Drop head tracker for summaries DAG (#6744)

The head tracker is a persisted piece of state that must be kept in sync with the fork-choice. It has been a source of pruning issues in the past, so we want to remove it
- see https://github.com/sigp/lighthouse/issues/1785

When implementing tree-states in the hot DB we have to change the pruning routine (more details below) so we want to do those changes first in isolation.
- see https://github.com/sigp/lighthouse/issues/6580
- If you want to see the full feature of tree-states hot https://github.com/dapplion/lighthouse/pull/39

Closes https://github.com/sigp/lighthouse/issues/1785


  **Current DB migration routine**

- Locate abandoned heads with head tracker
- Use a roots iterator to collect the ancestors of those heads can be pruned
- Delete those abandoned blocks / states
- Migrate the newly finalized chain to the freezer

In summary, it computes what it has to delete and keeps the rest. Then it migrates data to the freezer. If the abandoned forks routine has a bug it can break the freezer migration.

**Proposed migration routine (this PR)**

- Migrate the newly finalized chain to the freezer
- Load all state summaries from disk
- From those, just knowing the head and finalized block compute two sets: (1) descendants of finalized (2) newly finalized chain
- Iterate all summaries, if a summary does not belong to set (1) or (2), delete

This strategy is more sound as it just checks what's there in the hot DB, computes what it has to keep and deletes the rest. Because it does not rely and 3rd pieces of data we can drop the head tracker and pruning checkpoint. Since the DB migration happens **first** now, as long as the computation of the sets to keep is correct we won't have pruning issues.
This commit is contained in:
Lion - dapplion
2025-04-07 01:23:52 -03:00
committed by GitHub
parent b5d40e3db0
commit 70850fe58d
27 changed files with 1110 additions and 983 deletions

View File

@@ -8,7 +8,6 @@ use crate::eth1_finalization_cache::Eth1FinalizationCache;
use crate::fork_choice_signal::ForkChoiceSignalTx;
use crate::fork_revert::{reset_fork_choice_to_finalization, revert_to_fork_boundary};
use crate::graffiti_calculator::{GraffitiCalculator, GraffitiOrigin};
use crate::head_tracker::HeadTracker;
use crate::kzg_utils::blobs_to_data_column_sidecars;
use crate::light_client_server_cache::LightClientServerCache;
use crate::migrate::{BackgroundMigrator, MigratorConfig};
@@ -93,7 +92,6 @@ pub struct BeaconChainBuilder<T: BeaconChainTypes> {
slot_clock: Option<T::SlotClock>,
shutdown_sender: Option<Sender<ShutdownReason>>,
light_client_server_tx: Option<Sender<LightClientProducerEvent<T::EthSpec>>>,
head_tracker: Option<HeadTracker>,
validator_pubkey_cache: Option<ValidatorPubkeyCache<T>>,
spec: Arc<ChainSpec>,
chain_config: ChainConfig,
@@ -136,7 +134,6 @@ where
slot_clock: None,
shutdown_sender: None,
light_client_server_tx: None,
head_tracker: None,
validator_pubkey_cache: None,
spec: Arc::new(E::default_spec()),
chain_config: ChainConfig::default(),
@@ -314,10 +311,6 @@ where
self.genesis_block_root = Some(chain.genesis_block_root);
self.genesis_state_root = Some(genesis_block.state_root());
self.head_tracker = Some(
HeadTracker::from_ssz_container(&chain.ssz_head_tracker)
.map_err(|e| format!("Failed to decode head tracker for database: {:?}", e))?,
);
self.validator_pubkey_cache = Some(pubkey_cache);
self.fork_choice = Some(fork_choice);
@@ -729,7 +722,6 @@ where
.genesis_state_root
.ok_or("Cannot build without a genesis state root")?;
let validator_monitor_config = self.validator_monitor_config.unwrap_or_default();
let head_tracker = Arc::new(self.head_tracker.unwrap_or_default());
let beacon_proposer_cache: Arc<Mutex<BeaconProposerCache>> = <_>::default();
let mut validator_monitor =
@@ -769,8 +761,6 @@ where
&self.spec,
)?;
// Update head tracker.
head_tracker.register_block(block_root, block.parent_root(), block.slot());
(block_root, block, true)
}
Err(e) => return Err(descriptive_db_error("head block", &e)),
@@ -846,8 +836,7 @@ where
})?;
let migrator_config = self.store_migrator_config.unwrap_or_default();
let store_migrator =
BackgroundMigrator::new(store.clone(), migrator_config, genesis_block_root);
let store_migrator = BackgroundMigrator::new(store.clone(), migrator_config);
if let Some(slot) = slot_clock.now() {
validator_monitor.process_valid_state(
@@ -872,11 +861,10 @@ where
//
// This *must* be stored before constructing the `BeaconChain`, so that its `Drop` instance
// doesn't write a `PersistedBeaconChain` without the rest of the batch.
let head_tracker_reader = head_tracker.0.read();
self.pending_io_batch.push(BeaconChain::<
Witness<TSlotClock, TEth1Backend, E, THotStore, TColdStore>,
>::persist_head_in_batch_standalone(
genesis_block_root, &head_tracker_reader
genesis_block_root
));
self.pending_io_batch.push(BeaconChain::<
Witness<TSlotClock, TEth1Backend, E, THotStore, TColdStore>,
@@ -887,7 +875,6 @@ where
.hot_db
.do_atomically(self.pending_io_batch)
.map_err(|e| format!("Error writing chain & metadata to disk: {:?}", e))?;
drop(head_tracker_reader);
let genesis_validators_root = head_snapshot.beacon_state.genesis_validators_root();
let genesis_time = head_snapshot.beacon_state.genesis_time();
@@ -968,7 +955,6 @@ where
fork_choice_signal_tx,
fork_choice_signal_rx,
event_handler: self.event_handler,
head_tracker,
shuffling_cache: RwLock::new(ShufflingCache::new(
shuffling_cache_size,
head_shuffling_ids,