nimbus-eth1/nimbus/sync/beacon/worker/start_stop.nim

142 lines
5.0 KiB
Nim
Raw Normal View History

# Nimbus
# Copyright (c) 2023-2024 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:[].}
import
pkg/eth/[common, p2p],
../../../core/chain,
../../protocol,
../worker_desc,
Flare sync (#2627) * Cosmetics, small fixes, add stashed headers verifier * Remove direct `Era1` support why: Era1 is indirectly supported by using the import tool before syncing. * Clarify database persistent save function. why: Function relied on the last saved state block number which was wrong. It now relies on the tx-level. If it is 0, then data are saved directly. Otherwise the task that owns the tx will do it. * Extracted configuration constants into separate file * Enable single peer mode for debugging * Fix peer losing issue in multi-mode details: Running concurrent download peers was previously programmed as running a batch downloading and storing ~8k headers and then leaving the `async` function to be restarted by a scheduler. This was unfortunate because of occasionally occurring long waiting times for restart. While the time gap until restarting were typically observed a few millisecs, there were always a few outliers which well exceed several seconds. This seemed to let remote peers run into timeouts. * Prefix function names `unprocXxx()` and `stagedYyy()` by `headers` why: There will be other `unproc` and `staged` modules. * Remove cruft, update logging * Fix accounting issue details: When staging after fetching headers from the network, there was an off by 1 error occurring when the result was by one smaller than requested. Also, a whole range was mis-accounted when a peer was terminating connection immediately after responding. * Fix slow/error header accounting when fetching why: Originally set for detecting slow headers in a row, the counter was wrongly extended to general errors. * Ban peers for a while that respond with too few headers continuously why: Some peers only returned one header at a time. If these peers sit on a farm, they might collectively slow down the download process. * Update RPC beacon header updater why: Old function hook has slightly changed its meaning since it was used for snap sync. Also, the old hook is used by other functions already. * Limit number of peers or set to single peer mode details: Merge several concepts, single peer mode being one of it. * Some code clean up, fixings for removing of compiler warnings * De-noise header fetch related sources why: Header download looks relatively stable, so general debugging is not needed, anymore. This is the equivalent of removing the scaffold from the part of the building where work has completed. * More clean up and code prettification for headers stuff * Implement body fetch and block import details: Available headers are used stage blocks by combining existing headers with newly fetched blocks. Then these blocks are imported/executed via `persistBlocks()`. * Logger cosmetics and cleanup * Remove staged block queue debugging details: Feature still available, just not executed anymore * Docu, logging update * Update/simplify `runDaemon()` * Re-calibrate block body requests and soft config for import blocks batch why: * For fetching, larger fetch requests are mostly truncated anyway on MainNet. * For executing, smaller batch sizes reduce the memory needed for the price of longer execution times. * Update metrics counters * Docu update * Some fixes, formatting updates, etc. * Update `borrowed` type: uint -. uint64 also: Always convert to `uint64` rather than `uint` where appropriate
2024-09-27 15:07:42 +00:00
"."/[blocks_staged, blocks_unproc, db, headers_staged, headers_unproc]
when enableTicker:
import ./start_stop/ticker
# ------------------------------------------------------------------------------
# Private functions
# ------------------------------------------------------------------------------
when enableTicker:
proc tickerUpdater(ctx: BeaconCtxRef): TickerStatsUpdater =
## Legacy stuff, will be probably be superseded by `metrics`
return proc: auto =
TickerStats(
stored: ctx.db.getSavedStateBlockNumber(),
base: ctx.chain.baseNumber(),
latest: ctx.chain.latestNumber(),
coupler: ctx.layout.coupler,
dangling: ctx.layout.dangling,
final: ctx.layout.final,
head: ctx.layout.head,
target: ctx.target.consHead.number,
targetOk: ctx.target.final != 0,
Flare sync (#2627) * Cosmetics, small fixes, add stashed headers verifier * Remove direct `Era1` support why: Era1 is indirectly supported by using the import tool before syncing. * Clarify database persistent save function. why: Function relied on the last saved state block number which was wrong. It now relies on the tx-level. If it is 0, then data are saved directly. Otherwise the task that owns the tx will do it. * Extracted configuration constants into separate file * Enable single peer mode for debugging * Fix peer losing issue in multi-mode details: Running concurrent download peers was previously programmed as running a batch downloading and storing ~8k headers and then leaving the `async` function to be restarted by a scheduler. This was unfortunate because of occasionally occurring long waiting times for restart. While the time gap until restarting were typically observed a few millisecs, there were always a few outliers which well exceed several seconds. This seemed to let remote peers run into timeouts. * Prefix function names `unprocXxx()` and `stagedYyy()` by `headers` why: There will be other `unproc` and `staged` modules. * Remove cruft, update logging * Fix accounting issue details: When staging after fetching headers from the network, there was an off by 1 error occurring when the result was by one smaller than requested. Also, a whole range was mis-accounted when a peer was terminating connection immediately after responding. * Fix slow/error header accounting when fetching why: Originally set for detecting slow headers in a row, the counter was wrongly extended to general errors. * Ban peers for a while that respond with too few headers continuously why: Some peers only returned one header at a time. If these peers sit on a farm, they might collectively slow down the download process. * Update RPC beacon header updater why: Old function hook has slightly changed its meaning since it was used for snap sync. Also, the old hook is used by other functions already. * Limit number of peers or set to single peer mode details: Merge several concepts, single peer mode being one of it. * Some code clean up, fixings for removing of compiler warnings * De-noise header fetch related sources why: Header download looks relatively stable, so general debugging is not needed, anymore. This is the equivalent of removing the scaffold from the part of the building where work has completed. * More clean up and code prettification for headers stuff * Implement body fetch and block import details: Available headers are used stage blocks by combining existing headers with newly fetched blocks. Then these blocks are imported/executed via `persistBlocks()`. * Logger cosmetics and cleanup * Remove staged block queue debugging details: Feature still available, just not executed anymore * Docu, logging update * Update/simplify `runDaemon()` * Re-calibrate block body requests and soft config for import blocks batch why: * For fetching, larger fetch requests are mostly truncated anyway on MainNet. * For executing, smaller batch sizes reduce the memory needed for the price of longer execution times. * Update metrics counters * Docu update * Some fixes, formatting updates, etc. * Update `borrowed` type: uint -. uint64 also: Always convert to `uint64` rather than `uint` where appropriate
2024-09-27 15:07:42 +00:00
nHdrStaged: ctx.headersStagedQueueLen(),
hdrStagedTop: ctx.headersStagedTopKey(),
hdrUnprocTop: ctx.headersUnprocTop(),
nHdrUnprocessed: ctx.headersUnprocTotal() + ctx.headersUnprocBorrowed(),
nHdrUnprocFragm: ctx.headersUnprocChunks(),
nBlkStaged: ctx.blocksStagedQueueLen(),
blkStagedBottom: ctx.blocksStagedBottomKey(),
blkUnprocTop: ctx.blk.topRequest,
nBlkUnprocessed: ctx.blocksUnprocTotal() + ctx.blocksUnprocBorrowed(),
nBlkUnprocFragm: ctx.blocksUnprocChunks(),
reorg: ctx.pool.nReorg,
nBuddies: ctx.pool.nBuddies)
Flare sync (#2627) * Cosmetics, small fixes, add stashed headers verifier * Remove direct `Era1` support why: Era1 is indirectly supported by using the import tool before syncing. * Clarify database persistent save function. why: Function relied on the last saved state block number which was wrong. It now relies on the tx-level. If it is 0, then data are saved directly. Otherwise the task that owns the tx will do it. * Extracted configuration constants into separate file * Enable single peer mode for debugging * Fix peer losing issue in multi-mode details: Running concurrent download peers was previously programmed as running a batch downloading and storing ~8k headers and then leaving the `async` function to be restarted by a scheduler. This was unfortunate because of occasionally occurring long waiting times for restart. While the time gap until restarting were typically observed a few millisecs, there were always a few outliers which well exceed several seconds. This seemed to let remote peers run into timeouts. * Prefix function names `unprocXxx()` and `stagedYyy()` by `headers` why: There will be other `unproc` and `staged` modules. * Remove cruft, update logging * Fix accounting issue details: When staging after fetching headers from the network, there was an off by 1 error occurring when the result was by one smaller than requested. Also, a whole range was mis-accounted when a peer was terminating connection immediately after responding. * Fix slow/error header accounting when fetching why: Originally set for detecting slow headers in a row, the counter was wrongly extended to general errors. * Ban peers for a while that respond with too few headers continuously why: Some peers only returned one header at a time. If these peers sit on a farm, they might collectively slow down the download process. * Update RPC beacon header updater why: Old function hook has slightly changed its meaning since it was used for snap sync. Also, the old hook is used by other functions already. * Limit number of peers or set to single peer mode details: Merge several concepts, single peer mode being one of it. * Some code clean up, fixings for removing of compiler warnings * De-noise header fetch related sources why: Header download looks relatively stable, so general debugging is not needed, anymore. This is the equivalent of removing the scaffold from the part of the building where work has completed. * More clean up and code prettification for headers stuff * Implement body fetch and block import details: Available headers are used stage blocks by combining existing headers with newly fetched blocks. Then these blocks are imported/executed via `persistBlocks()`. * Logger cosmetics and cleanup * Remove staged block queue debugging details: Feature still available, just not executed anymore * Docu, logging update * Update/simplify `runDaemon()` * Re-calibrate block body requests and soft config for import blocks batch why: * For fetching, larger fetch requests are mostly truncated anyway on MainNet. * For executing, smaller batch sizes reduce the memory needed for the price of longer execution times. * Update metrics counters * Docu update * Some fixes, formatting updates, etc. * Update `borrowed` type: uint -. uint64 also: Always convert to `uint64` rather than `uint` where appropriate
2024-09-27 15:07:42 +00:00
proc updateBeaconHeaderCB(ctx: BeaconCtxRef): ReqBeaconSyncTargetCB =
## Update beacon header. This function is intended as a call back function
## for the RPC module.
return proc(h: Header; f: Hash32) {.gcsafe, raises: [].} =
# Rpc checks empty header against a zero hash rather than `emptyRoot`
if not ctx.target.locked:
if f != zeroHash32 and ctx.target.consHead.number < h.number:
ctx.target.consHead = h
ctx.target.final = BlockNumber(0)
ctx.target.finalHash = f
ctx.target.changed = true
# ------------------------------------------------------------------------------
# Public functions
# ------------------------------------------------------------------------------
when enableTicker:
proc setupTicker*(ctx: BeaconCtxRef) =
## Helper for `setup()`: Start ticker
ctx.pool.ticker = TickerRef.init(ctx.tickerUpdater)
proc destroyTicker*(ctx: BeaconCtxRef) =
## Helper for `release()`
ctx.pool.ticker.destroy()
ctx.pool.ticker = TickerRef(nil)
else:
template setupTicker*(ctx: BeaconCtxRef) = discard
template destroyTicker*(ctx: BeaconCtxRef) = discard
# ---------
proc setupDatabase*(ctx: BeaconCtxRef) =
Flare sync (#2627) * Cosmetics, small fixes, add stashed headers verifier * Remove direct `Era1` support why: Era1 is indirectly supported by using the import tool before syncing. * Clarify database persistent save function. why: Function relied on the last saved state block number which was wrong. It now relies on the tx-level. If it is 0, then data are saved directly. Otherwise the task that owns the tx will do it. * Extracted configuration constants into separate file * Enable single peer mode for debugging * Fix peer losing issue in multi-mode details: Running concurrent download peers was previously programmed as running a batch downloading and storing ~8k headers and then leaving the `async` function to be restarted by a scheduler. This was unfortunate because of occasionally occurring long waiting times for restart. While the time gap until restarting were typically observed a few millisecs, there were always a few outliers which well exceed several seconds. This seemed to let remote peers run into timeouts. * Prefix function names `unprocXxx()` and `stagedYyy()` by `headers` why: There will be other `unproc` and `staged` modules. * Remove cruft, update logging * Fix accounting issue details: When staging after fetching headers from the network, there was an off by 1 error occurring when the result was by one smaller than requested. Also, a whole range was mis-accounted when a peer was terminating connection immediately after responding. * Fix slow/error header accounting when fetching why: Originally set for detecting slow headers in a row, the counter was wrongly extended to general errors. * Ban peers for a while that respond with too few headers continuously why: Some peers only returned one header at a time. If these peers sit on a farm, they might collectively slow down the download process. * Update RPC beacon header updater why: Old function hook has slightly changed its meaning since it was used for snap sync. Also, the old hook is used by other functions already. * Limit number of peers or set to single peer mode details: Merge several concepts, single peer mode being one of it. * Some code clean up, fixings for removing of compiler warnings * De-noise header fetch related sources why: Header download looks relatively stable, so general debugging is not needed, anymore. This is the equivalent of removing the scaffold from the part of the building where work has completed. * More clean up and code prettification for headers stuff * Implement body fetch and block import details: Available headers are used stage blocks by combining existing headers with newly fetched blocks. Then these blocks are imported/executed via `persistBlocks()`. * Logger cosmetics and cleanup * Remove staged block queue debugging details: Feature still available, just not executed anymore * Docu, logging update * Update/simplify `runDaemon()` * Re-calibrate block body requests and soft config for import blocks batch why: * For fetching, larger fetch requests are mostly truncated anyway on MainNet. * For executing, smaller batch sizes reduce the memory needed for the price of longer execution times. * Update metrics counters * Docu update * Some fixes, formatting updates, etc. * Update `borrowed` type: uint -. uint64 also: Always convert to `uint64` rather than `uint` where appropriate
2024-09-27 15:07:42 +00:00
## Initalise database related stuff
# Initialise up queues and lists
ctx.headersStagedInit()
ctx.blocksStagedInit()
ctx.headersUnprocInit()
ctx.blocksUnprocInit()
# Load initial state from database if there is any
ctx.dbLoadSyncStateLayout()
Flare sync (#2627) * Cosmetics, small fixes, add stashed headers verifier * Remove direct `Era1` support why: Era1 is indirectly supported by using the import tool before syncing. * Clarify database persistent save function. why: Function relied on the last saved state block number which was wrong. It now relies on the tx-level. If it is 0, then data are saved directly. Otherwise the task that owns the tx will do it. * Extracted configuration constants into separate file * Enable single peer mode for debugging * Fix peer losing issue in multi-mode details: Running concurrent download peers was previously programmed as running a batch downloading and storing ~8k headers and then leaving the `async` function to be restarted by a scheduler. This was unfortunate because of occasionally occurring long waiting times for restart. While the time gap until restarting were typically observed a few millisecs, there were always a few outliers which well exceed several seconds. This seemed to let remote peers run into timeouts. * Prefix function names `unprocXxx()` and `stagedYyy()` by `headers` why: There will be other `unproc` and `staged` modules. * Remove cruft, update logging * Fix accounting issue details: When staging after fetching headers from the network, there was an off by 1 error occurring when the result was by one smaller than requested. Also, a whole range was mis-accounted when a peer was terminating connection immediately after responding. * Fix slow/error header accounting when fetching why: Originally set for detecting slow headers in a row, the counter was wrongly extended to general errors. * Ban peers for a while that respond with too few headers continuously why: Some peers only returned one header at a time. If these peers sit on a farm, they might collectively slow down the download process. * Update RPC beacon header updater why: Old function hook has slightly changed its meaning since it was used for snap sync. Also, the old hook is used by other functions already. * Limit number of peers or set to single peer mode details: Merge several concepts, single peer mode being one of it. * Some code clean up, fixings for removing of compiler warnings * De-noise header fetch related sources why: Header download looks relatively stable, so general debugging is not needed, anymore. This is the equivalent of removing the scaffold from the part of the building where work has completed. * More clean up and code prettification for headers stuff * Implement body fetch and block import details: Available headers are used stage blocks by combining existing headers with newly fetched blocks. Then these blocks are imported/executed via `persistBlocks()`. * Logger cosmetics and cleanup * Remove staged block queue debugging details: Feature still available, just not executed anymore * Docu, logging update * Update/simplify `runDaemon()` * Re-calibrate block body requests and soft config for import blocks batch why: * For fetching, larger fetch requests are mostly truncated anyway on MainNet. * For executing, smaller batch sizes reduce the memory needed for the price of longer execution times. * Update metrics counters * Docu update * Some fixes, formatting updates, etc. * Update `borrowed` type: uint -. uint64 also: Always convert to `uint64` rather than `uint` where appropriate
2024-09-27 15:07:42 +00:00
# Set blocks batch import value for block import
Flare sync (#2627) * Cosmetics, small fixes, add stashed headers verifier * Remove direct `Era1` support why: Era1 is indirectly supported by using the import tool before syncing. * Clarify database persistent save function. why: Function relied on the last saved state block number which was wrong. It now relies on the tx-level. If it is 0, then data are saved directly. Otherwise the task that owns the tx will do it. * Extracted configuration constants into separate file * Enable single peer mode for debugging * Fix peer losing issue in multi-mode details: Running concurrent download peers was previously programmed as running a batch downloading and storing ~8k headers and then leaving the `async` function to be restarted by a scheduler. This was unfortunate because of occasionally occurring long waiting times for restart. While the time gap until restarting were typically observed a few millisecs, there were always a few outliers which well exceed several seconds. This seemed to let remote peers run into timeouts. * Prefix function names `unprocXxx()` and `stagedYyy()` by `headers` why: There will be other `unproc` and `staged` modules. * Remove cruft, update logging * Fix accounting issue details: When staging after fetching headers from the network, there was an off by 1 error occurring when the result was by one smaller than requested. Also, a whole range was mis-accounted when a peer was terminating connection immediately after responding. * Fix slow/error header accounting when fetching why: Originally set for detecting slow headers in a row, the counter was wrongly extended to general errors. * Ban peers for a while that respond with too few headers continuously why: Some peers only returned one header at a time. If these peers sit on a farm, they might collectively slow down the download process. * Update RPC beacon header updater why: Old function hook has slightly changed its meaning since it was used for snap sync. Also, the old hook is used by other functions already. * Limit number of peers or set to single peer mode details: Merge several concepts, single peer mode being one of it. * Some code clean up, fixings for removing of compiler warnings * De-noise header fetch related sources why: Header download looks relatively stable, so general debugging is not needed, anymore. This is the equivalent of removing the scaffold from the part of the building where work has completed. * More clean up and code prettification for headers stuff * Implement body fetch and block import details: Available headers are used stage blocks by combining existing headers with newly fetched blocks. Then these blocks are imported/executed via `persistBlocks()`. * Logger cosmetics and cleanup * Remove staged block queue debugging details: Feature still available, just not executed anymore * Docu, logging update * Update/simplify `runDaemon()` * Re-calibrate block body requests and soft config for import blocks batch why: * For fetching, larger fetch requests are mostly truncated anyway on MainNet. * For executing, smaller batch sizes reduce the memory needed for the price of longer execution times. * Update metrics counters * Docu update * Some fixes, formatting updates, etc. * Update `borrowed` type: uint -. uint64 also: Always convert to `uint64` rather than `uint` where appropriate
2024-09-27 15:07:42 +00:00
if ctx.pool.nBodiesBatch < nFetchBodiesRequest:
if ctx.pool.nBodiesBatch == 0:
ctx.pool.nBodiesBatch = nFetchBodiesBatchDefault
else:
ctx.pool.nBodiesBatch = nFetchBodiesRequest
# Set length of `staged` queue
if ctx.pool.nBodiesBatch < nFetchBodiesBatchDefault:
const nBlocks = blocksStagedQueueLenMaxDefault * nFetchBodiesBatchDefault
ctx.pool.blocksStagedQuLenMax =
(nBlocks + ctx.pool.nBodiesBatch - 1) div ctx.pool.nBodiesBatch
else:
ctx.pool.blocksStagedQuLenMax = blocksStagedQueueLenMaxDefault
proc setupRpcMagic*(ctx: BeaconCtxRef) =
## Helper for `setup()`: Enable external pivot update via RPC
ctx.pool.chain.com.reqBeaconSyncTarget = ctx.updateBeaconHeaderCB
proc destroyRpcMagic*(ctx: BeaconCtxRef) =
## Helper for `release()`
ctx.pool.chain.com.reqBeaconSyncTarget = ReqBeaconSyncTargetCB(nil)
# ---------
proc startBuddy*(buddy: BeaconBuddyRef): bool =
## Convenience setting for starting a new worker
let
ctx = buddy.ctx
peer = buddy.peer
if peer.supports(protocol.eth) and peer.state(protocol.eth).initialized:
ctx.pool.nBuddies.inc # for metrics
return true
proc stopBuddy*(buddy: BeaconBuddyRef) =
buddy.ctx.pool.nBuddies.dec # for metrics
# ------------------------------------------------------------------------------
# End
# ------------------------------------------------------------------------------