nimbus-eth1/nimbus/core/validate.nim

349 lines
13 KiB
Nim
Raw Normal View History

# Nimbus
# Copyright (c) 2018-2024 Status Research & Development GmbH
# Licensed under either of
# * Apache License, version 2.0, ([LICENSE-APACHE](LICENSE-APACHE) or
# http://www.apache.org/licenses/LICENSE-2.0)
# * MIT license ([LICENSE-MIT](LICENSE-MIT) or
# http://opensource.org/licenses/MIT)
# at your option. This file may not be copied, modified, or distributed except
# according to those terms.
{.push raises: [].}
import
std/[sequtils, sets, strformat],
../db/ledger,
".."/[transaction, common/common],
".."/[errors],
../utils/utils,
"."/[dao, eip4844, gaslimit, withdrawals],
2022-12-02 04:35:41 +00:00
./pow/[difficulty, header],
nimcrypto/utils as cryptoutils,
2024-05-30 12:54:03 +00:00
stew/objects,
results
from stew/byteutils
import nil
export
results
const
daoForkBlockExtraData* =
byteutils.hexToByteArray[13](DAOForkBlockExtra).toSeq
# ------------------------------------------------------------------------------
# Private validator functions
# ------------------------------------------------------------------------------
proc validateHeader(
com: CommonRef;
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
blk: EthBlock;
parentHeader: BlockHeader;
checkSealOK: bool;
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
): Result[void,string] =
template header: BlockHeader = blk.header
# TODO this code is used for validating uncles also, though these get passed
# an empty body - avoid this by separating header and block validation
template inDAOExtraRange(blockNumber: BlockNumber): bool =
# EIP-799
# Blocks with block numbers in the range [1_920_000, 1_920_009]
# MUST have DAOForkBlockExtra
2022-12-02 04:35:41 +00:00
let daoForkBlock = com.daoForkBlock.get
let DAOHigh = daoForkBlock + DAOForkExtraRange
2022-12-02 04:35:41 +00:00
daoForkBlock <= blockNumber and
blockNumber < DAOHigh
if header.extraData.len > 32:
return err("BlockHeader.extraData larger than 32 bytes")
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
if header.gasUsed == 0 and 0 < blk.transactions.len:
return err("zero gasUsed but transactions present");
if header.gasUsed < 0 or header.gasUsed > header.gasLimit:
return err("gasUsed should be non negative and smaller or equal gasLimit")
if header.number != parentHeader.number + 1:
return err("Blocks must be numbered consecutively")
if header.timestamp <= parentHeader.timestamp:
return err("timestamp must be strictly later than parent")
if header.gasLimit > GAS_LIMIT_MAXIMUM:
return err("gasLimit exceeds GAS_LIMIT_MAXIMUM")
if com.daoForkSupport and inDAOExtraRange(header.number):
if header.extraData != daoForkBlockExtraData:
return err("header extra data should be marked DAO")
2022-12-02 04:35:41 +00:00
if com.consensus == ConsensusType.POS:
# EIP-4399 and EIP-3675
# no need to check mixHash because EIP-4399 override this field
# checking rule
if not header.difficulty.isZero:
return err("Non-zero difficulty in a post-merge block")
if not header.nonce.isZeroMemory:
return err("Non-zero nonce in a post-merge block")
if header.ommersHash != EMPTY_UNCLE_HASH:
return err("Invalid ommers hash in a post-merge block")
else:
2022-12-02 04:35:41 +00:00
let calcDiffc = com.calcDifficulty(header.timestamp, parentHeader)
if header.difficulty < calcDiffc:
return err("provided header difficulty is too low")
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
? com.validateWithdrawals(header, blk.withdrawals)
? com.validateEip4844Header(header, parentHeader, blk.transactions)
? com.validateGasLimitOrBaseFee(header, parentHeader)
ok()
2022-12-02 04:35:41 +00:00
proc validateUncles(com: CommonRef; header: BlockHeader;
uncles: openArray[BlockHeader];
checkSealOK: bool): Result[void,string]
{.gcsafe, raises: [].} =
let hasUncles = uncles.len > 0
let shouldHaveUncles = header.ommersHash != EMPTY_UNCLE_HASH
if not hasUncles and not shouldHaveUncles:
# optimization to avoid loading ancestors from DB, since the block has
# no uncles
return ok()
if hasUncles and not shouldHaveUncles:
return err("Block has uncles but header suggests uncles should be empty")
if shouldHaveUncles and not hasUncles:
return err("Header suggests block should have uncles but block has none")
# Check for duplicates
var uncleSet = HashSet[Hash256]()
for uncle in uncles:
Fearture/poa clique tuning (#765) * Provide API details: API is bundled via clique.nim. * Set extraValidation as default for PoA chains why: This triggers consensus verification and an update of the list of authorised signers. These signers are integral part of the PoA block chain. todo: Option argument to control validation for the nimbus binary. * Fix snapshot state block number why: Using sub-sequence here, so the len() function was wrong. * Optional start where block verification begins why: Can speed up time building loading initial parts of block chain. For PoA, this allows to prove & test that authorised signers can be (correctly) calculated starting at any point on the block chain. todo: On Goerli around blocks #193537..#197568, processing time increases disproportionally -- needs to be understand * For Clique test, get old grouping back (7 transactions per log entry) why: Forgot to change back after troubleshooting * Fix field/function/module-name misunderstanding why: Make compilation work * Use eth_types.blockHash() rather than utils.hash() in Clique modules why: Prefer lib module * Dissolve snapshot_misc.nim details: .. into clique_verify.nim (the other source file clique_unused.nim is inactive) * Hide unused AsyncLock in Clique descriptor details: Unused here but was part of the Go reference implementation * Remove fakeDiff flag from Clique descriptor details: This flag was a kludge in the Go reference implementation used for the canonical tests. The tests have been adapted so there is no need for the fakeDiff flag and its implementation. * Not observing minimum distance from epoch sync point why: For compiling PoA state, the go implementation will walk back to the epoch header with at least 90000 blocks apart from the current header in the absence of other synchronisation points. Here just the nearest epoch header is used. The assumption is that all the checkpoints before have been vetted already regardless of the current branch. details: The behaviour of using the nearest vs the minimum distance epoch is controlled by a flag and can be changed at run time. * Analysing processing time (patch adds some debugging/visualisation support) why: At the first half million blocks of the Goerli replay, blocks on the interval #194854..#196224 take exceptionally long to process, but not due to PoA processing. details: It turns out that much time is spent in p2p/excecutor.processBlock() where the elapsed transaction execution time is significantly greater for many of these blocks. Between the 1371 blocks #194854..#196224 there are 223 blocks with more than 1/2 seconds execution time whereas there are only 4 such blocks before and 13 such after this range up to #504192. * fix debugging symbol in clique_desc (causes CI failing) * Fixing canonical reference tests why: Two errors were introduced earlier but ovelooked: 1. "Remove fakeDiff flag .." patch was incomplete 2. "Not observing minimum distance .." introduced problem w/tests 23/24 details: Fixing 2. needed to revert the behaviour by setting the applySnapsMinBacklog flag for the Clique descriptor. Also a new test was added to lock the new behaviour. * Remove cruft why: Clique/PoA processing was intended to take place somewhere in executor/process_block.processBlock() but was decided later to run from chain/persist_block.persistBlock() instead. * Update API comment * ditto
2021-07-30 14:06:51 +00:00
let uncleHash = uncle.blockHash
if uncleHash in uncleSet:
return err("Block contains duplicate uncles")
else:
uncleSet.incl uncleHash
2022-12-02 04:35:41 +00:00
let chainDB = com.db
let recentAncestorHashes = try:
chainDB.getAncestorsHashes(MAX_UNCLE_DEPTH + 1, header)
except CatchableError as err:
return err("Block not present in database")
let recentUncleHashes = try:
chainDB.getUncleHashes(recentAncestorHashes)
except CatchableError as err:
return err("Ancenstors not present in database")
Fearture/poa clique tuning (#765) * Provide API details: API is bundled via clique.nim. * Set extraValidation as default for PoA chains why: This triggers consensus verification and an update of the list of authorised signers. These signers are integral part of the PoA block chain. todo: Option argument to control validation for the nimbus binary. * Fix snapshot state block number why: Using sub-sequence here, so the len() function was wrong. * Optional start where block verification begins why: Can speed up time building loading initial parts of block chain. For PoA, this allows to prove & test that authorised signers can be (correctly) calculated starting at any point on the block chain. todo: On Goerli around blocks #193537..#197568, processing time increases disproportionally -- needs to be understand * For Clique test, get old grouping back (7 transactions per log entry) why: Forgot to change back after troubleshooting * Fix field/function/module-name misunderstanding why: Make compilation work * Use eth_types.blockHash() rather than utils.hash() in Clique modules why: Prefer lib module * Dissolve snapshot_misc.nim details: .. into clique_verify.nim (the other source file clique_unused.nim is inactive) * Hide unused AsyncLock in Clique descriptor details: Unused here but was part of the Go reference implementation * Remove fakeDiff flag from Clique descriptor details: This flag was a kludge in the Go reference implementation used for the canonical tests. The tests have been adapted so there is no need for the fakeDiff flag and its implementation. * Not observing minimum distance from epoch sync point why: For compiling PoA state, the go implementation will walk back to the epoch header with at least 90000 blocks apart from the current header in the absence of other synchronisation points. Here just the nearest epoch header is used. The assumption is that all the checkpoints before have been vetted already regardless of the current branch. details: The behaviour of using the nearest vs the minimum distance epoch is controlled by a flag and can be changed at run time. * Analysing processing time (patch adds some debugging/visualisation support) why: At the first half million blocks of the Goerli replay, blocks on the interval #194854..#196224 take exceptionally long to process, but not due to PoA processing. details: It turns out that much time is spent in p2p/excecutor.processBlock() where the elapsed transaction execution time is significantly greater for many of these blocks. Between the 1371 blocks #194854..#196224 there are 223 blocks with more than 1/2 seconds execution time whereas there are only 4 such blocks before and 13 such after this range up to #504192. * fix debugging symbol in clique_desc (causes CI failing) * Fixing canonical reference tests why: Two errors were introduced earlier but ovelooked: 1. "Remove fakeDiff flag .." patch was incomplete 2. "Not observing minimum distance .." introduced problem w/tests 23/24 details: Fixing 2. needed to revert the behaviour by setting the applySnapsMinBacklog flag for the Clique descriptor. Also a new test was added to lock the new behaviour. * Remove cruft why: Clique/PoA processing was intended to take place somewhere in executor/process_block.processBlock() but was decided later to run from chain/persist_block.persistBlock() instead. * Update API comment * ditto
2021-07-30 14:06:51 +00:00
let blockHash = header.blockHash
for uncle in uncles:
Fearture/poa clique tuning (#765) * Provide API details: API is bundled via clique.nim. * Set extraValidation as default for PoA chains why: This triggers consensus verification and an update of the list of authorised signers. These signers are integral part of the PoA block chain. todo: Option argument to control validation for the nimbus binary. * Fix snapshot state block number why: Using sub-sequence here, so the len() function was wrong. * Optional start where block verification begins why: Can speed up time building loading initial parts of block chain. For PoA, this allows to prove & test that authorised signers can be (correctly) calculated starting at any point on the block chain. todo: On Goerli around blocks #193537..#197568, processing time increases disproportionally -- needs to be understand * For Clique test, get old grouping back (7 transactions per log entry) why: Forgot to change back after troubleshooting * Fix field/function/module-name misunderstanding why: Make compilation work * Use eth_types.blockHash() rather than utils.hash() in Clique modules why: Prefer lib module * Dissolve snapshot_misc.nim details: .. into clique_verify.nim (the other source file clique_unused.nim is inactive) * Hide unused AsyncLock in Clique descriptor details: Unused here but was part of the Go reference implementation * Remove fakeDiff flag from Clique descriptor details: This flag was a kludge in the Go reference implementation used for the canonical tests. The tests have been adapted so there is no need for the fakeDiff flag and its implementation. * Not observing minimum distance from epoch sync point why: For compiling PoA state, the go implementation will walk back to the epoch header with at least 90000 blocks apart from the current header in the absence of other synchronisation points. Here just the nearest epoch header is used. The assumption is that all the checkpoints before have been vetted already regardless of the current branch. details: The behaviour of using the nearest vs the minimum distance epoch is controlled by a flag and can be changed at run time. * Analysing processing time (patch adds some debugging/visualisation support) why: At the first half million blocks of the Goerli replay, blocks on the interval #194854..#196224 take exceptionally long to process, but not due to PoA processing. details: It turns out that much time is spent in p2p/excecutor.processBlock() where the elapsed transaction execution time is significantly greater for many of these blocks. Between the 1371 blocks #194854..#196224 there are 223 blocks with more than 1/2 seconds execution time whereas there are only 4 such blocks before and 13 such after this range up to #504192. * fix debugging symbol in clique_desc (causes CI failing) * Fixing canonical reference tests why: Two errors were introduced earlier but ovelooked: 1. "Remove fakeDiff flag .." patch was incomplete 2. "Not observing minimum distance .." introduced problem w/tests 23/24 details: Fixing 2. needed to revert the behaviour by setting the applySnapsMinBacklog flag for the Clique descriptor. Also a new test was added to lock the new behaviour. * Remove cruft why: Clique/PoA processing was intended to take place somewhere in executor/process_block.processBlock() but was decided later to run from chain/persist_block.persistBlock() instead. * Update API comment * ditto
2021-07-30 14:06:51 +00:00
let uncleHash = uncle.blockHash
if uncleHash == blockHash:
return err("Uncle has same hash as block")
# ensure the uncle has not already been included.
if uncleHash in recentUncleHashes:
return err("Duplicate uncle")
# ensure that the uncle is not one of the canonical chain blocks.
if uncleHash in recentAncestorHashes:
return err("Uncle cannot be an ancestor")
# ensure that the uncle was built off of one of the canonical chain
# blocks.
if (uncle.parentHash notin recentAncestorHashes) or
(uncle.parentHash == header.parentHash):
return err("Uncle's parent is not an ancestor")
if uncle.number >= header.number:
return err("uncle block number larger than current block number")
# check uncle against own parent
var parent: BlockHeader
if not chainDB.getBlockHeader(uncle.parentHash,parent):
return err("Uncle's parent has gone missing")
if uncle.timestamp <= parent.timestamp:
return err("Uncle's parent must me older")
let uncleParent = try:
chainDB.getBlockHeader(uncle.parentHash)
except BlockNotFound:
return err("Uncle parent not found")
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
? com.validateHeader(
EthBlock.init(uncle, BlockBody()), uncleParent, checkSealOK)
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
ok()
# ------------------------------------------------------------------------------
# Public function, extracted from executor
# ------------------------------------------------------------------------------
func gasCost*(tx: Transaction): UInt256 =
if tx.txType >= TxEip4844:
tx.gasLimit.u256 * tx.maxFeePerGas.u256 + tx.getTotalBlobGas.u256 * tx.maxFeePerBlobGas
elif tx.txType >= TxEip1559:
tx.gasLimit.u256 * tx.maxFeePerGas.u256
else:
tx.gasLimit.u256 * tx.gasPrice.u256
proc validateTxBasic*(
tx: Transaction; ## tx to validate
fork: EVMFork,
validateFork: bool = true): Result[void, string] =
if validateFork:
if tx.txType == TxEip2930 and fork < FkBerlin:
return err("invalid tx: Eip2930 Tx type detected before Berlin")
if tx.txType == TxEip1559 and fork < FkLondon:
return err("invalid tx: Eip1559 Tx type detected before London")
if tx.txType == TxEip4844 and fork < FkCancun:
return err("invalid tx: Eip4844 Tx type detected before Cancun")
2023-01-10 04:25:23 +00:00
if fork >= FkShanghai and tx.contractCreation and tx.payload.len > EIP3860_MAX_INITCODE_SIZE:
return err("invalid tx: initcode size exceeds maximum")
# The total must be the larger of the two
if tx.maxFeePerGasNorm < tx.maxPriorityFeePerGasNorm:
return err(&"invalid tx: maxFee is smaller than maPriorityFee. maxFee={tx.maxFeePerGas}, maxPriorityFee={tx.maxPriorityFeePerGasNorm}")
if tx.gasLimit < tx.intrinsicGas(fork):
return err(&"invalid tx: not enough gas to perform calculation. avail={tx.gasLimit}, require={tx.intrinsicGas(fork)}")
if fork >= FkCancun:
if tx.payload.len > MAX_CALLDATA_SIZE:
return err(&"invalid tx: payload len exceeds MAX_CALLDATA_SIZE. len={tx.payload.len}")
if tx.accessList.len > MAX_ACCESS_LIST_SIZE:
return err("invalid tx: access list len exceeds MAX_ACCESS_LIST_SIZE. len=" &
$tx.accessList.len)
for i, acl in tx.accessList:
if acl.storageKeys.len > MAX_ACCESS_LIST_STORAGE_KEYS:
return err("invalid tx: access list storage keys len exceeds MAX_ACCESS_LIST_STORAGE_KEYS. " &
&"index={i}, len={acl.storageKeys.len}")
if tx.txType >= TxEip4844:
if tx.to.isNone:
return err("invalid tx: destination must be not empty")
if tx.versionedHashes.len == 0:
return err("invalid tx: there must be at least one blob")
if tx.versionedHashes.len > MAX_BLOBS_PER_BLOCK:
return err(&"invalid tx: versioned hashes len exceeds MAX_BLOBS_PER_BLOCK={MAX_BLOBS_PER_BLOCK}. get={tx.versionedHashes.len}")
for i, bv in tx.versionedHashes:
if bv.data[0] != VERSIONED_HASH_VERSION_KZG:
return err("invalid tx: one of blobVersionedHash has invalid version. " &
&"get={bv.data[0].int}, expect={VERSIONED_HASH_VERSION_KZG.int}")
ok()
proc validateTransaction*(
roDB: ReadOnlyStateDB; ## Parent accounts environment for transaction
tx: Transaction; ## tx to validate
sender: EthAddress; ## tx.getSender or tx.ecRecover
maxLimit: GasInt; ## gasLimit from block header
baseFee: UInt256; ## baseFee from block header
excessBlobGas: uint64; ## excessBlobGas from parent block header
fork: EVMFork): Result[void, string] =
? validateTxBasic(tx, fork)
let
balance = roDB.getBalance(sender)
nonce = roDB.getNonce(sender)
# Note that the following check bears some plausibility but is _not_
# covered by the eip-1559 reference (sort of) pseudo code, for details
# see `https://eips.ethereum.org/EIPS/eip-1559#specification`_
#
# Rather this check is needed for surviving the post-London unit test
# eth_tests/GeneralStateTests/stEIP1559/lowGasLimit.json which seems to
# be sourced and generated from
# eth_tests/src/GeneralStateTestsFiller/stEIP1559/lowGasLimitFiller.yml
#
# Interestingly, the hive tests do not use this particular test but rather
# eth_tests/BlockchainTests/GeneralStateTests/stEIP1559/lowGasLimit.json
# from a parallel tests series which look like somehow expanded versions.
#
# The parallel lowGasLimit.json test never triggers the case checked below
# as the paricular transaction is omitted (the txs list is just set empty.)
if maxLimit < tx.gasLimit:
return err(&"invalid tx: block header gasLimit exceeded. maxLimit={maxLimit}, gasLimit={tx.gasLimit}")
# ensure that the user was willing to at least pay the base fee
if tx.maxFeePerGasNorm < baseFee.truncate(GasInt):
return err(&"invalid tx: maxFee is smaller than baseFee. maxFee={tx.maxFeePerGas}, baseFee={baseFee}")
# the signer must be able to fully afford the transaction
let gasCost = tx.gasCost()
if balance < gasCost:
return err(&"invalid tx: not enough cash for gas. avail={balance}, require={gasCost}")
if balance - gasCost < tx.value:
return err(&"invalid tx: not enough cash to send. avail={balance}, availMinusGas={balance-gasCost}, require={tx.value}")
if tx.nonce != nonce:
return err(&"invalid tx: account nonce mismatch. txNonce={tx.nonce}, accNonce={nonce}")
if tx.nonce == high(uint64):
return err(&"invalid tx: nonce at maximum")
# EIP-3607 Reject transactions from senders with deployed code
# The EIP spec claims this attack never happened before
# Clients might choose to disable this rule for RPC calls like
# `eth_call` and `eth_estimateGas`
# EOA = Externally Owned Account
let codeHash = roDB.getCodeHash(sender)
if codeHash != EMPTY_CODE_HASH:
return err(&"invalid tx: sender is not an EOA. sender={sender.toHex}, codeHash={codeHash.data.toHex}")
if tx.txType >= TxEip4844:
# ensure that the user was willing to at least pay the current data gasprice
let blobGasPrice = getBlobBaseFee(excessBlobGas)
if tx.maxFeePerBlobGas < blobGasPrice:
return err("invalid tx: maxFeePerBlobGas smaller than blobGasPrice. " &
&"maxFeePerBlobGas={tx.maxFeePerBlobGas}, blobGasPrice={blobGasPrice}")
ok()
# ------------------------------------------------------------------------------
# Public functions, extracted from test_blockchain_json
# ------------------------------------------------------------------------------
proc validateHeaderAndKinship*(
2022-12-02 04:35:41 +00:00
com: CommonRef;
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
blk: EthBlock;
parent: BlockHeader;
checkSealOK: bool;
): Result[void, string]
{.gcsafe, raises: [].} =
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
template header: BlockHeader = blk.header
if header.isGenesis:
if header.extraData.len > 32:
return err("BlockHeader.extraData larger than 32 bytes")
return ok()
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
? com.validateHeader(blk, parent, checkSealOK)
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
if blk.uncles.len > MAX_UNCLES:
return err("Number of uncles exceed limit.")
2022-12-02 04:35:41 +00:00
if com.consensus != ConsensusType.POS:
Consolidate block type for block processing (#2325) This PR consolidates the split header-body sequences into a single EthBlock sequence and cleans up the fallout from that which significantly reduces block processing overhead during import thanks to less garbage collection and fewer copies of things all around. Notably, since the number of headers must always match the number of bodies, we also get rid of a pointless degree of freedom that in the future could introduce unnecessary bugs. * only read header and body from era file * avoid several unnecessary copies along the block processing way * simplify signatures, cleaning up unused arguemnts and returns * use `stew/assign2` in a few strategic places where the generated nim assignent is slow and add a few `move` to work around poor analysis in nim 1.6 (will need to be revisited for 2.0) ``` stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv bps_x bps_y tps_x tps_y bpsd tpsd timed block_number (498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92% (713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21% (928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28% (1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50% (1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80% (1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91% (1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91% (2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61% (2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80% blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s bpsd (mean): 19.55% tpsd (mean): 19.55% Time (total): -29m13s, -15.14% ```
2024-06-09 14:32:20 +00:00
? com.validateUncles(header, blk.uncles, checkSealOK)
ok()
# ------------------------------------------------------------------------------
# End
# ------------------------------------------------------------------------------