feat(grafana): add RocksDB metrics dashboard (#21243)

Co-authored-by: Amp <amp@ampcode.com>

crates/node/builder/src/launch/common.rs

@@ -1277,6 +1277,10 @@ pub fn metrics_hooks<N: NodeTypesWithDB>(provider_factory: &ProviderFactory<N>)
                 })
             }
         })
+        .with_hook({
+            let rocksdb = provider_factory.rocksdb_provider();
+            move || throttle!(Duration::from_secs(5 * 60), || rocksdb.report_metrics())
+        })
         .build()
 }
 

crates/node/metrics/src/server.rs

@@ -106,6 +106,7 @@ impl MetricServer {
         // Describe metrics after recorder installation
         describe_db_metrics();
         describe_static_file_metrics();
+        describe_rocksdb_metrics();
         Collector::default().describe();
         describe_memory_stats();
         describe_io_stats();
@@ -238,6 +239,26 @@ fn describe_static_file_metrics() {
     );
 }
 
+fn describe_rocksdb_metrics() {
+    describe_gauge!(
+        "rocksdb.table_size",
+        Unit::Bytes,
+        "The estimated size of a RocksDB table (SST + memtable)"
+    );
+    describe_gauge!("rocksdb.table_entries", "The estimated number of keys in a RocksDB table");
+    describe_gauge!(
+        "rocksdb.pending_compaction_bytes",
+        Unit::Bytes,
+        "Bytes pending compaction for a RocksDB table"
+    );
+    describe_gauge!("rocksdb.sst_size", Unit::Bytes, "The size of SST files for a RocksDB table");
+    describe_gauge!(
+        "rocksdb.memtable_size",
+        Unit::Bytes,
+        "The size of memtables for a RocksDB table"
+    );
+}
+
 #[cfg(all(feature = "jemalloc", unix))]
 fn describe_memory_stats() {
     describe_gauge!(

crates/storage/provider/Cargo.toml

@@ -85,7 +85,7 @@ rand.workspace = true
 tokio = { workspace = true, features = ["sync", "macros", "rt-multi-thread"] }
 
 [features]
-edge = ["reth-storage-api/edge"]
+edge = ["reth-storage-api/edge", "rocksdb"]
 rocksdb = ["dep:rocksdb"]
 test-utils = [
     "reth-db/test-utils",

crates/storage/provider/src/providers/rocksdb/provider.rs

@@ -3,9 +3,11 @@ use crate::providers::{compute_history_rank, needs_prev_shard_check, HistoryInfo
 use alloy_consensus::transaction::TxHashRef;
 use alloy_primitives::{Address, BlockNumber, TxNumber, B256};
 use itertools::Itertools;
+use metrics::Label;
 use parking_lot::Mutex;
 use reth_chain_state::ExecutedBlock;
 use reth_db_api::{
+    database_metrics::DatabaseMetrics,
     models::{
         sharded_key::NUM_OF_INDICES_IN_SHARD, storage_sharded_key::StorageShardedKey, ShardedKey,
         StorageSettings,
@@ -529,6 +531,42 @@ impl Clone for RocksDBProvider {
     }
 }
 
+impl DatabaseMetrics for RocksDBProvider {
+    fn gauge_metrics(&self) -> Vec<(&'static str, f64, Vec<Label>)> {
+        let mut metrics = Vec::new();
+
+        for stat in self.table_stats() {
+            metrics.push((
+                "rocksdb.table_size",
+                stat.estimated_size_bytes as f64,
+                vec![Label::new("table", stat.name.clone())],
+            ));
+            metrics.push((
+                "rocksdb.table_entries",
+                stat.estimated_num_keys as f64,
+                vec![Label::new("table", stat.name.clone())],
+            ));
+            metrics.push((
+                "rocksdb.pending_compaction_bytes",
+                stat.pending_compaction_bytes as f64,
+                vec![Label::new("table", stat.name.clone())],
+            ));
+            metrics.push((
+                "rocksdb.sst_size",
+                stat.sst_size_bytes as f64,
+                vec![Label::new("table", stat.name.clone())],
+            ));
+            metrics.push((
+                "rocksdb.memtable_size",
+                stat.memtable_size_bytes as f64,
+                vec![Label::new("table", stat.name)],
+            ));
+        }
+
+        metrics
+    }
+}
+
 impl RocksDBProvider {
     /// Creates a new `RocksDB` provider.
     pub fn new(path: impl AsRef<Path>) -> ProviderResult<Self> {

crates/storage/provider/src/providers/rocksdb_stub.rs

@@ -5,8 +5,9 @@
 //! All method calls are cfg-guarded in the calling code, so only type definitions are needed here.
 
 use alloy_primitives::BlockNumber;
+use metrics::Label;
 use parking_lot::Mutex;
-use reth_db_api::models::StorageSettings;
+use reth_db_api::{database_metrics::DatabaseMetrics, models::StorageSettings};
 use reth_prune_types::PruneMode;
 use reth_storage_errors::{db::LogLevel, provider::ProviderResult};
 use std::{path::Path, sync::Arc};
@@ -82,6 +83,12 @@ impl RocksDBProvider {
     }
 }
 
+impl DatabaseMetrics for RocksDBProvider {
+    fn gauge_metrics(&self) -> Vec<(&'static str, f64, Vec<Label>)> {
+        vec![]
+    }
+}
+
 /// A stub batch writer for `RocksDB`.
 #[derive(Debug)]
 pub struct RocksDBBatch;