nimbus-eth1/execution_chain/nimbus_import.nim

371 lines
11 KiB
Nim
Raw Permalink Normal View History

# Nimbus
# Copyright (c) 2024-2025 Status Research & Development GmbH
# Licensed under either of
# * Apache License, version 2.0, ([LICENSE-APACHE](LICENSE-APACHE))
# * MIT license ([LICENSE-MIT](LICENSE-MIT))
# at your option.
# This file may not be copied, modified, or distributed except according to
# those terms.
2024-06-02 13:00:05 +02:00
{.push raises: [].}
import
chronicles,
metrics,
2024-06-02 13:00:05 +02:00
chronos/timer,
std/[strformat, strutils],
stew/io2,
beacon_chain/era_db,
beacon_chain/networking/network_metadata,
./config,
./common/common,
./core/chain,
./db/era1_db,
./utils/era_helpers
declareGauge nec_import_block_number, "Latest imported block number"
declareCounter nec_imported_blocks, "Blocks processed during import"
declareCounter nec_imported_transactions, "Transactions processed during import"
declareCounter nec_imported_gas, "Gas processed during import"
var running {.volatile.} = true
proc openCsv(name: string): File =
try:
let f = open(name, fmAppend)
let pos = f.getFileSize()
if pos == 0:
f.writeLine("block_number,blocks,slot,txs,gas,time")
f
except IOError as exc:
fatal "Could not open statistics output file", file = name, err = exc.msg
quit(QuitFailure)
proc getMetadata(networkId: NetworkId): auto =
# Network Specific Configurations
# TODO: the merge block number could be fetched from the era1 file instead,
# specially if the accumulator is added to the chain metadata
case networkId
of MainNet:
(
getMetadataForNetwork("mainnet").cfg,
# Mainnet Validators Root
Eth2Digest.fromHex(
"0x4b363db94e286120d76eb905340fdd4e54bfe9f06bf33ff6cf5ad27f511bfe95"
),
15537393'u64, # Last pre-merge block
4700013'u64, # First post-merge slot
)
of SepoliaNet:
(
getMetadataForNetwork("sepolia").cfg,
Eth2Digest.fromHex(
"0xd8ea171f3c94aea21ebc42a1ed61052acf3f9209c00e4efbaaddac09ed9b8078"
),
1450408'u64, # Last pre-merge block number
115193'u64, # First post-merge slot
)
of HoleskyNet:
(
getMetadataForNetwork("holesky").cfg,
Eth2Digest.fromHex(
"0x9143aa7c615a7f7115e2b6aac319c03529df8242ae705fba9df39b79c59fa8b1"
),
0'u64, # Last pre-merge block number
0'u64, # First post-merge slot
)
else:
fatal "Unsupported network", network = networkId
quit(QuitFailure)
template boolFlag(flags, b): PersistBlockFlags =
if b:
flags
else:
{}
proc importBlocks*(conf: NimbusConf, com: CommonRef) =
proc controlCHandler() {.noconv.} =
when defined(windows):
# workaround for https://github.com/nim-lang/Nim/issues/4057
setupForeignThreadGc()
running = false
setControlCHook(controlCHandler)
let
aristo: fork support via layers/txframes (#2960) * aristo: fork support via layers/txframes This change reorganises how the database is accessed: instead holding a "current frame" in the database object, a dag of frames is created based on the "base frame" held in `AristoDbRef` and all database access happens through this frame, which can be thought of as a consistent point-in-time snapshot of the database based on a particular fork of the chain. In the code, "frame", "transaction" and "layer" is used to denote more or less the same thing: a dag of stacked changes backed by the on-disk database. Although this is not a requirement, in practice each frame holds the change set of a single block - as such, the frame and its ancestors leading up to the on-disk state represents the state of the database after that block has been applied. "committing" means merging the changes to its parent frame so that the difference between them is lost and only the cumulative changes remain - this facility enables frames to be combined arbitrarily wherever they are in the dag. In particular, it becomes possible to consolidate a set of changes near the base of the dag and commit those to disk without having to re-do the in-memory frames built on top of them - this is useful for "flattening" a set of changes during a base update and sending those to storage without having to perform a block replay on top. Looking at abstractions, a side effect of this change is that the KVT and Aristo are brought closer together by considering them to be part of the "same" atomic transaction set - the way the code gets organised, applying a block and saving it to the kvt happens in the same "logical" frame - therefore, discarding the frame discards both the aristo and kvt changes at the same time - likewise, they are persisted to disk together - this makes reasoning about the database somewhat easier but has the downside of increased memory usage, something that perhaps will need addressing in the future. Because the code reasons more strictly about frames and the state of the persisted database, it also makes it more visible where ForkedChain should be used and where it is still missing - in particular, frames represent a single branch of history while forkedchain manages multiple parallel forks - user-facing services such as the RPC should use the latter, ie until it has been finalized, a getBlock request should consider all forks and not just the blocks in the canonical head branch. Another advantage of this approach is that `AristoDbRef` conceptually becomes more simple - removing its tracking of the "current" transaction stack simplifies reasoning about what can go wrong since this state now has to be passed around in the form of `AristoTxRef` - as such, many of the tests and facilities in the code that were dealing with "stack inconsistency" are now structurally prevented from happening. The test suite will need significant refactoring after this change. Once this change has been merged, there are several follow-ups to do: * there's no mechanism for keeping frames up to date as they get committed or rolled back - TODO * naming is confused - many names for the same thing for legacy reason * forkedchain support is still missing in lots of code * clean up redundant logic based on previous designs - in particular the debug and introspection code no longer makes sense * the way change sets are stored will probably need revisiting - because it's a stack of changes where each frame must be interrogated to find an on-disk value, with a base distance of 128 we'll at minimum have to perform 128 frame lookups for *every* database interaction - regardless, the "dag-like" nature will stay * dispose and commit are poorly defined and perhaps redundant - in theory, one could simply let the GC collect abandoned frames etc, though it's likely an explicit mechanism will remain useful, so they stay for now More about the changes: * `AristoDbRef` gains a `txRef` field (todo: rename) that "more or less" corresponds to the old `balancer` field * `AristoDbRef.stack` is gone - instead, there's a chain of `AristoTxRef` objects that hold their respective "layer" which has the actual changes * No more reasoning about "top" and "stack" - instead, each `AristoTxRef` can be a "head" that "more or less" corresponds to the old single-history `top` notion and its stack * `level` still represents "distance to base" - it's computed from the parent chain instead of being stored * one has to be careful not to use frames where forkedchain was intended - layers are only for a single branch of history! * fix layer vtop after rollback * engine fix * Fix test_txpool * Fix test_rpc * Fix copyright year * fix simulator * Fix copyright year * Fix copyright year * Fix tracer * Fix infinite recursion bug * Remove aristo and kvt empty files * Fic copyright year * Fix fc chain_kvt * ForkedChain refactoring * Fix merge master conflict * Fix copyright year * Reparent txFrame * Fix test * Fix txFrame reparent again * Cleanup and fix test * UpdateBase bugfix and fix test * Fixe newPayload bug discovered by hive * Fix engine api fcu * Clean up call template, chain_kvt, andn txguid * Fix copyright year * work around base block loading issue * Add test * Fix updateHead bug * Fix updateBase bug * Change func commitBase to proc commitBase * Touch up and fix debug mode crash --------- Co-authored-by: jangko <jangko128@gmail.com>
2025-02-06 08:04:50 +01:00
start = com.db.baseTxFrame().getSavedStateBlockNumber() + 1
(cfg, genesis_validators_root, lastEra1Block, firstSlotAfterMerge) =
getMetadata(conf.networkId)
time0 = Moment.now()
# These variables are used from closures on purpose, so as to place them on
# the heap rather than the stack
var
slot = 1'u64
time1 = Moment.now() # time at start of chunk
csv =
if conf.csvStats.isSome:
openCsv(conf.csvStats.get())
else:
File(nil)
flags =
boolFlag({PersistBlockFlag.NoValidation}, conf.noValidation) +
boolFlag({PersistBlockFlag.NoFullValidation}, not conf.fullValidation) +
boolFlag(NoPersistBodies, not conf.storeBodies) +
boolFlag({PersistBlockFlag.NoPersistReceipts}, not conf.storeReceipts) +
boolFlag({PersistBlockFlag.NoPersistSlotHashes}, not conf.storeSlotHashes)
blk: Block
persister = Persister.init(com, flags)
cstats: PersistStats # stats at start of chunk
defer:
if csv != nil:
close(csv)
template blockNumber(): uint64 =
start + uint64 persister.stats.blocks
nec_import_block_number.set(start.int64)
func f(value: float): string =
if value >= 1000:
&"{int(value)}"
elif value >= 100:
&"{value:4.1f}"
elif value >= 10:
&"{value:4.2f}"
else:
&"{value:4.3f}"
proc persistBlock() =
persister.persistBlock(blk).isOkOr:
fatal "Could not persist block", blockNumber = blk.header.number, error
quit(QuitFailure)
proc checkpoint(force: bool = false) =
let (blocks, txs, gas) = persister.stats
if not force and blocks.uint64 mod conf.chunkSize != 0:
return
persister.checkpoint().isOkOr:
fatal "Could not write database checkpoint", error
quit(QuitFailure)
let (cblocks, ctxs, cgas) =
(blocks - cstats.blocks, txs - cstats.txs, gas - cstats.gas)
if cblocks == 0:
return
cstats = persister.stats
let
time2 = Moment.now()
diff1 = (time2 - time1).nanoseconds().float / 1000000000
diff0 = (time2 - time0).nanoseconds().float / 1000000000
info "Imported blocks",
blockNumber,
slot,
blocks,
txs,
mgas = f(gas.float / 1000000),
bps = f(cblocks.float / diff1),
tps = f(ctxs.float / diff1),
mgps = f(cgas.float / 1000000 / diff1),
avgBps = f(blocks.float / diff0),
avgTps = f(txs.float / diff0),
avgMGps = f(gas.float / 1000000 / diff0),
elapsed = toString(time2 - time0, 3)
metrics.set(nec_import_block_number, int64(blockNumber))
nec_imported_blocks.inc(cblocks)
nec_imported_transactions.inc(ctxs)
nec_imported_gas.inc(int64 cgas)
if csv != nil:
# In the CSV, we store a line for every chunk of blocks processed so
# that the file can meaningfully be appended to when restarting the
# process - this way, each sample is independent
try:
csv.writeLine(
[$blockNumber, $cblocks, $slot, $ctxs, $cgas, $(time2 - time1).nanoseconds()].join(
","
)
)
csv.flushFile()
except IOError as exc:
warn "Could not write csv", err = exc.msg
time1 = time2
# Finds the slot number to resume the import process
# First it sets the initial lower bound to `firstSlotAfterMerge` + number of blocks after Era1
# Then it iterates over the slots to find the current slot number, along with reducing the
# search space by calculating the difference between the `blockNumber` and the `block_number` from the executionPayload
# of the slot, then adding the difference to the importedSlot. This pushes the lower bound more,
# making the search way smaller
proc updateLastImportedSlot(
era: EraDB,
historical_roots: openArray[Eth2Digest],
historical_summaries: openArray[HistoricalSummary],
endSlot: Slot,
): bool =
# Checks if the Nimbus block number is ahead the era block number
# First we load the last era number, and get the fist slot number
# Since the slot emptiness cannot be predicted, we iterate over to find the block and check
# if the block number is greater than the current block number
var
lastEra = era(endSlot - 1)
startSlot = start_slot(lastEra) - 8192
debug "Finding slot number to resume import", startSlot, endSlot
while startSlot < endSlot:
if not getEthBlockFromEra(
era, historical_roots, historical_summaries, startSlot, cfg, blk
):
startSlot += 1
if startSlot == endSlot - 1:
error "No blocks found in the last era file"
return false
continue
startSlot += 1
if blk.header.number < blockNumber:
notice "Available `era` files are already imported",
stateBlockNumber = blockNumber, eraBlockNumber = blk.header.number
return false
break
if blockNumber > 1:
# Setting the initial lower bound
slot = (blockNumber - lastEra1Block) + firstSlotAfterMerge
debug "Finding slot number after resuming import", slot
# BlockNumber based slot finding
var clNum = 0'u64
while clNum < blockNumber:
if not getEthBlockFromEra(
era, historical_roots, historical_summaries, Slot(slot), cfg, blk
):
slot += 1
continue
clNum = blk.header.number
# decreasing the lower bound with each iteration
slot += blockNumber - clNum
notice "Matched block to slot number", blockNumber, slot
return true
if lastEra1Block > 0 and start <= lastEra1Block:
let
era1Name =
case conf.networkId
of MainNet:
"mainnet"
of SepoliaNet:
"sepolia"
else:
raiseAssert "Other networks are unsupported or do not have an era1"
db = Era1DbRef.init(conf.era1Dir.string, era1Name).valueOr:
fatal "Could not open era1 database", era1Dir=conf.era1Dir, era1Name=era1Name, error=error
quit(QuitFailure)
notice "Importing era1 archive",
start, dataDir = conf.dataDir.string, era1Dir = conf.era1Dir.string
defer:
db.dispose()
proc loadEraBlock(blockNumber: uint64): bool =
db.getEthBlock(blockNumber, blk).isOkOr:
return false
true
while running and persister.stats.blocks.uint64 < conf.maxBlocks and
blockNumber <= lastEra1Block:
if not loadEraBlock(blockNumber):
notice "No more `era1` blocks to import", blockNumber, slot
break
persistBlock()
checkpoint()
block era1Import:
if blockNumber > lastEra1Block:
if not isDir(conf.eraDir.string):
if blockNumber == 0:
fatal "`era` directory not found, cannot start import",
blockNumber, eraDir = conf.eraDir.string
quit(QuitFailure)
else:
notice "`era` directory not found, stopping import at merge boundary",
blockNumber, eraDir = conf.eraDir.string
break era1Import
notice "Importing era archive",
blockNumber, dataDir = conf.dataDir.string, eraDir = conf.eraDir.string
let
eraDB = EraDB.new(cfg, conf.eraDir.string, genesis_validators_root)
(historical_roots, historical_summaries, endSlot) = loadHistoricalRootsFromEra(
conf.eraDir.string, cfg
).valueOr:
fatal "Could not load historical summaries",
eraDir = conf.eraDir.string, error
quit(QuitFailure)
# Load the last slot number
var moreEraAvailable = true
if blockNumber > lastEra1Block + 1:
moreEraAvailable = updateLastImportedSlot(
eraDB, historical_roots.asSeq(), historical_summaries.asSeq(), endSlot
)
if slot < firstSlotAfterMerge and firstSlotAfterMerge != 0:
# if resuming import we do not update the slot
slot = firstSlotAfterMerge
proc loadEra1Block(): bool =
# Separate proc to reduce stack usage of blk
if not getEthBlockFromEra(
eraDB,
historical_roots.asSeq(),
historical_summaries.asSeq(),
Slot(slot),
cfg,
blk,
):
return false
true
while running and moreEraAvailable and
persister.stats.blocks.uint64 < conf.maxBlocks and slot < endSlot:
if not loadEra1Block():
slot += 1
continue
slot += 1
persistBlock()
checkpoint()
# If there were no blocks written, we will not have loaded the block number
# and therefore should not call checkpoint().
if 0 < persister.stats.blocks:
checkpoint(true)
notice "Import complete",
blockNumber,
slot,
blocks = persister.stats.blocks,
txs = persister.stats.txs,
mgas = f(persister.stats.gas.float / 1000000)