perf(engine): gate sparse trie rayon fanout for small workloads

Amp-Thread-ID: https://ampcode.com/threads/T-019c7a7d-2f47-7569-a4d4-9316d84790be

.changelog/brave-dogs-fly.md

@@ -0,0 +1,10 @@
+---
+reth-engine-primitives: patch
+reth-engine-tree: patch
+reth-node-core: patch
+reth-trie-parallel: minor
+---
+
+Removed legacy proof calculation system and V2-specific configuration flags.
+
+Removed the legacy (non-V2) proof calculation code paths, simplified multiproof task architecture by removing the dual-mode system, and cleaned up V2-specific CLI flags (`--engine.disable-proof-v2`, `--engine.disable-trie-cache`) that are no longer needed. The codebase now exclusively uses V2 proofs with the sparse trie cache.

.changelog/calm-clams-buzz.md

@@ -0,0 +1,5 @@
+---
+reth-trie-sparse: patch
+---
+
+Refactored sparse trie node state tracking to use RLP nodes instead of hashes. Replaced `Option<B256>` hash fields with `SparseNodeState` enum that tracks either dirty nodes or cached RLP nodes with optional database storage flags. Added debug assertions to validate leaf path lengths and improved pruning logic to use node paths directly instead of path-hash tuples.

.changelog/dull-koalas-play.md

@@ -0,0 +1,5 @@
+---
+reth-trie-sparse: patch
+---
+
+Added recording of `SetRoot` operation in `ParallelSparseTrie::set_root` when the `trie-debug` feature is enabled.

.changelog/evil-fish-smile.md

@@ -0,0 +1,6 @@
+---
+reth-rpc-convert: minor
+reth-storage-rpc-provider: minor
+---
+
+Replaced the separate `TryFromBlockResponse`, `TryFromReceiptResponse`, and `TryFromTransactionResponse` traits with a unified `RpcResponseConverter` trait and default `EthRpcConverter` implementation. Removed the `op-alloy-network` dependency and refactored `RpcBlockchainProvider` to store a dynamic converter instance instead of relying on per-type trait bounds.

.changelog/fast-seals-play.md

@@ -0,0 +1,5 @@
+---
+reth-transaction-pool: minor
+---
+
+Added `consensus_ref` method to `PoolTransaction` trait for borrowing consensus transactions without cloning.

.changelog/fix-simulate-revert-code.md

@@ -0,0 +1,5 @@
+---
+reth-rpc-eth-types: patch
+---
+
+Updated `eth_simulateV1` revert error code from `-32000` to `3` to be consistent with `eth_call`, per [execution-apis#748](https://github.com/ethereum/execution-apis/pull/748).

.changelog/keen-geese-bake.md

@@ -0,0 +1,5 @@
+---
+reth-engine-tree: patch
+---
+
+Added sub-phase timing histograms to the sparse trie event loop, tracking channel wait, proof coalescing, multiproof reveal, and trie update durations separately.

.changelog/merry-koalas-nod.md

@@ -0,0 +1,6 @@
+---
+reth-rpc-eth-api: minor
+reth-rpc-server-types: minor
+---
+
+Added `eth_getStorageValues` RPC method for batch storage slot retrieval across multiple addresses.

.changelog/odd-donkeys-chirp.md

@@ -0,0 +1,5 @@
+---
+reth-engine-tree: patch
+---
+
+Fixed `compare_trie_updates` to return `bool` indicating whether differences were found, and updated the caller to properly use the return value instead of treating all successful comparisons as having no differences.

.changelog/odd-snails-play.md

@@ -0,0 +1,5 @@
+---
+reth-node-core: minor
+---
+
+Added `with_dev_block_time` helper method to `NodeConfig` for configuring dev miner block production interval.

.changelog/proud-crabs-bark.md

@@ -0,0 +1,5 @@
+---
+reth-db-api: patch
+---
+
+Changed `StoredNibblesSubKey` encoding to use a stack-allocated `[u8; 65]` array instead of a heap-allocated `Vec<u8>`, avoiding unnecessary heap allocation.

.changelog/proud-wolves-spin.md

@@ -0,0 +1,5 @@
+---
+reth-storage-api: patch
+---
+
+Added `Arc` to `auto_impl` derive for storage-api traits to support automatic `Arc` wrapper implementations.

.changelog/quick-mice-jump.md

@@ -0,0 +1,8 @@
+---
+reth: patch
+reth-engine-tree: patch
+reth-node-builder: patch
+reth-trie-sparse: minor
+---
+
+Added `trie-debug` feature for recording sparse trie mutations to aid in debugging state root mismatches.

.changelog/rich-lakes-bark.md

@@ -0,0 +1,5 @@
+---
+reth-provider: patch
+---
+
+Fixed sender pruning during block reorg to skip when sender_recovery is fully pruned, preventing a fatal crash when no sender data exists in static files.

.changelog/warm-donkeys-dry.md

@@ -0,0 +1,6 @@
+---
+reth-engine-local: minor
+reth-node-builder: minor
+---
+
+Added trigger-based `MiningMode` variant that allows blocks to be built on-demand via custom streams, and exposed `with_mining_mode` method on `DebugNodeLauncherFuture` to override default mining configuration.

.changelog/warm-pandas-cook.md

@@ -0,0 +1,5 @@
+---
+reth-transaction-pool: patch
+---
+
+Fixed a bug where transactions from the same sender were added to the pending subpool out of nonce order. Ensured `process_updates` runs before `add_new_transaction` so that lower-nonce promotions are enqueued before the newly inserted higher-nonce transaction, preserving correct ordering for live `BestTransactions` iterators.

.config/nextest.toml

@@ -1,6 +1,6 @@
 [profile.default]
 retries = { backoff = "exponential", count = 2, delay = "2s", jitter = true }
-slow-timeout = { period = "30s", terminate-after = 4 }
+slow-timeout = { period = "30s", terminate-after = 2 }
 
 [[profile.default.overrides]]
 filter = "test(general_state_tests)"

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

@@ -0,0 +1,99 @@
+#!/usr/bin/env bash
+#
+# Builds (or fetches from cache) reth binaries for benchmarking.
+#
+# Usage: bench-reth-build.sh <baseline|feature> <source-dir> <commit> [branch-sha]
+#
+#   baseline — build/fetch the baseline binary at <commit> (merge-base)
+#              source-dir must be checked out at <commit>
+#   feature  — build/fetch the candidate binary + reth-bench at <commit>
+#              source-dir must be checked out at <commit>
+#              optional branch-sha is the PR head commit for cache key
+#
+# Outputs:
+#   baseline: <source-dir>/target/profiling/reth
+#   feature:  <source-dir>/target/profiling/reth, reth-bench installed to cargo bin
+#
+# Required: mc (MinIO client) configured at /home/ubuntu/.mc
+set -euo pipefail
+
+MC="mc --config-dir /home/ubuntu/.mc"
+MODE="$1"
+SOURCE_DIR="$2"
+COMMIT="$3"
+
+# Verify a cached reth binary was built from the expected commit.
+# `reth --version` outputs "Commit SHA: <full-sha>" on its own line.
+verify_binary() {
+  local binary="$1" expected_commit="$2"
+  local version binary_sha
+  version=$("$binary" --version 2>/dev/null) || return 1
+  binary_sha=$(echo "$version" | sed -n 's/^Commit SHA: *//p')
+  if [ -z "$binary_sha" ]; then
+    echo "Warning: could not extract commit SHA from version output"
+    return 1
+  fi
+  if [ "$binary_sha" = "$expected_commit" ]; then
+    return 0
+  fi
+  echo "Cache mismatch: binary built from ${binary_sha} but expected ${expected_commit}"
+  return 1
+}
+
+case "$MODE" in
+  baseline|main)
+    BUCKET="minio/reth-binaries/${COMMIT}"
+    mkdir -p "${SOURCE_DIR}/target/profiling"
+
+    CACHE_VALID=false
+    if $MC stat "${BUCKET}/reth" &>/dev/null; then
+      echo "Cache hit for baseline (${COMMIT}), downloading binary..."
+      $MC cp "${BUCKET}/reth" "${SOURCE_DIR}/target/profiling/reth"
+      chmod +x "${SOURCE_DIR}/target/profiling/reth"
+      if verify_binary "${SOURCE_DIR}/target/profiling/reth" "${COMMIT}"; then
+        CACHE_VALID=true
+      else
+        echo "Cached baseline binary is stale, rebuilding..."
+      fi
+    fi
+    if [ "$CACHE_VALID" = false ]; then
+      echo "Building baseline (${COMMIT}) from source..."
+      cd "${SOURCE_DIR}"
+      cargo build --profile profiling --bin reth
+      $MC cp target/profiling/reth "${BUCKET}/reth"
+    fi
+    ;;
+
+  feature|branch)
+    BRANCH_SHA="${4:-$COMMIT}"
+    BUCKET="minio/reth-binaries/${BRANCH_SHA}"
+
+    CACHE_VALID=false
+    if $MC stat "${BUCKET}/reth" &>/dev/null && $MC stat "${BUCKET}/reth-bench" &>/dev/null; then
+      echo "Cache hit for ${BRANCH_SHA}, downloading binaries..."
+      mkdir -p "${SOURCE_DIR}/target/profiling"
+      $MC cp "${BUCKET}/reth" "${SOURCE_DIR}/target/profiling/reth"
+      $MC cp "${BUCKET}/reth-bench" /home/ubuntu/.cargo/bin/reth-bench
+      chmod +x "${SOURCE_DIR}/target/profiling/reth" /home/ubuntu/.cargo/bin/reth-bench
+      if verify_binary "${SOURCE_DIR}/target/profiling/reth" "${COMMIT}"; then
+        CACHE_VALID=true
+      else
+        echo "Cached feature binary is stale, rebuilding..."
+      fi
+    fi
+    if [ "$CACHE_VALID" = false ]; then
+      echo "Building feature (${COMMIT}) from source..."
+      cd "${SOURCE_DIR}"
+      rustup show active-toolchain || rustup default stable
+      make profiling
+      make install-reth-bench
+      $MC cp target/profiling/reth "${BUCKET}/reth"
+      $MC cp "$(which reth-bench)" "${BUCKET}/reth-bench"
+    fi
+    ;;
+
+  *)
+    echo "Usage: $0 <baseline|feature> <source-dir> <commit> [branch-sha]"
+    exit 1
+    ;;
+esac

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

@@ -0,0 +1,258 @@
+#!/usr/bin/env python3
+"""Generate benchmark charts from reth-bench CSV output.
+
+Usage:
+    bench-engine-charts.py <combined_csv> --output-dir <dir> [--baseline <baseline_csv>]
+
+Generates three PNG charts:
+  1. newPayload latency + Ggas/s per block (+ latency diff when baseline present)
+  2. Wait breakdown (persistence, execution cache, sparse trie) per block
+  3. Scatter plot of gas used vs latency
+
+When --baseline is provided, charts overlay both datasets for comparison.
+"""
+
+import argparse
+import csv
+import sys
+from pathlib import Path
+
+import numpy as np
+
+try:
+    import matplotlib
+
+    matplotlib.use("Agg")
+    import matplotlib.pyplot as plt
+except ImportError:
+    print("matplotlib is required: pip install matplotlib", file=sys.stderr)
+    sys.exit(1)
+
+GIGAGAS = 1_000_000_000
+
+
+def parse_combined_csv(path: str) -> list[dict]:
+    rows = []
+    with open(path) as f:
+        reader = csv.DictReader(f)
+        for row in reader:
+            rows.append(
+                {
+                    "block_number": int(row["block_number"]),
+                    "gas_used": int(row["gas_used"]),
+                    "new_payload_latency_us": int(row["new_payload_latency"]),
+                    "persistence_wait_us": int(row["persistence_wait"])
+                    if row.get("persistence_wait")
+                    else None,
+                    "execution_cache_wait_us": int(row.get("execution_cache_wait", 0)),
+                    "sparse_trie_wait_us": int(row.get("sparse_trie_wait", 0)),
+                }
+            )
+    return rows
+
+
+def plot_latency_and_throughput(
+    feature: list[dict], baseline: list[dict] | None, out: Path,
+    baseline_name: str = "baseline", feature_name: str = "feature",
+):
+    num_plots = 3 if baseline else 2
+    fig, axes = plt.subplots(num_plots, 1, figsize=(12, 4 * num_plots), sharex=True)
+    ax1, ax2 = axes[0], axes[1]
+
+    feat_x = [r["block_number"] for r in feature]
+    feat_lat = [r["new_payload_latency_us"] / 1_000 for r in feature]
+    feat_ggas = []
+    for r in feature:
+        lat_s = r["new_payload_latency_us"] / 1_000_000
+        feat_ggas.append(r["gas_used"] / lat_s / GIGAGAS if lat_s > 0 else 0)
+
+    if baseline:
+        base_x = [r["block_number"] for r in baseline]
+        base_lat = [r["new_payload_latency_us"] / 1_000 for r in baseline]
+        base_ggas = []
+        for r in baseline:
+            lat_s = r["new_payload_latency_us"] / 1_000_000
+            base_ggas.append(r["gas_used"] / lat_s / GIGAGAS if lat_s > 0 else 0)
+        ax1.plot(base_x, base_lat, linewidth=0.8, label=baseline_name, alpha=0.7)
+        ax2.plot(base_x, base_ggas, linewidth=0.8, label=baseline_name, alpha=0.7)
+
+    ax1.plot(feat_x, feat_lat, linewidth=0.8, label=feature_name)
+    ax1.set_ylabel("Latency (ms)")
+    ax1.set_title("newPayload Latency per Block")
+    ax1.grid(True, alpha=0.3)
+    if baseline:
+        ax1.legend()
+
+    ax2.plot(feat_x, feat_ggas, linewidth=0.8, label=feature_name)
+    ax2.set_ylabel("Ggas/s")
+    ax2.set_title("Execution Throughput per Block")
+    ax2.grid(True, alpha=0.3)
+    if baseline:
+        ax2.legend()
+
+    if baseline:
+        ax3 = axes[2]
+        base_by_block = {r["block_number"]: r["new_payload_latency_us"] for r in baseline}
+        blocks, diffs = [], []
+        for r in feature:
+            bn = r["block_number"]
+            if bn in base_by_block and base_by_block[bn] > 0:
+                pct = (r["new_payload_latency_us"] - base_by_block[bn]) / base_by_block[bn] * 100
+                blocks.append(bn)
+                diffs.append(pct)
+        if blocks:
+            colors = ["green" if d <= 0 else "red" for d in diffs]
+            ax3.bar(blocks, diffs, width=1.0, color=colors, alpha=0.7, edgecolor="none")
+            ax3.axhline(0, color="black", linewidth=0.5)
+        ax3.set_ylabel("Δ Latency (%)")
+        ax3.set_title("Per-Block newPayload Latency Change (feature vs baseline)")
+        ax3.grid(True, alpha=0.3, axis="y")
+
+    axes[-1].set_xlabel("Block Number")
+    fig.tight_layout()
+    fig.savefig(out, dpi=150)
+    plt.close(fig)
+
+
+def plot_wait_breakdown(
+    feature: list[dict], baseline: list[dict] | None, out: Path,
+    baseline_name: str = "baseline", feature_name: str = "feature",
+):
+    series = [
+        ("Persistence Wait", "persistence_wait_us"),
+        ("State Cache Wait", "execution_cache_wait_us"),
+        ("Trie Cache Wait", "sparse_trie_wait_us"),
+    ]
+
+    fig, axes = plt.subplots(len(series), 1, figsize=(12, 3 * len(series)), sharex=True)
+    for ax, (label, key) in zip(axes, series):
+        if baseline:
+            bx = [r["block_number"] for r in baseline if r[key] is not None]
+            by = [r[key] / 1_000 for r in baseline if r[key] is not None]
+            if bx:
+                ax.plot(bx, by, linewidth=0.8, label=baseline_name, alpha=0.7)
+
+        fx = [r["block_number"] for r in feature if r[key] is not None]
+        fy = [r[key] / 1_000 for r in feature if r[key] is not None]
+        if fx:
+            ax.plot(fx, fy, linewidth=0.8, label=feature_name)
+
+        ax.set_ylabel("ms")
+        ax.set_title(label)
+        ax.grid(True, alpha=0.3)
+        if baseline:
+            ax.legend()
+
+    axes[-1].set_xlabel("Block Number")
+    fig.suptitle("Wait Time Breakdown per Block", fontsize=14, y=1.01)
+    fig.tight_layout()
+    fig.savefig(out, dpi=150, bbox_inches="tight")
+    plt.close(fig)
+
+
+def _add_regression(ax, x, y, color, label):
+    """Add a linear regression line to the axes."""
+    if len(x) < 2:
+        return
+    xa, ya = np.array(x), np.array(y)
+    m, b = np.polyfit(xa, ya, 1)
+    x_range = np.linspace(xa.min(), xa.max(), 100)
+    ax.plot(x_range, m * x_range + b, color=color, linewidth=1.5, alpha=0.8,
+            label=label)
+
+
+def plot_gas_vs_latency(
+    feature: list[dict], baseline: list[dict] | None, out: Path,
+    baseline_name: str = "baseline", feature_name: str = "feature",
+):
+    fig, ax = plt.subplots(figsize=(8, 6))
+
+    if baseline:
+        bgas = [r["gas_used"] / 1_000_000 for r in baseline]
+        blat = [r["new_payload_latency_us"] / 1_000 for r in baseline]
+        ax.scatter(bgas, blat, s=8, alpha=0.5)
+        _add_regression(ax, bgas, blat, "tab:blue", baseline_name)
+
+    fgas = [r["gas_used"] / 1_000_000 for r in feature]
+    flat = [r["new_payload_latency_us"] / 1_000 for r in feature]
+    ax.scatter(fgas, flat, s=8, alpha=0.6)
+    _add_regression(ax, fgas, flat, "tab:orange", feature_name)
+
+    ax.set_xlabel("Gas Used (Mgas)")
+    ax.set_ylabel("newPayload Latency (ms)")
+    ax.set_title("Gas Used vs Latency")
+    ax.grid(True, alpha=0.3)
+    ax.legend()
+    fig.tight_layout()
+    fig.savefig(out, dpi=150)
+    plt.close(fig)
+
+
+def merge_csvs(paths: list[str]) -> list[dict]:
+    """Parse and merge multiple CSVs, averaging values for duplicate blocks."""
+    by_block: dict[int, list[dict]] = {}
+    for path in paths:
+        for row in parse_combined_csv(path):
+            by_block.setdefault(row["block_number"], []).append(row)
+
+    merged = []
+    for bn in sorted(by_block):
+        rows = by_block[bn]
+        if len(rows) == 1:
+            merged.append(rows[0])
+        else:
+            avg = {"block_number": bn}
+            for key in ("gas_used", "new_payload_latency_us"):
+                avg[key] = int(sum(r[key] for r in rows) / len(rows))
+            for key in ("persistence_wait_us", "execution_cache_wait_us", "sparse_trie_wait_us"):
+                vals = [r[key] for r in rows if r[key] is not None]
+                avg[key] = int(sum(vals) / len(vals)) if vals else None
+            merged.append(avg)
+    return merged
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Generate benchmark charts")
+    parser.add_argument(
+        "--feature", nargs="+", required=True,
+        help="Path(s) to feature combined_latency.csv",
+    )
+    parser.add_argument(
+        "--output-dir", required=True, help="Output directory for PNG charts"
+    )
+    parser.add_argument(
+        "--baseline", nargs="+", help="Path(s) to baseline combined_latency.csv"
+    )
+    parser.add_argument("--baseline-name", default="baseline", help="Label for baseline")
+    parser.add_argument("--feature-name", "--branch-name", default="feature", help="Label for feature")
+    args = parser.parse_args()
+
+    feature = merge_csvs(args.feature)
+    if not feature:
+        print("No results found in feature CSV(s)", file=sys.stderr)
+        sys.exit(1)
+
+    baseline = None
+    if args.baseline:
+        baseline = merge_csvs(args.baseline)
+        if not baseline:
+            print(
+                "Warning: no results in baseline CSV(s), skipping comparison",
+                file=sys.stderr,
+            )
+            baseline = None
+
+    out_dir = Path(args.output_dir)
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    bname = args.baseline_name
+    fname = args.feature_name
+    plot_latency_and_throughput(feature, baseline, out_dir / "latency_throughput.png", bname, fname)
+    plot_wait_breakdown(feature, baseline, out_dir / "wait_breakdown.png", bname, fname)
+    plot_gas_vs_latency(feature, baseline, out_dir / "gas_vs_latency.png", bname, fname)
+
+    print(f"Charts written to {out_dir}")
+
+
+if __name__ == "__main__":
+    main()

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

@@ -0,0 +1,103 @@
+#!/usr/bin/env bash
+#
+# Runs a single reth-bench cycle: mount snapshot → start node → warmup →
+# benchmark → stop node → recover snapshot.
+#
+# Usage: bench-reth-run.sh <label> <binary> <output-dir>
+#
+# Required env: SCHELK_MOUNT, BENCH_RPC_URL, BENCH_BLOCKS, BENCH_WARMUP_BLOCKS
+set -euo pipefail
+
+LABEL="$1"
+BINARY="$2"
+OUTPUT_DIR="$3"
+DATADIR="$SCHELK_MOUNT/datadir"
+mkdir -p "$OUTPUT_DIR"
+LOG="${OUTPUT_DIR}/node.log"
+
+cleanup() {
+  kill "$TAIL_PID" 2>/dev/null || true
+  if [ -n "${RETH_PID:-}" ] && sudo kill -0 "$RETH_PID" 2>/dev/null; then
+    sudo kill "$RETH_PID"
+    for i in $(seq 1 30); do
+      sudo kill -0 "$RETH_PID" 2>/dev/null || break
+      sleep 1
+    done
+    sudo kill -9 "$RETH_PID" 2>/dev/null || true
+    sleep 1
+  fi
+  if mountpoint -q "$SCHELK_MOUNT"; then
+    sudo umount -l "$SCHELK_MOUNT" || true
+    sudo schelk recover -y || true
+  fi
+}
+TAIL_PID=
+trap cleanup EXIT
+
+# Mount
+sudo schelk mount -y
+sync
+sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'
+echo "=== Cache state after drop ==="
+free -h
+grep Cached /proc/meminfo
+
+# Start reth
+# CPU layout: core 0 = OS/IRQs/reth-bench/aux, cores 1+ = reth node
+RETH_BENCH="$(which reth-bench)"
+ONLINE=$(nproc --all)
+RETH_CPUS="1-$(( ONLINE - 1 ))"
+sudo taskset -c "$RETH_CPUS" nice -n -20 "$BINARY" node \
+  --datadir "$DATADIR" \
+  --engine.accept-execution-requests-hash \
+  --http \
+  --http.port 8545 \
+  --ws \
+  --ws.api all \
+  --authrpc.port 8551 \
+  --disable-discovery \
+  --no-persist-peers \
+  > "$LOG" 2>&1 &
+
+RETH_PID=$!
+stdbuf -oL tail -f "$LOG" | sed -u "s/^/[reth] /" &
+TAIL_PID=$!
+
+for i in $(seq 1 60); do
+  if curl -sf http://127.0.0.1:8545 -X POST \
+    -H 'Content-Type: application/json' \
+    -d '{"jsonrpc":"2.0","method":"eth_blockNumber","params":[],"id":1}' \
+    > /dev/null 2>&1; then
+    echo "reth (${LABEL}) is ready after ${i}s"
+    break
+  fi
+  if [ "$i" -eq 60 ]; then
+    echo "::error::reth (${LABEL}) failed to start within 60s"
+    cat "$LOG"
+    exit 1
+  fi
+  sleep 1
+done
+
+# Run reth-bench with high priority but as the current user so output
+# 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] /"
+
+# 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] /"
+
+# cleanup runs via trap

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

@@ -0,0 +1,127 @@
+#!/usr/bin/env bash
+#
+# Downloads the latest nightly snapshot into the schelk volume with
+# progress reporting to the GitHub PR comment.
+#
+# Skips the download if the local ETag marker matches the remote one.
+#
+# Usage: bench-reth-snapshot.sh [--check]
+#   --check   Only check if a download is needed; exits 0 if up-to-date, 1 if not.
+#
+# Required env:
+#   SCHELK_MOUNT       – schelk mount point (e.g. /reth-bench)
+#   GITHUB_TOKEN       – token for GitHub API calls (only for download)
+#   BENCH_COMMENT_ID   – PR comment ID to update (optional)
+#   BENCH_REPO         – owner/repo (e.g. paradigmxyz/reth)
+#   BENCH_JOB_URL      – link to the Actions job
+#   BENCH_ACTOR        – user who triggered the benchmark
+#   BENCH_CONFIG       – config summary line
+set -euo pipefail
+
+BUCKET="minio/reth-snapshots/reth-1-minimal-nightly-previous.tar.zst"
+DATADIR="$SCHELK_MOUNT/datadir"
+ETAG_FILE="$HOME/.reth-bench-snapshot-etag"
+
+# Get remote metadata via JSON for reliable parsing
+MC_STAT=$(mc stat --json "$BUCKET" 2>/dev/null || true)
+REMOTE_ETAG=$(echo "$MC_STAT" | jq -r '.etag // empty')
+if [ -z "$REMOTE_ETAG" ]; then
+  echo "::warning::Failed to get ETag from mc stat, will re-download"
+  REMOTE_ETAG="unknown-$(date +%s)"
+fi
+
+LOCAL_ETAG=""
+[ -f "$ETAG_FILE" ] && LOCAL_ETAG=$(cat "$ETAG_FILE")
+
+if [ "$REMOTE_ETAG" = "$LOCAL_ETAG" ]; then
+  echo "Snapshot is up-to-date (ETag: ${REMOTE_ETAG})"
+  if [ "${1:-}" = "--check" ]; then
+    exit 0
+  fi
+  exit 0
+fi
+
+echo "Snapshot needs update (local: ${LOCAL_ETAG:-<none>}, remote: ${REMOTE_ETAG})"
+if [ "${1:-}" = "--check" ]; then
+  exit 1
+fi
+
+# Get compressed size for progress tracking
+TOTAL_BYTES=$(echo "$MC_STAT" | jq -r '.size // empty')
+if [ -z "$TOTAL_BYTES" ] || [ "$TOTAL_BYTES" = "0" ]; then
+  echo "::error::Failed to get snapshot size from mc stat"
+  exit 1
+fi
+echo "Snapshot size: $TOTAL_BYTES bytes ($(numfmt --to=iec "$TOTAL_BYTES"))"
+
+# Prepare mount
+mountpoint -q "$SCHELK_MOUNT" && sudo schelk recover -y || true
+sudo schelk mount -y
+sudo rm -rf "$DATADIR"
+sudo mkdir -p "$DATADIR"
+
+update_comment() {
+  local pct="$1"
+  [ -z "${BENCH_COMMENT_ID:-}" ] && return 0
+  local status="Building binaries & downloading snapshot… ${pct}%"
+  local body
+  body="$(printf 'cc @%s\n\n🚀 Benchmark started! [View job](%s)\n\n⏳ **Status:** %s\n\n%s' \
+    "$BENCH_ACTOR" "$BENCH_JOB_URL" "$status" "$BENCH_CONFIG")"
+  curl -sf -X PATCH \
+    -H "Authorization: token ${GITHUB_TOKEN}" \
+    -H "Accept: application/vnd.github.v3+json" \
+    "https://api.github.com/repos/${BENCH_REPO}/issues/comments/${BENCH_COMMENT_ID}" \
+    -d "$(jq -nc --arg body "$body" '{body: $body}')" \
+    > /dev/null 2>&1 || true
+}
+
+# Track compressed bytes flowing through the pipe
+DL_BYTES_FILE=$(mktemp)
+echo 0 > "$DL_BYTES_FILE"
+
+# Start progress reporter in background
+(
+  while true; do
+    sleep 10
+    CURRENT=$(cat "$DL_BYTES_FILE" 2>/dev/null || echo 0)
+    if [ "$TOTAL_BYTES" -gt 0 ]; then
+      PCT=$(( CURRENT * 100 / TOTAL_BYTES ))
+      [ "$PCT" -gt 100 ] && PCT=100
+      echo "Snapshot download: $(numfmt --to=iec "$CURRENT") / $(numfmt --to=iec "$TOTAL_BYTES") (${PCT}%)"
+      update_comment "$PCT"
+    fi
+  done
+) &
+PROGRESS_PID=$!
+trap 'kill $PROGRESS_PID 2>/dev/null || true; rm -f "$DL_BYTES_FILE"' EXIT
+
+# Download and extract; python byte counter tracks compressed bytes received
+mc cat "$BUCKET" | python3 -c "
+import sys
+count = 0
+while True:
+    data = sys.stdin.buffer.read(1048576)
+    if not data:
+        break
+    count += len(data)
+    sys.stdout.buffer.write(data)
+    with open('$DL_BYTES_FILE', 'w') as f:
+        f.write(str(count))
+" | pzstd -d -p 6 | sudo tar -xf - -C "$DATADIR"
+
+# Stop progress reporter
+kill $PROGRESS_PID 2>/dev/null || true
+wait $PROGRESS_PID 2>/dev/null || true
+
+update_comment "100"
+echo "Snapshot download complete"
+
+# Promote the new snapshot to become the schelk baseline (virgin volume).
+# This copies changed blocks from scratch → virgin so that future
+# `schelk recover` calls restore to this new state.
+sync
+sudo schelk promote -y
+
+# Save ETag marker
+echo "$REMOTE_ETAG" > "$ETAG_FILE"
+echo "Snapshot promoted to schelk baseline (ETag: ${REMOTE_ETAG})"

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

@@ -0,0 +1,504 @@
+#!/usr/bin/env python3
+"""Parse reth-bench CSV output and generate a summary JSON + markdown comparison.
+
+Usage:
+    bench-reth-summary.py <combined_csv> <gas_csv> \
+        --output-summary <summary.json> \
+        --output-markdown <comment.md> \
+        --baseline-csv <baseline_combined.csv> \
+        [--repo <owner/repo>] \
+        [--baseline-ref <sha>] \
+        [--feature-name <name>] \
+        [--feature-sha <sha>]
+
+Generates a paired statistical comparison between baseline and feature.
+Matches blocks by number and computes per-block diffs to cancel out gas
+variance. Fails if baseline or feature CSV is missing or empty.
+"""
+
+import argparse
+import csv
+import json
+import math
+import random
+import sys
+
+GIGAGAS = 1_000_000_000
+T_CRITICAL = 1.96  # two-tailed 95% confidence
+BOOTSTRAP_ITERATIONS = 10_000
+
+
+def _opt_int(row: dict, key: str) -> int | None:
+    """Return int value for a CSV field, or None if missing/empty."""
+    v = row.get(key)
+    if v is None or v == "":
+        return None
+    return int(v)
+
+
+def parse_combined_csv(path: str) -> list[dict]:
+    """Parse combined_latency.csv into a list of per-block dicts."""
+    rows = []
+    with open(path) as f:
+        reader = csv.DictReader(f)
+        for row in reader:
+            rows.append(
+                {
+                    "block_number": int(row["block_number"]),
+                    "gas_used": int(row["gas_used"]),
+                    "gas_limit": int(row["gas_limit"]),
+                    "transaction_count": int(row["transaction_count"]),
+                    "new_payload_latency_us": int(row["new_payload_latency"]),
+                    "fcu_latency_us": int(row["fcu_latency"]),
+                    "total_latency_us": int(row["total_latency"]),
+                    "persistence_wait_us": _opt_int(row, "persistence_wait"),
+                    "execution_cache_wait_us": _opt_int(row, "execution_cache_wait"),
+                    "sparse_trie_wait_us": _opt_int(row, "sparse_trie_wait"),
+                }
+            )
+    return rows
+
+
+def parse_gas_csv(path: str) -> list[dict]:
+    """Parse total_gas.csv into a list of per-block dicts."""
+    rows = []
+    with open(path) as f:
+        reader = csv.DictReader(f)
+        for row in reader:
+            rows.append(
+                {
+                    "block_number": int(row["block_number"]),
+                    "gas_used": int(row["gas_used"]),
+                    "time_us": int(row["time"]),
+                }
+            )
+    return rows
+
+
+def stddev(values: list[float], mean: float) -> float:
+    if len(values) < 2:
+        return 0.0
+    return math.sqrt(sum((v - mean) ** 2 for v in values) / (len(values) - 1))
+
+
+def percentile(sorted_vals: list[float], pct: int) -> float:
+    if not sorted_vals:
+        return 0.0
+    idx = int(len(sorted_vals) * pct / 100)
+    idx = min(idx, len(sorted_vals) - 1)
+    return sorted_vals[idx]
+
+
+def compute_stats(combined: list[dict]) -> dict:
+    """Compute per-run statistics from parsed CSV data."""
+    n = len(combined)
+    if n == 0:
+        return {}
+
+    latencies_ms = [r["new_payload_latency_us"] / 1_000 for r in combined]
+    sorted_lat = sorted(latencies_ms)
+    mean_lat = sum(latencies_ms) / n
+    std_lat = stddev(latencies_ms, mean_lat)
+
+    mgas_s_values = []
+    for r in combined:
+        lat_s = r["new_payload_latency_us"] / 1_000_000
+        if lat_s > 0:
+            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
+
+    return {
+        "n": n,
+        "mean_ms": mean_lat,
+        "stddev_ms": std_lat,
+        "p50_ms": percentile(sorted_lat, 50),
+        "p90_ms": percentile(sorted_lat, 90),
+        "p99_ms": percentile(sorted_lat, 99),
+        "mean_mgas_s": mean_mgas_s,
+    }
+
+
+def compute_wait_stats(combined: list[dict], field: str) -> dict:
+    """Compute mean/p50/p95 for a wait time field (in ms)."""
+    values_ms = []
+    for r in combined:
+        v = r.get(field)
+        if v is not None:
+            values_ms.append(v / 1_000)
+    if not values_ms:
+        return {}
+    n = len(values_ms)
+    mean_val = sum(values_ms) / n
+    sorted_vals = sorted(values_ms)
+    return {
+        "mean_ms": mean_val,
+        "p50_ms": percentile(sorted_vals, 50),
+        "p95_ms": percentile(sorted_vals, 95),
+    }
+
+
+def _paired_data(
+    baseline: list[dict], feature: list[dict]
+) -> tuple[list[tuple[float, 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
+    """
+    baseline_by_block = {r["block_number"]: r for r in baseline}
+    feature_by_block = {r["block_number"]: r for r in feature}
+    common_blocks = sorted(set(baseline_by_block) & set(feature_by_block))
+
+    pairs = []
+    lat_diffs_ms = []
+    mgas_diffs = []
+    for bn in common_blocks:
+        b = baseline_by_block[bn]
+        f = feature_by_block[bn]
+        b_ms = b["new_payload_latency_us"] / 1_000
+        f_ms = f["new_payload_latency_us"] / 1_000
+        pairs.append((b_ms, f_ms))
+        lat_diffs_ms.append(f_ms - b_ms)
+        b_lat_s = b["new_payload_latency_us"] / 1_000_000
+        f_lat_s = f["new_payload_latency_us"] / 1_000_000
+        if b_lat_s > 0 and f_lat_s > 0:
+            mgas_diffs.append(
+                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
+
+
+def compute_paired_stats(
+    baseline_runs: list[list[dict]],
+    feature_runs: list[list[dict]],
+) -> dict:
+    """Compute paired statistics between baseline and feature runs.
+
+    Each pair (baseline_runs[i], feature_runs[i]) produces per-block diffs.
+    All diffs are pooled for the final CI.
+    """
+    all_pairs = []
+    all_lat_diffs = []
+    all_mgas_diffs = []
+    blocks_per_pair = []
+    for baseline, feature in zip(baseline_runs, feature_runs):
+        pairs, lat_diffs, mgas_diffs = _paired_data(baseline, feature)
+        all_pairs.extend(pairs)
+        all_lat_diffs.extend(lat_diffs)
+        all_mgas_diffs.extend(mgas_diffs)
+        blocks_per_pair.append(len(pairs))
+
+    if not all_lat_diffs:
+        return {}
+
+    n = len(all_lat_diffs)
+    mean_diff = sum(all_lat_diffs) / n
+    std_diff = stddev(all_lat_diffs, mean_diff)
+    se = std_diff / math.sqrt(n) if n > 0 else 0.0
+    ci = T_CRITICAL * se
+
+    # Bootstrap CI on difference-of-percentiles (resample paired blocks)
+    base_lats = sorted([p[0] for p in all_pairs])
+    feature_lats = sorted([p[1] for p in all_pairs])
+    p50_diff = percentile(feature_lats, 50) - percentile(base_lats, 50)
+    p90_diff = percentile(feature_lats, 90) - percentile(base_lats, 90)
+    p99_diff = percentile(feature_lats, 99) - percentile(base_lats, 99)
+
+    rng = random.Random(42)
+    p50_boot, p90_boot, p99_boot = [], [], []
+    for _ in range(BOOTSTRAP_ITERATIONS):
+        sample = rng.choices(all_pairs, k=n)
+        b_sorted = sorted(p[0] for p in sample)
+        f_sorted = sorted(p[1] for p in sample)
+        p50_boot.append(percentile(f_sorted, 50) - percentile(b_sorted, 50))
+        p90_boot.append(percentile(f_sorted, 90) - percentile(b_sorted, 90))
+        p99_boot.append(percentile(f_sorted, 99) - percentile(b_sorted, 99))
+    p50_boot.sort()
+    p90_boot.sort()
+    p99_boot.sort()
+    lo = int(BOOTSTRAP_ITERATIONS * 0.025)
+    hi = int(BOOTSTRAP_ITERATIONS * 0.975)
+
+    mean_mgas_diff = sum(all_mgas_diffs) / len(all_mgas_diffs) if all_mgas_diffs else 0.0
+    std_mgas_diff = stddev(all_mgas_diffs, mean_mgas_diff) if len(all_mgas_diffs) > 1 else 0.0
+    mgas_se = std_mgas_diff / math.sqrt(len(all_mgas_diffs)) if all_mgas_diffs else 0.0
+    mgas_ci = T_CRITICAL * mgas_se
+
+    return {
+        "n": n,
+        "mean_diff_ms": mean_diff,
+        "ci_ms": ci,
+        "p50_diff_ms": p50_diff,
+        "p50_ci_ms": (p50_boot[hi] - p50_boot[lo]) / 2,
+        "p90_diff_ms": p90_diff,
+        "p90_ci_ms": (p90_boot[hi] - p90_boot[lo]) / 2,
+        "p99_diff_ms": p99_diff,
+        "p99_ci_ms": (p99_boot[hi] - p99_boot[lo]) / 2,
+        "mean_mgas_diff": mean_mgas_diff,
+        "mgas_ci": mgas_ci,
+        "blocks": max(blocks_per_pair),
+    }
+
+
+def compute_summary(combined: list[dict], gas: list[dict]) -> dict:
+    """Compute aggregate metrics from parsed CSV data."""
+    blocks = len(combined)
+    return {
+        "blocks": blocks,
+    }
+
+
+def format_duration(seconds: float) -> str:
+    if seconds >= 60:
+        return f"{seconds / 60:.1f}min"
+    return f"{seconds}s"
+
+
+def format_gas(gas: int) -> str:
+    if gas >= GIGAGAS:
+        return f"{gas / GIGAGAS:.1f}G"
+    if gas >= 1_000_000:
+        return f"{gas / 1_000_000:.1f}M"
+    return f"{gas:,}"
+
+
+
+def fmt_ms(v: float) -> str:
+    return f"{v:.2f}ms"
+
+
+def fmt_mgas(v: float) -> str:
+    return f"{v:.2f}"
+
+
+def change_str(pct: float, ci_pct: float, lower_is_better: bool) -> str:
+    """Format change% with paired CI significance.
+
+    Significant if the CI doesn't cross zero (i.e. |pct| > ci_pct).
+    """
+    significant = abs(pct) > ci_pct
+    if not significant:
+        emoji = "⚪"
+    elif (pct < 0) == lower_is_better:
+        emoji = "✅"
+    else:
+        emoji = "❌"
+
+    return f"{pct:+.2f}% {emoji} (±{ci_pct:.2f}%)"
+
+
+def generate_comparison_table(
+    run1: dict,
+    run2: dict,
+    paired: dict,
+    repo: str,
+    baseline_ref: str,
+    baseline_name: str,
+    feature_name: str,
+    feature_sha: str,
+) -> str:
+    """Generate a markdown comparison table between baseline and feature."""
+    n = paired["blocks"]
+
+    def pct(base: float, feat: float) -> float:
+        return (feat - base) / base * 100.0 if base > 0 else 0.0
+
+    mean_pct = pct(run1["mean_ms"], run2["mean_ms"])
+    gas_pct = pct(run1["mean_mgas_s"], run2["mean_mgas_s"])
+
+    p50_pct = pct(run1["p50_ms"], run2["p50_ms"])
+    p90_pct = pct(run1["p90_ms"], run2["p90_ms"])
+    p99_pct = pct(run1["p99_ms"], run2["p99_ms"])
+
+    # Bootstrap CIs as % of baseline percentile
+    p50_ci_pct = paired["p50_ci_ms"] / run1["p50_ms"] * 100.0 if run1["p50_ms"] > 0 else 0.0
+    p90_ci_pct = paired["p90_ci_ms"] / run1["p90_ms"] * 100.0 if run1["p90_ms"] > 0 else 0.0
+    p99_ci_pct = paired["p99_ci_ms"] / run1["p99_ms"] * 100.0 if run1["p99_ms"] > 0 else 0.0
+
+    # 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
+
+    base_url = f"https://github.com/{repo}/commit"
+    baseline_label = f"[`{baseline_name}`]({base_url}/{baseline_ref})"
+    feature_label = f"[`{feature_name}`]({base_url}/{feature_sha})"
+
+    lines = [
+        f"| Metric | {baseline_label} | {feature_label} | Change |",
+        "|--------|------|--------|--------|",
+        f"| Mean | {fmt_ms(run1['mean_ms'])} | {fmt_ms(run2['mean_ms'])} | {change_str(mean_pct, lat_ci_pct, lower_is_better=True)} |",
+        f"| StdDev | {fmt_ms(run1['stddev_ms'])} | {fmt_ms(run2['stddev_ms'])} | |",
+        f"| P50 | {fmt_ms(run1['p50_ms'])} | {fmt_ms(run2['p50_ms'])} | {change_str(p50_pct, p50_ci_pct, lower_is_better=True)} |",
+        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"*{n} blocks*",
+    ]
+    return "\n".join(lines)
+
+
+def generate_wait_time_table(
+    title: str,
+    baseline_stats: dict,
+    feature_stats: dict,
+    baseline_label: str,
+    feature_label: str,
+) -> str:
+    """Generate a markdown table for a wait time metric."""
+    if not baseline_stats or not feature_stats:
+        return ""
+    lines = [
+        f"### {title}",
+        "",
+        f"| Metric | {baseline_label} | {feature_label} |",
+        "|--------|------|--------|",
+        f"| Mean | {fmt_ms(baseline_stats['mean_ms'])} | {fmt_ms(feature_stats['mean_ms'])} |",
+        f"| P50 | {fmt_ms(baseline_stats['p50_ms'])} | {fmt_ms(feature_stats['p50_ms'])} |",
+        f"| P95 | {fmt_ms(baseline_stats['p95_ms'])} | {fmt_ms(feature_stats['p95_ms'])} |",
+    ]
+    return "\n".join(lines)
+
+
+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 = "",
+) -> str:
+    """Generate a markdown comment body."""
+    lines = ["## Benchmark Results", ""]
+    if behind_baseline > 0:
+        s = "s" if behind_baseline > 1 else ""
+        diff_link = f"https://github.com/{repo}/compare/{baseline_ref[:12]}...{baseline_name}"
+        lines.append(f"> ⚠️ Feature is [**{behind_baseline} commit{s} behind `{baseline_name}`**]({diff_link}). Consider rebasing for accurate results.")
+        lines.append("")
+    lines.append(comparison_table)
+    if wait_time_tables:
+        lines.append("")
+        lines.append("<details>")
+        lines.append("<summary>Wait Time Breakdown</summary>")
+        lines.append("")
+        for table in wait_time_tables:
+            if table:
+                lines.append(table)
+                lines.append("")
+        lines.append("</details>")
+    return "\n".join(lines)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Parse reth-bench ABBA results")
+    parser.add_argument(
+        "--baseline-csv", nargs="+", required=True,
+        help="Baseline combined_latency.csv files (A1, A2)",
+    )
+    parser.add_argument(
+        "--feature-csv", "--branch-csv", nargs="+", required=True,
+        help="Feature combined_latency.csv files (B1, B2)",
+    )
+    parser.add_argument("--gas-csv", required=True, help="Path to total_gas.csv")
+    parser.add_argument(
+        "--output-summary", required=True, help="Output JSON summary path"
+    )
+    parser.add_argument("--output-markdown", required=True, help="Output markdown path")
+    parser.add_argument(
+        "--repo", default="paradigmxyz/reth", help="GitHub repo (owner/name)"
+    )
+    parser.add_argument("--baseline-ref", default=None, help="Baseline commit SHA")
+    parser.add_argument("--baseline-name", default=None, help="Baseline display name")
+    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")
+    args = parser.parse_args()
+
+    if len(args.baseline_csv) != len(args.feature_csv):
+        print("Must provide equal number of baseline and feature CSVs", file=sys.stderr)
+        sys.exit(1)
+
+    baseline_runs = []
+    feature_runs = []
+    for path in args.baseline_csv:
+        data = parse_combined_csv(path)
+        if not data:
+            print(f"No results in {path}", file=sys.stderr)
+            sys.exit(1)
+        baseline_runs.append(data)
+    for path in args.feature_csv:
+        data = parse_combined_csv(path)
+        if not data:
+            print(f"No results in {path}", file=sys.stderr)
+            sys.exit(1)
+        feature_runs.append(data)
+
+    gas = parse_gas_csv(args.gas_csv)
+
+    all_baseline = [r for run in baseline_runs for r in run]
+    all_feature = [r for run in feature_runs for r in run]
+
+    summary = compute_summary(all_feature, gas)
+    with open(args.output_summary, "w") as f:
+        json.dump(summary, f, indent=2)
+    print(f"Summary written to {args.output_summary}")
+
+    baseline_stats = compute_stats(all_baseline)
+    feature_stats = compute_stats(all_feature)
+    paired_stats = compute_paired_stats(baseline_runs, feature_runs)
+
+    if not paired_stats:
+        print("No common blocks between baseline and feature runs", file=sys.stderr)
+        sys.exit(1)
+
+    baseline_ref = args.baseline_ref or "main"
+    baseline_name = args.baseline_name or "baseline"
+    feature_name = args.feature_name or "feature"
+    feature_sha = args.feature_ref or "unknown"
+
+    comparison_table = generate_comparison_table(
+        baseline_stats,
+        feature_stats,
+        paired_stats,
+        repo=args.repo,
+        baseline_ref=baseline_ref,
+        baseline_name=baseline_name,
+        feature_name=feature_name,
+        feature_sha=feature_sha,
+    )
+    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)")
+
+    base_url = f"https://github.com/{args.repo}/commit"
+    baseline_label = f"[`{baseline_name}`]({base_url}/{baseline_ref})"
+    feature_label = f"[`{feature_name}`]({base_url}/{feature_sha})"
+
+    wait_fields = [
+        ("persistence_wait_us", "Persistence Wait"),
+        ("sparse_trie_wait_us", "Trie Cache Update Wait"),
+        ("execution_cache_wait_us", "Execution Cache Update Wait"),
+    ]
+    wait_time_tables = []
+    for field, title in wait_fields:
+        b_stats = compute_wait_stats(all_baseline, field)
+        f_stats = compute_wait_stats(all_feature, field)
+        table = generate_wait_time_table(title, b_stats, f_stats, baseline_label, feature_label)
+        if table:
+            wait_time_tables.append(table)
+
+    markdown = generate_markdown(
+        summary, comparison_table,
+        wait_time_tables=wait_time_tables,
+        behind_baseline=args.behind_baseline,
+        repo=args.repo,
+        baseline_ref=baseline_ref,
+        baseline_name=baseline_name,
+    )
+
+    with open(args.output_markdown, "w") as f:
+        f.write(markdown)
+    print(f"Markdown written to {args.output_markdown}")
+
+
+if __name__ == "__main__":
+    main()

.github/scripts/bench-update-status.js

@@ -0,0 +1,27 @@
+// Updates the reth-bench PR comment with current status.
+//
+// Reads from environment:
+//   BENCH_COMMENT_ID  – GitHub comment ID to update
+//   BENCH_JOB_URL     – URL to the Actions job page
+//   BENCH_CONFIG      – Config line (blocks, warmup, refs)
+//   BENCH_ACTOR       – User who triggered the benchmark
+//
+// Usage from actions/github-script:
+//   const s = require('./.github/scripts/bench-update-status.js');
+//   await s({github, context, status: 'Building baseline binary...'});
+
+function buildBody(status) {
+  return `cc @${process.env.BENCH_ACTOR}\n\n🚀 Benchmark started! [View job](${process.env.BENCH_JOB_URL})\n\n⏳ **Status:** ${status}\n\n${process.env.BENCH_CONFIG}`;
+}
+
+async function updateStatus({ github, context, status }) {
+  await github.rest.issues.updateComment({
+    owner: context.repo.owner,
+    repo: context.repo.repo,
+    comment_id: parseInt(process.env.BENCH_COMMENT_ID),
+    body: buildBody(status),
+  });
+}
+
+updateStatus.buildBody = buildBody;
+module.exports = updateStatus;

.github/scripts/hive/expected_failures.yaml

@@ -59,10 +59,6 @@ engine-auth: [ ]
 #
 # System contract tests (already fixed and deployed):
 #
-# tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout and test_invalid_log_length
-#   System contract is already fixed and deployed; tests cover scenarios where contract is
-#   malformed which can't happen retroactively. No point in adding checks.
-#
 # tests/prague/eip7002_el_triggerable_withdrawals/test_contract_deployment.py::test_system_contract_deployment
 # tests/prague/eip7251_consolidations/test_contract_deployment.py::test_system_contract_deployment
 #   Post-fork system contract deployment tests. Should fix for spec compliance but not realistic
@@ -71,32 +67,8 @@ eels/consume-engine:
   - tests/prague/eip7702_set_code_tx/test_set_code_txs.py::test_set_code_to_non_empty_storage[fork_Prague-blockchain_test_engine-zero_nonce]-reth
   - tests/prague/eip7251_consolidations/test_contract_deployment.py::test_system_contract_deployment[fork_CancunToPragueAtTime15k-blockchain_test_engine-deploy_after_fork-nonzero_balance]-reth
   - tests/prague/eip7251_consolidations/test_contract_deployment.py::test_system_contract_deployment[fork_CancunToPragueAtTime15k-blockchain_test_engine-deploy_after_fork-zero_balance]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_amount_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_amount_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_index_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_index_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_pubkey_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_pubkey_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_signature_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_signature_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_withdrawal_credentials_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_withdrawal_credentials_size-value_zero]-reth
   - tests/prague/eip7002_el_triggerable_withdrawals/test_contract_deployment.py::test_system_contract_deployment[fork_CancunToPragueAtTime15k-blockchain_test_engine-deploy_after_fork-nonzero_balance]-reth
   - tests/prague/eip7002_el_triggerable_withdrawals/test_contract_deployment.py::test_system_contract_deployment[fork_CancunToPragueAtTime15k-blockchain_test_engine-deploy_after_fork-zero_balance]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_log_length[fork_Prague-blockchain_test_engine-slice_bytes_False]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_log_length[fork_Prague-blockchain_test_engine-slice_bytes_True]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_amount_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_amount_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_index_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_index_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_pubkey_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_pubkey_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_signature_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_signature_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_withdrawal_credentials_offset-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_withdrawal_credentials_size-value_zero]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_log_length[fork_Osaka-blockchain_test_engine-slice_bytes_False]-reth
-  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_log_length[fork_Osaka-blockchain_test_engine-slice_bytes_True]-reth
   - tests/paris/eip7610_create_collision/test_initcollision.py::test_init_collision_create_tx[fork_Osaka-tx_type_0-blockchain_test_engine_from_state_test-non-empty-balance-revert-initcode]-reth
   - tests/paris/eip7610_create_collision/test_initcollision.py::test_init_collision_create_tx[fork_Prague-tx_type_0-blockchain_test_engine_from_state_test-non-empty-balance-correct-initcode]-reth
   - tests/paris/eip7610_create_collision/test_initcollision.py::test_init_collision_create_tx[fork_Paris-tx_type_1-blockchain_test_engine_from_state_test-non-empty-balance-correct-initcode]-reth

.github/scripts/hive/ignored_tests.yaml

@@ -16,12 +16,16 @@ 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)
+  - 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)
   - Transaction Re-Org, Re-Org Out (Cancun) (reth)
   - Invalid Missing Ancestor ReOrg, StateRoot, EmptyTxs=False, Invalid P9 (Cancun) (reth)
+  - Invalid Missing Ancestor Syncing ReOrg, Timestamp, EmptyTxs=False, CanonicalReOrg=False, Invalid P8 (Cancun) (reth)
+  - Invalid Missing Ancestor Syncing ReOrg, Timestamp, EmptyTxs=False, CanonicalReOrg=True, Invalid P8 (Cancun) (reth)
   - Multiple New Payloads Extending Canonical Chain, Wait for Canonical Payload (Cancun) (reth)
 engine-api:
   - Transaction Re-Org, Re-Org Out (Paris) (reth)

.github/scripts/hive/run_simulator.sh

@@ -6,8 +6,14 @@ cd hivetests/
 sim="${1}"
 limit="${2}"
 
+# Use lower parallelism for eels tests to avoid OOM-killing the runner
+parallelism=16
+if [[ "${sim}" == *"eels"* ]]; then
+    parallelism=4
+fi
+
 run_hive() {
-    hive --sim "${sim}" --sim.limit "${limit}" --sim.parallelism 16 --client reth 2>&1 | tee /tmp/log || true
+    hive --sim "${sim}" --sim.limit "${limit}" --sim.parallelism "${parallelism}" --client reth 2>&1 | tee /tmp/log || true
 }
 
 check_log() {

.github/workflows/bench.yml

@@ -1,11 +1,40 @@
 # Runs benchmarks.
+#
+# The reth-bench job replays real blocks via the Engine API against a reth node
+# backed by a local snapshot managed with schelk.
+#
+# It runs the baseline binary and the feature (candidate) binary on the
+# same block range (snapshot recovered between runs) to compare performance.
 
 on:
-  pull_request:
   # TODO: Disabled temporarily for https://github.com/CodSpeedHQ/runner/issues/55
   # merge_group:
   push:
     branches: [main]
+  issue_comment:
+    types: [created, edited]
+  workflow_dispatch:
+    inputs:
+      blocks:
+        description: "Number of blocks to benchmark"
+        required: false
+        default: "500"
+        type: string
+      warmup:
+        description: "Number of warmup blocks"
+        required: false
+        default: "100"
+        type: string
+      baseline:
+        description: "Baseline git ref (default: merge-base)"
+        required: false
+        default: ""
+        type: string
+      feature:
+        description: "Feature git ref (default: branch head)"
+        required: false
+        default: ""
+        type: string
 
 env:
   CARGO_TERM_COLOR: always
@@ -14,9 +43,18 @@ env:
   RUSTC_WRAPPER: "sccache"
 
 name: bench
+
+permissions:
+  contents: write
+  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]
@@ -31,6 +69,7 @@ jobs:
       - 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
@@ -49,3 +88,714 @@ jobs:
           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, 'derek bench')) ||
+      github.event_name == 'workflow_dispatch'
+    name: reth-bench-ack
+    runs-on: ubuntu-latest
+    outputs:
+      pr: ${{ steps.args.outputs.pr }}
+      actor: ${{ steps.args.outputs.actor }}
+      blocks: ${{ steps.args.outputs.blocks }}
+      warmup: ${{ steps.args.outputs.warmup }}
+      baseline: ${{ steps.args.outputs.baseline }}
+      feature: ${{ steps.args.outputs.feature }}
+      baseline-name: ${{ steps.args.outputs.baseline-name }}
+      feature-name: ${{ steps.args.outputs.feature-name }}
+      comment-id: ${{ steps.ack.outputs.comment-id }}
+    steps:
+      - name: Check org membership
+        if: github.event_name == 'issue_comment'
+        uses: actions/github-script@v8
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const user = context.payload.comment.user.login;
+            try {
+              const { status } = await github.rest.orgs.checkMembershipForUser({
+                org: 'paradigmxyz',
+                username: user,
+              });
+              if (status !== 204 && status !== 302) {
+                core.setFailed(`@${user} is not a member of paradigmxyz`);
+              }
+            } catch (e) {
+              core.setFailed(`@${user} is not a member of paradigmxyz`);
+            }
+
+      - name: Parse arguments
+        id: args
+        uses: actions/github-script@v8
+        with:
+          script: |
+            let pr, actor, blocks, warmup, baseline, feature;
+
+            if (context.eventName === 'workflow_dispatch') {
+              actor = '${{ github.actor }}';
+              blocks = '${{ github.event.inputs.blocks }}' || '500';
+              warmup = '${{ github.event.inputs.warmup }}' || '100';
+              baseline = '${{ github.event.inputs.baseline }}';
+              feature = '${{ github.event.inputs.feature }}';
+
+              // Find PR for the selected branch
+              const branch = '${{ github.ref_name }}';
+              const { data: prs } = await github.rest.pulls.list({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                head: `${context.repo.owner}:${branch}`,
+                state: 'open',
+                per_page: 1,
+              });
+              pr = prs.length ? String(prs[0].number) : '';
+              if (!pr) {
+                core.info(`No open PR found for branch '${branch}', results will be in job summary`);
+              }
+            } else {
+              pr = String(context.issue.number);
+              actor = context.payload.comment.user.login;
+
+              const body = context.payload.comment.body.trim();
+              const intArgs = new Set(['blocks', 'warmup']);
+              const refArgs = new Set(['baseline', 'feature']);
+              const defaults = { blocks: '500', warmup: '100', baseline: '', feature: '' };
+              const unknown = [];
+              const invalid = [];
+              const args = body.replace(/^derek bench\s*/, '');
+              for (const part of args.split(/\s+/).filter(Boolean)) {
+                const eq = part.indexOf('=');
+                if (eq === -1) {
+                  unknown.push(part);
+                  continue;
+                }
+                const key = part.slice(0, eq);
+                const value = part.slice(eq + 1);
+                if (intArgs.has(key)) {
+                  if (!/^\d+$/.test(value)) {
+                    invalid.push(`\`${key}=${value}\` (must be a positive integer)`);
+                  } else {
+                    defaults[key] = value;
+                  }
+                } else if (refArgs.has(key)) {
+                  if (!value) {
+                    invalid.push(`\`${key}=\` (must be a git ref)`);
+                  } else {
+                    defaults[key] = value;
+                  }
+                } else {
+                  unknown.push(key);
+                }
+              }
+              const errors = [];
+              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:** \`derek bench [blocks=N] [warmup=N] [baseline=REF] [feature=REF]\``;
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: context.issue.number,
+                  body: msg,
+                });
+                core.setFailed(msg);
+                return;
+              }
+              blocks = defaults.blocks;
+              warmup = defaults.warmup;
+              baseline = defaults.baseline;
+              feature = defaults.feature;
+            }
+
+            // Resolve display names for baseline/feature
+            let baselineName = baseline || 'main';
+            let featureName = feature;
+            if (!featureName) {
+              if (pr) {
+                const { data: prData } = await github.rest.pulls.get({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  pull_number: parseInt(pr),
+                });
+                featureName = prData.head.ref;
+              } else {
+                featureName = '${{ github.ref_name }}';
+              }
+            }
+
+            core.setOutput('pr', pr || '');
+            core.setOutput('actor', actor);
+            core.setOutput('blocks', blocks);
+            core.setOutput('warmup', warmup);
+            core.setOutput('baseline', baseline);
+            core.setOutput('feature', feature);
+            core.setOutput('baseline-name', baselineName);
+            core.setOutput('feature-name', featureName);
+
+      - name: Acknowledge request
+        id: ack
+        uses: actions/github-script@v8
+        with:
+          script: |
+            if (context.eventName === 'issue_comment') {
+              await github.rest.reactions.createForIssueComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                comment_id: context.payload.comment.id,
+                content: 'eyes',
+              });
+            }
+
+            const pr = '${{ steps.args.outputs.pr }}';
+            if (!pr) return;
+
+            const runUrl = `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
+
+            // Count queued/waiting bench runs ahead of this one
+            let queueMsg = '';
+            let ahead = 0;
+            try {
+              const statuses = ['queued', 'in_progress', 'waiting', 'requested', 'pending'];
+              const allRuns = [];
+              for (const status of statuses) {
+                const { data: { workflow_runs: r } } = await github.rest.actions.listWorkflowRuns({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  workflow_id: 'bench.yml',
+                  status,
+                  per_page: 100,
+                });
+                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();
+              ahead = benchRuns.filter(r => r.id !== context.runId && new Date(r.created_at) <= thisCreatedAt).length;
+              if (ahead > 0) {
+                queueMsg = `\n🔢 **Queue position:** \`#${ahead + 1}\` (${ahead} job(s) ahead)`;
+              }
+            } catch (e) {
+              // Non-fatal — queue info is best-effort
+              core.info(`Could not fetch queue info: ${e.message}`);
+            }
+
+            const actor = '${{ steps.args.outputs.actor }}';
+            const blocks = '${{ steps.args.outputs.blocks }}';
+            const warmup = '${{ steps.args.outputs.warmup }}';
+            const baseline = '${{ steps.args.outputs.baseline-name }}';
+            const feature = '${{ steps.args.outputs.feature-name }}';
+            const config = `**Config:** ${blocks} blocks, ${warmup} warmup blocks, baseline: \`${baseline}\`, feature: \`${feature}\``;
+
+            const { data: comment } = await github.rest.issues.createComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: parseInt(pr),
+              body: `cc @${actor}\n\n🚀 Benchmark queued! [View run](${runUrl})\n\n⏳ **Status:** Waiting for runner...${queueMsg}\n\n${config}`,
+            });
+            core.setOutput('comment-id', String(comment.id));
+            core.setOutput('queue-position', String(ahead || 0));
+
+      - name: Poll queue position
+        if: steps.ack.outputs.comment-id && steps.ack.outputs.queue-position != '0'
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const pr = '${{ steps.args.outputs.pr }}';
+            const commentId = parseInt('${{ steps.ack.outputs.comment-id }}');
+            const actor = '${{ steps.args.outputs.actor }}';
+            const blocks = '${{ steps.args.outputs.blocks }}';
+            const warmup = '${{ steps.args.outputs.warmup }}';
+            const baseline = '${{ steps.args.outputs.baseline-name }}';
+            const feature = '${{ steps.args.outputs.feature-name }}';
+            const config = `**Config:** ${blocks} blocks, ${warmup} warmup blocks, baseline: \`${baseline}\`, feature: \`${feature}\``;
+            const runUrl = `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
+
+            async function getQueuePosition() {
+              const statuses = ['queued', 'in_progress', 'waiting', 'requested', 'pending'];
+              const allRuns = [];
+              for (const status of statuses) {
+                const { data: { workflow_runs: r } } = await github.rest.actions.listWorkflowRuns({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  workflow_id: 'bench.yml',
+                  status,
+                  per_page: 100,
+                });
+                allRuns.push(...r);
+              }
+              const benchRuns = allRuns.filter(r => r.event === 'issue_comment' || r.event === 'workflow_dispatch');
+              const thisRun = benchRuns.find(r => r.id === context.runId);
+              const thisCreatedAt = thisRun ? new Date(thisRun.created_at) : new Date();
+              return benchRuns.filter(r => r.id !== context.runId && new Date(r.created_at) <= thisCreatedAt).length;
+            }
+
+            let lastPosition = parseInt('${{ steps.ack.outputs.queue-position }}');
+            const sleep = ms => new Promise(r => setTimeout(r, ms));
+
+            while (true) {
+              await sleep(10_000);
+              try {
+                const ahead = await getQueuePosition();
+                if (ahead !== lastPosition) {
+                  lastPosition = ahead;
+                  const queueMsg = ahead > 0
+                    ? `\n🔢 **Queue position:** \`#${ahead + 1}\` (${ahead} job(s) ahead)`
+                    : '';
+                  await github.rest.issues.updateComment({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    comment_id: commentId,
+                    body: `cc @${actor}\n\n🚀 Benchmark queued! [View run](${runUrl})\n\n⏳ **Status:** Waiting for runner...${queueMsg}\n\n${config}`,
+                  });
+                }
+                if (ahead === 0) break;
+              } catch (e) {
+                core.info(`Queue poll error: ${e.message}`);
+              }
+            }
+
+  reth-bench:
+    needs: reth-bench-ack
+    name: reth-bench
+    runs-on: [self-hosted, Linux, X64]
+    timeout-minutes: 120
+    concurrency:
+      group: reth-bench-queue
+      cancel-in-progress: false
+    env:
+      BENCH_RPC_URL: https://ethereum.reth.rs/rpc
+      SCHELK_MOUNT: /reth-bench
+      BENCH_WORK_DIR: ${{ github.workspace }}/bench-work
+      BENCH_PR: ${{ needs.reth-bench-ack.outputs.pr }}
+      BENCH_ACTOR: ${{ needs.reth-bench-ack.outputs.actor }}
+      BENCH_BLOCKS: ${{ needs.reth-bench-ack.outputs.blocks }}
+      BENCH_WARMUP_BLOCKS: ${{ needs.reth-bench-ack.outputs.warmup }}
+      BENCH_COMMENT_ID: ${{ needs.reth-bench-ack.outputs.comment-id }}
+    steps:
+      - name: Resolve checkout ref
+        id: checkout-ref
+        uses: actions/github-script@v8
+        with:
+          script: |
+            if (!process.env.BENCH_PR) {
+              core.setOutput('ref', '${{ github.ref }}');
+              return;
+            }
+            const { data: pr } = await github.rest.pulls.get({
+              owner: context.repo.owner,
+              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`);
+            }
+
+      - uses: actions/checkout@v6
+        with:
+          submodules: true
+          fetch-depth: 0
+          ref: ${{ steps.checkout-ref.outputs.ref }}
+
+      - name: Resolve job URL and update status
+        if: env.BENCH_COMMENT_ID
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const { data: jobs } = await github.rest.actions.listJobsForWorkflowRun({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              run_id: context.runId,
+            });
+            const job = jobs.jobs.find(j => j.name === 'reth-bench');
+            const jobUrl = job ? job.html_url : `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
+            core.exportVariable('BENCH_JOB_URL', jobUrl);
+
+            const blocks = process.env.BENCH_BLOCKS;
+            const warmup = process.env.BENCH_WARMUP_BLOCKS;
+            const baseline = '${{ needs.reth-bench-ack.outputs.baseline-name }}';
+            const feature = '${{ needs.reth-bench-ack.outputs.feature-name }}';
+            core.exportVariable('BENCH_CONFIG', `**Config:** ${blocks} blocks, ${warmup} warmup blocks, baseline: \`${baseline}\`, feature: \`${feature}\``);
+
+            const { buildBody } = require('./.github/scripts/bench-update-status.js');
+            await github.rest.issues.updateComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              comment_id: parseInt(process.env.BENCH_COMMENT_ID),
+              body: buildBody('Building binaries...'),
+            });
+
+      - uses: dtolnay/rust-toolchain@stable
+      - uses: mozilla-actions/sccache-action@v0.0.9
+        continue-on-error: true
+
+      # Verify all required tools are available
+      - name: Check dependencies
+        run: |
+          export PATH="$HOME/.local/bin:$HOME/.cargo/bin:$PATH"
+          echo "$HOME/.local/bin" >> "$GITHUB_PATH"
+          echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
+          missing=()
+          for cmd in mc schelk cpupower taskset stdbuf python3 curl make uv pzstd jq; do
+            command -v "$cmd" &>/dev/null || missing+=("$cmd")
+          done
+          if [ ${#missing[@]} -gt 0 ]; then
+            echo "::error::Missing required tools: ${missing[*]}"
+            exit 1
+          fi
+          echo "All dependencies found"
+
+      # Build binaries
+      - name: Resolve PR head branch
+        id: pr-info
+        uses: actions/github-script@v8
+        with:
+          script: |
+            if (process.env.BENCH_PR) {
+              const { data: pr } = await github.rest.pulls.get({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                pull_number: parseInt(process.env.BENCH_PR),
+              });
+              core.setOutput('head-ref', pr.head.ref);
+              core.setOutput('head-sha', pr.head.sha);
+            } else {
+              core.setOutput('head-ref', '${{ github.ref_name }}');
+              core.setOutput('head-sha', '${{ github.sha }}');
+            }
+
+      - name: Resolve refs
+        id: refs
+        run: |
+          BASELINE_ARG="${{ needs.reth-bench-ack.outputs.baseline }}"
+          FEATURE_ARG="${{ needs.reth-bench-ack.outputs.feature }}"
+
+          if [ -n "$BASELINE_ARG" ]; then
+            git fetch origin "$BASELINE_ARG" --quiet 2>/dev/null || true
+            BASELINE_REF=$(git rev-parse "$BASELINE_ARG" 2>/dev/null || git rev-parse "origin/$BASELINE_ARG" 2>/dev/null)
+            BASELINE_NAME="$BASELINE_ARG"
+          else
+            BASELINE_REF=$(git merge-base HEAD origin/main 2>/dev/null || echo "${{ github.sha }}")
+            BASELINE_NAME="main"
+          fi
+
+          if [ -n "$FEATURE_ARG" ]; then
+            git fetch origin "$FEATURE_ARG" --quiet 2>/dev/null || true
+            FEATURE_REF=$(git rev-parse "$FEATURE_ARG" 2>/dev/null || git rev-parse "origin/$FEATURE_ARG" 2>/dev/null)
+            FEATURE_NAME="$FEATURE_ARG"
+          else
+            FEATURE_REF="${{ steps.pr-info.outputs.head-sha }}"
+            FEATURE_NAME="${{ steps.pr-info.outputs.head-ref }}"
+          fi
+
+          echo "baseline-ref=$BASELINE_REF" >> "$GITHUB_OUTPUT"
+          echo "baseline-name=$BASELINE_NAME" >> "$GITHUB_OUTPUT"
+          echo "feature-ref=$FEATURE_REF" >> "$GITHUB_OUTPUT"
+          echo "feature-name=$FEATURE_NAME" >> "$GITHUB_OUTPUT"
+
+      - name: Check if snapshot needs update
+        id: snapshot-check
+        run: |
+          if .github/scripts/bench-reth-snapshot.sh --check; then
+            echo "needed=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "needed=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Update status (snapshot needed)
+        if: env.BENCH_COMMENT_ID && steps.snapshot-check.outputs.needed == 'true'
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const s = require('./.github/scripts/bench-update-status.js');
+            await s({github, context, status: 'Building binaries & downloading snapshot...'});
+
+      - name: Prepare source dirs
+        run: |
+          BASELINE_REF="${{ steps.refs.outputs.baseline-ref }}"
+          if [ -d ../reth-baseline ]; then
+            git -C ../reth-baseline fetch origin "$BASELINE_REF"
+          else
+            git clone . ../reth-baseline
+          fi
+          git -C ../reth-baseline checkout "$BASELINE_REF"
+
+          FEATURE_REF="${{ steps.refs.outputs.feature-ref }}"
+          if [ -d ../reth-feature ]; then
+            git -C ../reth-feature fetch origin "$FEATURE_REF"
+          else
+            git clone . ../reth-feature
+          fi
+          git -C ../reth-feature checkout "$FEATURE_REF"
+
+      - name: Build binaries and download snapshot in parallel
+        id: build
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          BENCH_REPO: ${{ github.repository }}
+          SNAPSHOT_NEEDED: ${{ steps.snapshot-check.outputs.needed }}
+        run: |
+          BASELINE_DIR="$(cd ../reth-baseline && pwd)"
+          FEATURE_DIR="$(cd ../reth-feature && pwd)"
+
+          .github/scripts/bench-reth-build.sh baseline "${BASELINE_DIR}" "${{ steps.refs.outputs.baseline-ref }}" &
+          PID_BASELINE=$!
+          .github/scripts/bench-reth-build.sh feature "${FEATURE_DIR}" "${{ steps.refs.outputs.feature-ref }}" &
+          PID_FEATURE=$!
+
+          PID_SNAPSHOT=
+          if [ "$SNAPSHOT_NEEDED" = "true" ]; then
+            .github/scripts/bench-reth-snapshot.sh &
+            PID_SNAPSHOT=$!
+          fi
+
+          FAIL=0
+          wait $PID_BASELINE || FAIL=1
+          wait $PID_FEATURE || FAIL=1
+          [ -n "$PID_SNAPSHOT" ] && { wait $PID_SNAPSHOT || FAIL=1; }
+          if [ $FAIL -ne 0 ]; then
+            echo "::error::One or more parallel tasks failed (builds / snapshot download)"
+            exit 1
+          fi
+
+      # System tuning for reproducible benchmarks
+      - name: System setup
+        run: |
+          sudo cpupower frequency-set -g performance || true
+          # Disable turbo boost (Intel and AMD paths)
+          echo 1 | sudo tee /sys/devices/system/cpu/intel_pstate/no_turbo 2>/dev/null || true
+          echo 0 | sudo tee /sys/devices/system/cpu/cpufreq/boost 2>/dev/null || true
+          sudo swapoff -a || true
+          echo 0 | sudo tee /proc/sys/kernel/randomize_va_space || true
+          # Disable SMT (hyperthreading)
+          for cpu in /sys/devices/system/cpu/cpu*/topology/thread_siblings_list; do
+            first=$(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" || true
+            fi
+          done
+          echo "Online CPUs: $(nproc)"
+          # Disable transparent huge pages (compaction causes latency spikes)
+          for p in /sys/kernel/mm/transparent_hugepage /sys/kernel/mm/transparent_hugepages; do
+            [ -d "$p" ] && echo never | sudo tee "$p/enabled" && echo never | sudo tee "$p/defrag" && break
+          done || true
+          # Prevent deep C-states (avoids wake-up latency jitter)
+          sudo sh -c 'exec 3<>/dev/cpu_dma_latency; echo -ne "\x00\x00\x00\x00" >&3; sleep infinity' &
+          # Move all IRQs to core 0 (housekeeping core)
+          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
+          # Log environment for reproducibility
+          echo "=== Benchmark environment ==="
+          uname -r
+          lscpu | grep -E 'Model name|CPU\(s\)|MHz|NUMA'
+          cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
+          cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq
+          cat /sys/kernel/mm/transparent_hugepage/enabled 2>/dev/null || cat /sys/kernel/mm/transparent_hugepages/enabled 2>/dev/null || echo "THP: unknown"
+          free -h
+
+      # Clean up any leftover state
+      - name: Pre-flight cleanup
+        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
+          rm -rf "$BENCH_WORK_DIR"
+          mkdir -p "$BENCH_WORK_DIR"
+
+      - name: Update status (running benchmarks)
+        if: success() && env.BENCH_COMMENT_ID
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const s = require('./.github/scripts/bench-update-status.js');
+            await s({github, context, status: 'Running benchmarks...'});
+
+      # Interleaved run order (B-F-F-B) to reduce systematic bias from
+      # 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 "$BENCH_WORK_DIR/baseline-1"
+
+      - name: "Run benchmark: feature (1/2)"
+        id: run-feature-1
+        run: taskset -c 0 .github/scripts/bench-reth-run.sh feature ../reth-feature/target/profiling/reth "$BENCH_WORK_DIR/feature-1"
+
+      - 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 "$BENCH_WORK_DIR/feature-2"
+
+      - name: "Run benchmark: baseline (2/2)"
+        id: run-baseline-2
+        run: taskset -c 0 .github/scripts/bench-reth-run.sh baseline ../reth-baseline/target/profiling/reth "$BENCH_WORK_DIR/baseline-2"
+
+      # Results & charts
+      - name: Parse results
+        id: results
+        if: success()
+        env:
+          BASELINE_REF: ${{ steps.refs.outputs.baseline-ref }}
+          BASELINE_NAME: ${{ steps.refs.outputs.baseline-name }}
+          FEATURE_NAME: ${{ steps.refs.outputs.feature-name }}
+          FEATURE_REF: ${{ steps.refs.outputs.feature-ref }}
+        run: |
+          git fetch origin "${BASELINE_NAME}" --quiet 2>/dev/null || true
+          BASELINE_HEAD=$(git rev-parse "origin/${BASELINE_NAME}" 2>/dev/null || echo "")
+          BEHIND_BASELINE=0
+          if [ -n "$BASELINE_HEAD" ] && [ "$BASELINE_REF" != "$BASELINE_HEAD" ]; then
+            BEHIND_BASELINE=$(git rev-list --count "${BASELINE_REF}..${BASELINE_HEAD}" 2>/dev/null || echo "0")
+          fi
+
+          SUMMARY_ARGS="--output-summary $BENCH_WORK_DIR/summary.json"
+          SUMMARY_ARGS="$SUMMARY_ARGS --output-markdown $BENCH_WORK_DIR/comment.md"
+          SUMMARY_ARGS="$SUMMARY_ARGS --repo ${{ github.repository }}"
+          SUMMARY_ARGS="$SUMMARY_ARGS --baseline-ref ${BASELINE_REF}"
+          SUMMARY_ARGS="$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 $BENCH_WORK_DIR/feature-2/combined_latency.csv"
+          SUMMARY_ARGS="$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
+          # shellcheck disable=SC2086
+          python3 .github/scripts/bench-reth-summary.py $SUMMARY_ARGS
+
+      - name: Generate charts
+        if: success()
+        env:
+          BASELINE_NAME: ${{ steps.refs.outputs.baseline-name }}
+          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 $BENCH_WORK_DIR/baseline-2/combined_latency.csv"
+          CHART_ARGS="$CHART_ARGS --baseline-name ${BASELINE_NAME}"
+          CHART_ARGS="$CHART_ARGS --feature-name ${FEATURE_NAME}"
+          # shellcheck disable=SC2086
+          uv run --with matplotlib python3 .github/scripts/bench-reth-charts.py $CHART_ARGS
+
+      - name: Upload results
+        if: success()
+        uses: actions/upload-artifact@v6
+        with:
+          name: bench-reth-results
+          path: ${{ env.BENCH_WORK_DIR }}
+
+      - name: Push charts
+        id: push-charts
+        if: success() && env.BENCH_PR
+        run: |
+          PR_NUMBER=${{ env.BENCH_PR }}
+          RUN_ID=${{ github.run_id }}
+          CHART_DIR="pr/${PR_NUMBER}/${RUN_ID}"
+
+          if git fetch origin bench-charts 2>/dev/null; then
+            git checkout bench-charts
+          else
+            git checkout --orphan bench-charts
+            git rm -rf . 2>/dev/null || true
+          fi
+
+          mkdir -p "${CHART_DIR}"
+          cp "$BENCH_WORK_DIR"/charts/*.png "${CHART_DIR}/"
+          git add "${CHART_DIR}"
+          git -c user.name="github-actions" -c user.email="github-actions@github.com" \
+            commit -m "bench charts for PR #${PR_NUMBER} run ${RUN_ID}"
+          git push origin bench-charts
+          echo "sha=$(git rev-parse HEAD)" >> "$GITHUB_OUTPUT"
+
+      - name: Compare & comment
+        if: success()
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const fs = require('fs');
+
+            let comment = '';
+            try {
+              comment = fs.readFileSync(process.env.BENCH_WORK_DIR + '/comment.md', 'utf8');
+            } catch (e) {
+              comment = '⚠️ Engine benchmark completed but failed to generate comparison.';
+            }
+
+            const sha = '${{ steps.push-charts.outputs.sha }}';
+            const prNumber = process.env.BENCH_PR;
+            const runId = '${{ github.run_id }}';
+
+            if (sha && prNumber) {
+              const baseUrl = `https://raw.githubusercontent.com/${context.repo.owner}/${context.repo.repo}/${sha}/pr/${prNumber}/${runId}`;
+              const charts = [
+                { file: 'latency_throughput.png', label: 'Latency, Throughput & Diff' },
+                { file: 'wait_breakdown.png', label: 'Wait Time Breakdown' },
+                { file: 'gas_vs_latency.png', label: 'Gas vs Latency' },
+              ];
+              let chartMarkdown = '\n\n### Charts\n\n';
+              for (const chart of charts) {
+                chartMarkdown += `<details><summary>${chart.label}</summary>\n\n`;
+                chartMarkdown += `![${chart.label}](${baseUrl}/${chart.file})\n\n`;
+                chartMarkdown += `</details>\n\n`;
+              }
+              comment += chartMarkdown;
+            }
+
+            const jobUrl = process.env.BENCH_JOB_URL || `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
+            const body = `cc @${process.env.BENCH_ACTOR}\n\n✅ Benchmark complete! [View job](${jobUrl})\n\n${comment}`;
+            const ackCommentId = process.env.BENCH_COMMENT_ID;
+
+            if (ackCommentId) {
+              await github.rest.issues.updateComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                comment_id: parseInt(ackCommentId),
+                body,
+              });
+            } else {
+              // No PR — write results to job summary
+              await core.summary.addRaw(body).write();
+            }
+
+      - name: Update status (failed)
+        if: failure() && env.BENCH_COMMENT_ID
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const steps_status = [
+              ['building binaries${{ 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)', '${{ steps.run-baseline-2.outcome }}'],
+            ];
+            const failed = steps_status.find(([, o]) => o === 'failure');
+            const failedStep = failed ? failed[0] : 'unknown step';
+
+            await github.rest.issues.updateComment({
+              owner: context.repo.owner, repo: context.repo.repo,
+              comment_id: parseInt(process.env.BENCH_COMMENT_ID),
+              body: `cc @${process.env.BENCH_ACTOR}\n\n❌ Benchmark failed while ${failedStep}. [View logs](${process.env.BENCH_JOB_URL})`,
+            });
+
+      - name: Upload node log
+        if: failure()
+        uses: actions/upload-artifact@v6
+        with:
+          name: reth-node-log
+          path: |
+            ${{ env.BENCH_WORK_DIR }}/*/node.log
+
+      - name: Restore system settings
+        if: always()
+        run: |
+          sudo systemctl start irqbalance cron atd 2>/dev/null || true

.github/workflows/book.yml

@@ -15,7 +15,7 @@ env:
 
 jobs:
   build:
-    runs-on: depot-ubuntu-latest-8
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-8' || 'ubuntu-latest' }}
     timeout-minutes: 90
     steps:
       - name: Checkout

.github/workflows/check-alloy.yml

@@ -25,7 +25,7 @@ env:
 jobs:
   check:
     name: Check compilation with patched alloy
-    runs-on: depot-ubuntu-latest-16
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-16' || 'ubuntu-latest' }}
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4

.github/workflows/compact.yml

@@ -18,7 +18,7 @@ env:
 name: compact-codec
 jobs:
   compact-codec:
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     strategy:
       matrix:
         bin:

.github/workflows/docker-test.yml

@@ -15,7 +15,6 @@ on:
 
 jobs:
   build:
-    if: github.repository == 'paradigmxyz/reth'
     timeout-minutes: 45
     runs-on: ubuntu-latest
     permissions:
@@ -31,10 +30,22 @@ jobs:
           echo "sha=${{ github.sha }}" >> "$GITHUB_OUTPUT"
           echo "describe=$(git describe --always --tags)" >> "$GITHUB_OUTPUT"
 
+      - name: Detect fork
+        id: fork
+        run: |
+          if [ "${{ github.event_name }}" = "pull_request" ] && [ "${{ github.event.pull_request.head.repo.full_name }}" != "${{ github.repository }}" ]; then
+            echo "is_fork=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "is_fork=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      # Depot build (upstream only)
       - name: Set up Depot CLI
+        if: steps.fork.outputs.is_fork == 'false'
         uses: depot/setup-action@v1
 
-      - name: Build reth image
+      - name: Build reth image (Depot)
+        if: steps.fork.outputs.is_fork == 'false'
         uses: depot/bake-action@v1
         env:
           DEPOT_TOKEN: ${{ secrets.DEPOT_TOKEN }}
@@ -46,6 +57,24 @@ jobs:
           targets: ${{ inputs.hive_target }}
           push: false
 
+      # Docker build (forks)
+      - name: Set up Docker Buildx
+        if: steps.fork.outputs.is_fork == 'true'
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build reth image (Docker)
+        if: steps.fork.outputs.is_fork == 'true'
+        uses: docker/bake-action@v6
+        env:
+          VERGEN_GIT_SHA: ${{ steps.git.outputs.sha }}
+          VERGEN_GIT_DESCRIBE: ${{ steps.git.outputs.describe }}
+        with:
+          files: docker-bake.hcl
+          targets: ${{ inputs.hive_target }}
+          push: false
+          set: |
+            *.dockerfile=Dockerfile
+
       - name: Upload reth image
         uses: actions/upload-artifact@v6
         with:

.github/workflows/e2e.yml

@@ -20,7 +20,7 @@ concurrency:
 jobs:
   test:
     name: e2e-testsuite
-    runs-on: depot-ubuntu-latest-4
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
     env:
       RUST_BACKTRACE: 1
     timeout-minutes: 90
@@ -47,7 +47,7 @@ jobs:
 
   rocksdb:
     name: e2e-rocksdb
-    runs-on: depot-ubuntu-latest-4
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
     env:
       RUST_BACKTRACE: 1
     timeout-minutes: 60

.github/workflows/hive.yml

@@ -32,7 +32,7 @@ jobs:
   prepare-hive:
     if: github.repository == 'paradigmxyz/reth'
     timeout-minutes: 45
-    runs-on: depot-ubuntu-latest-4
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
     steps:
       - uses: actions/checkout@v6
       - name: Checkout hive tests
@@ -188,7 +188,8 @@ jobs:
       - build-reth-edge
       - prepare-hive
     name: ${{ matrix.storage }} / ${{ matrix.scenario.sim }}${{ matrix.scenario.limit && format(' - {0}', matrix.scenario.limit) }}
-    runs-on: depot-ubuntu-latest-4
+    # Use larger runners for eels tests to avoid OOM runner crashes
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && (contains(matrix.scenario.sim, 'eels') && 'depot-ubuntu-latest-8' || 'depot-ubuntu-latest-4') || 'ubuntu-latest' }}
     permissions:
       issues: write
     steps:

.github/workflows/integration.yml

@@ -24,7 +24,7 @@ jobs:
   test:
     name: test / ${{ matrix.network }} / ${{ matrix.storage }}
     if: github.event_name != 'schedule'
-    runs-on: depot-ubuntu-latest-4
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
     env:
       RUST_BACKTRACE: 1
     strategy:

.github/workflows/kurtosis.yml

@@ -31,7 +31,7 @@ jobs:
     strategy:
       fail-fast: false
     name: run kurtosis
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     needs:
       - build-reth
     steps:

.github/workflows/lint.yml

@@ -13,7 +13,7 @@ env:
 jobs:
   clippy-binaries:
     name: clippy binaries / ${{ matrix.type }}
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 30
     strategy:
       matrix:
@@ -42,7 +42,7 @@ jobs:
 
   clippy:
     name: clippy
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -59,7 +59,7 @@ jobs:
           RUSTFLAGS: -D warnings
 
   wasm:
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -79,7 +79,7 @@ jobs:
           .github/scripts/check_wasm.sh
 
   riscv:
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v6
@@ -98,7 +98,7 @@ jobs:
 
   crate-checks:
     name: crate-checks (${{ matrix.partition }}/${{ matrix.total_partitions }})
-    runs-on: depot-ubuntu-latest-4
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
     strategy:
       matrix:
         partition: [1, 2, 3]
@@ -117,14 +117,14 @@ jobs:
 
   msrv:
     name: MSRV
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
       - uses: rui314/setup-mold@v1
       - uses: dtolnay/rust-toolchain@master
         with:
-          toolchain: "1.88" # MSRV
+          toolchain: "1.93" # MSRV
       - uses: mozilla-actions/sccache-action@v0.0.9
       - uses: Swatinem/rust-cache@v2
         with:
@@ -135,7 +135,7 @@ jobs:
 
   docs:
     name: docs
-    runs-on: depot-ubuntu-latest-4
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -153,7 +153,7 @@ jobs:
 
   fmt:
     name: fmt
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -167,7 +167,7 @@ jobs:
 
   udeps:
     name: udeps
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -182,7 +182,7 @@ jobs:
 
   book:
     name: book
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -240,7 +240,7 @@ jobs:
   # Checks that selected crates can compile with power set of features
   features:
     name: features
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -264,7 +264,7 @@ jobs:
 
   # Check crates correctly propagate features
   feature-propagation:
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     timeout-minutes: 20
     steps:
       - uses: actions/checkout@v6

.github/workflows/release.yml

@@ -102,7 +102,7 @@ jobs:
       - name: Install cross main
         id: cross_main
         run: |
-          cargo install cross --git https://github.com/cross-rs/cross
+          cargo install cross --locked --git https://github.com/cross-rs/cross
       - uses: Swatinem/rust-cache@v2
         with:
           cache-on-failure: true

.github/workflows/stage.yml

@@ -23,7 +23,7 @@ jobs:
     name: stage-run-test
     # Only run stage commands test in merge groups
     if: github.event_name == 'merge_group'
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     env:
       RUST_LOG: info,sync=error
       RUST_BACKTRACE: 1
@@ -38,7 +38,7 @@ jobs:
           cache-on-failure: true
       - name: Build reth
         run: |
-          cargo install --path bin/reth
+          cargo install --locked --path bin/reth
       - name: Run headers stage
         run: |
           reth stage run headers --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints

.github/workflows/sync-era.yml

@@ -19,7 +19,7 @@ jobs:
   sync:
     if: github.repository == 'paradigmxyz/reth'
     name: sync (${{ matrix.chain.bin }})
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     env:
       RUST_LOG: info,sync=error
       RUST_BACKTRACE: 1

.github/workflows/sync.yml

@@ -19,7 +19,7 @@ jobs:
   sync:
     if: github.repository == 'paradigmxyz/reth'
     name: sync (${{ matrix.chain.bin }})
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     env:
       RUST_LOG: info,sync=error
       RUST_BACKTRACE: 1

.github/workflows/unit.yml

@@ -20,7 +20,7 @@ concurrency:
 jobs:
   test:
     name: test / ${{ matrix.type }} / ${{ matrix.storage }}
-    runs-on: depot-ubuntu-latest-4
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
     env:
       RUST_BACKTRACE: 1
       EDGE_FEATURES: ${{ matrix.storage == 'edge' && 'edge' || '' }}
@@ -57,7 +57,7 @@ jobs:
 
   state:
     name: Ethereum state tests
-    runs-on: depot-ubuntu-latest-4
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
     env:
       RUST_LOG: info,sync=error
       RUST_BACKTRACE: 1
@@ -92,7 +92,7 @@ jobs:
 
   doc:
     name: doc tests
-    runs-on: depot-ubuntu-latest
+    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
     env:
       RUST_BACKTRACE: 1
     timeout-minutes: 30

CLAUDE.md

@@ -313,6 +313,74 @@ GLOBAL_COUNTER.fetch_add(1, Ordering::SeqCst);
 Before adding a comment, ask: Would someone reading just the current code (no PR, no history) find this helpful?
 
 
+#### Rust Style Guides
+
+##### Type Ordering in Files
+
+When defining structs, traits, and functions in a file, follow this ordering convention. The file's primary type (matching the file name) comes first, followed by supporting public types, then private types and helpers.
+
+```rust
+use ...;
+
+/// The primary type of this file (matches filename).
+pub struct PayloadProcessor { ... }
+
+impl PayloadProcessor { ... }
+
+// Followed by public auxiliary types that support the primary type
+
+/// Configuration for the processor.
+pub struct PayloadProcessorConfig { ... }
+
+/// Result type returned by processor operations.
+pub struct ProcessorResult { ... }
+
+// Followed by public traits related to the primary type
+
+pub trait ProcessorExt { ... }
+
+// Followed by private helper types
+
+struct InternalState { ... }
+
+// Followed by private helper functions
+
+fn validate_input() { ... }
+```
+
+❌ **Bad**: Adding new traits and auxiliary types **above** the file's primary type (see [#22133](https://github.com/paradigmxyz/reth/pull/22133)):
+
+```rust
+use ...;
+
+// ❌ BAD - new auxiliary struct added before the file's main type
+pub struct CacheWaitDurations { ... }
+
+// ❌ BAD - new trait added before the file's main type  
+pub trait WaitForCaches { ... }
+
+// The file's primary type is buried below unrelated additions
+pub struct PayloadProcessor { ... }
+```
+
+✅ **Good**: New types go **after** the primary type:
+
+```rust
+use ...;
+
+// ✅ The file's primary type stays at the top
+pub struct PayloadProcessor { ... }
+
+impl PayloadProcessor { ... }
+
+// ✅ Auxiliary types follow the primary type
+pub struct CacheWaitDurations { ... }
+
+pub trait WaitForCaches { ... }
+
+impl WaitForCaches for PayloadProcessor { ... }
+```
+
 ### Example Contribution Workflow
 
 Let's say you want to fix a bug where external IP resolution fails on startup:

Cargo.toml

@@ -1,7 +1,7 @@
 [workspace.package]
 version = "1.11.0"
 edition = "2024"
-rust-version = "1.88"
+rust-version = "1.93"
 license = "MIT OR Apache-2.0"
 homepage = "https://paradigmxyz.github.io/reth"
 repository = "https://github.com/paradigmxyz/reth"
@@ -27,7 +27,6 @@ members = [
     "crates/engine/invalid-block-hooks/",
     "crates/engine/local",
     "crates/engine/primitives/",
-    "crates/engine/service",
     "crates/engine/tree/",
     "crates/engine/util/",
     "crates/era",
@@ -349,7 +348,6 @@ reth-ecies = { path = "crates/net/ecies" }
 reth-engine-local = { path = "crates/engine/local" }
 reth-engine-primitives = { path = "crates/engine/primitives", default-features = false }
 reth-engine-tree = { path = "crates/engine/tree" }
-reth-engine-service = { path = "crates/engine/service" }
 reth-engine-util = { path = "crates/engine/util" }
 reth-era = { path = "crates/era" }
 reth-era-downloader = { path = "crates/era-downloader" }
@@ -461,33 +459,33 @@ alloy-trie = { version = "0.9.4", default-features = false }
 
 alloy-hardforks = "0.4.5"
 
-alloy-consensus = { version = "1.6.3", default-features = false }
-alloy-contract = { version = "1.6.3", default-features = false }
-alloy-eips = { version = "1.6.3", default-features = false }
-alloy-genesis = { version = "1.6.3", default-features = false }
-alloy-json-rpc = { version = "1.6.3", default-features = false }
-alloy-network = { version = "1.6.3", default-features = false }
-alloy-network-primitives = { version = "1.6.3", default-features = false }
-alloy-provider = { version = "1.6.3", features = ["reqwest", "debug-api"], default-features = false }
-alloy-pubsub = { version = "1.6.3", default-features = false }
-alloy-rpc-client = { version = "1.6.3", default-features = false }
-alloy-rpc-types = { version = "1.6.3", features = ["eth"], default-features = false }
-alloy-rpc-types-admin = { version = "1.6.3", default-features = false }
-alloy-rpc-types-anvil = { version = "1.6.3", default-features = false }
-alloy-rpc-types-beacon = { version = "1.6.3", default-features = false }
-alloy-rpc-types-debug = { version = "1.6.3", default-features = false }
-alloy-rpc-types-engine = { version = "1.6.3", default-features = false }
-alloy-rpc-types-eth = { version = "1.6.3", default-features = false }
-alloy-rpc-types-mev = { version = "1.6.3", default-features = false }
-alloy-rpc-types-trace = { version = "1.6.3", default-features = false }
-alloy-rpc-types-txpool = { version = "1.6.3", default-features = false }
-alloy-serde = { version = "1.6.3", default-features = false }
-alloy-signer = { version = "1.6.3", default-features = false }
-alloy-signer-local = { version = "1.6.3", default-features = false }
-alloy-transport = { version = "1.6.3" }
-alloy-transport-http = { version = "1.6.3", features = ["reqwest-rustls-tls"], default-features = false }
-alloy-transport-ipc = { version = "1.6.3", default-features = false }
-alloy-transport-ws = { version = "1.6.3", default-features = false }
+alloy-consensus = { version = "1.7.3", default-features = false }
+alloy-contract = { version = "1.7.3", default-features = false }
+alloy-eips = { version = "1.7.3", default-features = false }
+alloy-genesis = { version = "1.7.3", default-features = false }
+alloy-json-rpc = { version = "1.7.3", default-features = false }
+alloy-network = { version = "1.7.3", default-features = false }
+alloy-network-primitives = { version = "1.7.3", default-features = false }
+alloy-provider = { version = "1.7.3", features = ["reqwest", "debug-api"], default-features = false }
+alloy-pubsub = { version = "1.7.3", default-features = false }
+alloy-rpc-client = { version = "1.7.3", default-features = false }
+alloy-rpc-types = { version = "1.7.3", features = ["eth"], default-features = false }
+alloy-rpc-types-admin = { version = "1.7.3", default-features = false }
+alloy-rpc-types-anvil = { version = "1.7.3", default-features = false }
+alloy-rpc-types-beacon = { version = "1.7.3", default-features = false }
+alloy-rpc-types-debug = { version = "1.7.3", default-features = false }
+alloy-rpc-types-engine = { version = "1.7.3", default-features = false }
+alloy-rpc-types-eth = { version = "1.7.3", default-features = false }
+alloy-rpc-types-mev = { version = "1.7.3", default-features = false }
+alloy-rpc-types-trace = { version = "1.7.3", default-features = false }
+alloy-rpc-types-txpool = { version = "1.7.3", default-features = false }
+alloy-serde = { version = "1.7.3", default-features = false }
+alloy-signer = { version = "1.7.3", default-features = false }
+alloy-signer-local = { version = "1.7.3", default-features = false }
+alloy-transport = { version = "1.7.3" }
+alloy-transport-http = { version = "1.7.3", features = ["reqwest-rustls-tls"], default-features = false }
+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 }
@@ -530,6 +528,7 @@ notify = { version = "8.0.0", default-features = false, features = ["macos_fseve
 nybbles = { version = "0.4.8", default-features = false }
 once_cell = { version = "1.19", default-features = false, features = ["critical-section"] }
 parking_lot = "0.12"
+quanta = "0.12"
 paste = "1.0"
 rand = "0.9"
 rayon = "1.7"
@@ -652,7 +651,7 @@ ethereum_ssz_derive = "0.10.1"
 jemalloc_pprof = { version = "0.8", default-features = false }
 tikv-jemalloc-ctl = "0.6"
 tikv-jemallocator = "0.6"
-tracy-client = "0.18.0"
+tracy-client = { version = "0.18.0", features = ["demangle"] }
 snmalloc-rs = { version = "0.3.7", features = ["build_cc"] }
 
 aes = "0.8.1"
@@ -665,6 +664,7 @@ cipher = "0.4.3"
 comfy-table = "7.0"
 concat-kdf = "0.1.0"
 crossbeam-channel = "0.5.13"
+crossbeam-utils = "0.8"
 crossterm = "0.29.0"
 csv = "1.3.0"
 ctrlc = "3.4"

Cross.toml

@@ -19,10 +19,11 @@ pre-build = [
 image = "ubuntu:24.04"
 pre-build = [
     "apt update",
-    "apt install --yes gcc gcc-riscv64-linux-gnu libclang-dev make",
+    "apt install --yes gcc gcc-riscv64-linux-gnu g++-riscv64-linux-gnu libclang-dev make",
 ]
 env.passthrough = [
     "CARGO_TARGET_RISCV64GC_UNKNOWN_LINUX_GNU_LINKER=riscv64-linux-gnu-gcc",
+    "CXX_riscv64gc_unknown_linux_gnu=riscv64-linux-gnu-g++",
 ]
 
 [build.env]

Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker.io/docker/dockerfile:1.7-labs
 
-FROM lukemathwalker/cargo-chef:latest-rust-1 AS chef
+FROM lukemathwalker/cargo-chef:latest-rust-1.93 AS chef
 WORKDIR /app
 
 LABEL org.opencontainers.image.source=https://github.com/paradigmxyz/reth

Dockerfile.depot

@@ -4,7 +4,7 @@
 # Usage:
 #   reth: --build-arg BINARY=reth
 
-FROM rust:1 AS builder
+FROM rust:1.93 AS builder
 WORKDIR /app
 
 LABEL org.opencontainers.image.source=https://github.com/paradigmxyz/reth

Makefile

@@ -80,7 +80,7 @@ build-native-%:
 #
 # These commands require that:
 #
-# - `cross` is installed (`cargo install cross`).
+# - `cross` is installed (`cargo install --locked cross`).
 # - Docker is running.
 # - The current user is in the `docker` group.
 #
@@ -261,7 +261,7 @@ lint-typos: ensure-typos
 
 ensure-typos:
 	@if ! command -v typos &> /dev/null; then \
-		echo "typos not found. Please install it by running the command 'cargo install typos-cli' or refer to the following link for more information: https://github.com/crate-ci/typos"; \
+		echo "typos not found. Please install it by running the command 'cargo install --locked typos-cli' or refer to the following link for more information: https://github.com/crate-ci/typos"; \
 		exit 1; \
     fi
 

README.md

@@ -93,7 +93,7 @@ When updating this, also update:
 - .github/workflows/lint.yml
 -->
 
-The Minimum Supported Rust Version (MSRV) of this project is [1.88.0](https://blog.rust-lang.org/2025/06/26/Rust-1.88.0/).
+The Minimum Supported Rust Version (MSRV) of this project is [1.93.0](https://blog.rust-lang.org/2026/01/22/Rust-1.93.0/).
 
 See the docs for detailed instructions on how to [build from source](https://reth.rs/installation/source/).
 

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

@@ -29,6 +29,8 @@ pub(crate) struct BenchContext {
     pub(crate) next_block: u64,
     /// Whether the chain is an OP rollup.
     pub(crate) is_optimism: bool,
+    /// Whether to use `reth_newPayload` endpoint instead of `engine_newPayload*`.
+    pub(crate) use_reth_namespace: bool,
 }
 
 impl BenchContext {
@@ -140,6 +142,14 @@ impl BenchContext {
         };
 
         let next_block = first_block.header.number + 1;
-        Ok(Self { auth_provider, block_provider, benchmark_mode, next_block, is_optimism })
+        let use_reth_namespace = bench_args.reth_new_payload;
+        Ok(Self {
+            auth_provider,
+            block_provider,
+            benchmark_mode,
+            next_block,
+            is_optimism,
+            use_reth_namespace,
+        })
     }
 }

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

@@ -6,7 +6,7 @@ use crate::{
         helpers::{build_payload, parse_gas_limit, prepare_payload_request, rpc_block_to_header},
         output::GasRampPayloadFile,
     },
-    valid_payload::{call_forkchoice_updated, call_new_payload, payload_to_new_payload},
+    valid_payload::{call_forkchoice_updated, call_new_payload_with_reth, payload_to_new_payload},
 };
 use alloy_eips::BlockNumberOrTag;
 use alloy_provider::{network::AnyNetwork, Provider, RootProvider};
@@ -47,6 +47,14 @@ pub struct Command {
     /// Output directory for benchmark results and generated payloads.
     #[arg(long, value_name = "OUTPUT")]
     output: PathBuf,
+
+    /// Use `reth_newPayload` endpoint instead of `engine_newPayload*`.
+    ///
+    /// The `reth_newPayload` endpoint is a reth-specific extension that takes `ExecutionData`
+    /// directly, waits for persistence and cache updates to complete before processing,
+    /// and returns server-side timing breakdowns (latency, persistence wait, cache wait).
+    #[arg(long, default_value = "false", verbatim_doc_comment)]
+    reth_new_payload: bool,
 }
 
 /// Mode for determining when to stop ramping.
@@ -138,6 +146,9 @@ impl Command {
                 );
             }
         }
+        if self.reth_new_payload {
+            info!("Using reth_newPayload endpoint");
+        }
 
         let mut blocks_processed = 0u64;
         let total_benchmark_duration = Instant::now();
@@ -163,7 +174,7 @@ impl Command {
             // Regenerate the payload from the modified block, but keep the original sidecar
             // which contains the actual execution requests data (not just the hash)
             let (payload, _) = ExecutionPayload::from_block_unchecked(block_hash, &block);
-            let (version, params) = payload_to_new_payload(
+            let (version, params, execution_data) = payload_to_new_payload(
                 payload,
                 sidecar,
                 false,
@@ -174,13 +185,18 @@ impl Command {
             // 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, block_hash, params: params.clone() };
+            let file = GasRampPayloadFile {
+                version: version 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");
 
-            call_new_payload(&provider, version, params).await?;
+            let reth_data = self.reth_new_payload.then_some(execution_data);
+            let _ = call_new_payload_with_reth(&provider, version, params, reth_data).await?;
 
             let forkchoice_state = ForkchoiceState {
                 head_block_hash: block_hash,

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

@@ -0,0 +1,156 @@
+//! Prometheus metrics scraper for reth-bench.
+//!
+//! Scrapes a node's Prometheus metrics endpoint after each block to record
+//! execution and state root durations with block-level granularity.
+
+use csv::Writer;
+use eyre::Context;
+use reqwest::Client;
+use serde::Serialize;
+use std::{path::Path, time::Duration};
+use tracing::info;
+
+/// Suffix for the metrics CSV output file.
+pub(crate) const METRICS_OUTPUT_SUFFIX: &str = "metrics.csv";
+
+/// A single row of scraped prometheus metrics for one block.
+#[derive(Debug, Clone, Serialize)]
+pub(crate) struct MetricsRow {
+    /// The block number.
+    pub(crate) block_number: u64,
+    /// EVM execution duration in seconds (from `sync_execution_execution_duration` gauge).
+    pub(crate) execution_duration_secs: Option<f64>,
+    /// State root computation duration in seconds (from
+    /// `sync_block_validation_state_root_duration` gauge).
+    pub(crate) state_root_duration_secs: Option<f64>,
+}
+
+/// Scrapes a Prometheus metrics endpoint after each block to collect
+/// execution and state root durations.
+pub(crate) struct MetricsScraper {
+    /// The full URL of the Prometheus metrics endpoint.
+    url: String,
+    /// Reusable HTTP client.
+    client: Client,
+    /// Collected metrics rows, one per block.
+    rows: Vec<MetricsRow>,
+}
+
+impl MetricsScraper {
+    /// Creates a new scraper if a URL is provided.
+    pub(crate) fn maybe_new(url: Option<String>) -> Option<Self> {
+        url.map(|url| {
+            info!(target: "reth-bench", %url, "Prometheus metrics scraping enabled");
+            let client = Client::builder()
+                .timeout(Duration::from_secs(5))
+                .build()
+                .expect("failed to build reqwest client");
+            Self { url, client, rows: Vec::new() }
+        })
+    }
+
+    /// Scrapes the metrics endpoint and records values for the given block.
+    pub(crate) async fn scrape_after_block(&mut self, block_number: u64) -> eyre::Result<()> {
+        let text = self
+            .client
+            .get(&self.url)
+            .send()
+            .await
+            .wrap_err("failed to fetch metrics endpoint")?
+            .error_for_status()
+            .wrap_err("metrics endpoint returned error status")?
+            .text()
+            .await
+            .wrap_err("failed to read metrics response body")?;
+
+        let execution = parse_gauge(&text, "sync_execution_execution_duration");
+        let state_root = parse_gauge(&text, "sync_block_validation_state_root_duration");
+
+        self.rows.push(MetricsRow {
+            block_number,
+            execution_duration_secs: execution,
+            state_root_duration_secs: state_root,
+        });
+        Ok(())
+    }
+
+    /// Writes collected metrics to a CSV file in the output directory.
+    pub(crate) fn write_csv(&self, output_dir: &Path) -> eyre::Result<()> {
+        let path = output_dir.join(METRICS_OUTPUT_SUFFIX);
+        info!(target: "reth-bench", "Writing scraped metrics to file: {:?}", path);
+        let mut writer = Writer::from_path(&path)?;
+        for row in &self.rows {
+            writer.serialize(row)?;
+        }
+        writer.flush()?;
+        Ok(())
+    }
+}
+
+/// Parses a Prometheus gauge value from exposition-format text.
+///
+/// Searches for lines starting with `name` followed by either a space or `{`
+/// (for labeled metrics), then parses the numeric value. Returns the last
+/// matching sample to handle metrics emitted with multiple label sets.
+fn parse_gauge(text: &str, name: &str) -> Option<f64> {
+    let mut result = None;
+    for line in text.lines() {
+        let line = line.trim();
+        if line.is_empty() || line.starts_with('#') {
+            continue;
+        }
+
+        if !line.starts_with(name) {
+            continue;
+        }
+
+        // Ensure we match the full metric name, not a prefix of another metric.
+        let rest = &line[name.len()..];
+        if !rest.starts_with(' ') && !rest.starts_with('{') {
+            continue;
+        }
+
+        // Format: `metric_name{labels} value [timestamp]` or `metric_name value [timestamp]`
+        // Value is always the second whitespace-separated token.
+        let mut parts = line.split_whitespace();
+        if let Some(value_str) = parts.nth(1) &&
+            let Ok(v) = value_str.parse::<f64>()
+        {
+            result = Some(v);
+        }
+    }
+    result
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_parse_gauge_simple() {
+        let text = r#"# HELP sync_execution_execution_duration Duration of execution
+# TYPE sync_execution_execution_duration gauge
+sync_execution_execution_duration 0.123456
+"#;
+        assert_eq!(parse_gauge(text, "sync_execution_execution_duration"), Some(0.123456));
+    }
+
+    #[test]
+    fn test_parse_gauge_missing() {
+        let text = "some_other_metric 1.0\n";
+        assert_eq!(parse_gauge(text, "sync_execution_execution_duration"), None);
+    }
+
+    #[test]
+    fn test_parse_gauge_with_labels() {
+        let text = "sync_block_validation_state_root_duration{instance=\"node1\"} 0.5\n";
+        assert_eq!(parse_gauge(text, "sync_block_validation_state_root_duration"), Some(0.5));
+    }
+
+    #[test]
+    fn test_parse_gauge_prefix_no_false_match() {
+        let text =
+            "sync_execution_execution_duration_total 99.0\nsync_execution_execution_duration 0.5\n";
+        assert_eq!(parse_gauge(text, "sync_execution_execution_duration"), Some(0.5));
+    }
+}

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

@@ -12,6 +12,7 @@ pub(crate) mod helpers;
 pub use generate_big_block::{
     RawTransaction, RpcTransactionSource, TransactionCollector, TransactionSource,
 };
+pub(crate) mod metrics_scraper;
 mod new_payload_fcu;
 mod new_payload_only;
 mod output;

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

@@ -13,6 +13,7 @@ use crate::{
     bench::{
         context::BenchContext,
         helpers::parse_duration,
+        metrics_scraper::MetricsScraper,
         output::{
             write_benchmark_results, CombinedResult, NewPayloadResult, TotalGasOutput, TotalGasRow,
         },
@@ -20,7 +21,7 @@ use crate::{
             derive_ws_rpc_url, setup_persistence_subscription, PersistenceWaiter,
         },
     },
-    valid_payload::{block_to_new_payload, call_forkchoice_updated, call_new_payload},
+    valid_payload::{block_to_new_payload, call_forkchoice_updated, call_new_payload_with_reth},
 };
 use alloy_provider::Provider;
 use alloy_rpc_types_engine::ForkchoiceState;
@@ -30,7 +31,7 @@ use reth_cli_runner::CliContext;
 use reth_engine_primitives::config::DEFAULT_PERSISTENCE_THRESHOLD;
 use reth_node_core::args::BenchmarkArgs;
 use std::time::{Duration, Instant};
-use tracing::{debug, info};
+use tracing::{debug, info, warn};
 
 /// `reth benchmark new-payload-fcu` command
 #[derive(Debug, Parser)]
@@ -150,10 +151,17 @@ impl Command {
             auth_provider,
             mut next_block,
             is_optimism,
-            ..
+            use_reth_namespace,
         } = BenchContext::new(&self.benchmark, self.rpc_url).await?;
 
         let total_blocks = benchmark_mode.total_blocks();
+
+        let mut metrics_scraper = MetricsScraper::maybe_new(self.benchmark.metrics_url.clone());
+
+        if use_reth_namespace {
+            info!("Using reth_newPayload endpoint");
+        }
+
         let buffer_size = self.rpc_block_buffer_size;
 
         // Use a oneshot channel to propagate errors from the spawned task
@@ -230,16 +238,40 @@ impl Command {
                 finalized_block_hash: finalized,
             };
 
-            let (version, params) = block_to_new_payload(block, is_optimism)?;
+            let (version, params, execution_data) = block_to_new_payload(block, is_optimism)?;
             let start = Instant::now();
-            call_new_payload(&auth_provider, version, params).await?;
+            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?;
 
-            let new_payload_result = NewPayloadResult { gas_used, latency: start.elapsed() };
+            let np_latency =
+                server_timings.as_ref().map(|t| t.latency).unwrap_or_else(|| start.elapsed());
+            let new_payload_result = NewPayloadResult {
+                gas_used,
+                latency: np_latency,
+                persistence_wait: server_timings.as_ref().and_then(|t| t.persistence_wait),
+                execution_cache_wait: server_timings
+                    .as_ref()
+                    .map(|t| t.execution_cache_wait)
+                    .unwrap_or_default(),
+                sparse_trie_wait: server_timings
+                    .as_ref()
+                    .map(|t| t.sparse_trie_wait)
+                    .unwrap_or_default(),
+            };
 
+            let fcu_start = Instant::now();
             call_forkchoice_updated(&auth_provider, version, forkchoice_state, None).await?;
+            let fcu_latency = fcu_start.elapsed();
 
-            let total_latency = start.elapsed();
-            let fcu_latency = total_latency - new_payload_result.latency;
+            let total_latency = if server_timings.is_some() {
+                // When using server-side latency for newPayload, derive total from the
+                // independently measured components to avoid mixing server-side and
+                // client-side (network-inclusive) timings.
+                np_latency + fcu_latency
+            } else {
+                start.elapsed()
+            };
             let combined_result = CombinedResult {
                 block_number,
                 gas_limit,
@@ -259,6 +291,12 @@ impl Command {
             };
             info!(target: "reth-bench", progress, %combined_result);
 
+            if let Some(scraper) = metrics_scraper.as_mut() &&
+                let Err(err) = scraper.scrape_after_block(block_number).await
+            {
+                warn!(target: "reth-bench", %err, block_number, "Failed to scrape metrics");
+            }
+
             if let Some(w) = &mut waiter {
                 w.on_block(block_number).await?;
             }
@@ -284,6 +322,10 @@ impl Command {
             write_benchmark_results(path, &gas_output_results, &combined_results)?;
         }
 
+        if let (Some(path), Some(scraper)) = (&self.benchmark.output, &metrics_scraper) {
+            scraper.write_csv(path)?;
+        }
+
         let gas_output =
             TotalGasOutput::with_combined_results(gas_output_results, &combined_results)?;
 

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

@@ -3,12 +3,13 @@
 use crate::{
     bench::{
         context::BenchContext,
+        metrics_scraper::MetricsScraper,
         output::{
             NewPayloadResult, TotalGasOutput, TotalGasRow, GAS_OUTPUT_SUFFIX,
             NEW_PAYLOAD_OUTPUT_SUFFIX,
         },
     },
-    valid_payload::{block_to_new_payload, call_new_payload},
+    valid_payload::{block_to_new_payload, call_new_payload_with_reth},
 };
 use alloy_provider::Provider;
 use clap::Parser;
@@ -49,10 +50,17 @@ impl Command {
             auth_provider,
             mut next_block,
             is_optimism,
-            ..
+            use_reth_namespace,
         } = BenchContext::new(&self.benchmark, self.rpc_url).await?;
 
         let total_blocks = benchmark_mode.total_blocks();
+
+        let mut metrics_scraper = MetricsScraper::maybe_new(self.benchmark.metrics_url.clone());
+
+        if use_reth_namespace {
+            info!("Using reth_newPayload endpoint");
+        }
+
         let buffer_size = self.rpc_block_buffer_size;
 
         // Use a oneshot channel to propagate errors from the spawned task
@@ -100,12 +108,28 @@ impl Command {
 
             debug!(target: "reth-bench", number=?block.header.number, "Sending payload to engine");
 
-            let (version, params) = block_to_new_payload(block, is_optimism)?;
+            let (version, params, execution_data) = block_to_new_payload(block, is_optimism)?;
 
             let start = Instant::now();
-            call_new_payload(&auth_provider, version, params).await?;
+            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?;
 
-            let new_payload_result = NewPayloadResult { gas_used, latency: start.elapsed() };
+            let latency =
+                server_timings.as_ref().map(|t| t.latency).unwrap_or_else(|| start.elapsed());
+            let new_payload_result = NewPayloadResult {
+                gas_used,
+                latency,
+                persistence_wait: server_timings.as_ref().and_then(|t| t.persistence_wait),
+                execution_cache_wait: server_timings
+                    .as_ref()
+                    .map(|t| t.execution_cache_wait)
+                    .unwrap_or_default(),
+                sparse_trie_wait: server_timings
+                    .as_ref()
+                    .map(|t| t.sparse_trie_wait)
+                    .unwrap_or_default(),
+            };
             blocks_processed += 1;
             let progress = match total_blocks {
                 Some(total) => format!("{blocks_processed}/{total}"),
@@ -121,6 +145,12 @@ impl Command {
             let row =
                 TotalGasRow { block_number, transaction_count, gas_used, time: current_duration };
             results.push((row, new_payload_result));
+
+            if let Some(scraper) = metrics_scraper.as_mut() &&
+                let Err(err) = scraper.scrape_after_block(block_number).await
+            {
+                tracing::warn!(target: "reth-bench", %err, block_number, "Failed to scrape metrics");
+            }
         }
 
         // Check if the spawned task encountered an error
@@ -151,6 +181,10 @@ impl Command {
             }
             writer.flush()?;
 
+            if let Some(scraper) = &metrics_scraper {
+                scraper.write_csv(&path)?;
+            }
+
             info!(target: "reth-bench", "Finished writing benchmark output files to {:?}.", path);
         }
 

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

@@ -27,6 +27,9 @@ pub(crate) struct GasRampPayloadFile {
     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
@@ -37,6 +40,12 @@ pub(crate) struct NewPayloadResult {
     pub(crate) gas_used: u64,
     /// The latency of the `newPayload` call.
     pub(crate) latency: Duration,
+    /// Time spent waiting for persistence. `None` when no persistence was in-flight.
+    pub(crate) persistence_wait: Option<Duration>,
+    /// Time spent waiting for execution cache lock.
+    pub(crate) execution_cache_wait: Duration,
+    /// Time spent waiting for sparse trie lock.
+    pub(crate) sparse_trie_wait: Duration,
 }
 
 impl NewPayloadResult {
@@ -67,9 +76,12 @@ impl Serialize for NewPayloadResult {
     {
         // convert the time to microseconds
         let time = self.latency.as_micros();
-        let mut state = serializer.serialize_struct("NewPayloadResult", 2)?;
+        let mut state = serializer.serialize_struct("NewPayloadResult", 5)?;
         state.serialize_field("gas_used", &self.gas_used)?;
         state.serialize_field("latency", &time)?;
+        state.serialize_field("persistence_wait", &self.persistence_wait.map(|d| d.as_micros()))?;
+        state.serialize_field("execution_cache_wait", &self.execution_cache_wait.as_micros())?;
+        state.serialize_field("sparse_trie_wait", &self.sparse_trie_wait.as_micros())?;
         state.end()
     }
 }
@@ -126,7 +138,7 @@ impl Serialize for CombinedResult {
         let fcu_latency = self.fcu_latency.as_micros();
         let new_payload_latency = self.new_payload_result.latency.as_micros();
         let total_latency = self.total_latency.as_micros();
-        let mut state = serializer.serialize_struct("CombinedResult", 7)?;
+        let mut state = serializer.serialize_struct("CombinedResult", 10)?;
 
         // flatten the new payload result because this is meant for CSV writing
         state.serialize_field("block_number", &self.block_number)?;
@@ -136,6 +148,18 @@ impl Serialize for CombinedResult {
         state.serialize_field("new_payload_latency", &new_payload_latency)?;
         state.serialize_field("fcu_latency", &fcu_latency)?;
         state.serialize_field("total_latency", &total_latency)?;
+        state.serialize_field(
+            "persistence_wait",
+            &self.new_payload_result.persistence_wait.map(|d| d.as_micros()),
+        )?;
+        state.serialize_field(
+            "execution_cache_wait",
+            &self.new_payload_result.execution_cache_wait.as_micros(),
+        )?;
+        state.serialize_field(
+            "sparse_trie_wait",
+            &self.new_payload_result.sparse_trie_wait.as_micros(),
+        )?;
         state.end()
     }
 }

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

@@ -15,6 +15,7 @@ use crate::{
     authenticated_transport::AuthenticatedTransportConnect,
     bench::{
         helpers::parse_duration,
+        metrics_scraper::MetricsScraper,
         output::{
             write_benchmark_results, CombinedResult, GasRampPayloadFile, NewPayloadResult,
             TotalGasOutput, TotalGasRow,
@@ -23,12 +24,15 @@ use crate::{
             derive_ws_rpc_url, setup_persistence_subscription, PersistenceWaiter,
         },
     },
-    valid_payload::{call_forkchoice_updated, call_new_payload},
+    valid_payload::{call_forkchoice_updated, call_new_payload_with_reth},
 };
 use alloy_primitives::B256;
 use alloy_provider::{ext::EngineApi, network::AnyNetwork, Provider, RootProvider};
 use alloy_rpc_client::ClientBuilder;
-use alloy_rpc_types_engine::{ExecutionPayloadEnvelopeV4, ForkchoiceState, JwtSecret};
+use alloy_rpc_types_engine::{
+    CancunPayloadFields, ExecutionData, ExecutionPayloadEnvelopeV4, ExecutionPayloadSidecar,
+    ForkchoiceState, JwtSecret, PraguePayloadFields,
+};
 use clap::Parser;
 use eyre::Context;
 use reth_cli_runner::CliContext;
@@ -124,6 +128,22 @@ pub struct Command {
     /// If not provided, derives from engine RPC URL by changing scheme to ws and port to 8546.
     #[arg(long, value_name = "WS_RPC_URL", verbatim_doc_comment)]
     ws_rpc_url: Option<String>,
+
+    /// Use `reth_newPayload` endpoint instead of `engine_newPayload*`.
+    ///
+    /// The `reth_newPayload` endpoint is a reth-specific extension that takes `ExecutionData`
+    /// directly, waits for persistence and cache updates to complete before processing,
+    /// and returns server-side timing breakdowns (latency, persistence wait, cache wait).
+    #[arg(long, default_value = "false", verbatim_doc_comment)]
+    reth_new_payload: bool,
+
+    /// Optional Prometheus metrics endpoint to scrape after each block.
+    ///
+    /// When provided, reth-bench will fetch metrics from this URL after each
+    /// payload, recording per-block execution and state root durations.
+    /// Results are written to `metrics.csv` in the output directory.
+    #[arg(long = "metrics-url", value_name = "URL", verbatim_doc_comment)]
+    metrics_url: Option<String>,
 }
 
 /// A loaded payload ready for execution.
@@ -163,6 +183,9 @@ impl Command {
                 self.persistence_threshold
             );
         }
+        if self.reth_new_payload {
+            info!("Using reth_newPayload endpoint");
+        }
 
         // Set up waiter based on configured options
         // When both are set: wait at least wait_time, and also wait for persistence if needed
@@ -190,6 +213,8 @@ impl Command {
             (None, false) => None,
         };
 
+        let mut metrics_scraper = MetricsScraper::maybe_new(self.metrics_url.clone());
+
         // Set up authenticated engine provider
         let jwt =
             std::fs::read_to_string(&self.jwt_secret).wrap_err("Failed to read JWT secret file")?;
@@ -248,7 +273,15 @@ impl Command {
                 "Executing gas ramp payload (newPayload + FCU)"
             );
 
-            call_new_payload(&auth_provider, payload.version, payload.file.params.clone()).await?;
+            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?;
 
             let fcu_state = ForkchoiceState {
                 head_block_hash: payload.file.block_hash,
@@ -303,20 +336,47 @@ impl Command {
                 "Sending newPayload"
             );
 
-            let status = auth_provider
-                .new_payload_v4(
-                    execution_payload.clone(),
-                    vec![],
-                    B256::ZERO,
-                    envelope.execution_requests.to_vec(),
-                )
-                .await?;
+            let params = serde_json::to_value((
+                execution_payload.clone(),
+                Vec::<B256>::new(),
+                B256::ZERO,
+                envelope.execution_requests.to_vec(),
+            ))?;
 
-            let new_payload_result = NewPayloadResult { gas_used, latency: start.elapsed() };
+            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() },
+                ),
+            });
 
-            if !status.is_valid() {
-                return Err(eyre::eyre!("Payload rejected: {:?}", status));
-            }
+            let server_timings = call_new_payload_with_reth(
+                &auth_provider,
+                EngineApiMessageVersion::V4,
+                params,
+                reth_data,
+            )
+            .await?;
+
+            let np_latency =
+                server_timings.as_ref().map(|t| t.latency).unwrap_or_else(|| start.elapsed());
+            let new_payload_result = NewPayloadResult {
+                gas_used,
+                latency: np_latency,
+                persistence_wait: server_timings.as_ref().and_then(|t| t.persistence_wait),
+                execution_cache_wait: server_timings
+                    .as_ref()
+                    .map(|t| t.execution_cache_wait)
+                    .unwrap_or_default(),
+                sparse_trie_wait: server_timings
+                    .as_ref()
+                    .map(|t| t.sparse_trie_wait)
+                    .unwrap_or_default(),
+            };
 
             let fcu_state = ForkchoiceState {
                 head_block_hash: block_hash,
@@ -326,10 +386,12 @@ impl Command {
 
             debug!(target: "reth-bench", method = "engine_forkchoiceUpdatedV3", ?fcu_state, "Sending forkchoiceUpdated");
 
+            let fcu_start = Instant::now();
             let fcu_result = auth_provider.fork_choice_updated_v3(fcu_state, None).await?;
+            let fcu_latency = fcu_start.elapsed();
 
-            let total_latency = start.elapsed();
-            let fcu_latency = total_latency - new_payload_result.latency;
+            let total_latency =
+                if server_timings.is_some() { np_latency + fcu_latency } else { start.elapsed() };
 
             let combined_result = CombinedResult {
                 block_number,
@@ -344,6 +406,12 @@ impl Command {
             let progress = format!("{}/{}", i + 1, payloads.len());
             info!(target: "reth-bench", progress, %combined_result);
 
+            if let Some(scraper) = metrics_scraper.as_mut() &&
+                let Err(err) = scraper.scrape_after_block(block_number).await
+            {
+                tracing::warn!(target: "reth-bench", %err, block_number, "Failed to scrape metrics");
+            }
+
             if let Some(w) = &mut waiter {
                 w.on_block(block_number).await?;
             }
@@ -352,7 +420,7 @@ impl Command {
                 TotalGasRow { block_number, transaction_count, gas_used, time: current_duration };
             results.push((gas_row, combined_result));
 
-            debug!(target: "reth-bench", ?status, ?fcu_result, "Payload executed successfully");
+            debug!(target: "reth-bench", ?fcu_result, "Payload executed successfully");
             parent_hash = block_hash;
         }
 
@@ -367,6 +435,10 @@ impl Command {
             write_benchmark_results(path, &gas_output_results, &combined_results)?;
         }
 
+        if let (Some(path), Some(scraper)) = (&self.output, &metrics_scraper) {
+            scraper.write_csv(path)?;
+        }
+
         let gas_output =
             TotalGasOutput::with_combined_results(gas_output_results, &combined_results)?;
         info!(

bin/reth-bench/src/valid_payload.rs

@@ -6,12 +6,14 @@ use alloy_eips::eip7685::Requests;
 use alloy_primitives::B256;
 use alloy_provider::{ext::EngineApi, network::AnyRpcBlock, Network, Provider};
 use alloy_rpc_types_engine::{
-    ExecutionPayload, ExecutionPayloadInputV2, ExecutionPayloadSidecar, ForkchoiceState,
-    ForkchoiceUpdated, PayloadAttributes, PayloadStatus,
+    ExecutionData, ExecutionPayload, ExecutionPayloadInputV2, ExecutionPayloadSidecar,
+    ForkchoiceState, ForkchoiceUpdated, PayloadAttributes, PayloadStatus,
 };
 use alloy_transport::TransportResult;
 use op_alloy_rpc_types_engine::OpExecutionPayloadV4;
 use reth_node_api::EngineApiMessageVersion;
+use serde::Deserialize;
+use std::time::Duration;
 use tracing::{debug, error};
 
 /// An extension trait for providers that implement the engine API, to wait for a VALID response.
@@ -161,10 +163,13 @@ where
     }
 }
 
+/// Converts an RPC block into versioned engine API params and an [`ExecutionData`].
+///
+/// Returns `(version, versioned_params, execution_data)`.
 pub(crate) fn block_to_new_payload(
     block: AnyRpcBlock,
     is_optimism: bool,
-) -> eyre::Result<(EngineApiMessageVersion, serde_json::Value)> {
+) -> eyre::Result<(EngineApiMessageVersion, serde_json::Value, ExecutionData)> {
     let block = block
         .into_inner()
         .map_header(|header| header.map(|h| h.into_header_with_defaults()))
@@ -179,13 +184,19 @@ pub(crate) fn block_to_new_payload(
     payload_to_new_payload(payload, sidecar, is_optimism, block.withdrawals_root, None)
 }
 
+/// Converts an execution payload and sidecar into versioned engine API params and an
+/// [`ExecutionData`].
+///
+/// Returns `(version, versioned_params, execution_data)`.
 pub(crate) fn payload_to_new_payload(
     payload: ExecutionPayload,
     sidecar: ExecutionPayloadSidecar,
     is_optimism: bool,
     withdrawals_root: Option<B256>,
     target_version: Option<EngineApiMessageVersion>,
-) -> eyre::Result<(EngineApiMessageVersion, serde_json::Value)> {
+) -> eyre::Result<(EngineApiMessageVersion, serde_json::Value, ExecutionData)> {
+    let execution_data = ExecutionData { payload: payload.clone(), sidecar: sidecar.clone() };
+
     let (version, params) = match payload {
         ExecutionPayload::V3(payload) => {
             let cancun = sidecar.cancun().unwrap();
@@ -244,7 +255,7 @@ pub(crate) fn payload_to_new_payload(
         }
     };
 
-    Ok((version, params))
+    Ok((version, params, execution_data))
 }
 
 /// Calls the correct `engine_newPayload` method depending on the given [`ExecutionPayload`] and its
@@ -252,32 +263,109 @@ pub(crate) fn payload_to_new_payload(
 ///
 /// # Panics
 /// If the given payload is a V3 payload, but a parent beacon block root is provided as `None`.
+#[allow(dead_code)]
 pub(crate) async fn call_new_payload<N: Network, P: Provider<N>>(
     provider: P,
     version: EngineApiMessageVersion,
     params: serde_json::Value,
-) -> TransportResult<()> {
-    let method = version.method_name();
+) -> TransportResult<Option<NewPayloadTimingBreakdown>> {
+    call_new_payload_with_reth(provider, version, params, None).await
+}
 
-    debug!(target: "reth-bench", method, "Sending newPayload");
+/// 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>,
+    #[serde(default)]
+    execution_cache_wait_us: u64,
+    #[serde(default)]
+    sparse_trie_wait_us: u64,
+}
 
-    let mut status: PayloadStatus = provider.client().request(method, &params).await?;
+/// Server-side timing breakdown from `reth_newPayload` endpoint.
+#[derive(Debug, Clone, Copy, Default)]
+pub(crate) struct NewPayloadTimingBreakdown {
+    /// Server-side execution latency.
+    pub(crate) latency: Duration,
+    /// Time spent waiting for persistence. `None` when no persistence was in-flight.
+    pub(crate) persistence_wait: Option<Duration>,
+    /// Time spent waiting for execution cache lock.
+    pub(crate) execution_cache_wait: Duration,
+    /// Time spent waiting for sparse trie lock.
+    pub(crate) sparse_trie_wait: Duration,
+}
 
-    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:?}"),
-            ))))
+/// Calls either `engine_newPayload*` or `reth_newPayload` depending on whether
+/// `reth_execution_data` 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.
+///
+/// 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,
+    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");
+
+        debug!(target: "reth-bench", method, "Sending newPayload");
+
+        let mut resp: RethPayloadStatus = provider.client().request(method, &reth_params).await?;
+
+        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_syncing() {
-            return Err(alloy_json_rpc::RpcError::UnsupportedFeature(
-                "invalid range: no canonical state found for parent of requested block",
-            ))
+
+        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?;
         }
-        status = provider.client().request(method, &params).await?;
+        Ok(None)
     }
-    Ok(())
 }
 
 /// Calls the correct `engine_forkchoiceUpdated` method depending on the given

bin/reth/Cargo.toml

@@ -190,6 +190,7 @@ min-trace-logs = [
     "reth-node-core/min-trace-logs",
 ]
 
+trie-debug = ["reth-node-builder/trie-debug", "reth-node-core/trie-debug"]
 rocksdb = ["reth-ethereum-cli/rocksdb", "reth-node-core/rocksdb"]
 edge = ["rocksdb"]
 

crates/cli/commands/Cargo.toml

@@ -43,7 +43,7 @@ reth-node-metrics.workspace = true
 reth-ethereum-primitives = { workspace = true, optional = true }
 reth-provider.workspace = true
 reth-prune.workspace = true
-reth-prune-types = { workspace = true, optional = true }
+reth-prune-types.workspace = true
 reth-revm.workspace = true
 reth-stages.workspace = true
 reth-stages-types = { workspace = true, optional = true }
@@ -125,7 +125,7 @@ arbitrary = [
     "reth-stages-types/test-utils",
     "reth-trie-common/test-utils",
     "reth-codecs/arbitrary",
-    "reth-prune-types?/arbitrary",
+    "reth-prune-types/arbitrary",
     "reth-stages-types?/arbitrary",
     "reth-trie-common/arbitrary",
     "alloy-consensus/arbitrary",

crates/cli/commands/src/common.rs

@@ -89,13 +89,15 @@ impl<C: ChainSpecParser> EnvironmentArgs<C> {
     /// Initializes environment according to [`AccessRights`] and returns an instance of
     /// [`Environment`].
     ///
-    /// Internally builds a [`reth_tasks::Runtime`] attached to the current tokio handle for
-    /// parallel storage I/O.
-    pub fn init<N: CliNodeTypes>(&self, access: AccessRights) -> eyre::Result<Environment<N>>
+    /// The provided `runtime` is used for parallel storage I/O.
+    pub fn init<N: CliNodeTypes>(
+        &self,
+        access: AccessRights,
+        runtime: reth_tasks::Runtime,
+    ) -> eyre::Result<Environment<N>>
     where
         C: ChainSpecParser<ChainSpec = N::ChainSpec>,
     {
-        let runtime = reth_tasks::Runtime::with_existing_handle(tokio::runtime::Handle::current())?;
         let data_dir = self.datadir.clone().resolve_datadir(self.chain.chain());
         let db_path = data_dir.db();
         let sf_path = data_dir.static_files();

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

@@ -16,6 +16,7 @@ mod copy;
 mod diff;
 mod get;
 mod list;
+mod prune_checkpoints;
 mod repair_trie;
 mod settings;
 mod state;
@@ -67,6 +68,8 @@ pub enum Subcommands {
     Path,
     /// Manage storage settings
     Settings(settings::Command),
+    /// View or set prune checkpoints
+    PruneCheckpoints(prune_checkpoints::Command),
     /// Gets storage size information for an account
     AccountStorage(account_storage::Command),
     /// Gets account state and storage at a specific block
@@ -83,7 +86,8 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> Command<C>
         /// provided command.
         macro_rules! db_exec {
             ($env:expr, $tool:ident, $N:ident, $access_rights:expr, $command:block) => {
-                let Environment { provider_factory, .. } = $env.init::<$N>($access_rights)?;
+                let Environment { provider_factory, .. } =
+                    $env.init::<$N>($access_rights, ctx.task_executor.clone())?;
 
                 let $tool = DbTool::new(provider_factory)?;
                 $command;
@@ -204,6 +208,11 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> Command<C>
                     command.execute(&tool)?;
                 });
             }
+            Subcommands::PruneCheckpoints(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/prune_checkpoints.rs

@@ -0,0 +1,221 @@
+//! `reth db prune-checkpoints` command for viewing and setting prune checkpoint values.
+
+use clap::{Args, Parser, Subcommand, ValueEnum};
+use reth_db_common::DbTool;
+use reth_provider::{providers::ProviderNodeTypes, DBProvider, DatabaseProviderFactory};
+use reth_prune_types::{PruneCheckpoint, PruneMode, PruneSegment};
+use reth_storage_api::{PruneCheckpointReader, PruneCheckpointWriter};
+
+use crate::common::AccessRights;
+
+/// `reth db prune-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,
+        }
+    }
+}
+
+#[derive(Debug, Subcommand)]
+enum Subcommands {
+    /// Get prune checkpoint(s) from database.
+    ///
+    /// Shows the current prune progress for each segment, including the highest
+    /// pruned block/tx number and the active prune mode.
+    Get {
+        /// Specific segment to query. If omitted, shows all segments.
+        #[arg(long, value_enum)]
+        segment: Option<SegmentArg>,
+    },
+    /// Set a prune checkpoint for a segment.
+    ///
+    /// WARNING: Manually setting checkpoints can cause data inconsistencies.
+    /// Only use this if you know what you're doing (e.g., recovering from a
+    /// corrupted checkpoint or forcing a re-prune from a specific block).
+    Set(SetArgs),
+}
+
+/// Arguments for the `set` subcommand
+#[derive(Debug, Args)]
+pub struct SetArgs {
+    /// The prune segment to update
+    #[arg(long, value_enum)]
+    segment: SegmentArg,
+
+    /// Highest pruned block number
+    #[arg(long)]
+    block_number: Option<u64>,
+
+    /// Highest pruned transaction number
+    #[arg(long)]
+    tx_number: Option<u64>,
+
+    /// Prune mode to write: full, distance, or before
+    #[arg(long, value_enum)]
+    mode: PruneModeArg,
+
+    /// Value for distance or before mode (required unless mode is full)
+    #[arg(long, required_if_eq_any([("mode", "distance"), ("mode", "before")]))]
+    mode_value: Option<u64>,
+}
+
+/// CLI-friendly prune segment names (excludes deprecated variants)
+#[derive(Debug, Clone, Copy, ValueEnum)]
+#[clap(rename_all = "kebab-case")]
+pub enum SegmentArg {
+    SenderRecovery,
+    TransactionLookup,
+    Receipts,
+    ContractLogs,
+    AccountHistory,
+    StorageHistory,
+    Bodies,
+}
+
+impl From<SegmentArg> for PruneSegment {
+    fn from(arg: SegmentArg) -> Self {
+        match arg {
+            SegmentArg::SenderRecovery => Self::SenderRecovery,
+            SegmentArg::TransactionLookup => Self::TransactionLookup,
+            SegmentArg::Receipts => Self::Receipts,
+            SegmentArg::ContractLogs => Self::ContractLogs,
+            SegmentArg::AccountHistory => Self::AccountHistory,
+            SegmentArg::StorageHistory => Self::StorageHistory,
+            SegmentArg::Bodies => Self::Bodies,
+        }
+    }
+}
+
+/// CLI-friendly prune mode
+#[derive(Debug, Clone, Copy, ValueEnum)]
+#[clap(rename_all = "kebab-case")]
+pub enum PruneModeArg {
+    /// Prune all blocks
+    Full,
+    /// Keep the last N blocks (requires --mode-value)
+    Distance,
+    /// Prune blocks before a specific block number (requires --mode-value)
+    Before,
+}
+
+impl Command {
+    /// Execute the command
+    pub fn execute<N: ProviderNodeTypes>(self, tool: &DbTool<N>) -> eyre::Result<()> {
+        match self.command {
+            Subcommands::Get { segment } => Self::get(tool, segment),
+            Subcommands::Set(args) => Self::set(tool, args),
+        }
+    }
+
+    fn get<N: ProviderNodeTypes>(
+        tool: &DbTool<N>,
+        segment: Option<SegmentArg>,
+    ) -> eyre::Result<()> {
+        let provider = tool.provider_factory.provider()?;
+
+        match segment {
+            Some(seg) => {
+                let segment: PruneSegment = seg.into();
+                match provider.get_prune_checkpoint(segment)? {
+                    Some(checkpoint) => print_checkpoint(segment, &checkpoint),
+                    None => println!("No checkpoint found for {segment}"),
+                }
+            }
+            None => {
+                let mut checkpoints = provider.get_prune_checkpoints()?;
+                checkpoints.sort_by_key(|(seg, _)| *seg);
+                if checkpoints.is_empty() {
+                    println!("No prune checkpoints found.");
+                } else {
+                    println!(
+                        "{:<25} {:>15} {:>15} {:>20}",
+                        "Segment", "Block Number", "Tx Number", "Prune Mode"
+                    );
+                    println!("{}", "-".repeat(80));
+                    for (segment, checkpoint) in &checkpoints {
+                        println!(
+                            "{:<25} {:>15} {:>15} {:>20}",
+                            segment.to_string(),
+                            fmt_opt(checkpoint.block_number),
+                            fmt_opt(checkpoint.tx_number),
+                            fmt_mode(&checkpoint.prune_mode),
+                        );
+                    }
+                }
+            }
+        }
+
+        Ok(())
+    }
+
+    fn set<N: ProviderNodeTypes>(tool: &DbTool<N>, args: SetArgs) -> eyre::Result<()> {
+        eyre::ensure!(
+            args.block_number.is_some() || args.tx_number.is_some(),
+            "at least one of --block-number or --tx-number must be provided"
+        );
+
+        let prune_mode = match args.mode {
+            PruneModeArg::Full => PruneMode::Full,
+            PruneModeArg::Distance => PruneMode::Distance(
+                args.mode_value
+                    .ok_or_else(|| eyre::eyre!("--mode-value is required for distance mode"))?,
+            ),
+            PruneModeArg::Before => PruneMode::Before(
+                args.mode_value
+                    .ok_or_else(|| eyre::eyre!("--mode-value is required for before mode"))?,
+            ),
+        };
+
+        let segment: PruneSegment = args.segment.into();
+        let checkpoint = PruneCheckpoint {
+            block_number: args.block_number,
+            tx_number: args.tx_number,
+            prune_mode,
+        };
+
+        let provider_rw = tool.provider_factory.database_provider_rw()?;
+
+        // Show previous value if any
+        if let Some(prev) = provider_rw.get_prune_checkpoint(segment)? {
+            println!("Previous checkpoint for {segment}:");
+            print_checkpoint(segment, &prev);
+            println!();
+        }
+
+        provider_rw.save_prune_checkpoint(segment, checkpoint)?;
+        provider_rw.commit()?;
+
+        println!("Updated checkpoint for {segment}:");
+        print_checkpoint(segment, &checkpoint);
+
+        Ok(())
+    }
+}
+
+fn print_checkpoint(segment: PruneSegment, checkpoint: &PruneCheckpoint) {
+    println!("  Segment:      {segment}");
+    println!("  Block Number: {}", fmt_opt(checkpoint.block_number));
+    println!("  Tx Number:    {}", fmt_opt(checkpoint.tx_number));
+    println!("  Prune Mode:   {}", fmt_mode(&checkpoint.prune_mode));
+}
+
+fn fmt_opt(val: Option<u64>) -> String {
+    val.map_or("-".to_string(), |n| n.to_string())
+}
+
+fn fmt_mode(mode: &PruneMode) -> String {
+    match mode {
+        PruneMode::Full => "Full".to_string(),
+        PruneMode::Distance(d) => format!("Distance({d})"),
+        PruneMode::Before(b) => format!("Before({b})"),
+    }
+}

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

@@ -285,7 +285,6 @@ fn verify_and_repair<N: ProviderNodeTypes>(tool: &DbTool<N>) -> eyre::Result<()>
                 // (We can't just use `upsert` method with a dup cursor, it's not properly
                 // supported)
                 let nibbles = StoredNibblesSubKey(path);
-                let entry = StorageTrieEntry { nibbles: nibbles.clone(), node };
                 if storage_trie_cursor
                     .seek_by_key_subkey(account, nibbles.clone())?
                     .filter(|v| v.nibbles == nibbles)
@@ -293,6 +292,7 @@ fn verify_and_repair<N: ProviderNodeTypes>(tool: &DbTool<N>) -> eyre::Result<()>
                 {
                     storage_trie_cursor.delete_current()?;
                 }
+                let entry = StorageTrieEntry { nibbles, node };
                 storage_trie_cursor.upsert(account, &entry)?;
             }
             Output::Progress(path) => {

crates/cli/commands/src/download.rs

@@ -384,15 +384,19 @@ fn resumable_download(url: &str, target_dir: &Path) -> Result<(PathBuf, u64)> {
     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
         {
-            fs::rename(&part_path, &final_path)?;
-            info!(target: "reth::cli", "Download complete: {}", final_path.display());
-            return Ok((final_path, total));
+            return finalize_download(total);
         }
 
         if attempt > 1 {
@@ -476,9 +480,7 @@ fn resumable_download(url: &str, target_dir: &Path) -> Result<(PathBuf, u64)> {
             continue;
         }
 
-        fs::rename(&part_path, &final_path)?;
-        info!(target: "reth::cli", "Download complete: {}", final_path.display());
-        return Ok((final_path, current_total));
+        return finalize_download(current_total);
     }
 
     Err(last_error

crates/cli/commands/src/export_era.rs

@@ -44,11 +44,11 @@ pub struct ExportArgs {
 
 impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> ExportEraCommand<C> {
     /// Execute `export-era` command
-    pub async fn execute<N>(self) -> eyre::Result<()>
+    pub async fn execute<N>(self, runtime: reth_tasks::Runtime) -> eyre::Result<()>
     where
         N: CliNodeTypes<ChainSpec = C::ChainSpec>,
     {
-        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RO)?;
+        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RO, runtime)?;
 
         // Either specified path or default to `<data-dir>/<chain>/era1-export/`
         let data_dir = match &self.export.path {

crates/cli/commands/src/import.rs

@@ -47,6 +47,7 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> ImportComm
     pub async fn execute<N, Comp>(
         self,
         components: impl FnOnce(Arc<N::ChainSpec>) -> Comp,
+        runtime: reth_tasks::Runtime,
     ) -> eyre::Result<()>
     where
         N: CliNodeTypes<ChainSpec = C::ChainSpec>,
@@ -54,7 +55,8 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> ImportComm
     {
         info!(target: "reth::cli", "reth {} starting", version_metadata().short_version);
 
-        let Environment { provider_factory, config, .. } = self.env.init::<N>(AccessRights::RW)?;
+        let Environment { provider_factory, config, .. } =
+            self.env.init::<N>(AccessRights::RW, runtime.clone())?;
 
         let components = components(provider_factory.chain_spec());
 
@@ -85,6 +87,7 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> ImportComm
                 &config,
                 executor.clone(),
                 consensus.clone(),
+                runtime.clone(),
             )
             .await?;
 

crates/cli/commands/src/import_core.rs

@@ -87,6 +87,7 @@ pub async fn import_blocks_from_file<N>(
     config: &Config,
     executor: impl ConfigureEvm<Primitives = N::Primitives> + 'static,
     consensus: Arc<impl FullConsensus<N::Primitives> + 'static>,
+    runtime: reth_tasks::Runtime,
 ) -> eyre::Result<ImportResult>
 where
     N: ProviderNodeTypes,
@@ -147,6 +148,7 @@ where
             static_file_producer.clone(),
             import_config.no_state,
             executor.clone(),
+            runtime.clone(),
         )?;
 
         // override the tip
@@ -257,6 +259,7 @@ where
 ///
 /// If configured to execute, all stages will run. Otherwise, only stages that don't require state
 /// will run.
+#[expect(clippy::too_many_arguments)]
 pub fn build_import_pipeline_impl<N, C, E>(
     config: &Config,
     provider_factory: ProviderFactory<N>,
@@ -265,6 +268,7 @@ pub fn build_import_pipeline_impl<N, C, E>(
     static_file_producer: StaticFileProducer<ProviderFactory<N>>,
     disable_exec: bool,
     evm_config: E,
+    runtime: reth_tasks::Runtime,
 ) -> eyre::Result<(Pipeline<N>, impl futures::Stream<Item = NodeEvent<N::Primitives>> + use<N, C, E>)>
 where
     N: ProviderNodeTypes,
@@ -283,7 +287,7 @@ where
 
     let mut header_downloader = ReverseHeadersDownloaderBuilder::new(config.stages.headers)
         .build(file_client.clone(), consensus.clone())
-        .into_task();
+        .into_task_with(&runtime);
     // TODO: The pipeline should correctly configure the downloader on its own.
     // Find the possibility to remove unnecessary pre-configuration.
     header_downloader.update_local_head(local_head);
@@ -291,7 +295,7 @@ where
 
     let mut body_downloader = BodiesDownloaderBuilder::new(config.stages.bodies)
         .build(file_client.clone(), consensus.clone(), provider_factory.clone())
-        .into_task();
+        .into_task_with(&runtime);
     // TODO: The pipeline should correctly configure the downloader on its own.
     // Find the possibility to remove unnecessary pre-configuration.
     body_downloader

crates/cli/commands/src/import_era.rs

@@ -64,13 +64,14 @@ impl TryFromChain for ChainKind {
 
 impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> ImportEraCommand<C> {
     /// Execute `import-era` command
-    pub async fn execute<N>(self) -> eyre::Result<()>
+    pub async fn execute<N>(self, runtime: reth_tasks::Runtime) -> eyre::Result<()>
     where
         N: CliNodeTypes<ChainSpec = C::ChainSpec>,
     {
         info!(target: "reth::cli", "reth {} starting", version_metadata().short_version);
 
-        let Environment { provider_factory, config, .. } = self.env.init::<N>(AccessRights::RW)?;
+        let Environment { provider_factory, config, .. } =
+            self.env.init::<N>(AccessRights::RW, runtime)?;
 
         let mut hash_collector = Collector::new(config.stages.etl.file_size, config.stages.etl.dir);
 

crates/cli/commands/src/init_cmd.rs

@@ -18,10 +18,13 @@ pub struct InitCommand<C: ChainSpecParser> {
 
 impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> InitCommand<C> {
     /// Execute the `init` command
-    pub async fn execute<N: CliNodeTypes<ChainSpec = C::ChainSpec>>(self) -> eyre::Result<()> {
+    pub async fn execute<N: CliNodeTypes<ChainSpec = C::ChainSpec>>(
+        self,
+        runtime: reth_tasks::Runtime,
+    ) -> eyre::Result<()> {
         info!(target: "reth::cli", "reth init starting");
 
-        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RW)?;
+        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RW, runtime)?;
 
         let genesis_block_number = provider_factory.chain_spec().genesis_header().number();
         let hash = provider_factory

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

@@ -65,7 +65,7 @@ pub struct InitStateCommand<C: ChainSpecParser> {
 
 impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> InitStateCommand<C> {
     /// Execute the `init` command
-    pub async fn execute<N>(self) -> eyre::Result<()>
+    pub async fn execute<N>(self, runtime: reth_tasks::Runtime) -> eyre::Result<()>
     where
         N: CliNodeTypes<
             ChainSpec = C::ChainSpec,
@@ -74,7 +74,8 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> InitStateC
     {
         info!(target: "reth::cli", "Reth init-state starting");
 
-        let Environment { config, provider_factory, .. } = self.env.init::<N>(AccessRights::RW)?;
+        let Environment { config, provider_factory, .. } =
+            self.env.init::<N>(AccessRights::RW, runtime)?;
 
         let static_file_provider = provider_factory.static_file_provider();
         let provider_rw = provider_factory.database_provider_rw()?;

crates/cli/commands/src/p2p/mod.rs

@@ -16,6 +16,7 @@ use reth_node_core::{
     args::{DatadirArgs, NetworkArgs},
     utils::get_single_header,
 };
+use reth_tasks::Runtime;
 
 pub mod bootnode;
 pub mod enode;
@@ -194,17 +195,18 @@ impl<C: ChainSpecParser> DownloadArgs<C> {
         let rlpx_socket = (self.network.addr, self.network.port).into();
         let boot_nodes = self.chain.bootnodes().unwrap_or_default();
 
-        let net = NetworkConfigBuilder::<N::NetworkPrimitives>::new(p2p_secret_key)
-            .peer_config(config.peers_config_with_basic_nodes_from_file(None))
-            .external_ip_resolver(self.network.nat.clone())
-            .network_id(self.network.network_id)
-            .boot_nodes(boot_nodes.clone())
-            .apply(|builder| {
-                self.network.discovery.apply_to_builder(builder, rlpx_socket, boot_nodes)
-            })
-            .build_with_noop_provider(self.chain.clone())
-            .manager()
-            .await?;
+        let net =
+            NetworkConfigBuilder::<N::NetworkPrimitives>::new(p2p_secret_key, Runtime::test())
+                .peer_config(config.peers_config_with_basic_nodes_from_file(None))
+                .external_ip_resolver(self.network.nat.clone())
+                .network_id(self.network.network_id)
+                .boot_nodes(boot_nodes.clone())
+                .apply(|builder| {
+                    self.network.discovery.apply_to_builder(builder, rlpx_socket, boot_nodes)
+                })
+                .build_with_noop_provider(self.chain.clone())
+                .manager()
+                .await?;
         let handle = net.handle().clone();
         tokio::task::spawn(net);
 

crates/cli/commands/src/prune.rs

@@ -36,7 +36,7 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> PruneComma
         self,
         ctx: CliContext,
     ) -> eyre::Result<()> {
-        let env = self.env.init::<N>(AccessRights::RW)?;
+        let env = self.env.init::<N>(AccessRights::RW, ctx.task_executor.clone())?;
         let provider_factory = env.provider_factory;
         let config = env.config.prune;
         let data_dir = env.data_dir;

crates/cli/commands/src/re_execute.rs

@@ -60,11 +60,15 @@ impl<C: ChainSpecParser> Command<C> {
 
 impl<C: ChainSpecParser<ChainSpec: EthChainSpec + Hardforks + EthereumHardforks>> Command<C> {
     /// Execute `re-execute` command
-    pub async fn execute<N>(self, components: impl CliComponentsBuilder<N>) -> eyre::Result<()>
+    pub async fn execute<N>(
+        self,
+        components: impl CliComponentsBuilder<N>,
+        runtime: reth_tasks::Runtime,
+    ) -> eyre::Result<()>
     where
         N: CliNodeTypes<ChainSpec = C::ChainSpec>,
     {
-        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RO)?;
+        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RO, runtime)?;
 
         let components = components(provider_factory.chain_spec());
 

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

@@ -37,11 +37,11 @@ pub struct Command<C: ChainSpecParser> {
 
 impl<C: ChainSpecParser> Command<C> {
     /// Execute `db` command
-    pub async fn execute<N: CliNodeTypes>(self) -> eyre::Result<()>
+    pub async fn execute<N: CliNodeTypes>(self, runtime: reth_tasks::Runtime) -> eyre::Result<()>
     where
         C: ChainSpecParser<ChainSpec = N::ChainSpec>,
     {
-        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RW)?;
+        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RW, runtime)?;
 
         let tool = DbTool::new(provider_factory)?;
 

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

@@ -16,6 +16,7 @@ use reth_stages::{stages::ExecutionStage, Stage, StageCheckpoint, UnwindInput};
 use std::sync::Arc;
 use tracing::info;
 
+#[expect(clippy::too_many_arguments)]
 pub(crate) async fn dump_execution_stage<N, E, C>(
     db_tool: &DbTool<N>,
     from: u64,
@@ -24,6 +25,7 @@ pub(crate) async fn dump_execution_stage<N, E, C>(
     should_run: bool,
     evm_config: E,
     consensus: C,
+    runtime: reth_tasks::Runtime,
 ) -> eyre::Result<()>
 where
     N: ProviderNodeTypes<DB = DatabaseEnv>,
@@ -37,7 +39,6 @@ where
     unwind_and_copy(db_tool, from, tip_block_number, &output_db, evm_config.clone())?;
 
     if should_run {
-        let runtime = reth_tasks::Runtime::with_existing_handle(tokio::runtime::Handle::current())?;
         dry_run(
             ProviderFactory::<N>::new(
                 output_db,

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

@@ -18,6 +18,7 @@ pub(crate) async fn dump_hashing_account_stage<N: ProviderNodeTypes<DB = Databas
     to: BlockNumber,
     output_datadir: ChainPath<DataDirPath>,
     should_run: bool,
+    runtime: reth_tasks::Runtime,
 ) -> Result<()> {
     let (output_db, tip_block_number) = setup(from, to, &output_datadir.db(), db_tool)?;
 
@@ -33,7 +34,6 @@ pub(crate) async fn dump_hashing_account_stage<N: ProviderNodeTypes<DB = Databas
     unwind_and_copy(db_tool, from, tip_block_number, &output_db)?;
 
     if should_run {
-        let runtime = reth_tasks::Runtime::with_existing_handle(tokio::runtime::Handle::current())?;
         dry_run(
             ProviderFactory::<N>::new(
                 output_db,

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

@@ -17,13 +17,13 @@ pub(crate) async fn dump_hashing_storage_stage<N: ProviderNodeTypes<DB = Databas
     to: u64,
     output_datadir: ChainPath<DataDirPath>,
     should_run: bool,
+    runtime: reth_tasks::Runtime,
 ) -> Result<()> {
     let (output_db, tip_block_number) = setup(from, to, &output_datadir.db(), db_tool)?;
 
     unwind_and_copy(db_tool, from, tip_block_number, &output_db)?;
 
     if should_run {
-        let runtime = reth_tasks::Runtime::with_existing_handle(tokio::runtime::Handle::current())?;
         dry_run(
             ProviderFactory::<N>::new(
                 output_db,

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

@@ -24,6 +24,7 @@ use reth_stages::{
 };
 use tracing::info;
 
+#[expect(clippy::too_many_arguments)]
 pub(crate) async fn dump_merkle_stage<N>(
     db_tool: &DbTool<N>,
     from: BlockNumber,
@@ -32,6 +33,7 @@ pub(crate) async fn dump_merkle_stage<N>(
     should_run: bool,
     evm_config: impl ConfigureEvm<Primitives = N::Primitives>,
     consensus: impl FullConsensus<N::Primitives> + 'static,
+    runtime: reth_tasks::Runtime,
 ) -> Result<()>
 where
     N: ProviderNodeTypes<DB = DatabaseEnv>,
@@ -57,7 +59,6 @@ where
     unwind_and_copy(db_tool, (from, to), tip_block_number, &output_db, evm_config, consensus)?;
 
     if should_run {
-        let runtime = reth_tasks::Runtime::with_existing_handle(tokio::runtime::Handle::current())?;
         dry_run(
             ProviderFactory::<N>::new(
                 output_db,

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

@@ -72,30 +72,36 @@ pub struct StageCommand {
 }
 
 macro_rules! handle_stage {
-    ($stage_fn:ident, $tool:expr, $command:expr) => {{
+    ($stage_fn:ident, $tool:expr, $command:expr, $runtime:expr) => {{
         let StageCommand { output_datadir, from, to, dry_run, .. } = $command;
         let output_datadir =
             output_datadir.with_chain($tool.chain().chain(), DatadirArgs::default());
-        $stage_fn($tool, *from, *to, output_datadir, *dry_run).await?
+        $stage_fn($tool, *from, *to, output_datadir, *dry_run, $runtime).await?
     }};
 
-    ($stage_fn:ident, $tool:expr, $command:expr, $executor:expr, $consensus:expr) => {{
+    ($stage_fn:ident, $tool:expr, $command:expr, $executor:expr, $consensus:expr, $runtime:expr) => {{
         let StageCommand { output_datadir, from, to, dry_run, .. } = $command;
         let output_datadir =
             output_datadir.with_chain($tool.chain().chain(), DatadirArgs::default());
-        $stage_fn($tool, *from, *to, output_datadir, *dry_run, $executor, $consensus).await?
+        $stage_fn($tool, *from, *to, output_datadir, *dry_run, $executor, $consensus, $runtime)
+            .await?
     }};
 }
 
 impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> Command<C> {
     /// Execute `dump-stage` command
-    pub async fn execute<N, Comp, F>(self, components: F) -> eyre::Result<()>
+    pub async fn execute<N, Comp, F>(
+        self,
+        components: F,
+        runtime: reth_tasks::Runtime,
+    ) -> eyre::Result<()>
     where
         N: CliNodeTypes<ChainSpec = C::ChainSpec>,
         Comp: CliNodeComponents<N>,
         F: FnOnce(Arc<C::ChainSpec>) -> Comp,
     {
-        let Environment { provider_factory, .. } = self.env.init::<N>(AccessRights::RO)?;
+        let Environment { provider_factory, .. } =
+            self.env.init::<N>(AccessRights::RO, runtime.clone())?;
         let tool = DbTool::new(provider_factory)?;
         let components = components(tool.chain());
         let evm_config = components.evm_config().clone();
@@ -103,12 +109,23 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> Command<C>
 
         match &self.command {
             Stages::Execution(cmd) => {
-                handle_stage!(dump_execution_stage, &tool, cmd, evm_config, consensus)
+                handle_stage!(
+                    dump_execution_stage,
+                    &tool,
+                    cmd,
+                    evm_config,
+                    consensus,
+                    runtime.clone()
+                )
+            }
+            Stages::StorageHashing(cmd) => {
+                handle_stage!(dump_hashing_storage_stage, &tool, cmd, runtime.clone())
+            }
+            Stages::AccountHashing(cmd) => {
+                handle_stage!(dump_hashing_account_stage, &tool, cmd, runtime.clone())
             }
-            Stages::StorageHashing(cmd) => handle_stage!(dump_hashing_storage_stage, &tool, cmd),
-            Stages::AccountHashing(cmd) => handle_stage!(dump_hashing_account_stage, &tool, cmd),
             Stages::Merkle(cmd) => {
-                handle_stage!(dump_merkle_stage, &tool, cmd, evm_config, consensus)
+                handle_stage!(dump_merkle_stage, &tool, cmd, evm_config, consensus, runtime.clone())
             }
         }
 

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

@@ -49,11 +49,12 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + Hardforks + EthereumHardforks>
         N: CliNodeTypes<ChainSpec = C::ChainSpec>,
         Comp: CliNodeComponents<N>,
     {
+        let executor = ctx.task_executor.clone();
         match self.command {
             Subcommands::Run(command) => command.execute::<N, _, _>(ctx, components).await,
-            Subcommands::Drop(command) => command.execute::<N>().await,
-            Subcommands::Dump(command) => command.execute::<N, _, _>(components).await,
-            Subcommands::Unwind(command) => command.execute::<N, _, _>(components).await,
+            Subcommands::Drop(command) => command.execute::<N>(executor).await,
+            Subcommands::Dump(command) => command.execute::<N, _, _>(components, executor).await,
+            Subcommands::Unwind(command) => command.execute::<N, _, _>(components, executor).await,
         }
     }
 }

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

@@ -119,8 +119,9 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + Hardforks + EthereumHardforks>
         // Does not do anything on windows.
         let _ = fdlimit::raise_fd_limit();
 
+        let runtime = ctx.task_executor.clone();
         let Environment { provider_factory, config, data_dir } =
-            self.env.init::<N>(AccessRights::RW)?;
+            self.env.init::<N>(AccessRights::RW, ctx.task_executor.clone())?;
 
         let mut provider_rw = provider_factory.database_provider_rw()?;
         let components = components(provider_factory.chain_spec());
@@ -171,6 +172,7 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + Hardforks + EthereumHardforks>
                             provider_factory.chain_spec(),
                             p2p_secret_key,
                             default_peers_path,
+                            runtime.clone(),
                         )
                         .build(provider_factory.clone())
                         .start_network()
@@ -226,6 +228,7 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + Hardforks + EthereumHardforks>
                             provider_factory.chain_spec(),
                             p2p_secret_key,
                             default_peers_path,
+                            runtime.clone(),
                         )
                         .build(provider_factory.clone())
                         .start_network()

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

@@ -46,12 +46,14 @@ impl<C: ChainSpecParser<ChainSpec: EthChainSpec + EthereumHardforks>> Command<C>
     pub async fn execute<N: CliNodeTypes<ChainSpec = C::ChainSpec>, F, Comp>(
         self,
         components: F,
+        runtime: reth_tasks::Runtime,
     ) -> eyre::Result<()>
     where
         Comp: CliNodeComponents<N>,
         F: FnOnce(Arc<C::ChainSpec>) -> Comp,
     {
-        let Environment { provider_factory, config, .. } = self.env.init::<N>(AccessRights::RW)?;
+        let Environment { provider_factory, config, .. } =
+            self.env.init::<N>(AccessRights::RW, runtime)?;
 
         let target = self.command.unwind_target(provider_factory.clone())?;
 

crates/cli/runner/src/lib.rs

@@ -47,6 +47,11 @@ impl CliRunner {
         self
     }
 
+    /// Returns a clone of the underlying [`Runtime`](reth_tasks::Runtime).
+    pub fn runtime(&self) -> reth_tasks::Runtime {
+        self.runtime.clone()
+    }
+
     /// Executes an async block on the runtime and blocks until completion.
     pub fn block_on<F, T>(&self, fut: F) -> T
     where

crates/e2e-test-utils/src/payload.rs

@@ -54,12 +54,20 @@ impl<T: PayloadTypes> PayloadTestContext<T> {
         Ok(())
     }
 
-    /// Wait until the best built payload is ready
+    /// Wait until the best built payload is ready.
+    ///
+    /// Panics if the payload builder does not produce a non-empty payload within 30 seconds.
     pub async fn wait_for_built_payload(&self, payload_id: PayloadId) {
+        let start = std::time::Instant::now();
         loop {
             let payload =
                 self.payload_builder.best_payload(payload_id).await.transpose().ok().flatten();
             if payload.is_none_or(|p| p.block().body().transactions().is_empty()) {
+                assert!(
+                    start.elapsed() < std::time::Duration::from_secs(30),
+                    "timed out waiting for a non-empty payload for {payload_id} — \
+                     check that the chain spec supports all generated tx types"
+                );
                 tokio::time::sleep(std::time::Duration::from_millis(20)).await;
                 continue
             }

crates/e2e-test-utils/src/setup_builder.rs

@@ -112,7 +112,7 @@ where
         Vec<NodeHelperType<N, BlockchainProvider<NodeTypesWithDBAdapter<N, TmpDB>>>>,
         Wallet,
     )> {
-        let runtime = Runtime::with_existing_handle(tokio::runtime::Handle::current())?;
+        let runtime = Runtime::test();
 
         let network_config = NetworkArgs {
             discovery: DiscoveryArgs { disable_discovery: true, ..DiscoveryArgs::default() },

crates/e2e-test-utils/src/setup_import.rs

@@ -15,7 +15,6 @@ use reth_provider::{
 };
 use reth_rpc_server_types::RpcModuleSelection;
 use reth_stages_types::StageId;
-use reth_tasks::Runtime;
 use std::{path::Path, sync::Arc};
 use tempfile::TempDir;
 use tracing::{debug, info, span, Level};
@@ -66,7 +65,7 @@ pub async fn setup_engine_with_chain_import(
         + Copy
         + 'static,
 ) -> eyre::Result<ChainImportResult> {
-    let runtime = Runtime::with_existing_handle(tokio::runtime::Handle::current())?;
+    let runtime = reth_tasks::Runtime::test();
 
     let network_config = NetworkArgs {
         discovery: DiscoveryArgs { disable_discovery: true, ..DiscoveryArgs::default() },
@@ -149,6 +148,7 @@ pub async fn setup_engine_with_chain_import(
             &config,
             evm_config,
             consensus,
+            runtime.clone(),
         )
         .await?;
 
@@ -343,6 +343,7 @@ mod tests {
             let evm_config = reth_node_ethereum::EthEvmConfig::new(chain_spec.clone());
             // Use NoopConsensus to skip gas limit validation for test imports
             let consensus = reth_consensus::noop::NoopConsensus::arc();
+            let runtime = reth_tasks::Runtime::test();
 
             let result = import_blocks_from_file(
                 &rlp_path,
@@ -351,6 +352,7 @@ mod tests {
                 &config,
                 evm_config,
                 consensus,
+                runtime,
             )
             .await
             .unwrap();
@@ -509,6 +511,7 @@ mod tests {
         let evm_config = reth_node_ethereum::EthEvmConfig::new(chain_spec.clone());
         // Use NoopConsensus to skip gas limit validation for test imports
         let consensus = reth_consensus::noop::NoopConsensus::arc();
+        let runtime = reth_tasks::Runtime::test();
 
         let result = import_blocks_from_file(
             &rlp_path,
@@ -517,6 +520,7 @@ mod tests {
             &config,
             evm_config,
             consensus,
+            runtime,
         )
         .await
         .unwrap();

crates/engine/local/src/miner.rs

@@ -3,7 +3,7 @@
 use alloy_primitives::{TxHash, B256};
 use alloy_rpc_types_engine::ForkchoiceState;
 use eyre::OptionExt;
-use futures_util::{stream::Fuse, StreamExt};
+use futures_util::{stream::Fuse, Stream, StreamExt};
 use reth_engine_primitives::ConsensusEngineHandle;
 use reth_payload_builder::PayloadBuilderHandle;
 use reth_payload_primitives::{
@@ -14,6 +14,7 @@ use reth_storage_api::BlockReader;
 use reth_transaction_pool::TransactionPool;
 use std::{
     collections::VecDeque,
+    fmt,
     future::Future,
     pin::Pin,
     task::{Context, Poll},
@@ -24,7 +25,6 @@ use tokio_stream::wrappers::ReceiverStream;
 use tracing::error;
 
 /// A mining mode for the local dev engine.
-#[derive(Debug)]
 pub enum MiningMode<Pool: TransactionPool + Unpin> {
     /// In this mode a block is built as soon as
     /// a valid transaction reaches the pool.
@@ -43,6 +43,25 @@ pub enum MiningMode<Pool: TransactionPool + Unpin> {
     },
     /// In this mode a block is built at a fixed interval.
     Interval(Interval),
+    /// In this mode a block is built when the trigger stream yields a value.
+    ///
+    /// This is a general-purpose trigger that can be fired on demand, for example via a channel
+    /// or any other [`Stream`] implementation.
+    Trigger(Pin<Box<dyn Stream<Item = ()> + Send + Sync>>),
+}
+
+impl<Pool: TransactionPool + Unpin> fmt::Debug for MiningMode<Pool> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            Self::Instant { max_transactions, accumulated, .. } => f
+                .debug_struct("Instant")
+                .field("max_transactions", max_transactions)
+                .field("accumulated", accumulated)
+                .finish(),
+            Self::Interval(interval) => f.debug_tuple("Interval").field(interval).finish(),
+            Self::Trigger(_) => f.debug_tuple("Trigger").finish(),
+        }
+    }
 }
 
 impl<Pool: TransactionPool + Unpin> MiningMode<Pool> {
@@ -57,6 +76,14 @@ impl<Pool: TransactionPool + Unpin> MiningMode<Pool> {
         let start = tokio::time::Instant::now() + duration;
         Self::Interval(tokio::time::interval_at(start, duration))
     }
+
+    /// Constructor for a [`MiningMode::Trigger`]
+    ///
+    /// Accepts any stream that yields `()` values, each of which triggers a new block to be
+    /// mined. This can be backed by a channel, a custom stream, or any other async source.
+    pub fn trigger(trigger: impl Stream<Item = ()> + Send + Sync + 'static) -> Self {
+        Self::Trigger(Box::pin(trigger))
+    }
 }
 
 impl<Pool: TransactionPool + Unpin> Future for MiningMode<Pool> {
@@ -91,6 +118,12 @@ impl<Pool: TransactionPool + Unpin> Future for MiningMode<Pool> {
                 }
                 Poll::Pending
             }
+            Self::Trigger(trigger) => {
+                if trigger.poll_next_unpin(cx).is_ready() {
+                    return Poll::Ready(())
+                }
+                Poll::Pending
+            }
         }
     }
 }

crates/engine/primitives/src/config.rs

@@ -32,28 +32,18 @@ fn default_account_worker_count() -> usize {
 /// The size of proof targets chunk to spawn in one multiproof calculation.
 pub const DEFAULT_MULTIPROOF_TASK_CHUNK_SIZE: usize = 60;
 
-/// The size of proof targets chunk to spawn in one multiproof calculation when V2 proofs are
-/// enabled. This is 4x the default chunk size to take advantage of more efficient V2 proof
-/// computation.
-pub const DEFAULT_MULTIPROOF_TASK_CHUNK_SIZE_V2: usize = DEFAULT_MULTIPROOF_TASK_CHUNK_SIZE * 4;
+/// The size of proof targets chunk optimized for small blocks (≤20M gas used).
+/// Benchmarks: <https://gist.github.com/yongkangc/fda9c24846f0ba891376bcf81b002008>
+pub const SMALL_BLOCK_MULTIPROOF_CHUNK_SIZE: usize = 30;
+
+/// Gas threshold below which the small block chunk size is used.
+pub const SMALL_BLOCK_GAS_THRESHOLD: u64 = 20_000_000;
 
 /// Default number of reserved CPU cores for non-reth processes.
 ///
 /// This will be deducted from the thread count of main reth global threadpool.
 pub const DEFAULT_RESERVED_CPU_CORES: usize = 1;
 
-/// Returns the default maximum concurrency for prewarm task based on available parallelism.
-fn default_prewarm_max_concurrency() -> usize {
-    #[cfg(feature = "std")]
-    {
-        std::thread::available_parallelism().map_or(16, |n| n.get())
-    }
-    #[cfg(not(feature = "std"))]
-    {
-        16
-    }
-}
-
 /// Default depth for sparse trie pruning.
 ///
 /// Nodes at this depth and below are converted to hash stubs to reduce memory.
@@ -161,20 +151,14 @@ pub struct TreeConfig {
     /// where immediate payload regeneration is desired despite the head not changing or moving to
     /// an ancestor.
     always_process_payload_attributes_on_canonical_head: bool,
-    /// Maximum concurrency for the prewarm task.
-    prewarm_max_concurrency: usize,
     /// 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 V2 storage proofs.
-    disable_proof_v2: bool,
     /// Whether to disable cache metrics recording (can be expensive with large cached state).
     disable_cache_metrics: bool,
-    /// Whether to disable sparse trie cache.
-    disable_trie_cache: bool,
     /// Depth for sparse trie pruning after state root computation.
     sparse_trie_prune_depth: usize,
     /// Maximum number of storage tries to retain after pruning.
@@ -209,13 +193,10 @@ impl Default for TreeConfig {
             precompile_cache_disabled: false,
             state_root_fallback: false,
             always_process_payload_attributes_on_canonical_head: false,
-            prewarm_max_concurrency: default_prewarm_max_concurrency(),
             allow_unwind_canonical_header: false,
             storage_worker_count: default_storage_worker_count(),
             account_worker_count: default_account_worker_count(),
-            disable_proof_v2: false,
             disable_cache_metrics: false,
-            disable_trie_cache: false,
             sparse_trie_prune_depth: DEFAULT_SPARSE_TRIE_PRUNE_DEPTH,
             sparse_trie_max_storage_tries: DEFAULT_SPARSE_TRIE_MAX_STORAGE_TRIES,
             disable_sparse_trie_cache_pruning: false,
@@ -246,11 +227,9 @@ impl TreeConfig {
         precompile_cache_disabled: bool,
         state_root_fallback: bool,
         always_process_payload_attributes_on_canonical_head: bool,
-        prewarm_max_concurrency: usize,
         allow_unwind_canonical_header: bool,
         storage_worker_count: usize,
         account_worker_count: usize,
-        disable_proof_v2: bool,
         disable_cache_metrics: bool,
         sparse_trie_prune_depth: usize,
         sparse_trie_max_storage_tries: usize,
@@ -275,13 +254,10 @@ impl TreeConfig {
             precompile_cache_disabled,
             state_root_fallback,
             always_process_payload_attributes_on_canonical_head,
-            prewarm_max_concurrency,
             allow_unwind_canonical_header,
             storage_worker_count,
             account_worker_count,
-            disable_proof_v2,
             disable_cache_metrics,
-            disable_trie_cache: false,
             sparse_trie_prune_depth,
             sparse_trie_max_storage_tries,
             disable_sparse_trie_cache_pruning: false,
@@ -324,16 +300,9 @@ impl TreeConfig {
         self.multiproof_chunk_size
     }
 
-    /// Return the multiproof task chunk size, using the V2 default if V2 proofs are enabled
-    /// and the chunk size is at the default value.
+    /// Return the effective multiproof task chunk size.
     pub const fn effective_multiproof_chunk_size(&self) -> usize {
-        if !self.disable_proof_v2 &&
-            self.multiproof_chunk_size == DEFAULT_MULTIPROOF_TASK_CHUNK_SIZE
-        {
-            DEFAULT_MULTIPROOF_TASK_CHUNK_SIZE_V2
-        } else {
-            self.multiproof_chunk_size
-        }
+        self.multiproof_chunk_size
     }
 
     /// Return the number of reserved CPU cores for non-reth processes
@@ -533,17 +502,6 @@ impl TreeConfig {
         self.has_enough_parallelism && !self.legacy_state_root
     }
 
-    /// Setter for prewarm max concurrency.
-    pub const fn with_prewarm_max_concurrency(mut self, prewarm_max_concurrency: usize) -> Self {
-        self.prewarm_max_concurrency = prewarm_max_concurrency;
-        self
-    }
-
-    /// Return the prewarm max concurrency.
-    pub const fn prewarm_max_concurrency(&self) -> usize {
-        self.prewarm_max_concurrency
-    }
-
     /// Return the number of storage proof worker threads.
     pub const fn storage_worker_count(&self) -> usize {
         self.storage_worker_count
@@ -580,17 +538,6 @@ impl TreeConfig {
         self
     }
 
-    /// Return whether V2 storage proofs are disabled.
-    pub const fn disable_proof_v2(&self) -> bool {
-        self.disable_proof_v2
-    }
-
-    /// Setter for whether to disable V2 storage proofs.
-    pub const fn with_disable_proof_v2(mut self, disable_proof_v2: bool) -> Self {
-        self.disable_proof_v2 = disable_proof_v2;
-        self
-    }
-
     /// Returns whether cache metrics recording is disabled.
     pub const fn disable_cache_metrics(&self) -> bool {
         self.disable_cache_metrics
@@ -602,17 +549,6 @@ impl TreeConfig {
         self
     }
 
-    /// Returns whether sparse trie cache is disabled.
-    pub const fn disable_trie_cache(&self) -> bool {
-        self.disable_trie_cache
-    }
-
-    /// Setter for whether to disable sparse trie cache.
-    pub const fn with_disable_trie_cache(mut self, value: bool) -> Self {
-        self.disable_trie_cache = value;
-        self
-    }
-
     /// Returns the sparse trie prune depth.
     pub const fn sparse_trie_prune_depth(&self) -> usize {
         self.sparse_trie_prune_depth

crates/engine/primitives/src/message.rs

@@ -15,6 +15,7 @@ use futures::{future::Either, FutureExt, TryFutureExt};
 use reth_errors::RethResult;
 use reth_payload_builder_primitives::PayloadBuilderError;
 use reth_payload_primitives::{EngineApiMessageVersion, PayloadTypes};
+use std::time::Duration;
 use tokio::sync::{mpsc::UnboundedSender, oneshot};
 
 /// Type alias for backwards compat
@@ -142,6 +143,20 @@ impl Future for PendingPayloadId {
     }
 }
 
+/// Timing breakdown for `reth_newPayload` responses.
+#[derive(Debug, Clone, Copy)]
+pub struct NewPayloadTimings {
+    /// Server-side execution latency.
+    pub latency: Duration,
+    /// Time spent waiting for persistence to complete.
+    /// `None` when no persistence was in-flight.
+    pub persistence_wait: Option<Duration>,
+    /// Time spent waiting for the execution cache lock.
+    pub execution_cache_wait: Duration,
+    /// Time spent waiting for the sparse trie lock.
+    pub sparse_trie_wait: Duration,
+}
+
 /// A message for the beacon engine from other components of the node (engine RPC API invoked by the
 /// consensus layer).
 #[derive(Debug)]
@@ -153,6 +168,16 @@ pub enum BeaconEngineMessage<Payload: PayloadTypes> {
         /// The sender for returning payload status result.
         tx: oneshot::Sender<Result<PayloadStatus, BeaconOnNewPayloadError>>,
     },
+    /// Message with new payload used by `reth_newPayload` endpoint.
+    ///
+    /// Waits for persistence, execution cache, and sparse trie locks before processing,
+    /// and returns detailed timing breakdown alongside the payload status.
+    RethNewPayload {
+        /// The execution payload received by Engine API.
+        payload: Payload::ExecutionData,
+        /// The sender for returning payload status result and timing breakdown.
+        tx: oneshot::Sender<Result<(PayloadStatus, NewPayloadTimings), BeaconOnNewPayloadError>>,
+    },
     /// Message with updated forkchoice state.
     ForkchoiceUpdated {
         /// The updated forkchoice state.
@@ -178,6 +203,15 @@ impl<Payload: PayloadTypes> Display for BeaconEngineMessage<Payload> {
                     payload.block_hash()
                 )
             }
+            Self::RethNewPayload { payload, .. } => {
+                write!(
+                    f,
+                    "RethNewPayload(parent: {}, number: {}, hash: {})",
+                    payload.parent_hash(),
+                    payload.block_number(),
+                    payload.block_hash()
+                )
+            }
             Self::ForkchoiceUpdated { state, payload_attrs, .. } => {
                 // we don't want to print the entire payload attributes, because for OP this
                 // includes all txs
@@ -223,6 +257,19 @@ where
         rx.await.map_err(|_| BeaconOnNewPayloadError::EngineUnavailable)?
     }
 
+    /// Sends a new payload message used by `reth_newPayload` endpoint.
+    ///
+    /// Waits for persistence, execution cache, and sparse trie locks before processing,
+    /// and returns detailed timing breakdown alongside the payload status.
+    pub async fn reth_new_payload(
+        &self,
+        payload: Payload::ExecutionData,
+    ) -> Result<(PayloadStatus, NewPayloadTimings), BeaconOnNewPayloadError> {
+        let (tx, rx) = oneshot::channel();
+        let _ = self.to_engine.send(BeaconEngineMessage::RethNewPayload { payload, tx });
+        rx.await.map_err(|_| BeaconOnNewPayloadError::EngineUnavailable)?
+    }
+
     /// Sends a forkchoice update message to the beacon consensus engine and waits for a response.
     ///
     /// See also <https://github.com/ethereum/execution-apis/blob/3d627c95a4d3510a8187dd02e0250ecb4331d27e/src/engine/shanghai.md#engine_forkchoiceupdatedv2>

crates/engine/service/Cargo.toml

@@ -1,47 +0,0 @@
-[package]
-name = "reth-engine-service"
-version.workspace = true
-edition.workspace = true
-rust-version.workspace = true
-license.workspace = true
-homepage.workspace = true
-repository.workspace = true
-
-[lints]
-workspace = true
-
-[dependencies]
-# reth
-reth-consensus.workspace = true
-reth-engine-tree.workspace = true
-reth-evm.workspace = true
-reth-network-p2p.workspace = true
-reth-payload-builder.workspace = true
-reth-provider.workspace = true
-reth-prune.workspace = true
-reth-stages-api.workspace = true
-reth-tasks.workspace = true
-reth-node-types.workspace = true
-reth-chainspec.workspace = true
-reth-engine-primitives.workspace = true
-reth-trie-db.workspace = true
-
-# async
-futures.workspace = true
-pin-project.workspace = true
-
-# misc
-
-[dev-dependencies]
-reth-engine-tree = { workspace = true, features = ["test-utils"] }
-reth-ethereum-consensus.workspace = true
-reth-ethereum-engine-primitives.workspace = true
-reth-evm-ethereum.workspace = true
-reth-exex-types.workspace = true
-reth-primitives-traits.workspace = true
-reth-node-ethereum.workspace = true
-reth-trie-db.workspace = true
-
-alloy-eips.workspace = true
-tokio = { workspace = true, features = ["sync"] }
-tokio-stream.workspace = true

crates/engine/service/src/lib.rs

@@ -1,12 +0,0 @@
-//! Engine service implementation.
-
-#![doc(
-    html_logo_url = "https://raw.githubusercontent.com/paradigmxyz/reth/main/assets/reth-docs.png",
-    html_favicon_url = "https://avatars0.githubusercontent.com/u/97369466?s=256",
-    issue_tracker_base_url = "https://github.com/paradigmxyz/reth/issues/"
-)]
-#![cfg_attr(docsrs, feature(doc_cfg))]
-#![cfg_attr(not(test), warn(unused_crate_dependencies))]
-
-/// Engine Service
-pub mod service;

crates/engine/service/src/service.rs

@@ -1,229 +0,0 @@
-use futures::{Stream, StreamExt};
-use pin_project::pin_project;
-use reth_chainspec::EthChainSpec;
-use reth_consensus::FullConsensus;
-use reth_engine_primitives::{BeaconEngineMessage, ConsensusEngineEvent};
-use reth_engine_tree::{
-    backfill::PipelineSync,
-    download::BasicBlockDownloader,
-    engine::{EngineApiKind, EngineApiRequest, EngineApiRequestHandler, EngineHandler},
-    persistence::PersistenceHandle,
-    tree::{EngineApiTreeHandler, EngineValidator, TreeConfig},
-};
-pub use reth_engine_tree::{
-    chain::{ChainEvent, ChainOrchestrator},
-    engine::EngineApiEvent,
-};
-use reth_evm::ConfigureEvm;
-use reth_network_p2p::BlockClient;
-use reth_node_types::{BlockTy, NodeTypes};
-use reth_payload_builder::PayloadBuilderHandle;
-use reth_provider::{
-    providers::{BlockchainProvider, ProviderNodeTypes},
-    ProviderFactory, StorageSettingsCache,
-};
-use reth_prune::PrunerWithFactory;
-use reth_stages_api::{MetricEventsSender, Pipeline};
-use reth_tasks::TaskSpawner;
-use reth_trie_db::ChangesetCache;
-use std::{
-    pin::Pin,
-    sync::Arc,
-    task::{Context, Poll},
-};
-
-/// Alias for consensus engine stream.
-pub type EngineMessageStream<T> = Pin<Box<dyn Stream<Item = BeaconEngineMessage<T>> + Send + Sync>>;
-
-/// Alias for chain orchestrator.
-type EngineServiceType<N, Client> = ChainOrchestrator<
-    EngineHandler<
-        EngineApiRequestHandler<
-            EngineApiRequest<<N as NodeTypes>::Payload, <N as NodeTypes>::Primitives>,
-            <N as NodeTypes>::Primitives,
-        >,
-        EngineMessageStream<<N as NodeTypes>::Payload>,
-        BasicBlockDownloader<Client, BlockTy<N>>,
-    >,
-    PipelineSync<N>,
->;
-
-/// The type that drives the chain forward and communicates progress.
-#[pin_project]
-#[expect(missing_debug_implementations)]
-// TODO(mattsse): remove hidden once fixed : <https://github.com/rust-lang/rust/issues/135363>
-//  otherwise rustdoc fails to resolve the alias
-#[doc(hidden)]
-pub struct EngineService<N, Client>
-where
-    N: ProviderNodeTypes,
-    Client: BlockClient<Block = BlockTy<N>> + 'static,
-{
-    orchestrator: EngineServiceType<N, Client>,
-}
-
-impl<N, Client> EngineService<N, Client>
-where
-    N: ProviderNodeTypes,
-    Client: BlockClient<Block = BlockTy<N>> + 'static,
-{
-    /// Constructor for `EngineService`.
-    #[expect(clippy::too_many_arguments)]
-    pub fn new<V, C>(
-        consensus: Arc<dyn FullConsensus<N::Primitives>>,
-        chain_spec: Arc<N::ChainSpec>,
-        client: Client,
-        incoming_requests: EngineMessageStream<N::Payload>,
-        pipeline: Pipeline<N>,
-        pipeline_task_spawner: Box<dyn TaskSpawner>,
-        provider: ProviderFactory<N>,
-        blockchain_db: BlockchainProvider<N>,
-        pruner: PrunerWithFactory<ProviderFactory<N>>,
-        payload_builder: PayloadBuilderHandle<N::Payload>,
-        payload_validator: V,
-        tree_config: TreeConfig,
-        sync_metrics_tx: MetricEventsSender,
-        evm_config: C,
-        changeset_cache: ChangesetCache,
-    ) -> Self
-    where
-        V: EngineValidator<N::Payload>,
-        C: ConfigureEvm<Primitives = N::Primitives> + 'static,
-    {
-        let engine_kind =
-            if chain_spec.is_optimism() { EngineApiKind::OpStack } else { EngineApiKind::Ethereum };
-
-        let downloader = BasicBlockDownloader::new(client, consensus.clone());
-        let use_hashed_state = provider.cached_storage_settings().use_hashed_state();
-
-        let persistence_handle =
-            PersistenceHandle::<N::Primitives>::spawn_service(provider, pruner, sync_metrics_tx);
-
-        let canonical_in_memory_state = blockchain_db.canonical_in_memory_state();
-
-        let (to_tree_tx, from_tree) = EngineApiTreeHandler::spawn_new(
-            blockchain_db,
-            consensus,
-            payload_validator,
-            persistence_handle,
-            payload_builder,
-            canonical_in_memory_state,
-            tree_config,
-            engine_kind,
-            evm_config,
-            changeset_cache,
-            use_hashed_state,
-        );
-
-        let engine_handler = EngineApiRequestHandler::new(to_tree_tx, from_tree);
-        let handler = EngineHandler::new(engine_handler, downloader, incoming_requests);
-
-        let backfill_sync = PipelineSync::new(pipeline, pipeline_task_spawner);
-
-        Self { orchestrator: ChainOrchestrator::new(handler, backfill_sync) }
-    }
-
-    /// Returns a mutable reference to the orchestrator.
-    pub fn orchestrator_mut(&mut self) -> &mut EngineServiceType<N, Client> {
-        &mut self.orchestrator
-    }
-}
-
-impl<N, Client> Stream for EngineService<N, Client>
-where
-    N: ProviderNodeTypes,
-    Client: BlockClient<Block = BlockTy<N>> + 'static,
-{
-    type Item = ChainEvent<ConsensusEngineEvent<N::Primitives>>;
-
-    fn poll_next(self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Option<Self::Item>> {
-        let mut orchestrator = self.project().orchestrator;
-        StreamExt::poll_next_unpin(&mut orchestrator, cx)
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use reth_chainspec::{ChainSpecBuilder, MAINNET};
-    use reth_engine_primitives::{BeaconEngineMessage, NoopInvalidBlockHook};
-    use reth_engine_tree::{test_utils::TestPipelineBuilder, tree::BasicEngineValidator};
-    use reth_ethereum_consensus::EthBeaconConsensus;
-    use reth_ethereum_engine_primitives::EthEngineTypes;
-    use reth_evm_ethereum::EthEvmConfig;
-    use reth_exex_types::FinishedExExHeight;
-    use reth_network_p2p::test_utils::TestFullBlockClient;
-    use reth_node_ethereum::EthereumEngineValidator;
-    use reth_primitives_traits::SealedHeader;
-    use reth_provider::{
-        providers::BlockchainProvider, test_utils::create_test_provider_factory_with_chain_spec,
-    };
-    use reth_prune::Pruner;
-    use reth_tasks::TokioTaskExecutor;
-    use reth_trie_db::ChangesetCache;
-    use std::sync::Arc;
-    use tokio::sync::{mpsc::unbounded_channel, watch};
-    use tokio_stream::wrappers::UnboundedReceiverStream;
-
-    #[test]
-    fn eth_chain_orchestrator_build() {
-        let chain_spec = Arc::new(
-            ChainSpecBuilder::default()
-                .chain(MAINNET.chain)
-                .genesis(MAINNET.genesis.clone())
-                .paris_activated()
-                .build(),
-        );
-        let consensus = Arc::new(EthBeaconConsensus::new(chain_spec.clone()));
-
-        let client = TestFullBlockClient::default();
-
-        let (_tx, rx) = unbounded_channel::<BeaconEngineMessage<EthEngineTypes>>();
-        let incoming_requests = UnboundedReceiverStream::new(rx);
-
-        let pipeline = TestPipelineBuilder::new().build(chain_spec.clone());
-        let pipeline_task_spawner = Box::<TokioTaskExecutor>::default();
-        let provider_factory = create_test_provider_factory_with_chain_spec(chain_spec.clone());
-
-        let blockchain_db =
-            BlockchainProvider::with_latest(provider_factory.clone(), SealedHeader::default())
-                .unwrap();
-        let engine_payload_validator = EthereumEngineValidator::new(chain_spec.clone());
-        let (_tx, rx) = watch::channel(FinishedExExHeight::NoExExs);
-        let pruner = Pruner::new_with_factory(provider_factory.clone(), vec![], 0, 0, None, rx);
-        let evm_config = EthEvmConfig::new(chain_spec.clone());
-
-        let changeset_cache = ChangesetCache::new();
-
-        let engine_validator = BasicEngineValidator::new(
-            blockchain_db.clone(),
-            consensus.clone(),
-            evm_config.clone(),
-            engine_payload_validator,
-            TreeConfig::default(),
-            Box::new(NoopInvalidBlockHook::default()),
-            changeset_cache.clone(),
-            reth_tasks::Runtime::test(),
-        );
-
-        let (sync_metrics_tx, _sync_metrics_rx) = unbounded_channel();
-        let (tx, _rx) = unbounded_channel();
-        let _eth_service = EngineService::new(
-            consensus,
-            chain_spec,
-            client,
-            Box::pin(incoming_requests),
-            pipeline,
-            pipeline_task_spawner,
-            provider_factory,
-            blockchain_db,
-            pruner,
-            PayloadBuilderHandle::new(tx),
-            engine_validator,
-            TreeConfig::default(),
-            sync_metrics_tx,
-            evm_config,
-            changeset_cache,
-        );
-    }
-}

crates/engine/tree/Cargo.toml

@@ -29,7 +29,7 @@ reth-provider.workspace = true
 reth-prune.workspace = true
 reth-revm = { workspace = true, features = ["optional-balance-check"] }
 reth-stages-api.workspace = true
-reth-tasks.workspace = true
+reth-tasks = { workspace = true, features = ["rayon"] }
 reth-trie-parallel.workspace = true
 reth-trie-sparse = { workspace = true, features = ["std", "metrics"] }
 reth-trie.workspace = true
@@ -54,7 +54,6 @@ thiserror.workspace = true
 tokio = { workspace = true, features = ["rt", "rt-multi-thread", "sync", "macros"] }
 fixed-cache.workspace = true
 moka = { workspace = true, features = ["sync"] }
-smallvec.workspace = true
 
 # metrics
 metrics.workspace = true
@@ -73,6 +72,7 @@ reth-prune-types = { workspace = true, optional = true }
 reth-stages = { workspace = true, optional = true }
 reth-static-file = { workspace = true, optional = true }
 reth-tracing = { workspace = true, optional = true }
+serde_json = { workspace = true, optional = true }
 
 [dev-dependencies]
 # reth
@@ -114,6 +114,10 @@ harness = false
 name = "state_root_task"
 harness = false
 
+[[bench]]
+name = "sparse_trie_small_work"
+harness = false
+
 [features]
 test-utils = [
     "reth-chain-state/test-utils",
@@ -143,6 +147,7 @@ test-utils = [
     "reth-evm-ethereum/test-utils",
     "reth-tasks/test-utils",
 ]
+trie-debug = ["reth-trie-sparse/trie-debug", "dep:serde_json"]
 rocksdb = [
     "reth-provider/rocksdb",
     "reth-prune/rocksdb",

crates/engine/tree/benches/sparse_trie_small_work.rs

@@ -0,0 +1,131 @@
+//! Microbenchmark: serial vs parallel crossover for sparse trie storage operations.
+//!
+//! The key question: at what (active_tries, work_per_item) does Rayon become worthwhile?
+//!
+//! We sweep both dimensions to produce a crossover map suitable for threshold selection.
+
+use alloy_primitives::{keccak256, B256};
+use rayon::iter::{IndexedParallelIterator, IntoParallelIterator, ParallelIterator};
+use revm_primitives::{hash_map::Entry, B256Map};
+use std::{hint::black_box, time::Instant};
+
+/// Active tries sweep — fine granularity around expected crossover.
+const ACTIVE_TRIES: [usize; 16] = [1, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 24, 28, 32, 48, 64];
+
+/// Simulated per-item work costs in keccak256 iterations.
+/// 1 keccak ≈ 200ns, so:
+///   1  → ~200ns  (trivial: hashmap-only updates)
+///   5  → ~1µs    (light trie update, few nodes)
+///  25  → ~5µs    (moderate trie update)
+///  50  → ~10µs   (heavy trie update / shallow root)
+/// 250  → ~50µs   (large storage trie root computation)
+/// 500  → ~100µs  (very large storage trie root)
+const WORK_SIZES: [usize; 6] = [1, 5, 25, 50, 250, 500];
+
+const ROUNDS: usize = 5_000;
+const TRIALS: usize = 5;
+
+/// Simulates per-trie work by running `n_hashes` keccak256 rounds.
+#[inline(never)]
+fn simulated_work(seed: u64, n_hashes: usize) -> B256 {
+    let mut input = [0u8; 32];
+    input[24..].copy_from_slice(&seed.to_be_bytes());
+    let mut h = keccak256(input);
+    for _ in 1..n_hashes {
+        h = keccak256(h);
+    }
+    h
+}
+
+fn main() {
+    eprintln!(
+        "Sweeping {} active_tries x {} work_sizes x {} trials x {} rounds",
+        ACTIVE_TRIES.len(),
+        WORK_SIZES.len(),
+        TRIALS,
+        ROUNDS
+    );
+
+    // Warmup rayon pool
+    let _: B256 = (0..1024u64)
+        .into_par_iter()
+        .map(|i| simulated_work(i, 10))
+        .reduce(|| B256::ZERO, |a, b| a ^ b);
+
+    println!("work_hashes,active_tries,mode,trial,total_us,us_per_round");
+
+    for &work in &WORK_SIZES {
+        for &active in &ACTIVE_TRIES {
+            // Serial
+            for trial in 0..TRIALS {
+                let start = Instant::now();
+                let mut acc = B256::ZERO;
+                for r in 0..ROUNDS {
+                    for i in 0..active {
+                        acc ^= simulated_work((r * active + i) as u64, work);
+                    }
+                }
+                black_box(acc);
+                let total_us = start.elapsed().as_micros();
+                let us_per_round = total_us as f64 / ROUNDS as f64;
+                println!("{work},{active},serial,{trial},{total_us},{us_per_round:.2}");
+            }
+
+            // Parallel with min_len = active (effectively serial in rayon — measures overhead)
+            for trial in 0..TRIALS {
+                let start = Instant::now();
+                let mut acc = B256::ZERO;
+                for r in 0..ROUNDS {
+                    let round = (0..active)
+                        .into_par_iter()
+                        .with_min_len(active)
+                        .map(|i| simulated_work((r * active + i) as u64, work))
+                        .reduce(|| B256::ZERO, |a, b| a ^ b);
+                    acc ^= round;
+                }
+                black_box(acc);
+                let total_us = start.elapsed().as_micros();
+                let us_per_round = total_us as f64 / ROUNDS as f64;
+                println!("{work},{active},par_noop,{trial},{total_us},{us_per_round:.2}");
+            }
+
+            // Parallel with min_len=8 (the production setting)
+            for trial in 0..TRIALS {
+                let start = Instant::now();
+                let mut acc = B256::ZERO;
+                for r in 0..ROUNDS {
+                    let round = (0..active)
+                        .into_par_iter()
+                        .with_min_len(8)
+                        .map(|i| simulated_work((r * active + i) as u64, work))
+                        .reduce(|| B256::ZERO, |a, b| a ^ b);
+                    acc ^= round;
+                }
+                black_box(acc);
+                let total_us = start.elapsed().as_micros();
+                let us_per_round = total_us as f64 / ROUNDS as f64;
+                println!("{work},{active},par_ml8,{trial},{total_us},{us_per_round:.2}");
+            }
+
+            // Parallel with min_len=1 (maximum splitting)
+            for trial in 0..TRIALS {
+                let start = Instant::now();
+                let mut acc = B256::ZERO;
+                for r in 0..ROUNDS {
+                    let round = (0..active)
+                        .into_par_iter()
+                        .with_min_len(1)
+                        .map(|i| simulated_work((r * active + i) as u64, work))
+                        .reduce(|| B256::ZERO, |a, b| a ^ b);
+                    acc ^= round;
+                }
+                black_box(acc);
+                let total_us = start.elapsed().as_micros();
+                let us_per_round = total_us as f64 / ROUNDS as f64;
+                println!("{work},{active},par_ml1,{trial},{total_us},{us_per_round:.2}");
+            }
+        }
+    }
+
+    eprintln!("Done.");
+}

crates/engine/tree/src/backfill.rs

@@ -10,7 +10,7 @@
 use futures::FutureExt;
 use reth_provider::providers::ProviderNodeTypes;
 use reth_stages_api::{ControlFlow, Pipeline, PipelineError, PipelineTarget, PipelineWithResult};
-use reth_tasks::TaskSpawner;
+use reth_tasks::Runtime;
 use std::task::{ready, Context, Poll};
 use tokio::sync::oneshot;
 use tracing::trace;
@@ -80,7 +80,7 @@ pub enum BackfillEvent {
 #[derive(Debug)]
 pub struct PipelineSync<N: ProviderNodeTypes> {
     /// The type that can spawn the pipeline task.
-    pipeline_task_spawner: Box<dyn TaskSpawner>,
+    pipeline_task_spawner: Runtime,
     /// The current state of the pipeline.
     /// The pipeline is used for large ranges.
     pipeline_state: PipelineState<N>,
@@ -90,7 +90,7 @@ pub struct PipelineSync<N: ProviderNodeTypes> {
 
 impl<N: ProviderNodeTypes> PipelineSync<N> {
     /// Create a new instance.
-    pub fn new(pipeline: Pipeline<N>, pipeline_task_spawner: Box<dyn TaskSpawner>) -> Self {
+    pub fn new(pipeline: Pipeline<N>, pipeline_task_spawner: Runtime) -> Self {
         Self {
             pipeline_task_spawner,
             pipeline_state: PipelineState::Idle(Some(Box::new(pipeline))),
@@ -140,10 +140,10 @@ impl<N: ProviderNodeTypes> PipelineSync<N> {
                 let pipeline = pipeline.take().expect("exists");
                 self.pipeline_task_spawner.spawn_critical_blocking_task(
                     "pipeline task",
-                    Box::pin(async move {
+                    async move {
                         let result = pipeline.run_as_fut(Some(target)).await;
                         let _ = tx.send(result);
-                    }),
+                    },
                 );
                 self.pipeline_state = PipelineState::Running(rx);
 
@@ -241,7 +241,7 @@ mod tests {
     use reth_provider::test_utils::MockNodeTypesWithDB;
     use reth_stages::ExecOutput;
     use reth_stages_api::StageCheckpoint;
-    use reth_tasks::TokioTaskExecutor;
+    use reth_tasks::Runtime;
     use std::{collections::VecDeque, future::poll_fn, sync::Arc};
 
     struct TestHarness {
@@ -267,7 +267,7 @@ mod tests {
                 })]))
                 .build(chain_spec);
 
-            let pipeline_sync = PipelineSync::new(pipeline, Box::<TokioTaskExecutor>::default());
+            let pipeline_sync = PipelineSync::new(pipeline, Runtime::test());
             let client = TestFullBlockClient::default();
             let header = Header {
                 base_fee_per_gas: Some(7),

crates/engine/tree/src/launch.rs

@@ -0,0 +1,110 @@
+//! Engine orchestrator launch helper.
+//!
+//! Provides [`build_engine_orchestrator`](crate::launch::build_engine_orchestrator) which wires
+//! together all engine components and returns a
+//! [`ChainOrchestrator`](crate::chain::ChainOrchestrator) ready to be polled as a `Stream`.
+
+use crate::{
+    backfill::PipelineSync,
+    chain::ChainOrchestrator,
+    download::BasicBlockDownloader,
+    engine::{EngineApiKind, EngineApiRequest, EngineApiRequestHandler, EngineHandler},
+    persistence::PersistenceHandle,
+    tree::{EngineApiTreeHandler, EngineValidator, TreeConfig, WaitForCaches},
+};
+use futures::Stream;
+use reth_consensus::FullConsensus;
+use reth_engine_primitives::BeaconEngineMessage;
+use reth_evm::ConfigureEvm;
+use reth_network_p2p::BlockClient;
+use reth_payload_builder::PayloadBuilderHandle;
+use reth_primitives_traits::NodePrimitives;
+use reth_provider::{
+    providers::{BlockchainProvider, ProviderNodeTypes},
+    ProviderFactory, StorageSettingsCache,
+};
+use reth_prune::PrunerWithFactory;
+use reth_stages_api::{MetricEventsSender, Pipeline};
+use reth_tasks::Runtime;
+use reth_trie_db::ChangesetCache;
+use std::sync::Arc;
+
+/// Builds the engine [`ChainOrchestrator`] that drives the chain forward.
+///
+/// This spawns and wires together the following components:
+///
+/// - **[`BasicBlockDownloader`]** — downloads blocks on demand from the network during live sync.
+/// - **[`PersistenceHandle`]** — spawns the persistence service on a background thread for writing
+///   blocks and performing pruning outside the critical consensus path.
+/// - **[`EngineApiTreeHandler`]** — spawns the tree handler that processes engine API requests
+///   (`newPayload`, `forkchoiceUpdated`) and maintains the in-memory chain state.
+/// - **[`EngineApiRequestHandler`]** + **[`EngineHandler`]** — glue that routes incoming CL
+///   messages to the tree handler and manages download requests.
+/// - **[`PipelineSync`]** — wraps the staged sync [`Pipeline`] for backfill sync when the node
+///   needs to catch up over large block ranges.
+///
+/// The returned orchestrator implements [`Stream`] and yields
+/// [`ChainEvent`]s.
+///
+/// [`ChainEvent`]: crate::chain::ChainEvent
+#[expect(clippy::too_many_arguments, clippy::type_complexity)]
+pub fn build_engine_orchestrator<N, Client, S, V, C>(
+    engine_kind: EngineApiKind,
+    consensus: Arc<dyn FullConsensus<N::Primitives>>,
+    client: Client,
+    incoming_requests: S,
+    pipeline: Pipeline<N>,
+    pipeline_task_spawner: Runtime,
+    provider: ProviderFactory<N>,
+    blockchain_db: BlockchainProvider<N>,
+    pruner: PrunerWithFactory<ProviderFactory<N>>,
+    payload_builder: PayloadBuilderHandle<N::Payload>,
+    payload_validator: V,
+    tree_config: TreeConfig,
+    sync_metrics_tx: MetricEventsSender,
+    evm_config: C,
+    changeset_cache: ChangesetCache,
+) -> ChainOrchestrator<
+    EngineHandler<
+        EngineApiRequestHandler<EngineApiRequest<N::Payload, N::Primitives>, N::Primitives>,
+        S,
+        BasicBlockDownloader<Client, <N::Primitives as NodePrimitives>::Block>,
+    >,
+    PipelineSync<N>,
+>
+where
+    N: ProviderNodeTypes,
+    Client: BlockClient<Block = <N::Primitives as NodePrimitives>::Block> + 'static,
+    S: Stream<Item = BeaconEngineMessage<N::Payload>> + Send + Sync + Unpin + 'static,
+    V: EngineValidator<N::Payload> + WaitForCaches,
+    C: ConfigureEvm<Primitives = N::Primitives> + 'static,
+{
+    let downloader = BasicBlockDownloader::new(client, consensus.clone());
+    let use_hashed_state = provider.cached_storage_settings().use_hashed_state();
+
+    let persistence_handle =
+        PersistenceHandle::<N::Primitives>::spawn_service(provider, pruner, sync_metrics_tx);
+
+    let canonical_in_memory_state = blockchain_db.canonical_in_memory_state();
+
+    let (to_tree_tx, from_tree) = EngineApiTreeHandler::spawn_new(
+        blockchain_db,
+        consensus,
+        payload_validator,
+        persistence_handle,
+        payload_builder,
+        canonical_in_memory_state,
+        tree_config,
+        engine_kind,
+        evm_config,
+        changeset_cache,
+        use_hashed_state,
+    );
+
+    let engine_handler = EngineApiRequestHandler::new(to_tree_tx, from_tree);
+    let handler = EngineHandler::new(engine_handler, downloader, incoming_requests);
+
+    let backfill_sync = PipelineSync::new(pipeline, pipeline_task_spawner);
+
+    ChainOrchestrator::new(handler, backfill_sync)
+}

crates/engine/tree/src/lib.rs

@@ -100,6 +100,8 @@ pub mod chain;
 pub mod download;
 /// Engine Api chain handler support.
 pub mod engine;
+/// Engine orchestrator launch helper.
+pub mod launch;
 /// Metrics support.
 pub mod metrics;
 /// The background writer service, coordinating write operations on static files and the database.

crates/engine/tree/src/persistence.rs

@@ -4,7 +4,7 @@ use crossbeam_channel::Sender as CrossbeamSender;
 use reth_chain_state::ExecutedBlock;
 use reth_errors::ProviderError;
 use reth_ethereum_primitives::EthPrimitives;
-use reth_primitives_traits::NodePrimitives;
+use reth_primitives_traits::{FastInstant as Instant, NodePrimitives};
 use reth_provider::{
     providers::ProviderNodeTypes, BlockExecutionWriter, BlockHashReader, ChainStateBlockWriter,
     DBProvider, DatabaseProviderFactory, ProviderFactory, SaveBlocksMode,
@@ -18,7 +18,6 @@ use std::{
         Arc,
     },
     thread::JoinHandle,
-    time::Instant,
 };
 use thiserror::Error;
 use tracing::{debug, error, instrument};
@@ -119,7 +118,7 @@ where
         Ok(())
     }
 
-    #[instrument(level = "debug", target = "engine::persistence", skip_all, fields(new_tip_num))]
+    #[instrument(level = "debug", target = "engine::persistence", skip_all, fields(%new_tip_num))]
     fn on_remove_blocks_above(
         &self,
         new_tip_num: u64,

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

@@ -3,7 +3,7 @@ use alloy_primitives::{Address, StorageKey, StorageValue, B256};
 use metrics::{Gauge, Histogram};
 use reth_errors::ProviderResult;
 use reth_metrics::Metrics;
-use reth_primitives_traits::{Account, Bytecode};
+use reth_primitives_traits::{Account, Bytecode, FastInstant as Instant};
 use reth_provider::{
     AccountReader, BlockHashReader, BytecodeReader, HashedPostStateProvider, StateProofProvider,
     StateProvider, StateRootProvider, StorageRootProvider,
@@ -14,7 +14,7 @@ use reth_trie::{
 };
 use std::{
     sync::atomic::{AtomicU64, Ordering},
-    time::{Duration, Instant},
+    time::Duration,
 };
 
 /// Nanoseconds per second