if current_len > last_sent_len {
                 last_sent_len = current_len;
@@ -1521,7 +1583,7 @@ where
         ctx: &TreeCtx<'_, N>,
         hashed_state: LazyHashedPostState,
         trie_output: Arc<TrieUpdates>,
-        overlay_factory: OverlayStateProviderFactory<P>,
+        changeset_provider: impl TrieCursorFactory + Send + 'static,
     ) -> ExecutedBlock<N> {
         // Capture parent hash and ancestor overlays for deferred trie input construction.
         let (anchor_hash, overlay_blocks) = ctx
@@ -1550,7 +1612,11 @@ where
         // Capture block info and cache handle for changeset computation
         let block_hash = block.hash();
         let block_number = block.number();
-        let changeset_cache = self.changeset_cache.clone();
+
+        // Register a pending changeset entry so that concurrent readers will wait for
+        // this computation to finish rather than falling back to the expensive DB path.
+        // The guard ensures the pending entry is cancelled if the task panics.
+        let pending_changeset_guard = self.changeset_cache.register_pending(block_hash);
 
         // Spawn background task to compute trie data. Calling `wait_cloned` will compute from
         // the stored inputs and cache the result, so subsequent calls return immediately.
@@ -1585,20 +1651,15 @@ where
                         .record(anchored.trie_input.state.total_len() as f64);
                 }
 
-                // Compute and cache changesets using the computed trie_updates
+                // Compute and cache changesets using the computed trie_updates.
+                // Use the pre-created provider to avoid races with changeset cache
+                // eviction that can happen between task spawn and execution.
                 let changeset_start = Instant::now();
 
-                // Get a provider from the overlay factory for trie cursor access
-                let changeset_result =
-                    overlay_factory.database_provider_ro().and_then(|provider| {
-                        reth_trie::changesets::compute_trie_changesets(
-                            &provider,
-                            &computed.trie_updates,
-                        )
-                        .map_err(ProviderError::Database)
-                    });
-
-                match changeset_result {
+                match reth_trie::changesets::compute_trie_changesets(
+                    &changeset_provider,
+                    &computed.trie_updates,
+                ) {
                     Ok(changesets) => {
                         debug!(
                             target: "engine::tree::changeset",
@@ -1607,7 +1668,7 @@ where
                             "Computed and caching changesets"
                         );
 
-                        changeset_cache.insert(block_hash, block_number, Arc::new(changesets));
+                        pending_changeset_guard.resolve(block_number, Arc::new(changesets));
                     }
                     Err(e) => {
                         warn!(
@@ -1639,10 +1700,142 @@ where
             deferred_trie_data,
         )
     }
-}
 
-/// Output of block or payload validation.
-pub type ValidationOutcome<N, E = InsertPayloadError<BlockTy<N>>> = Result<ExecutedBlock<N>, E>;
+    fn calculate_timing_stats(
+        &self,
+        block: &RecoveredBlock<N::Block>,
+        provider_stats: Arc<StateProviderStats>,
+        cache_stats: Option<Arc<CacheStats>>,
+        output: &BlockExecutionOutput<N::Receipt>,
+        execution_duration: Duration,
+        state_hash_duration: Duration,
+    ) -> Box<ExecutionTimingStats> {
+        let accounts_read = provider_stats.total_account_fetches();
+        let storage_read = provider_stats.total_storage_fetches();
+        let code_read = provider_stats.total_code_fetches();
+        let code_bytes_read = provider_stats.total_code_fetched_bytes();
+
+        // Write stats from BundleState (final state changes)
+        let accounts_changed = output.state.state.len();
+        let accounts_deleted =
+            output.state.state.values().filter(|acc| acc.was_destroyed()).count();
+        let storage_slots_changed =
+            output.state.state.values().map(|account| account.storage.len()).sum::<usize>();
+        let storage_slots_deleted = output
+            .state
+            .state
+            .values()
+            .flat_map(|account| account.storage.values())
+            .filter(|slot| {
+                slot.present_value.is_zero() && !slot.previous_or_original_value.is_zero()
+            })
+            .count();
+
+        // Helper: check if account represents a new contract deployment
+        let is_new_deployment = |acc: &BundleAccount| -> bool {
+            let has_code_now = acc.info.as_ref().is_some_and(|info| info.code_hash != KECCAK_EMPTY);
+            let had_no_code_before = acc
+                .original_info
+                .as_ref()
+                .map(|info| info.code_hash == KECCAK_EMPTY)
+                .unwrap_or(true);
+            has_code_now && had_no_code_before
+        };
+
+        let bytecodes_changed =
+            output.state.state.values().filter(|acc| is_new_deployment(acc)).count();
+
+        // Unique new code hashes to count actual bytes persisted (deduplicated)
+        let unique_new_code_hashes: B256Set = output
+            .state
+            .state
+            .values()
+            .filter(|acc| is_new_deployment(acc))
+            .filter_map(|acc| acc.info.as_ref().map(|info| info.code_hash))
+            .collect();
+        let code_bytes_written: usize = unique_new_code_hashes
+            .iter()
+            .filter_map(|hash| {
+                output.state.contracts.get(hash).map(|bytecode| bytecode.original_bytes().len())
+            })
+            .sum();
+
+        // Total time spent fetching state during execution
+        let state_read_duration = provider_stats.total_account_fetch_latency() +
+            provider_stats.total_storage_fetch_latency() +
+            provider_stats.total_code_fetch_latency();
+
+        // EIP-7702 delegation tracking from bytecode changes
+        // Count new EIP-7702 bytecodes as delegations set
+        let eip7702_delegations_set =
+            output.state.contracts.values().filter(|bytecode| bytecode.is_eip7702()).count();
+        // Delegations cleared: accounts where bytecode changed FROM EIP-7702 TO empty
+        // This detects when an EIP-7702 delegation is removed by setting code to empty
+        // Note: Clearing a delegation does NOT destroy the account - it just empties the
+        // bytecode
+        let eip7702_delegations_cleared = output
+            .state
+            .state
+            .values()
+            .filter(|acc| {
+                // Check if original bytecode was EIP-7702
+                let original_was_eip7702 = acc
+                    .original_info
+                    .as_ref()
+                    .and_then(|info| info.code.as_ref())
+                    .map(|bytecode| bytecode.is_eip7702())
+                    .unwrap_or(false);
+
+                // Check if current code is empty (delegation cleared)
+                let code_now_empty =
+                    acc.info.as_ref().map(|info| info.code_hash == KECCAK_EMPTY).unwrap_or(false);
+
+                original_was_eip7702 && code_now_empty
+            })
+            .count();
+
+        // Get cache statistics for detailed block logging
+        let (account_cache_hits, account_cache_misses) = cache_stats
+            .as_ref()
+            .map(|s| (s.account_hits(), s.account_misses()))
+            .unwrap_or_default();
+        let (storage_cache_hits, storage_cache_misses) = cache_stats
+            .as_ref()
+            .map(|s| (s.storage_hits(), s.storage_misses()))
+            .unwrap_or_default();
+        let (code_cache_hits, code_cache_misses) =
+            cache_stats.as_ref().map(|s| (s.code_hits(), s.code_misses())).unwrap_or_default();
+
+        // Build execution timing stats for detailed block logging
+        Box::new(ExecutionTimingStats {
+            block_number: block.number(),
+            block_hash: block.hash(),
+            gas_used: output.result.gas_used,
+            tx_count: block.transaction_count(),
+            execution_duration,
+            state_read_duration,
+            state_hash_duration,
+            accounts_read,
+            storage_read,
+            code_read,
+            code_bytes_read,
+            accounts_changed,
+            accounts_deleted,
+            storage_slots_changed,
+            storage_slots_deleted,
+            bytecodes_changed,
+            code_bytes_written,
+            eip7702_delegations_set,
+            eip7702_delegations_cleared,
+            account_cache_hits,
+            account_cache_misses,
+            storage_cache_hits,
+            storage_cache_misses,
+            code_cache_hits,
+            code_cache_misses,
+        })
+    }
+}
 
 /// Strategy describing how to compute the state root.
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]

crates/engine/tree/src/tree/persistence_state.rs

@@ -20,6 +20,7 @@
 //! The [`PersistenceState`] tracks ongoing persistence operations and coordinates
 //! between the main execution thread and background persistence workers.
 
+use crate::persistence::PersistenceResult;
 use alloy_eips::BlockNumHash;
 use alloy_primitives::B256;
 use crossbeam_channel::Receiver as CrossbeamReceiver;
@@ -36,7 +37,7 @@ pub struct PersistenceState {
     /// Receiver end of channel where the result of the persistence task will be
     /// sent when done. A None value means there's no persistence task in progress.
     pub(crate) rx:
-        Option<(CrossbeamReceiver<Option<BlockNumHash>>, Instant, CurrentPersistenceAction)>,
+        Option<(CrossbeamReceiver<PersistenceResult>, Instant, CurrentPersistenceAction)>,
 }
 
 impl PersistenceState {
@@ -50,7 +51,7 @@ impl PersistenceState {
     pub(crate) fn start_remove(
         &mut self,
         new_tip_num: u64,
-        rx: CrossbeamReceiver<Option<BlockNumHash>>,
+        rx: CrossbeamReceiver<PersistenceResult>,
     ) {
         self.rx =
             Some((rx, Instant::now(), CurrentPersistenceAction::RemovingBlocks { new_tip_num }));
@@ -60,7 +61,7 @@ impl PersistenceState {
     pub(crate) fn start_save(
         &mut self,
         highest: BlockNumHash,
-        rx: CrossbeamReceiver<Option<BlockNumHash>>,
+        rx: CrossbeamReceiver<PersistenceResult>,
     ) {
         self.rx = Some((rx, Instant::now(), CurrentPersistenceAction::SavingBlocks { highest }));
     }

crates/engine/tree/src/tree/precompile_cache.rs

@@ -1,6 +1,9 @@
 //! Contains a precompile cache backed by `schnellru::LruMap` (LRU by length).
 
-use alloy_primitives::Bytes;
+use alloy_primitives::{
+    map::{DefaultHashBuilder, FbBuildHasher},
+    Bytes,
+};
 use moka::policy::EvictionPolicy;
 use reth_evm::precompiles::{DynPrecompile, Precompile, PrecompileInput};
 use reth_primitives_traits::dashmap::DashMap;
@@ -13,7 +16,7 @@ const MAX_CACHE_SIZE: u32 = 10_000;
 
 /// Stores caches for each precompile.
 #[derive(Debug, Clone, Default)]
-pub struct PrecompileCacheMap<S>(Arc<DashMap<Address, PrecompileCache<S>>>)
+pub struct PrecompileCacheMap<S>(Arc<DashMap<Address, PrecompileCache<S>, FbBuildHasher<20>>>)
 where
     S: Eq + Hash + std::fmt::Debug + Send + Sync + Clone + 'static;
 
@@ -37,9 +40,7 @@ where
 
 /// Cache for precompiles, for each input stores the result.
 #[derive(Debug, Clone)]
-pub struct PrecompileCache<S>(
-    moka::sync::Cache<Bytes, CacheEntry<S>, alloy_primitives::map::DefaultHashBuilder>,
-)
+pub struct PrecompileCache<S>(moka::sync::Cache<Bytes, CacheEntry<S>, DefaultHashBuilder>)
 where
     S: Eq + Hash + std::fmt::Debug + Send + Sync + Clone + 'static;
 
@@ -168,11 +169,11 @@ where
     }
 
     fn call(&self, input: PrecompileInput<'_>) -> PrecompileResult {
-        if let Some(entry) = &self.cache.get(input.data, self.spec_id.clone()) {
+        if let Some(entry) = &self.cache.get(input.data, self.spec_id.clone()) &&
+            input.gas >= entry.gas_used()
+        {
             self.increment_by_one_precompile_cache_hits();
-            if input.gas >= entry.gas_used() {
-                return entry.to_precompile_result()
-            }
+            return entry.to_precompile_result()
         }
 
         let calldata = input.data;