nimbus-eth2/beacon_chain/consensus_object_pools/blockchain_dag.nim

1950 lines
72 KiB
Nim
Raw Normal View History

# beacon_chain
# Copyright (c) 2018-2022 Status Research & Development GmbH
# Licensed and distributed under either of
# * MIT license (license terms in the root directory or at https://opensource.org/licenses/MIT).
# * Apache v2 license (license terms in the root directory or at https://www.apache.org/licenses/LICENSE-2.0).
# at your option. This file may not be copied, modified, or distributed except according to those terms.
{.push raises: [Defect].}
import
std/[algorithm, options, sequtils, tables, sets],
stew/[assign2, byteutils, results],
metrics, snappy, chronicles,
../spec/[beaconstate, eth2_merkleization, eth2_ssz_serialization, helpers,
disentangle eth2 types from the ssz library (#2785) * reorganize ssz dependencies This PR continues the work in https://github.com/status-im/nimbus-eth2/pull/2646, https://github.com/status-im/nimbus-eth2/pull/2779 as well as past issues with serialization and type, to disentangle SSZ from eth2 and at the same time simplify imports and exports with a structured approach. The principal idea here is that when a library wants to introduce SSZ support, they do so via 3 files: * `ssz_codecs` which imports and reexports `codecs` - this covers the basic byte conversions and ensures no overloads get lost * `xxx_merkleization` imports and exports `merkleization` to specialize and get access to `hash_tree_root` and friends * `xxx_ssz_serialization` imports and exports `ssz_serialization` to specialize ssz for a specific library Those that need to interact with SSZ always import the `xxx_` versions of the modules and never `ssz` itself so as to keep imports simple and safe. This is similar to how the REST / JSON-RPC serializers are structured in that someone wanting to serialize spec types to REST-JSON will import `eth2_rest_serialization` and nothing else. * split up ssz into a core library that is independendent of eth2 types * rename `bytes_reader` to `codec` to highlight that it contains coding and decoding of bytes and native ssz types * remove tricky List init overload that causes compile issues * get rid of top-level ssz import * reenable merkleization tests * move some "standard" json serializers to spec * remove `ValidatorIndex` serialization for now * remove test_ssz_merkleization * add tests for over/underlong byte sequences * fix broken seq[byte] test - seq[byte] is not an SSZ type There are a few things this PR doesn't solve: * like #2646 this PR is weak on how to handle root and other dontSerialize fields that "sometimes" should be computed - the same problem appears in REST / JSON-RPC etc * Fix a build problem on macOS * Another way to fix the macOS builds Co-authored-by: Zahary Karadjov <zahary@gmail.com>
2021-08-18 18:57:58 +00:00
state_transition, validator],
".."/beacon_chain_db,
../spec/datatypes/[phase0, altair, bellatrix],
"."/[block_pools_types, block_quarantine]
export
eth2_merkleization, eth2_ssz_serialization,
block_pools_types, results, beacon_chain_db
# https://github.com/ethereum/eth2.0-metrics/blob/master/metrics.md#interop-metrics
declareGauge beacon_head_root, "Root of the head block of the beacon chain"
declareGauge beacon_head_slot, "Slot of the head block of the beacon chain"
# https://github.com/ethereum/eth2.0-metrics/blob/master/metrics.md#interop-metrics
declareGauge beacon_finalized_epoch, "Current finalized epoch" # On epoch transition
declareGauge beacon_finalized_root, "Current finalized root" # On epoch transition
declareGauge beacon_current_justified_epoch, "Current justified epoch" # On epoch transition
declareGauge beacon_current_justified_root, "Current justified root" # On epoch transition
declareGauge beacon_previous_justified_epoch, "Current previously justified epoch" # On epoch transition
declareGauge beacon_previous_justified_root, "Current previously justified root" # On epoch transition
declareGauge beacon_reorgs_total_total, "Total occurrences of reorganizations of the chain" # On fork choice; backwards-compat name (used to be a counter)
declareGauge beacon_reorgs_total, "Total occurrences of reorganizations of the chain" # Interop copy
declareCounter beacon_state_data_cache_hits, "EpochRef hits"
declareCounter beacon_state_data_cache_misses, "EpochRef misses"
declareCounter beacon_state_rewinds, "State database rewinds"
declareGauge beacon_active_validators, "Number of validators in the active validator set"
declareGauge beacon_current_active_validators, "Number of validators in the active validator set" # Interop copy
declareGauge beacon_pending_deposits, "Number of pending deposits (state.eth1_data.deposit_count - state.eth1_deposit_index)" # On block
declareGauge beacon_processed_deposits_total, "Number of total deposits included on chain" # On block
logScope: topics = "chaindag"
const
# When finality happens, we prune historical states from the database except
# for a snapshort every 32 epochs from which replays can happen - there's a
# balance here between making long replays and saving on disk space
EPOCHS_PER_STATE_SNAPSHOT = 32
proc putBlock*(
dag: ChainDAGRef, signedBlock: ForkyTrustedSignedBeaconBlock) =
dag.db.putBlock(signedBlock)
proc updateState*(
dag: ChainDAGRef, state: var ForkedHashedBeaconState, bs: BlockSlot, save: bool,
cache: var StateCache): bool {.gcsafe.}
template withStateVars*(
stateInternal: var ForkedHashedBeaconState, body: untyped): untyped =
## Inject a few more descriptive names for the members of `stateData` -
## the stateData instance may get mutated through these names as well
template state(): ForkedHashedBeaconState {.inject, used.} = stateInternal
template stateRoot(): Eth2Digest {.inject, used.} =
getStateRoot(stateInternal)
body
template withUpdatedState*(
dag: ChainDAGRef, state: var ForkedHashedBeaconState,
blockSlot: BlockSlot, okBody: untyped, failureBody: untyped): untyped =
## Helper template that updates stateData to a particular BlockSlot - usage of
## stateData is unsafe outside of block, or across `await` boundaries
block:
var cache {.inject.} = StateCache()
if updateState(dag, state, blockSlot, false, cache):
template blck(): BlockRef {.inject, used.} = blockSlot.blck
withStateVars(state):
okBody
else:
failureBody
func get_effective_balances(validators: openArray[Validator], epoch: Epoch):
seq[Gwei] =
## Get the balances from a state as counted for fork choice
result.newSeq(validators.len) # zero-init
for i in 0 ..< result.len:
# All non-active validators have a 0 balance
let validator = unsafeAddr validators[i]
performance fixes (#2259) * performance fixes * don't mark tree cache as dirty on read-only List accesses * store only blob in memory for keys and signatures, parse blob lazily * compare public keys by blob instead of parsing / converting to raw * compare Eth2Digest using non-constant-time comparison * avoid some unnecessary validator copying This branch will in particular speed up deposit processing which has been slowing down block replay. Pre (mainnet, 1600 blocks): ``` All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3450.269, 0.000, 3450.269, 3450.269, 1, Initialize DB 0.417, 0.822, 0.036, 21.098, 1400, Load block from database 16.521, 0.000, 16.521, 16.521, 1, Load state from database 27.906, 50.846, 8.104, 1507.633, 1350, Apply block 52.617, 37.029, 20.640, 135.938, 50, Apply epoch block ``` Post: ``` 3502.715, 0.000, 3502.715, 3502.715, 1, Initialize DB 0.080, 0.560, 0.035, 21.015, 1400, Load block from database 17.595, 0.000, 17.595, 17.595, 1, Load state from database 15.706, 11.028, 8.300, 107.537, 1350, Apply block 33.217, 12.622, 17.331, 60.580, 50, Apply epoch block ``` * more perf fixes * load EpochRef cache into StateCache more aggressively * point out security concern with public key cache * reuse proposer index from state when processing block * avoid genericAssign in a few more places * don't parse key when signature is unparseable * fix `==` overload for Eth2Digest * preallocate validator list when getting active validators * speed up proposer index calculation a little bit * reuse cache when replaying blocks in ncli_db * avoid a few more copying loops ``` Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3279.158, 0.000, 3279.158, 3279.158, 1, Initialize DB 0.072, 0.357, 0.035, 13.400, 1400, Load block from database 17.295, 0.000, 17.295, 17.295, 1, Load state from database 5.918, 9.896, 0.198, 98.028, 1350, Apply block 15.888, 10.951, 7.902, 39.535, 50, Apply epoch block 0.000, 0.000, 0.000, 0.000, 0, Database block store ``` * clear full balance cache before processing rewards and penalties ``` All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3947.901, 0.000, 3947.901, 3947.901, 1, Initialize DB 0.124, 0.506, 0.026, 202.370, 363345, Load block from database 97.614, 0.000, 97.614, 97.614, 1, Load state from database 0.186, 0.188, 0.012, 99.561, 357262, Advance slot, non-epoch 14.161, 5.966, 1.099, 395.511, 11524, Advance slot, epoch 1.372, 4.170, 0.017, 276.401, 363345, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database block store ```
2021-01-25 12:04:18 +00:00
if validator[].is_active_validator(epoch):
result[i] = validator[].effective_balance
proc updateValidatorKeys*(dag: ChainDAGRef, validators: openArray[Validator]) =
# Update validator key cache - must be called every time a valid block is
# applied to the state - this is important to ensure that when we sync blocks
# without storing a state (non-epoch blocks essentially), the deposits from
# those blocks are persisted to the in-database cache of immutable validator
# data (but no earlier than that the whole block as been validated)
dag.db.updateImmutableValidators(validators)
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
proc updateFinalizedBlocks*(dag: ChainDAGRef) =
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
if dag.db.db.readOnly: return # TODO abstraction leak - where to put this?
dag.db.withManyWrites:
let high = dag.db.finalizedBlocks.high.expect(
"wrote at least tailRef during init")
for s in high + 1 .. dag.finalizedHead.slot:
let tailIdx = int(s - dag.tail.slot)
if not isNil(dag.finalizedBlocks[tailIdx]):
dag.db.finalizedBlocks.insert(s, dag.finalizedBlocks[tailIdx].root)
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
func validatorKey*(
dag: ChainDAGRef, index: ValidatorIndex or uint64): Option[CookedPubKey] =
## Returns the validator pubkey for the index, assuming it's been observed
## at any point in time - this function may return pubkeys for indicies that
## are not (yet) part of the head state (if the key has been observed on a
## non-head branch)!
dag.db.immutableValidators.load(index)
func validatorKey*(
epochRef: EpochRef, index: ValidatorIndex or uint64): Option[CookedPubKey] =
## Returns the validator pubkey for the index, assuming it's been observed
## at any point in time - this function may return pubkeys for indicies that
## are not (yet) part of the head state (if the key has been observed on a
## non-head branch)!
validatorKey(epochRef.dag, index)
func init*(
T: type EpochRef, dag: ChainDAGRef, state: ForkedHashedBeaconState,
blck: BlockRef, cache: var StateCache): T =
let
epoch = state.get_current_epoch()
proposer_dependent_root = withState(state): state.proposer_dependent_root
attester_dependent_root = withState(state): state.attester_dependent_root
epochRef = EpochRef(
dag: dag, # This gives access to the validator pubkeys through an EpochRef
key: blck.epochAncestor(epoch),
eth1_data: getStateField(state, eth1_data),
eth1_deposit_index: getStateField(state, eth1_deposit_index),
current_justified_checkpoint:
getStateField(state, current_justified_checkpoint),
finalized_checkpoint: getStateField(state, finalized_checkpoint),
proposer_dependent_root: proposer_dependent_root,
shuffled_active_validator_indices:
cache.get_shuffled_active_validator_indices(state, epoch),
attester_dependent_root: attester_dependent_root,
merge_transition_complete:
case state.kind:
of BeaconStateFork.Phase0: false
of BeaconStateFork.Altair: false
of BeaconStateFork.Bellatrix:
2022-01-06 18:35:38 +00:00
# https://github.com/ethereum/consensus-specs/blob/v1.1.7/specs/merge/beacon-chain.md#is_merge_transition_complete
state.bellatrixData.data.latest_execution_payload_header !=
ExecutionPayloadHeader()
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
)
epochStart = epoch.start_slot()
doAssert epochRef.key.blck != nil, "epochAncestor should not fail for state block"
for i in 0'u64..<SLOTS_PER_EPOCH:
epochRef.beacon_proposers[i] = get_beacon_proposer_index(
state, cache, epochStart + i)
# When fork choice runs, it will need the effective balance of the justified
# checkpoint - we pre-load the balances here to avoid rewinding the justified
# state later and compress them because not all checkpoints end up being used
# for fork choice - specially during long periods of non-finalization
proc snappyEncode(inp: openArray[byte]): seq[byte] =
try:
snappy.encode(inp)
except CatchableError as err:
raiseAssert err.msg
epochRef.effective_balances_bytes =
snappyEncode(SSZ.encode(
List[Gwei, Limit VALIDATOR_REGISTRY_LIMIT](
get_effective_balances(getStateField(state, validators).asSeq, epoch))))
epochRef
func effective_balances*(epochRef: EpochRef): seq[Gwei] =
try:
SSZ.decode(snappy.decode(epochRef.effective_balances_bytes, uint32.high),
List[Gwei, Limit VALIDATOR_REGISTRY_LIMIT]).toSeq()
except CatchableError as exc:
raiseAssert exc.msg
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
func getBlockRef*(dag: ChainDAGRef, root: Eth2Digest): Opt[BlockRef] =
## Retrieve a resolved block reference, if available - this function does
## not return historical finalized blocks, see `getBlockAtSlot` for a function
## that covers the entire known history
let key = KeyedBlockRef.asLookupKey(root)
# HashSet lacks the api to do check-and-get in one lookup - `[]` will return
# the copy of the instance in the set which has more fields than `root` set!
if key in dag.forkBlocks:
try: ok(dag.forkBlocks[key].blockRef())
except KeyError: raiseAssert "contains"
else:
err()
func getBlockAtSlot*(dag: ChainDAGRef, slot: Slot): Opt[BlockSlot] =
## Retrieve the canonical block at the given slot, or the last block that
## comes before - similar to atSlot, but without the linear scan - see
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
## getBlockIdAtSlot for a version that covers backfill blocks as well
## May return an empty BlockSlot (where blck is nil!)
if slot == dag.genesis.slot:
return ok dag.genesis.atSlot(slot)
if slot > dag.finalizedHead.slot:
return ok dag.head.atSlot(slot) # Linear iteration is the fastest we have
doAssert dag.finalizedHead.slot >= dag.tail.slot
doAssert dag.tail.slot >= dag.backfill.slot
doAssert dag.finalizedBlocks.len ==
(dag.finalizedHead.slot - dag.tail.slot).int + 1, "see updateHead"
if slot >= dag.tail.slot:
var pos = int(slot - dag.tail.slot)
while true:
if dag.finalizedBlocks[pos] != nil:
return ok dag.finalizedBlocks[pos].atSlot(slot)
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
doAssert pos > 0, "We should have returned the tail"
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
pos = pos - 1
err() # Not found
func getBlockIdAtSlot*(dag: ChainDAGRef, slot: Slot): Opt[BlockSlotId] =
## Retrieve the canonical block at the given slot, or the last block that
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
## comes before - similar to atSlot, but without the linear scan - may hit
## the database to look up early indices.
let bs = dag.getBlockAtSlot(slot) # Try looking in recent blocks first
if bs.isSome:
return bs.get().toBlockSlotId()
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
let finlow = dag.db.finalizedBlocks.low.expect("at least tailRef written")
if slot >= finlow:
var pos = slot
while true:
let root = dag.db.finalizedBlocks.get(pos)
if root.isSome():
return ok BlockSlotId.init(
BlockId(root: root.get(), slot: pos), slot)
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
doAssert pos > finlow, "We should have returned the finlow"
pos = pos - 1
err() # not backfilled yet, and not genesis
proc getBlockId*(dag: ChainDAGRef, root: Eth2Digest): Opt[BlockId] =
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
## Look up block id by root in history - useful for turning a root into a
## slot - may hit the database, may return blocks that have since become
## unviable - use `getBlockIdAtSlot` to check that the block is still viable
## if used in a sensitive context
block: # If we have a BlockRef, this is the fastest way to get a block id
let blck = dag.getBlockRef(root)
if blck.isOk():
return ok(blck.get().bid)
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
block: # We might have a summary in the database
let summary = dag.db.getBeaconBlockSummary(root)
if summary.isOk():
return ok(BlockId(root: root, slot: summary.get().slot))
err()
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
func isCanonical*(dag: ChainDAGRef, bid: BlockId): bool =
let current = dag.getBlockIdAtSlot(bid.slot).valueOr:
return false # We don't know, so ..
return current.bid == bid
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
func epochAncestor*(blck: BlockRef, epoch: Epoch): EpochKey =
## The state transition works by storing information from blocks in a
## "working" area until the epoch transition, then batching work collected
## during the epoch. Thus, last block in the ancestor epochs is the block
## that has an impact on epoch currently considered.
##
## This function returns an epoch key pointing to that epoch boundary, i.e. the
## boundary where the last block has been applied to the state and epoch
## processing has been done.
var blck = blck
while blck.slot.epoch >= epoch and not blck.parent.isNil:
blck = blck.parent
if blck.slot.epoch > epoch:
EpochKey() # The searched-for epoch predates our tail block
else:
EpochKey(epoch: epoch, blck: blck)
func findEpochRef*(
dag: ChainDAGRef, blck: BlockRef, epoch: Epoch): Opt[EpochRef] =
## Look for an existing cached EpochRef, but unlike `getEpochRef`, don't
## try to create one by recreating the epoch state
let ancestor = epochAncestor(blck, epoch)
if isNil(ancestor.blck):
# We can't compute EpochRef instances for states before the tail because
# we do not have them!
return err()
for i in 0..<dag.epochRefs.len:
if dag.epochRefs[i] != nil and dag.epochRefs[i].key == ancestor:
return ok(dag.epochRefs[i])
err()
performance fixes (#2259) * performance fixes * don't mark tree cache as dirty on read-only List accesses * store only blob in memory for keys and signatures, parse blob lazily * compare public keys by blob instead of parsing / converting to raw * compare Eth2Digest using non-constant-time comparison * avoid some unnecessary validator copying This branch will in particular speed up deposit processing which has been slowing down block replay. Pre (mainnet, 1600 blocks): ``` All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3450.269, 0.000, 3450.269, 3450.269, 1, Initialize DB 0.417, 0.822, 0.036, 21.098, 1400, Load block from database 16.521, 0.000, 16.521, 16.521, 1, Load state from database 27.906, 50.846, 8.104, 1507.633, 1350, Apply block 52.617, 37.029, 20.640, 135.938, 50, Apply epoch block ``` Post: ``` 3502.715, 0.000, 3502.715, 3502.715, 1, Initialize DB 0.080, 0.560, 0.035, 21.015, 1400, Load block from database 17.595, 0.000, 17.595, 17.595, 1, Load state from database 15.706, 11.028, 8.300, 107.537, 1350, Apply block 33.217, 12.622, 17.331, 60.580, 50, Apply epoch block ``` * more perf fixes * load EpochRef cache into StateCache more aggressively * point out security concern with public key cache * reuse proposer index from state when processing block * avoid genericAssign in a few more places * don't parse key when signature is unparseable * fix `==` overload for Eth2Digest * preallocate validator list when getting active validators * speed up proposer index calculation a little bit * reuse cache when replaying blocks in ncli_db * avoid a few more copying loops ``` Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3279.158, 0.000, 3279.158, 3279.158, 1, Initialize DB 0.072, 0.357, 0.035, 13.400, 1400, Load block from database 17.295, 0.000, 17.295, 17.295, 1, Load state from database 5.918, 9.896, 0.198, 98.028, 1350, Apply block 15.888, 10.951, 7.902, 39.535, 50, Apply epoch block 0.000, 0.000, 0.000, 0.000, 0, Database block store ``` * clear full balance cache before processing rewards and penalties ``` All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3947.901, 0.000, 3947.901, 3947.901, 1, Initialize DB 0.124, 0.506, 0.026, 202.370, 363345, Load block from database 97.614, 0.000, 97.614, 97.614, 1, Load state from database 0.186, 0.188, 0.012, 99.561, 357262, Advance slot, non-epoch 14.161, 5.966, 1.099, 395.511, 11524, Advance slot, epoch 1.372, 4.170, 0.017, 276.401, 363345, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database block store ```
2021-01-25 12:04:18 +00:00
func loadStateCache(
dag: ChainDAGRef, cache: var StateCache, blck: BlockRef, epoch: Epoch) =
# When creating a state cache, we want the current and the previous epoch
# information to be preloaded as both of these are used in state transition
# functions
template load(e: Epoch) =
block:
let epoch = e
if epoch notin cache.shuffled_active_validator_indices:
let epochRef = dag.findEpochRef(blck, epoch)
if epochRef.isSome():
cache.shuffled_active_validator_indices[epoch] =
epochRef[].shuffled_active_validator_indices
let start_slot = epoch.start_slot()
for i, idx in epochRef[].beacon_proposers:
cache.beacon_proposer_indices[start_slot + i] = idx
load(epoch)
if epoch > 0:
load(epoch - 1)
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
func containsForkBlock*(dag: ChainDAGRef, root: Eth2Digest): bool =
## Checks for blocks at the finalized checkpoint or newer
KeyedBlockRef.asLookupKey(root) in dag.forkBlocks
proc containsBlock(
cfg: RuntimeConfig, db: BeaconChainDB, slot: Slot, root: Eth2Digest): bool =
db.containsBlock(root, cfg.blockForkAtEpoch(slot.epoch))
func isFinalizedStateSnapshot(slot: Slot): bool =
slot.is_epoch and slot.epoch mod EPOCHS_PER_STATE_SNAPSHOT == 0
func isStateCheckpoint(bs: BlockSlot): bool =
## State checkpoints are the points in time for which we store full state
## snapshots, which later serve as rewind starting points when replaying state
## transitions from database, for example during reorgs.
##
# As a policy, we only store epoch boundary states without the epoch block
# (if it exists) applied - the rest can be reconstructed by loading an epoch
# boundary state and applying the missing blocks.
# We also avoid states that were produced with empty slots only - as such,
# there is only a checkpoint for the first epoch after a block.
# The tail block also counts as a state checkpoint!
(bs.slot == bs.blck.slot and bs.blck.parent == nil) or
(bs.slot.is_epoch and bs.slot.epoch == (bs.blck.slot.epoch + 1))
proc getState(
db: BeaconChainDB, cfg: RuntimeConfig, slot: Slot, state_root: Eth2Digest,
state: var ForkedHashedBeaconState, rollback: RollbackProc): bool =
let expectedFork = cfg.stateForkAtEpoch(slot.epoch)
if state.kind != expectedFork:
# Avoid temporary (!)
state = (ref ForkedHashedBeaconState)(kind: expectedFork)[]
let ok = withState(state):
db.getState(state_root, state.data, rollback)
if not ok:
return false
setStateRoot(state, state_root)
true
proc getState(
db: BeaconChainDB, cfg: RuntimeConfig, state: var ForkedHashedBeaconState,
bs: BlockSlot, rollback: RollbackProc): bool =
if not bs.isStateCheckpoint():
return false
let root = db.getStateRoot(bs.blck.root, bs.slot)
if not root.isSome():
return false
if not db.getState(cfg, bs.slot, root.get(), state, rollback):
return false
true
proc getForkedBlock*(db: BeaconChainDB, root: Eth2Digest):
Opt[ForkedTrustedSignedBeaconBlock] =
# When we only have a digest, we don't know which fork it's from so we try
# them one by one - this should be used sparingly
if (let blck = db.getBlock(root, bellatrix.TrustedSignedBeaconBlock);
blck.isSome()):
ok(ForkedTrustedSignedBeaconBlock.init(blck.get()))
elif (let blck = db.getBlock(root, altair.TrustedSignedBeaconBlock);
blck.isSome()):
ok(ForkedTrustedSignedBeaconBlock.init(blck.get()))
elif (let blck = db.getBlock(root, phase0.TrustedSignedBeaconBlock);
blck.isSome()):
ok(ForkedTrustedSignedBeaconBlock.init(blck.get()))
else:
err()
proc getBlock*(
dag: ChainDAGRef, bid: BlockId,
T: type ForkyTrustedSignedBeaconBlock): Opt[T] =
withState(dag.headState):
dag.db.getBlock(bid.root, T)
proc getBlockSSZ*(dag: ChainDAGRef, bid: BlockId, bytes: var seq[byte]): bool =
# Load the SSZ-encoded data of a block into `bytes`, overwriting the existing
# content
# careful: there are two snappy encodings in use, with and without framing!
# Returns true if the block is found, false if not
let fork = dag.cfg.blockForkAtEpoch(bid.slot.epoch)
dag.db.getBlockSSZ(bid.root, bytes, fork)
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
proc getForkedBlock*(
dag: ChainDAGRef, bid: BlockId): Opt[ForkedTrustedSignedBeaconBlock] =
let fork = dag.cfg.blockForkAtEpoch(bid.slot.epoch)
result.ok(ForkedTrustedSignedBeaconBlock(kind: fork))
withBlck(result.get()):
type T = type(blck)
blck = getBlock(dag, bid, T).valueOr:
result.err()
return
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
proc getForkedBlock*(
dag: ChainDAGRef, root: Eth2Digest): Opt[ForkedTrustedSignedBeaconBlock] =
let bid = dag.getBlockId(root)
if bid.isSome():
dag.getForkedBlock(bid.get())
else:
# In case we didn't have a summary - should be rare, but ..
dag.db.getForkedBlock(root)
proc updateBeaconMetrics(
state: ForkedHashedBeaconState, bid: BlockId, cache: var StateCache) =
# https://github.com/ethereum/eth2.0-metrics/blob/master/metrics.md#additional-metrics
# both non-negative, so difference can't overflow or underflow int64
beacon_head_root.set(bid.root.toGaugeValue)
beacon_head_slot.set(bid.slot.toGaugeValue)
withState(state):
beacon_pending_deposits.set(
(state.data.eth1_data.deposit_count -
state.data.eth1_deposit_index).toGaugeValue)
beacon_processed_deposits_total.set(
state.data.eth1_deposit_index.toGaugeValue)
beacon_current_justified_epoch.set(
state.data.current_justified_checkpoint.epoch.toGaugeValue)
beacon_current_justified_root.set(
state.data.current_justified_checkpoint.root.toGaugeValue)
beacon_previous_justified_epoch.set(
state.data.previous_justified_checkpoint.epoch.toGaugeValue)
beacon_previous_justified_root.set(
state.data.previous_justified_checkpoint.root.toGaugeValue)
beacon_finalized_epoch.set(
state.data.finalized_checkpoint.epoch.toGaugeValue)
beacon_finalized_root.set(
state.data.finalized_checkpoint.root.toGaugeValue)
let active_validators = count_active_validators(
state.data, state.data.slot.epoch, cache).toGaugeValue
beacon_active_validators.set(active_validators)
beacon_current_active_validators.set(active_validators)
import blockchain_dag_light_client
export
blockchain_dag_light_client.getBestLightClientUpdateForPeriod,
blockchain_dag_light_client.getLatestLightClientUpdate,
blockchain_dag_light_client.getOptimisticLightClientUpdate,
blockchain_dag_light_client.getLightClientBootstrap
proc init*(T: type ChainDAGRef, cfg: RuntimeConfig, db: BeaconChainDB,
validatorMonitor: ref ValidatorMonitor, updateFlags: UpdateFlags,
onBlockCb: OnBlockCallback = nil, onHeadCb: OnHeadCallback = nil,
onReorgCb: OnReorgCallback = nil,
onFinCb: OnFinalizedCallback = nil,
onOptimisticLCUpdateCb: OnOptimisticLightClientUpdateCallback = nil,
serveLightClientData = false,
importLightClientData = ImportLightClientData.None
): ChainDAGRef =
# TODO we require that the db contains both a head and a tail block -
# asserting here doesn't seem like the right way to go about it however..
# Tail is the first block for which we can construct a state - either
# genesis or a checkpoint
let
startTick = Moment.now()
tailRoot = db.getTailBlock().expect("Tail root in database, corrupt?")
tailBlock = db.getForkedBlock(tailRoot).expect(
"Tail block in database, corrupt?")
tailRef = withBlck(tailBlock): BlockRef.init(tailRoot, blck.message)
2020-10-06 15:32:17 +00:00
# Backfills are blocks that we have in the database, but can't construct a
# state for without replaying from genesis
var
# The most recent block that we load from the finalized blocks table
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
midRef: BlockRef
# Start by loading basic block information about finalized blocks - this
# generally goes from genesis (or the earliest backfilled block) all the way
# to the latest block finalized in the `head` history - we have to be careful
# though, versions prior to 1.7.0 did not store finalized blocks in the
# database, and / or the application might have crashed between the head and
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
# finalized blocks updates.
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
for slot, root in db.finalizedBlocks:
if slot < tailRef.slot:
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
discard # TODO don't load this range at all from the database
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
elif slot == tailRef.slot:
if root != tailRef.root:
fatal "Finalized blocks do not meet with tail, database corrupt?",
tail = shortLog(tailRef), root = shortLog(root)
quit 1
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
midRef = tailRef
else: # slot > tailRef.slot
if midRef == nil:
fatal "First finalized block beyond tail, database corrupt?",
tail = shortLog(tailRef), slot, root = shortLog(root)
quit 1
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
let next = BlockRef.init(root, slot)
link(midRef, next)
midRef = next
let
finalizedTick = Moment.now()
headRoot = db.getHeadBlock().expect("Head root in database, corrupt?")
var
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
headRef: BlockRef
curRef: BlockRef
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
finalizedBlocks = newSeq[Eth2Digest](
if midRef == nil: tailRef.slot.int + 1
else: 0
)
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
# Load the part from head going backwards - if we found any entries in the
# finalized block table, we'll stop at `midRef`, otherwise we'll keep going
# as far as we can find headers and fill in the finalized blocks from tail
for blck in db.getAncestorSummaries(headRoot):
if midRef != nil and blck.summary.slot <= midRef.slot:
if midRef.slot != blck.summary.slot or midRef.root != blck.root:
2022-02-01 20:23:18 +00:00
fatal "Finalized block table does not match ancestor summaries, database corrupt?",
head = shortLog(headRoot), cur = shortLog(curRef),
mid = shortLog(midRef), blck = shortLog(blck.root)
2022-02-01 20:23:18 +00:00
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
quit 1
if curRef == nil:
# When starting from checkpoint, head == tail and there won't be any
# blocks in between
headRef = tailRef
else:
link(midRef, curRef)
# The finalized blocks form a linear history by definition - we can skip
# straight to the tail
curRef = tailRef
break
if blck.summary.slot < tailRef.slot:
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
doAssert midRef == nil,
"If we loaded any blocks from the finalized slot table, they should have included tailRef"
finalizedBlocks[blck.summary.slot.int] = blck.root
elif blck.summary.slot == tailRef.slot:
if curRef == nil:
curRef = tailRef
headRef = tailRef
else:
link(tailRef, curRef)
curRef = curRef.parent
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
if midRef == nil:
finalizedBlocks[blck.summary.slot.int] = blck.root
else:
let newRef = BlockRef.init(blck.root, blck.summary.slot)
if curRef == nil:
curRef = newRef
headRef = newRef
else:
link(newRef, curRef)
curRef = curRef.parent
trace "Populating block dag", key = curRef.root, val = curRef
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
if finalizedBlocks.len > 0 and not db.db.readOnly: # TODO abstraction leak
db.withManyWrites:
for i, root in finalizedBlocks.mpairs:
if root.isZero: continue
db.finalizedBlocks.insert(Slot(i), root)
let backfill = block:
let backfillSlot = db.finalizedBlocks.low.expect("tail at least")
if backfillSlot < tailRef.slot:
let backfillRoot = db.finalizedBlocks.get(backfillSlot).expect(
"low to be loadable")
db.getBeaconBlockSummary(backfillRoot).expect(
"Backfill block must have a summary")
else:
withBlck(tailBlock): blck.message.toBeaconBlockSummary()
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
let summariesTick = Moment.now()
if curRef != tailRef:
fatal "Head block does not lead to tail - database corrupt?",
tailRef, headRef, curRef, tailRoot, headRoot
quit 1
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
while not containsBlock(cfg, db, headRef.slot, headRef.root):
# When the database has been written with a pre-fork version of the
# software, it may happen that blocks produced using an "unforked"
# chain get written to the database - we need to skip such blocks
# when loading the database with a fork-compatible version
if isNil(headRef.parent):
fatal "Cannot find block for head root - database corrupt?",
headRef = shortLog(headRef)
headRef = headRef.parent
# Because of incorrect hardfork check, there might be no head block, in which
# case it's equivalent to the tail block
if headRef == nil:
headRef = tailRef
let genesisRef = if tailRef.slot == GENESIS_SLOT:
tailRef
else:
let
genesisRoot = db.getGenesisBlock().expect(
"preInit should have initialized the database with a genesis block root")
BlockRef.init(genesisRoot, GENESIS_SLOT)
let dag = ChainDAGRef(
db: db,
validatorMonitor: validatorMonitor,
2020-10-06 15:32:17 +00:00
genesis: genesisRef,
tail: tailRef,
head: headRef,
backfill: backfill,
finalizedHead: tailRef.atSlot(),
lastPrunePoint: tailRef.atSlot(),
# Tail is implicitly finalized - we'll adjust it below when computing the
# head state
heads: @[headRef],
clearanceBlck: headRef,
# The only allowed flag right now is verifyFinalization, as the others all
# allow skipping some validation.
updateFlags: {verifyFinalization} * updateFlags,
Implement split preset/config support (#2710) * Implement split preset/config support This is the initial bulk refactor to introduce runtime config values in a number of places, somewhat replacing the existing mechanism of loading network metadata. It still needs more work, this is the initial refactor that introduces runtime configuration in some of the places that need it. The PR changes the way presets and constants work, to match the spec. In particular, a "preset" now refers to the compile-time configuration while a "cfg" or "RuntimeConfig" is the dynamic part. A single binary can support either mainnet or minimal, but not both. Support for other presets has been removed completely (can be readded, in case there's need). There's a number of outstanding tasks: * `SECONDS_PER_SLOT` still needs fixing * loading custom runtime configs needs redoing * checking constants against YAML file * yeerongpilly support `build/nimbus_beacon_node --network=yeerongpilly --discv5:no --log-level=DEBUG` * load fork epoch from config * fix fork digest sent in status * nicer error string for request failures * fix tools * one more * fixup * fixup * fixup * use "standard" network definition folder in local testnet Files are loaded from their standard locations, including genesis etc, to conform to the format used in the `eth2-networks` repo. * fix launch scripts, allow unknown config values * fix base config of rest test * cleanups * bundle mainnet config using common loader * fix spec links and names * only include supported preset in binary * drop yeerongpilly, add altair-devnet-0, support boot_enr.yaml
2021-07-12 13:01:38 +00:00
cfg: cfg,
serveLightClientData: serveLightClientData,
importLightClientData: importLightClientData,
onBlockAdded: onBlockCb,
onHeadChanged: onHeadCb,
onReorgHappened: onReorgCb,
onFinHappened: onFinCb,
onOptimisticLightClientUpdate: onOptimisticLCUpdateCb
)
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
block: # Initialize dag states
var
cur = headRef.atSlot()
# Now that we have a head block, we need to find the most recent state that
# we have saved in the database
while cur.blck != nil and
not getState(db, cfg, dag.headState, cur, noRollback):
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
cur = cur.parentOrSlot()
if cur.blck == nil:
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
fatal "No state found in head history, database corrupt?",
genesisRef, tailRef, headRef
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
# TODO Potentially we could recover from here instead of crashing - what
# would be a good recovery model?
quit 1
let
configFork = case dag.headState.kind
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
of BeaconStateFork.Phase0: genesisFork(cfg)
of BeaconStateFork.Altair: altairFork(cfg)
of BeaconStateFork.Bellatrix: bellatrixFork(cfg)
statefork = getStateField(dag.headState, fork)
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
if stateFork != configFork:
error "State from database does not match network, check --network parameter",
genesisRef, tailRef, headRef, stateFork, configFork
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
quit 1
# db state is likely a epoch boundary state which is what we want for epochs
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
assign(dag.epochRefState, dag.headState)
dag.forkDigests = newClone ForkDigests.init(
cfg, getStateField(dag.headState, genesis_validators_root))
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
let forkVersions =
[cfg.GENESIS_FORK_VERSION, cfg.ALTAIR_FORK_VERSION,
cfg.BELLATRIX_FORK_VERSION, cfg.SHARDING_FORK_VERSION]
for i in 0 ..< forkVersions.len:
for j in i+1 ..< forkVersions.len:
doAssert forkVersions[i] != forkVersions[j]
doAssert cfg.ALTAIR_FORK_EPOCH <= cfg.BELLATRIX_FORK_EPOCH
doAssert cfg.BELLATRIX_FORK_EPOCH <= cfg.SHARDING_FORK_EPOCH
doAssert dag.updateFlags in [{}, {verifyFinalization}]
# The state we loaded into `headState` is the last state we saved, which may
# come from earlier than the head block
var cache: StateCache
if not dag.updateState(dag.headState, headRef.atSlot(), false, cache):
fatal "Unable to load head state, database corrupt?",
head = shortLog(headRef)
quit 1
# Clearance most likely happens from head - assign it after rewinding head
assign(dag.clearanceState, dag.headState)
withState(dag.headState):
dag.validatorMonitor[].registerState(state.data)
updateBeaconMetrics(dag.headState, dag.head.bid, cache)
# The tail block is "implicitly" finalized as it was given either as a
# checkpoint block, or is the genesis, thus we use it as a lower bound when
# computing the finalized head
let
finalized_checkpoint =
getStateField(dag.headState, finalized_checkpoint)
finalizedSlot = max(finalized_checkpoint.epoch.start_slot(), tailRef.slot)
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
block: # Set up finalizedHead -> head
var tmp = dag.head
while tmp.slot > finalizedSlot:
dag.forkBlocks.incl(KeyedBlockRef.init(tmp))
tmp = tmp.parent
# Fork blocks always include the latest finalized block which serves as the
# "root" of the fork DAG
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
dag.forkBlocks.incl(KeyedBlockRef.init(tmp))
dag.finalizedHead = tmp.atSlot(finalizedSlot)
block: # Set up tail -> finalizedHead
chaindag: don't keep backfill block table in memory (#3429) This PR names and documents the concept of the archive: a range of slots for which we have degraded functionality in terms of historical access - in particular: * we don't support rewinding to states in this range * we don't keep an in-memory representation of the block dag The archive de-facto exists in a trusted-node-synced node, but this PR gives it a name and drops the in-memory digest index. In order to satisfy `GetBlocksByRange` requests, we ensure that we have blocks for the entire archive period via backfill. Future versions may relax this further, adding a "pre-archive" period that is fully pruned. During by-slot searches in the archive (both for libp2p and rest requests), an extra database lookup is used to covert the given `slot` to a `root` - future versions will avoid this using era files which natively are indexed by `slot`. That said, the lookup is quite fast compared to the actual block loading given how trivial the table is - it's hard to measure, even. A collateral benefit of this PR is that checkpoint-synced nodes will see 100-200MB memory usage savings, thanks to the dropped in-memory cache - future pruning work will bring this benefit to full nodes as well. * document chaindag storage architecture and assumptions * look up parent using block id instead of full block in clearance (future-proofing the code against a future in which blocks come from era files) * simplify finalized block init, always writing the backfill portion to db at startup (to ensure lookups work as expected) * preallocate some extra memory for finalized blocks, to avoid immediate realloc
2022-02-26 18:16:19 +00:00
# Room for all finalized blocks from the tail onwards
let n = (dag.finalizedHead.slot - dag.tail.slot).int + 1
# Make room for some more blocks to avoid an instant reallocation
dag.finalizedBlocks = newSeqOfCap[BlockRef](int(n * 3 / 2))
dag.finalizedBlocks.setLen(n)
var tmp = dag.finalizedHead.blck
while not isNil(tmp):
dag.finalizedBlocks[(tmp.slot - dag.tail.slot).int] = tmp
tmp = tmp.parent
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
let stateTick = Moment.now()
# Pruning metadata
dag.lastPrunePoint = dag.finalizedHead
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
# Fill validator key cache in case we're loading an old database that doesn't
# have a cache
dag.updateValidatorKeys(getStateField(dag.headState, validators).asSeq())
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
dag.updateFinalizedBlocks()
withState(dag.headState):
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
when stateFork >= BeaconStateFork.Altair:
dag.headSyncCommittees = state.data.get_sync_committee_cache(cache)
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
info "Block DAG initialized",
head = shortLog(dag.head),
finalizedHead = shortLog(dag.finalizedHead),
tail = shortLog(dag.tail),
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
backfill = (dag.backfill.slot, shortLog(dag.backfill.parent_root)),
finalizedDur = finalizedTick - startTick,
summariesDur = summariesTick - finalizedTick,
stateDur = stateTick - summariesTick,
indexDur = Moment.now() - stateTick
dag.initLightClientCache()
dag
template genesisValidatorsRoot*(dag: ChainDAGRef): Eth2Digest =
getStateField(dag.headState, genesis_validators_root)
func getEpochRef*(
dag: ChainDAGRef, state: ForkedHashedBeaconState, blck: BlockRef,
cache: var StateCache): EpochRef =
## Get a cached `EpochRef` or construct one based on the given state - always
## returns an EpochRef instance
let
epoch = state.get_current_epoch()
var epochRef = dag.findEpochRef(blck, epoch)
if epochRef.isErr:
let res = EpochRef.init(dag, state, blck, cache)
if epoch >= dag.finalizedHead.slot.epoch():
# Only cache epoch information for unfinalized blocks - earlier states
# are seldomly used (ie RPC), so no need to cache
# Because we put a cap on the number of epochRefs we store, we want to
# prune the least useful state - for now, we'll assume that to be the
# oldest epochRef we know about.
var
oldest = 0
for x in 0..<dag.epochRefs.len:
let candidate = dag.epochRefs[x]
if candidate == nil:
oldest = x
break
if candidate.key.epoch < dag.epochRefs[oldest].epoch:
oldest = x
dag.epochRefs[oldest] = res
res
else:
epochRef.get()
proc getEpochRef*(
dag: ChainDAGRef, blck: BlockRef, epoch: Epoch,
preFinalized: bool): Opt[EpochRef] =
## Return a cached EpochRef or construct one from the database, if possible -
## returns `none` on failure.
##
## When `preFinalized` is true, include epochs from before the finalized
## checkpoint in the search - this potentially can result in long processing
## times due to state replays.
##
## Requests for epochs >= dag.finalizedHead.slot.epoch always return an
## instance. One must be careful to avoid race conditions in `async` code
## where the finalized head might change during an `await`.
##
## Requests for epochs < dag.finalizedHead.slot.epoch may fail, either because
## the search was limited by the `preFinalized` flag or because state history
## has been pruned - none will be returned in this case.
if not preFinalized and epoch < dag.finalizedHead.slot.epoch:
return err()
let epochRef = dag.findEpochRef(blck, epoch)
if epochRef.isOk():
beacon_state_data_cache_hits.inc
return epochRef
beacon_state_data_cache_misses.inc
let
ancestor = epochAncestor(blck, epoch)
if isNil(ancestor.blck): # past the tail
return err()
let epochBlck = ancestor.blck.atEpochStart(ancestor.epoch)
dag.withUpdatedState(dag.epochRefState, epochBlck) do:
ok(dag.getEpochRef(state, blck, cache))
do:
err()
proc getFinalizedEpochRef*(dag: ChainDAGRef): EpochRef =
dag.getEpochRef(
dag.finalizedHead.blck, dag.finalizedHead.slot.epoch, false).expect(
"getEpochRef for finalized head should always succeed")
func stateCheckpoint*(bs: BlockSlot): BlockSlot =
## The first ancestor BlockSlot that is a state checkpoint
var bs = bs
while not isStateCheckPoint(bs):
bs = bs.parentOrSlot
bs
template forkAtEpoch*(dag: ChainDAGRef, epoch: Epoch): Fork =
forkAtEpoch(dag.cfg, epoch)
func forkDigestAtEpoch*(dag: ChainDAGRef, epoch: Epoch): ForkDigest =
case dag.cfg.stateForkAtEpoch(epoch)
of BeaconStateFork.Bellatrix: dag.forkDigests.bellatrix
of BeaconStateFork.Altair: dag.forkDigests.altair
of BeaconStateFork.Phase0: dag.forkDigests.phase0
proc getState(
dag: ChainDAGRef, state: var ForkedHashedBeaconState, bs: BlockSlot): bool =
## Load a state from the database given a block and a slot - this will first
## lookup the state root in the state root table then load the corresponding
## state, if it exists
let restoreAddr =
# Any restore point will do as long as it's not the object being updated
if unsafeAddr(state) == unsafeAddr(dag.headState):
unsafeAddr dag.clearanceState
else:
unsafeAddr dag.headState
let v = addr state
func restore() =
assign(v[], restoreAddr[])
getState(dag.db, dag.cfg, state, bs, restore)
proc putState(dag: ChainDAGRef, state: ForkedHashedBeaconState, blck: BlockRef) =
# Store a state and its root
logScope:
blck = shortLog(blck)
stateSlot = shortLog(getStateField(state, slot))
stateRoot = shortLog(getStateRoot(state))
if not isStateCheckpoint(blck.atSlot(getStateField(state, slot))):
return
# Don't consider legacy tables here, they are slow to read so we'll want to
# rewrite things in the new table anyway.
if dag.db.containsState(getStateRoot(state), legacy = false):
return
let startTick = Moment.now()
# Ideally we would save the state and the root lookup cache in a single
# transaction to prevent database inconsistencies, but the state loading code
# is resilient against one or the other going missing
withState(state):
dag.db.putState(state)
debug "Stored state", putStateDur = Moment.now() - startTick
proc getBlockRange*(
dag: ChainDAGRef, startSlot: Slot, skipStep: uint64,
output: var openArray[BlockId]): Natural =
## This function populates an `output` buffer of blocks
## with a slots ranging from `startSlot` up to, but not including,
## `startSlot + skipStep * output.len`, skipping any slots that don't have
## a block.
##
## Blocks will be written to `output` from the end without gaps, even if
## a block is missing in a particular slot. The return value shows how
## many slots were missing blocks - to iterate over the result, start
## at this index.
##
## If there were no blocks in the range, `output.len` will be returned.
let
requestedCount = output.lenu64
headSlot = dag.head.slot
trace "getBlockRange entered",
head = shortLog(dag.head.root), requestedCount, startSlot, skipStep, headSlot
if startSlot < dag.backfill.slot:
notice "Got request for pre-backfill slot",
startSlot, backfillSlot = dag.backfill.slot
return output.len
if headSlot <= startSlot or requestedCount == 0:
return output.len # Identical to returning an empty set of block as indicated above
let
runway = uint64(headSlot - startSlot)
# This is the number of blocks that will follow the start block
extraSlots = min(runway div skipStep, requestedCount - 1)
# If `skipStep` is very large, `extraSlots` should be 0 from
# the previous line, so `endSlot` will be equal to `startSlot`:
endSlot = startSlot + extraSlots * skipStep
var
curSlot = endSlot
o = output.len
# Process all blocks that follow the start block (may be zero blocks)
while curSlot > startSlot:
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
let bs = dag.getBlockIdAtSlot(curSlot)
if bs.isSome and bs.get().isProposed():
o -= 1
output[o] = bs.get().bid
curSlot -= skipStep
# Handle start slot separately (to avoid underflow when computing curSlot)
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
let bs = dag.getBlockIdAtSlot(startSlot)
if bs.isSome and bs.get().isProposed():
o -= 1
output[o] = bs.get().bid
o # Return the index of the first non-nil item in the output
proc advanceSlots(
dag: ChainDAGRef, state: var ForkedHashedBeaconState, blck: BlockRef,
slot: Slot, save: bool, cache: var StateCache, info: var ForkedEpochInfo) =
# Given a state, advance it zero or more slots by applying empty slot
# processing - the state must be positions at a slot before or equal to the
# target
doAssert getStateField(state, slot) <= slot
while getStateField(state, slot) < slot:
let preEpoch = getStateField(state, slot).epoch
loadStateCache(dag, cache, blck, getStateField(state, slot).epoch)
process_slots(
dag.cfg, state, getStateField(state, slot) + 1, cache, info,
dag.updateFlags).expect("process_slots shouldn't fail when state slot is correct")
if save:
dag.putState(state, blck)
# The reward information in the state transition is computed for epoch
# transitions - when transitioning into epoch N, the activities in epoch
# N-2 are translated into balance updates, and this is what we capture
# in the monitor. This may be inaccurate during a deep reorg (>1 epoch)
# which is an acceptable tradeoff for monitoring.
withState(state):
let postEpoch = state.data.slot.epoch
if preEpoch != postEpoch:
dag.validatorMonitor[].registerEpochInfo(postEpoch, info, state.data)
proc applyBlock(
dag: ChainDAGRef, state: var ForkedHashedBeaconState, bid: BlockId,
cache: var StateCache, info: var ForkedEpochInfo): Result[void, cstring] =
case dag.cfg.blockForkAtEpoch(bid.slot.epoch)
of BeaconBlockFork.Phase0:
let data = getBlock(dag, bid, phase0.TrustedSignedBeaconBlock).valueOr:
return err("Block load failed")
state_transition(
dag.cfg, state, data, cache, info,
dag.updateFlags + {slotProcessed}, noRollback)
of BeaconBlockFork.Altair:
let data = getBlock(dag, bid, altair.TrustedSignedBeaconBlock).valueOr:
return err("Block load failed")
state_transition(
dag.cfg, state, data, cache, info,
dag.updateFlags + {slotProcessed}, noRollback)
of BeaconBlockFork.Bellatrix:
let data = getBlock(dag, bid, bellatrix.TrustedSignedBeaconBlock).valueOr:
return err("Block load failed")
state_transition(
dag.cfg, state, data, cache, info,
dag.updateFlags + {slotProcessed}, noRollback)
proc applyBlock(
dag: ChainDAGRef,
state: var ForkedHashedBeaconState, blck: BlockRef,
cache: var StateCache, info: var ForkedEpochInfo) =
# Apply a single block to the state - the state must be positioned at the
# parent of the block with a slot lower than the one of the block being
# applied
doAssert state.matches_block(blck.parent.root)
loadStateCache(dag, cache, blck.parent, getStateField(state, slot).epoch)
performance fixes (#2259) * performance fixes * don't mark tree cache as dirty on read-only List accesses * store only blob in memory for keys and signatures, parse blob lazily * compare public keys by blob instead of parsing / converting to raw * compare Eth2Digest using non-constant-time comparison * avoid some unnecessary validator copying This branch will in particular speed up deposit processing which has been slowing down block replay. Pre (mainnet, 1600 blocks): ``` All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3450.269, 0.000, 3450.269, 3450.269, 1, Initialize DB 0.417, 0.822, 0.036, 21.098, 1400, Load block from database 16.521, 0.000, 16.521, 16.521, 1, Load state from database 27.906, 50.846, 8.104, 1507.633, 1350, Apply block 52.617, 37.029, 20.640, 135.938, 50, Apply epoch block ``` Post: ``` 3502.715, 0.000, 3502.715, 3502.715, 1, Initialize DB 0.080, 0.560, 0.035, 21.015, 1400, Load block from database 17.595, 0.000, 17.595, 17.595, 1, Load state from database 15.706, 11.028, 8.300, 107.537, 1350, Apply block 33.217, 12.622, 17.331, 60.580, 50, Apply epoch block ``` * more perf fixes * load EpochRef cache into StateCache more aggressively * point out security concern with public key cache * reuse proposer index from state when processing block * avoid genericAssign in a few more places * don't parse key when signature is unparseable * fix `==` overload for Eth2Digest * preallocate validator list when getting active validators * speed up proposer index calculation a little bit * reuse cache when replaying blocks in ncli_db * avoid a few more copying loops ``` Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3279.158, 0.000, 3279.158, 3279.158, 1, Initialize DB 0.072, 0.357, 0.035, 13.400, 1400, Load block from database 17.295, 0.000, 17.295, 17.295, 1, Load state from database 5.918, 9.896, 0.198, 98.028, 1350, Apply block 15.888, 10.951, 7.902, 39.535, 50, Apply epoch block 0.000, 0.000, 0.000, 0.000, 0, Database block store ``` * clear full balance cache before processing rewards and penalties ``` All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 3947.901, 0.000, 3947.901, 3947.901, 1, Initialize DB 0.124, 0.506, 0.026, 202.370, 363345, Load block from database 97.614, 0.000, 97.614, 97.614, 1, Load state from database 0.186, 0.188, 0.012, 99.561, 357262, Advance slot, non-epoch 14.161, 5.966, 1.099, 395.511, 11524, Advance slot, epoch 1.372, 4.170, 0.017, 276.401, 363345, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database block store ```
2021-01-25 12:04:18 +00:00
dag.applyBlock(state, blck.bid, cache, info).expect(
"Blocks from database must not fail to apply")
proc updateState*(
dag: ChainDAGRef, state: var ForkedHashedBeaconState, bs: BlockSlot,
save: bool, cache: var StateCache): bool =
## Rewind or advance state such that it matches the given block and slot -
## this may include replaying from an earlier snapshot if blck is on a
## different branch or has advanced to a higher slot number than slot
## If `bs.slot` is higher than `bs.blck.slot`, `updateState` will fill in
## with empty/non-block slots
# First, see if we're already at the requested block. If we are, also check
# that the state has not been advanced past the desired block - if it has,
# an earlier state must be loaded since there's no way to undo the slot
# transitions
if isNil(bs.blck):
info "Requesting state for unknown block, historical data not available?",
head = shortLog(dag.head), tail = shortLog(dag.tail)
return false
let
startTick = Moment.now()
current {.used.} = withState(state):
BlockSlotId.init(state.latest_block_id, state.data.slot)
var
ancestors: seq[BlockRef]
found = false
template exactMatch(state: ForkedHashedBeaconState, bs: BlockSlot): bool =
# The block is the same and we're at an early enough slot - the state can
# be used to arrive at the desired blockslot
state.matches_block_slot(bs.blck.root, bs.slot)
template canAdvance(state: ForkedHashedBeaconState, bs: BlockSlot): bool =
# The block is the same and we're at an early enough slot - the state can
# be used to arrive at the desired blockslot
state.can_advance_slots(bs.blck.root, bs.slot)
# Fast path: check all caches for an exact match - this is faster than
# advancing a state where there's epoch processing to do, by a wide margin -
# it also avoids `hash_tree_root` for slot processing
if exactMatch(state, bs):
found = true
elif not save:
# When required to save states, we cannot rely on the caches because that
# would skip the extra processing that save does - not all information that
# goes into the database is cached
if exactMatch(dag.headState, bs):
assign(state, dag.headState)
found = true
elif exactMatch(dag.clearanceState, bs):
assign(state, dag.clearanceState)
found = true
elif exactMatch(dag.epochRefState, bs):
assign(state, dag.epochRefState)
found = true
const RewindBlockThreshold = 64
if not found:
# No exact match found - see if any in-memory state can be used as a base
# onto which we can apply a few blocks - there's a tradeoff here between
# loading the state from disk and performing the block applications
var cur = bs
while ancestors.len < RewindBlockThreshold:
if isNil(cur.blck): # tail reached
break
if canAdvance(state, cur): # Typical case / fast path when there's no reorg
found = true
break
if not save: # see above
if canAdvance(dag.headState, cur):
assign(state, dag.headState)
found = true
break
if canAdvance(dag.clearanceState, cur):
assign(state, dag.clearanceState)
found = true
break
if canAdvance(dag.epochRefState, cur):
assign(state, dag.epochRefState)
found = true
break
if cur.isProposed():
# This is not an empty slot, so the block will need to be applied to
# eventually reach bs
ancestors.add(cur.blck)
# Move slot by slot to capture epoch boundary states
cur = cur.parentOrSlot()
if not found:
debug "UpdateStateData cache miss",
current = shortLog(current), target = shortLog(bs)
# Either the state is too new or was created by applying a different block.
# We'll now resort to loading the state from the database then reapplying
# blocks until we reach the desired point in time.
var cur = bs
ancestors.setLen(0)
# Look for a state in the database and load it - as long as it cannot be
# found, keep track of the blocks that are needed to reach it from the
# state that eventually will be found.
# If we hit the tail, it means that we've reached a point for which we can
# no longer recreate history - this happens for example when starting from
# a checkpoint block
let startEpoch = bs.slot.epoch
while not canAdvance(state, cur) and not dag.getState(state, cur):
# There's no state saved for this particular BlockSlot combination, and
# the state we have can't trivially be advanced (in case it was older than
# RewindBlockThreshold), keep looking..
if cur.isProposed():
# This is not an empty slot, so the block will need to be applied to
# eventually reach bs
ancestors.add(cur.blck)
if cur.slot == dag.tail.slot or
(cur.slot.epoch + EPOCHS_PER_STATE_SNAPSHOT * 2 < startEpoch):
# We've either walked two full state snapshot lengths or hit the tail
# and still can't find a matching state: this can happen when
# starting the node from an arbitrary finalized checkpoint and not
# backfilling the states
notice "Request for pruned historical state",
request = shortLog(bs), tail = shortLog(dag.tail), cur = shortLog(cur)
return false
# Move slot by slot to capture epoch boundary states
cur = cur.parentOrSlot()
beacon_state_rewinds.inc()
# Starting state has been assigned, either from memory or database
let
assignTick = Moment.now()
ancestor {.used.} = withState(state):
BlockSlotId.init(state.latest_block_id, state.data.slot)
ancestorRoot {.used.} = getStateRoot(state)
var info: ForkedEpochInfo
# Time to replay all the blocks between then and now
for i in countdown(ancestors.len - 1, 0):
# Because the ancestors are in the database, there's no need to persist them
# again. Also, because we're applying blocks that were loaded from the
# database, we can skip certain checks that have already been performed
# before adding the block to the database.
dag.applyBlock(state, ancestors[i], cache, info)
# ...and make sure to process empty slots as requested
dag.advanceSlots(state, bs.blck, bs.slot, save, cache, info)
# ...and make sure to load the state cache, if it exists
loadStateCache(dag, cache, bs.blck, getStateField(state, slot).epoch)
let
assignDur = assignTick - startTick
replayDur = Moment.now() - assignTick
# TODO https://github.com/status-im/nim-chronicles/issues/108
if (assignDur + replayDur) >= 250.millis:
# This might indicate there's a cache that's not in order or a disk that is
# too slow - for now, it's here for investigative purposes and the cutoff
# time might need tuning
info "State replayed",
blocks = ancestors.len,
slots = getStateField(state, slot) - ancestor.slot,
current = shortLog(current),
ancestor = shortLog(ancestor),
target = shortLog(bs),
ancestorStateRoot = shortLog(ancestorRoot),
targetStateRoot = shortLog(getStateRoot(state)),
found,
assignDur,
replayDur
elif ancestors.len > 0:
debug "State replayed",
blocks = ancestors.len,
slots = getStateField(state, slot) - ancestor.slot,
current = shortLog(current),
ancestor = shortLog(ancestor),
target = shortLog(bs),
ancestorStateRoot = shortLog(ancestorRoot),
targetStateRoot = shortLog(getStateRoot(state)),
found,
assignDur,
replayDur
else: # Normal case!
trace "State advanced",
blocks = ancestors.len,
slots = getStateField(state, slot) - ancestor.slot,
current = shortLog(current),
ancestor = shortLog(ancestor),
target = shortLog(bs),
ancestorStateRoot = shortLog(ancestorRoot),
targetStateRoot = shortLog(getStateRoot(state)),
found,
assignDur,
replayDur
true
proc delState(dag: ChainDAGRef, bs: BlockSlot) =
# Delete state state and mapping for a particular block+slot
if not isStateCheckpoint(bs):
return # We only ever save epoch states
if (let root = dag.db.getStateRoot(bs.blck.root, bs.slot); root.isSome()):
dag.db.delState(root.get())
dag.db.delStateRoot(bs.blck.root, bs.slot)
proc pruneBlocksDAG(dag: ChainDAGRef) =
## This prunes the block DAG
## This does NOT prune the cached state checkpoints and EpochRef
## This must be done after a new finalization point is reached
## to invalidate pending blocks or attestations referring
## to a now invalid fork.
##
## This does NOT update the `dag.lastPrunePoint` field.
## as the caches and fork choice can be pruned at a later time.
# Clean up block refs, walking block by block
let startTick = Moment.now()
# Finalization means that we choose a single chain as the canonical one -
# it also means we're no longer interested in any branches from that chain
# up to the finalization point
let hlen = dag.heads.len
for i in 0..<hlen:
let n = hlen - i - 1
let head = dag.heads[n]
if dag.finalizedHead.blck.isAncestorOf(head):
continue
var cur = head.atSlot()
while not cur.blck.isAncestorOf(dag.finalizedHead.blck):
# Update light client data
dag.deleteLightClientData(cur.blck.bid)
dag.delState(cur) # TODO: should we move that disk I/O to `onSlotEnd`
if cur.isProposed():
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
dag.forkBlocks.excl(KeyedBlockRef.init(cur.blck))
dag.db.delBlock(cur.blck.root)
if cur.blck.parent.isNil:
break
cur = cur.parentOrSlot
dag.heads.del(n)
debug "Pruned the blockchain DAG",
currentCandidateHeads = dag.heads.len,
prunedHeads = hlen - dag.heads.len,
dagPruneDur = Moment.now() - startTick
iterator syncSubcommittee*(
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
syncCommittee: openArray[ValidatorIndex],
subcommitteeIdx: SyncSubcommitteeIndex): ValidatorIndex =
var i = subcommitteeIdx.asInt * SYNC_SUBCOMMITTEE_SIZE
let onePastEndIdx = min(syncCommittee.len, i + SYNC_SUBCOMMITTEE_SIZE)
while i < onePastEndIdx:
yield syncCommittee[i]
inc i
iterator syncSubcommitteePairs*(
syncCommittee: openArray[ValidatorIndex],
subcommitteeIdx: SyncSubcommitteeIndex): tuple[validatorIdx: ValidatorIndex,
subcommitteeIdx: int] =
var i = subcommitteeIdx.asInt * SYNC_SUBCOMMITTEE_SIZE
let onePastEndIdx = min(syncCommittee.len, i + SYNC_SUBCOMMITTEE_SIZE)
while i < onePastEndIdx:
yield (syncCommittee[i], i)
inc i
func syncCommitteeParticipants*(dag: ChainDAGRef,
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
slot: Slot): seq[ValidatorIndex] =
withState(dag.headState):
when stateFork >= BeaconStateFork.Altair:
let
period = sync_committee_period(slot)
curPeriod = sync_committee_period(state.data.slot)
if period == curPeriod:
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
@(dag.headSyncCommittees.current_sync_committee)
elif period == curPeriod + 1:
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
@(dag.headSyncCommittees.next_sync_committee)
else: @[]
else:
@[]
func getSubcommitteePositionsAux(
dag: ChainDAGRef,
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
syncCommittee: openArray[ValidatorIndex],
subcommitteeIdx: SyncSubcommitteeIndex,
validatorIdx: uint64): seq[uint64] =
var pos = 0'u64
for valIdx in syncCommittee.syncSubcommittee(subcommitteeIdx):
if validatorIdx == uint64(valIdx):
result.add pos
inc pos
func getSubcommitteePositions*(
dag: ChainDAGRef,
slot: Slot,
subcommitteeIdx: SyncSubcommitteeIndex,
validatorIdx: uint64): seq[uint64] =
withState(dag.headState):
when stateFork >= BeaconStateFork.Altair:
let
period = sync_committee_period(slot)
curPeriod = sync_committee_period(state.data.slot)
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
template search(syncCommittee: openArray[ValidatorIndex]): seq[uint64] =
dag.getSubcommitteePositionsAux(
syncCommittee, subcommitteeIdx, validatorIdx)
if period == curPeriod:
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
search(dag.headSyncCommittees.current_sync_committee)
elif period == curPeriod + 1:
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
search(dag.headSyncCommittees.next_sync_committee)
else: @[]
else:
@[]
template syncCommitteeParticipants*(
dag: ChainDAGRef,
slot: Slot,
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
subcommitteeIdx: SyncSubcommitteeIndex): seq[ValidatorIndex] =
toSeq(syncSubcommittee(dag.syncCommitteeParticipants(slot), subcommitteeIdx))
iterator syncCommitteeParticipants*(
dag: ChainDAGRef,
slot: Slot,
subcommitteeIdx: SyncSubcommitteeIndex,
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
aggregationBits: SyncCommitteeAggregationBits): ValidatorIndex =
for pos, valIdx in dag.syncCommitteeParticipants(slot, subcommitteeIdx):
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
if pos < aggregationBits.bits and aggregationBits[pos]:
yield valIdx
func needStateCachesAndForkChoicePruning*(dag: ChainDAGRef): bool =
dag.lastPrunePoint != dag.finalizedHead
proc pruneStateCachesDAG*(dag: ChainDAGRef) =
## This prunes the cached state checkpoints and EpochRef
## This does NOT prune the state associated with invalidated blocks on a fork
## They are pruned via `pruneBlocksDAG`
##
## This updates the `dag.lastPrunePoint` variable
doAssert dag.needStateCachesAndForkChoicePruning()
let startTick = Moment.now()
block: # Remove states, walking slot by slot
# We remove all state checkpoints that come _before_ the current finalized
# head, as we might frequently be asked to replay states from the
# finalized checkpoint and onwards (for example when validating blocks and
# attestations)
var
cur = dag.finalizedHead.stateCheckpoint.parentOrSlot
prev = dag.lastPrunePoint.stateCheckpoint.parentOrSlot
while cur.blck != nil and cur != prev:
if not isFinalizedStateSnapshot(cur.slot) and
cur.slot != dag.tail.slot:
dag.delState(cur)
cur = cur.parentOrSlot
let statePruneTick = Moment.now()
block: # Clean up old EpochRef instances
# After finalization, we can clear up the epoch cache and save memory -
# it will be recomputed if needed
for i in 0..<dag.epochRefs.len:
if dag.epochRefs[i] != nil and
dag.epochRefs[i].epoch < dag.finalizedHead.slot.epoch:
dag.epochRefs[i] = nil
let epochRefPruneTick = Moment.now()
dag.lastPrunePoint = dag.finalizedHead
2021-03-17 06:30:16 +00:00
debug "Pruned the state checkpoints and DAG caches.",
statePruneDur = statePruneTick - startTick,
epochRefPruneDur = epochRefPruneTick - statePruneTick
proc updateHead*(
dag: ChainDAGRef,
newHead: BlockRef,
quarantine: var Quarantine) =
## Update what we consider to be the current head, as given by the fork
## choice.
##
## The choice of head affects the choice of finalization point - the order
## of operations naturally becomes important here - after updating the head,
## blocks that were once considered potential candidates for a tree will
## now fall from grace, or no longer be considered resolved.
doAssert not newHead.isNil()
doAssert not newHead.parent.isNil() or newHead.slot <= dag.tail.slot
logScope:
newHead = shortLog(newHead)
if dag.head == newHead:
trace "No head block update"
return
let
lastHead = dag.head
lastHeadStateRoot = getStateRoot(dag.headState)
# Start off by making sure we have the right state - updateStateData will try
# to use existing in-memory states to make this smooth
var cache: StateCache
if not updateState(
dag, dag.headState, newHead.atSlot(), false, cache):
# Advancing the head state should never fail, given that the tail is
# implicitly finalised, the head is an ancestor of the tail and we always
# store the tail state in the database, as well as every epoch slot state in
# between
fatal "Unable to load head state during head update, database corrupt?",
lastHead = shortLog(lastHead)
quit 1
dag.head = newHead
dag.db.putHeadBlock(newHead.root)
updateBeaconMetrics(dag.headState, dag.head.bid, cache)
withState(dag.headState):
Speed up altair block processing 2x (#3115) * Speed up altair block processing >2x Like #3089, this PR drastially speeds up historical REST queries and other long state replays. * cache sync committee validator indices * use ~80mb less memory for validator pubkey mappings * batch-verify sync aggregate signature (fixes #2985) * document sync committee hack with head block vs sync message block * add batch signature verification failure tests Before: ``` ../env.sh nim c -d:release -r ncli_db --db:mainnet_0/db bench --start-slot:-1000 All time are ms Average, StdDev, Min, Max, Samples, Test Validation is turned off meaning that no BLS operations are performed 5830.675, 0.000, 5830.675, 5830.675, 1, Initialize DB 0.481, 1.878, 0.215, 59.167, 981, Load block from database 8422.566, 0.000, 8422.566, 8422.566, 1, Load state from database 6.996, 1.678, 0.042, 14.385, 969, Advance slot, non-epoch 93.217, 8.318, 84.192, 122.209, 32, Advance slot, epoch 20.513, 23.665, 11.510, 201.561, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` After: ``` 7081.422, 0.000, 7081.422, 7081.422, 1, Initialize DB 0.553, 2.122, 0.175, 66.692, 981, Load block from database 5439.446, 0.000, 5439.446, 5439.446, 1, Load state from database 6.829, 1.575, 0.043, 12.156, 969, Advance slot, non-epoch 94.716, 2.749, 88.395, 100.026, 32, Advance slot, epoch 11.636, 23.766, 4.889, 205.250, 981, Apply block, no slot processing 0.000, 0.000, 0.000, 0.000, 0, Database load 0.000, 0.000, 0.000, 0.000, 0, Database store ``` * add comment
2021-11-24 12:43:50 +00:00
when stateFork >= BeaconStateFork.Altair:
dag.headSyncCommittees = state.data.get_sync_committee_cache(cache)
let
finalized_checkpoint =
getStateField(dag.headState, finalized_checkpoint)
finalizedSlot = max(finalized_checkpoint.epoch.start_slot(), dag.tail.slot)
finalizedHead = newHead.atSlot(finalizedSlot)
doAssert (not finalizedHead.blck.isNil),
"Block graph should always lead to a finalized block"
# Update light client data
dag.processHeadChangeForLightClient()
let (isAncestor, ancestorDepth) = lastHead.getDepth(newHead)
if not(isAncestor):
notice "Updated head block with chain reorg",
lastHead = shortLog(lastHead),
headParent = shortLog(newHead.parent),
stateRoot = shortLog(getStateRoot(dag.headState)),
headBlock = shortLog(dag.head),
stateSlot = shortLog(getStateField(dag.headState, slot)),
justified = shortLog(getStateField(
dag.headState, current_justified_checkpoint)),
finalized = shortLog(getStateField(dag.headState, finalized_checkpoint))
if not(isNil(dag.onReorgHappened)):
let data = ReorgInfoObject.init(dag.head.slot, uint64(ancestorDepth),
lastHead.root, newHead.root,
lastHeadStateRoot,
getStateRoot(dag.headState))
dag.onReorgHappened(data)
# A reasonable criterion for "reorganizations of the chain"
quarantine.clearAfterReorg()
beacon_reorgs_total_total.inc()
beacon_reorgs_total.inc()
else:
debug "Updated head block",
head = shortLog(dag.head),
stateRoot = shortLog(getStateRoot(dag.headState)),
justified = shortLog(getStateField(
dag.headState, current_justified_checkpoint)),
finalized = shortLog(getStateField(dag.headState, finalized_checkpoint))
if not(isNil(dag.onHeadChanged)):
let
currentEpoch = epoch(newHead.slot)
depRoot = withState(dag.headState): state.proposer_dependent_root
prevDepRoot = withState(dag.headState): state.attester_dependent_root
epochTransition = (finalizedHead != dag.finalizedHead)
let data = HeadChangeInfoObject.init(dag.head.slot, dag.head.root,
getStateRoot(dag.headState),
epochTransition, depRoot,
prevDepRoot)
dag.onHeadChanged(data)
withState(dag.headState):
# Every time the head changes, the "canonical" view of balances and other
# state-related metrics change - notify the validator monitor.
# Doing this update during head update ensures there's a reasonable number
# of such updates happening - at most once per valid block.
dag.validatorMonitor[].registerState(state.data)
if finalizedHead != dag.finalizedHead:
debug "Reached new finalization checkpoint",
head = shortLog(dag.head),
stateRoot = shortLog(getStateRoot(dag.headState)),
Logging and startup improvements (#3038) * Logging and startup improvements Color support for released binaries! * startup scripts no longer log to file by default - this only affects source builds - released binaries don't support file logging * add --log-stdout option to control logging to stdout (colors, json) * detect tty:s vs redirected logs and log accordingly * add option to disable log colors at runtime * simplify several "common" logs, showing the most important information earlier and more clearly * remove line numbers / file information / tid - these take up space and are of little use to end users * still enabled in debug builds and tools * remove `testnet_servers_image` compile-time option * server images, released binaries and compile-from-source now offer the same behaviour and features * fixes https://github.com/status-im/nimbus-eth2/issues/2326 * fixes https://github.com/status-im/nimbus-eth2/issues/1794 * remove instanteneous block speed from sync message, keeping only average before: ``` INF 2021-10-28 16:45:59.000+02:00 Slot start topics="beacnde" tid=386429 file=nimbus_beacon_node.nim:884 lastSlot=2384027 wallSlot=2384028 delay=461us84ns peers=0 head=75a10ee5:3348 headEpoch=104 finalized=cd6804ba:3264 finalizedEpoch=102 sync="wwwwwwwwww:0:0.0000:0.0000:00h00m (3348)" INF 2021-10-28 16:45:59.046+02:00 Slot end topics="beacnde" tid=386429 file=nimbus_beacon_node.nim:821 slot=2384028 nextSlot=2384029 head=75a10ee5:3348 headEpoch=104 finalizedHead=cd6804ba:3264 finalizedEpoch=102 nextAttestationSlot=-1 nextProposalSlot=-1 nextActionWait=n/a ``` after: ``` INF 2021-10-28 22:43:23.033+02:00 Slot start topics="beacnde" slot=2385815 epoch=74556 sync="DDPDDPUDDD:10:5.2258:01h19m (2361088)" peers=37 head=eacd2dae:2361096 finalized=73782:a4751487 delay=33ms687us715ns INF 2021-10-28 22:43:23.291+02:00 Slot end topics="beacnde" slot=2385815 nextActionWait=n/a nextAttestationSlot=-1 nextProposalSlot=-1 head=eacd2dae:2361096 ``` * fix comment * documentation updates * mention `--log-file` may be deprecated in the future * update various docs
2021-11-02 17:06:36 +00:00
justified = shortLog(getStateField(
dag.headState, current_justified_checkpoint)),
finalized = shortLog(getStateField(dag.headState, finalized_checkpoint))
block:
# Update `dag.finalizedBlocks` with all newly finalized blocks (those
# newer than the previous finalized head), then update `dag.finalizedHead`
dag.finalizedBlocks.setLen(finalizedHead.slot - dag.tail.slot + 1)
var tmp = finalizedHead.blck
while not isNil(tmp) and tmp.slot >= dag.finalizedHead.slot:
dag.finalizedBlocks[(tmp.slot - dag.tail.slot).int] = tmp
limit by-root requests to non-finalized blocks (#3293) * limit by-root requests to non-finalized blocks Presently, we keep a mapping from block root to `BlockRef` in memory - this has simplified reasoning about the dag, but is not sustainable with the chain growing. We can distinguish between two cases where by-root access is useful: * unfinalized blocks - this is where the beacon chain is operating generally, by validating incoming data as interesting for future fork choice decisions - bounded by the length of the unfinalized period * finalized blocks - historical access in the REST API etc - no bounds, really In this PR, we limit the by-root block index to the first use case: finalized chain data can more efficiently be addressed by slot number. Future work includes: * limiting the `BlockRef` horizon in general - each instance is 40 bytes+overhead which adds up - this needs further refactoring to deal with the tail vs state problem * persisting the finalized slot-to-hash index - this one also keeps growing unbounded (albeit slowly) Anyway, this PR easily shaves ~128mb of memory usage at the time of writing. * No longer honor `BeaconBlocksByRoot` requests outside of the non-finalized period - previously, Nimbus would generously return any block through this libp2p request - per the spec, finalized blocks should be fetched via `BeaconBlocksByRange` instead. * return `Opt[BlockRef]` instead of `nil` when blocks can't be found - this becomes a lot more common now and thus deserves more attention * `dag.blocks` -> `dag.forkBlocks` - this index only carries unfinalized blocks from now - `finalizedBlocks` covers the other `BlockRef` instances * in backfill, verify that the last backfilled block leads back to genesis, or panic * add backfill timings to log * fix missing check that `BlockRef` block can be fetched with `getForkedBlock` reliably * shortcut doppelganger check when feature is not enabled * in REST/JSON-RPC, fetch blocks without involving `BlockRef` * fix dag.blocks ref
2022-01-21 11:33:16 +00:00
if tmp != finalizedHead.blck:
# The newly finalized block itself should remain in here so that fork
# choice still can find it via root
dag.forkBlocks.excl(KeyedBlockRef.init(tmp))
tmp = tmp.parent
dag.finalizedHead = finalizedHead
Store finalized block roots in database (3s startup) (#3320) * Store finalized block roots in database (3s startup) When the chain has finalized a checkpoint, the history from that point onwards becomes linear - this is exploited in `.era` files to allow constant-time by-slot lookups. In the database, we can do the same by storing finalized block roots in a simple sparse table indexed by slot, bringing the two representations closer to each other in terms of conceptual layout and performance. Doing so has a number of interesting effects: * mainnet startup time is improved 3-5x (3s on my laptop) * the _first_ startup might take slightly longer as the new index is being built - ~10s on the same laptop * we no longer rely on the beacon block summaries to load the full dag - this is a lot faster because we no longer have to look up each block by parent root * a collateral benefit is that we no longer need to load the full summaries table into memory - we get the RSS benefits of #3164 without the CPU hit. Other random stuff: * simplify forky block generics * fix withManyWrites multiple evaluation * fix validator key cache not being updated properly in chaindag read-only mode * drop pre-altair summaries from `kvstore` * recreate missing summaries from altair+ blocks as well (in case database has lost some to an involuntary restart) * print database startup timings in chaindag load log * avoid allocating superfluos state at startup * use a recursive sql query to load the summaries of the unfinalized blocks
2022-01-30 16:51:04 +00:00
dag.updateFinalizedBlocks()
# Pruning the block dag is required every time the finalized head changes
# in order to clear out blocks that are no longer viable and should
# therefore no longer be considered as part of the chain we're following
dag.pruneBlocksDAG()
# Update light client data
dag.processFinalizationForLightClient()
# Send notification about new finalization point via callback.
if not(isNil(dag.onFinHappened)):
let stateRoot =
if dag.finalizedHead.slot == dag.head.slot: getStateRoot(dag.headState)
elif dag.finalizedHead.slot + SLOTS_PER_HISTORICAL_ROOT > dag.head.slot:
getStateField(dag.headState, state_roots).data[
int(dag.finalizedHead.slot mod SLOTS_PER_HISTORICAL_ROOT)]
else:
Eth2Digest() # The thing that finalized was >8192 blocks old?
let data = FinalizationInfoObject.init(
dag.finalizedHead.blck.root,
stateRoot,
dag.finalizedHead.slot.epoch)
dag.onFinHappened(dag, data)
proc isInitialized*(T: type ChainDAGRef, db: BeaconChainDB): Result[void, cstring] =
# Lightweight check to see if we have the minimal information needed to
# load up a database - we don't check head here - if something is wrong with
# head, it's likely an initialized, but corrupt database - init will detect
# that
let
genesisBlockRoot = db.getGenesisBlock()
if not genesisBlockRoot.isSome():
return err("Genesis block root missing")
let
genesisBlock = db.getForkedBlock(genesisBlockRoot.get())
if not genesisBlock.isSome():
return err("Genesis block missing")
let
genesisStateRoot = withBlck(genesisBlock.get()): blck.message.state_root
if not db.containsState(genesisStateRoot):
return err("Genesis state missing")
let
tailBlockRoot = db.getTailBlock()
if not tailBlockRoot.isSome():
return err("Tail block root missing")
let
tailBlock = db.getForkedBlock(tailBlockRoot.get())
if not tailBlock.isSome():
return err("Tail block missing")
let
tailStateRoot = withBlck(tailBlock.get()): blck.message.state_root
if not db.containsState(tailStateRoot):
return err("Tail state missing")
ok()
proc preInit*(
T: type ChainDAGRef, db: BeaconChainDB,
genesisState, tailState: ForkedHashedBeaconState,
tailBlock: ForkedTrustedSignedBeaconBlock) =
# write a genesis state, the way the ChainDAGRef expects it to be stored in
# database
logScope:
genesisStateRoot = getStateRoot(genesisState)
genesisStateSlot = getStateField(genesisState, slot)
tailStateRoot = getStateRoot(tailState)
tailStateSlot = getStateField(tailState, slot)
let genesisBlockRoot = withState(genesisState):
if state.root != getStateRoot(tailState):
# Different tail and genesis
if state.data.slot >= getStateField(tailState, slot):
fatal "Tail state must be newer or the same as genesis state"
quit 1
let tail_genesis_validators_root =
getStateField(tailState, genesis_validators_root)
if state.data.genesis_validators_root != tail_genesis_validators_root:
fatal "Tail state doesn't match genesis validators root, it is likely from a different network!",
genesis_validators_root = shortLog(state.data.genesis_validators_root),
tail_genesis_validators_root = shortLog(tail_genesis_validators_root)
quit 1
let blck = get_initial_beacon_block(state)
db.putBlock(blck)
db.putState(state)
db.putGenesisBlock(blck.root)
blck.root
else: # tail and genesis are the same
withBlck(tailBlock):
db.putGenesisBlock(blck.root)
blck.root
withState(tailState):
withBlck(tailBlock):
# When looking up the state root of the tail block, we don't use the
# BlockSlot->state_root map, so the only way the init code can find the
# state is through the state root in the block - this could be relaxed
# down the line
if blck.message.state_root != state.root:
fatal "State must match the given block",
tailBlck = shortLog(blck)
quit 1
db.putBlock(blck)
db.putState(state)
db.putTailBlock(blck.root)
db.putHeadBlock(blck.root)
notice "New database from snapshot",
genesisBlockRoot = shortLog(genesisBlockRoot),
genesisStateRoot = shortLog(getStateRoot(genesisState)),
tailBlockRoot = shortLog(blck.root),
tailStateRoot = shortLog(state.root),
fork = state.data.fork,
validators = state.data.validators.len()
proc getProposer*(
dag: ChainDAGRef, head: BlockRef, slot: Slot): Option[ValidatorIndex] =
let
epochRef = block:
let tmp = dag.getEpochRef(head, slot.epoch(), false)
if tmp.isErr():
return none(ValidatorIndex)
tmp.get()
slotInEpoch = slot.since_epoch_start()
let proposer = epochRef.beacon_proposers[slotInEpoch]
if proposer.isSome():
if proposer.get().uint64 >= dag.db.immutableValidators.lenu64():
# Sanity check - it should never happen that the key cache doesn't contain
# a key for the selected proposer - that would mean that we somehow
# created validators in the state without updating the cache!
warn "Proposer key not found",
keys = dag.db.immutableValidators.lenu64(), proposer = proposer.get()
return none(ValidatorIndex)
proposer
proc aggregateAll*(
dag: ChainDAGRef,
validator_indices: openArray[ValidatorIndex]): Result[CookedPubKey, cstring] =
if validator_indices.len == 0:
# Aggregation spec requires non-empty collection
# - https://tools.ietf.org/html/draft-irtf-cfrg-bls-signature-04
# Eth2 spec requires at least one attesting index in attestation
# - https://github.com/ethereum/consensus-specs/blob/v1.1.10/specs/phase0/beacon-chain.md#is_valid_indexed_attestation
return err("aggregate: no attesting keys")
let
firstKey = dag.validatorKey(validator_indices[0])
if not firstKey.isSome():
return err("aggregate: invalid validator index")
var aggregateKey{.noinit.}: AggregatePublicKey
aggregateKey.init(firstKey.get())
for i in 1 ..< validator_indices.len:
let key = dag.validatorKey(validator_indices[i])
if not key.isSome():
return err("aggregate: invalid validator index")
aggregateKey.aggregate(key.get())
ok(finish(aggregateKey))
proc aggregateAll*(
dag: ChainDAGRef,
validator_indices: openArray[ValidatorIndex|uint64],
bits: BitSeq | BitArray): Result[CookedPubKey, cstring] =
if validator_indices.len() != bits.len():
return err("aggregateAll: mismatch in bits length")
var
aggregateKey{.noinit.}: AggregatePublicKey
inited = false
for i in 0..<bits.len():
if bits[i]:
let key = dag.validatorKey(validator_indices[i])
if not key.isSome():
return err("aggregate: invalid validator index")
if inited:
aggregateKey.aggregate(key.get)
else:
aggregateKey = AggregatePublicKey.init(key.get)
inited = true
if not inited:
err("aggregate: no attesting keys")
else:
ok(finish(aggregateKey))
func needsBackfill*(dag: ChainDAGRef): bool =
dag.backfill.slot > dag.genesis.slot
proc rebuildIndex*(dag: ChainDAGRef) =
## After a checkpoint sync, we lack intermediate states to replay from - this
## function rebuilds them so that historical replay can take place again
if dag.backfill.slot > 0:
debug "Backfill not complete, cannot rebuild archive"
return
if dag.tail.slot == dag.genesis.slot:
# The tail is the earliest slot for which we're supposed to have states -
# if it's sufficiently recent, don't do anything
debug "Archive does not need rebuilding"
return
# First, we check what states we already have in the database - that allows
# resuming the operation at any time
let
roots = dag.db.loadStateRoots()
var
canonical = newSeq[Eth2Digest](
(dag.finalizedHead.slot.epoch + EPOCHS_PER_STATE_SNAPSHOT - 1) div
EPOCHS_PER_STATE_SNAPSHOT)
# `junk` puts in place some infrastructure to prune unnecessary states - it
# will be more useful in the future as a base for pruning
junk: seq[((Slot, Eth2Digest), Eth2Digest)]
for k, v in roots:
if k[0] >= dag.finalizedHead.slot:
continue # skip newer stuff
if not isFinalizedStateSnapshot(k[0]):
# `tail` will move at the end of the process, so we won't need any
# intermediate states
junk.add((k, v))
continue # skip non-snapshot slots
if k[0] > 0:
let bs = dag.getBlockIdAtSlot(k[0] - 1)
if bs.isNone or bs.get().bid.root != k[1]:
# remove things that are no longer a canonical part of the chain or
# cannot be reached via a block
junk.add((k, v))
continue
if not dag.db.containsState(v):
continue # If it's not in the database..
canonical[k[0].epoch div EPOCHS_PER_STATE_SNAPSHOT] = v
let
state = (ref ForkedHashedBeaconState)()
var
cache: StateCache
info: ForkedEpochInfo
# `canonical` holds all slots at which a state is expected to appear, using a
# zero root whenever a particular state is missing - this way, if there's
# partial progress or gaps, they will be dealt with correctly
for i, state_root in canonical.mpairs():
if not state_root.isZero:
continue
doAssert i > 0, "Genesis should always be available"
let
startSlot = Epoch((i - 1) * EPOCHS_PER_STATE_SNAPSHOT).start_slot
slot = Epoch(i * EPOCHS_PER_STATE_SNAPSHOT).start_slot
info "Recreating state snapshot",
slot, startStateRoot = canonical[i - 1], startSlot
if getStateRoot(state[]) != canonical[i - 1]:
if not dag.db.getState(dag.cfg, startSlot, canonical[i - 1], state[], noRollback):
error "Can't load start state, database corrupt?",
startStateRoot = shortLog(canonical[i - 1]), slot = startSlot
return
for slot in startSlot..<startSlot + (EPOCHS_PER_STATE_SNAPSHOT * SLOTS_PER_EPOCH):
let bids = dag.getBlockIdAtSlot(slot).valueOr:
warn "Block id missing, cannot continue - database corrupt?", slot
return
# The slot check is needed to avoid re-applying a block
if bids.isProposed and getStateField(state[], latest_block_header).slot < bids.bid.slot:
let res = dag.applyBlock(state[], bids.bid, cache, info)
if res.isErr:
error "Failed to apply block while ", bids, slot
return
if slot.is_epoch:
cache.prune(slot.epoch)
process_slots(
dag.cfg, state[], slot, cache, info,
dag.updateFlags).expect("process_slots shouldn't fail when state slot is correct")
withState(state[]):
dag.db.putState(state)
state_root = state.root
# Now that we have states all the way to genesis, we can adjust the tail
# and readjust the in-memory indices to what they would look like if we had
# started with an earlier tail
dag.db.putTailBlock(dag.genesis.root)
var
midRef = dag.genesis
finBlocks = newSeqOfCap[BlockRef](
(dag.finalizedHead.slot.int + 1) * 3 div 2)
finBlocks.setLen(dag.finalizedHead.slot.int + 1)
finBlocks[dag.tail.slot.int..^1] = dag.finalizedBlocks
finBlocks[0] = dag.genesis
for slot, root in dag.db.finalizedBlocks:
if slot == midRef.slot:
continue
if slot == dag.tail.slot:
link(midRef, dag.tail)
break
let next = BlockRef.init(root, slot)
link(midRef, next)
midRef = next
finBlocks[midRef.slot.int] = midRef
dag.finalizedBlocks = finBlocks
dag.tail = dag.genesis
if junk.len > 0:
info "Dropping redundant states", states = junk.len
for i in junk:
dag.db.delState(i[1])