core, eth: faster snapshot generation (#22504)

* eth/protocols: persist received state segments

* core: initial implementation

* core/state/snapshot: add tests

* core, eth: updates

* eth/protocols/snapshot: count flat state size

* core/state: add metrics

* core/state/snapshot: skip unnecessary deletion

* core/state/snapshot: rename

* core/state/snapshot: use the global batch

* core/state/snapshot: add logs and fix wiping

* core/state/snapshot: fix

* core/state/snapshot: save generation progress even if the batch is empty

* core/state/snapshot: fixes

* core/state/snapshot: fix initial account range length

* core/state/snapshot: fix initial account range

* eth/protocols/snap: store flat states during the healing

* eth/protocols/snap: print logs

* core/state/snapshot: refactor (#4)

* core/state/snapshot: refactor

* core/state/snapshot: tiny fix and polish

Co-authored-by: rjl493456442 <garyrong0905@gmail.com>

* core, eth: fixes

* core, eth: fix healing writer

* core, trie, eth: fix paths

* eth/protocols/snap: fix encoding

* eth, core: add debug log

* core/state/generate: release iterator asap (#5)

core/state/snapshot: less copy

core/state/snapshot: revert split loop

core/state/snapshot: handle storage becoming empty, improve test robustness

core/state: test modified codehash

core/state/snapshot: polish

* core/state/snapshot: optimize stats counter

* core, eth: add metric

* core/state/snapshot: update comments

* core/state/snapshot: improve tests

* core/state/snapshot: replace secure trie with standard trie

* core/state/snapshot: wrap return as the struct

* core/state/snapshot: skip wiping correct states

* core/state/snapshot: updates

* core/state/snapshot: fixes

* core/state/snapshot: fix panic due to reference flaw in closure

* core/state/snapshot: fix errors in state generation logic + fix log output

* core/state/snapshot: remove an error case

* core/state/snapshot: fix condition-check for exhausted snap state

* core/state/snapshot: use stackTrie for small tries

* core/state/snapshot: don't resolve small storage tries in vain

* core/state/snapshot: properly clean up storage of deleted accounts

* core/state/snapshot: avoid RLP-encoding in some cases + minor nitpicks

* core/state/snapshot: fix error (+testcase)

* core/state/snapshot: clean up tests a bit

* core/state/snapshot: work in progress on better tests

* core/state/snapshot: polish code

* core/state/snapshot: fix trie iteration abortion trigger

* core/state/snapshot: fixes flaws

* core/state/snapshot: remove panic

* core/state/snapshot: fix abort

* core/state/snapshot: more tests (plus failing testcase)

* core/state/snapshot: more testcases + fix for failing test

* core/state/snapshot: testcase for malformed data

* core/state/snapshot: some test nitpicks

* core/state/snapshot: improvements to logging

* core/state/snapshot: testcase to demo error in abortion

* core/state/snapshot: fix abortion

* cmd/geth: make verify-state report the root

* trie: fix failing test

* core/state/snapshot: add timer metrics

* core/state/snapshot: fix metrics

* core/state/snapshot: udpate tests

* eth/protocols/snap: write snapshot account even if code or state is needed

* core/state/snapshot: fix diskmore check

* core/state/snapshot: review fixes

* core/state/snapshot: improve error message

* cmd/geth: rename 'error' to 'err' in logs

* core/state/snapshot: fix some review concerns

* core/state/snapshot, eth/protocols/snap: clear snapshot marker when starting/resuming snap sync

* core: add error log

* core/state/snapshot: use proper timers for metrics collection

* core/state/snapshot: address some review concerns

* eth/protocols/snap: improved log message

* eth/protocols/snap: fix heal logs to condense infos

* core/state/snapshot: wait for generator termination before restarting

* core/state/snapshot: revert timers to counters to track total time

Co-authored-by: Martin Holst Swende <martin@swende.se>
Co-authored-by: Péter Szilágyi <peterke@gmail.com>
This commit is contained in:
gary rong
2021-04-15 04:23:11 +08:00
committed by GitHub
parent a50251e6cb
commit 7088f1e814
16 changed files with 1370 additions and 210 deletions

View File

@ -24,10 +24,11 @@ import (
"github.com/ethereum/go-ethereum/core/rawdb"
"github.com/ethereum/go-ethereum/ethdb"
"github.com/ethereum/go-ethereum/log"
"github.com/ethereum/go-ethereum/metrics"
)
// wipeSnapshot starts a goroutine to iterate over the entire key-value database
// and delete all the data associated with the snapshot (accounts, storage,
// and delete all the data associated with the snapshot (accounts, storage,
// metadata). After all is done, the snapshot range of the database is compacted
// to free up unused data blocks.
func wipeSnapshot(db ethdb.KeyValueStore, full bool) chan struct{} {
@ -53,10 +54,10 @@ func wipeSnapshot(db ethdb.KeyValueStore, full bool) chan struct{} {
// removed in sync to avoid data races. After all is done, the snapshot range of
// the database is compacted to free up unused data blocks.
func wipeContent(db ethdb.KeyValueStore) error {
if err := wipeKeyRange(db, "accounts", rawdb.SnapshotAccountPrefix, len(rawdb.SnapshotAccountPrefix)+common.HashLength); err != nil {
if err := wipeKeyRange(db, "accounts", rawdb.SnapshotAccountPrefix, nil, nil, len(rawdb.SnapshotAccountPrefix)+common.HashLength, snapWipedAccountMeter, true); err != nil {
return err
}
if err := wipeKeyRange(db, "storage", rawdb.SnapshotStoragePrefix, len(rawdb.SnapshotStoragePrefix)+2*common.HashLength); err != nil {
if err := wipeKeyRange(db, "storage", rawdb.SnapshotStoragePrefix, nil, nil, len(rawdb.SnapshotStoragePrefix)+2*common.HashLength, snapWipedStorageMeter, true); err != nil {
return err
}
// Compact the snapshot section of the database to get rid of unused space
@ -82,8 +83,11 @@ func wipeContent(db ethdb.KeyValueStore) error {
}
// wipeKeyRange deletes a range of keys from the database starting with prefix
// and having a specific total key length.
func wipeKeyRange(db ethdb.KeyValueStore, kind string, prefix []byte, keylen int) error {
// and having a specific total key length. The start and limit is optional for
// specifying a particular key range for deletion.
//
// Origin is included for wiping and limit is excluded if they are specified.
func wipeKeyRange(db ethdb.KeyValueStore, kind string, prefix []byte, origin []byte, limit []byte, keylen int, meter metrics.Meter, report bool) error {
// Batch deletions together to avoid holding an iterator for too long
var (
batch = db.NewBatch()
@ -92,7 +96,11 @@ func wipeKeyRange(db ethdb.KeyValueStore, kind string, prefix []byte, keylen int
// Iterate over the key-range and delete all of them
start, logged := time.Now(), time.Now()
it := db.NewIterator(prefix, nil)
it := db.NewIterator(prefix, origin)
var stop []byte
if limit != nil {
stop = append(prefix, limit...)
}
for it.Next() {
// Skip any keys with the correct prefix but wrong length (trie nodes)
key := it.Key()
@ -102,6 +110,9 @@ func wipeKeyRange(db ethdb.KeyValueStore, kind string, prefix []byte, keylen int
if len(key) != keylen {
continue
}
if stop != nil && bytes.Compare(key, stop) >= 0 {
break
}
// Delete the key and periodically recreate the batch and iterator
batch.Delete(key)
items++
@ -116,7 +127,7 @@ func wipeKeyRange(db ethdb.KeyValueStore, kind string, prefix []byte, keylen int
seekPos := key[len(prefix):]
it = db.NewIterator(prefix, seekPos)
if time.Since(logged) > 8*time.Second {
if time.Since(logged) > 8*time.Second && report {
log.Info("Deleting state snapshot leftovers", "kind", kind, "wiped", items, "elapsed", common.PrettyDuration(time.Since(start)))
logged = time.Now()
}
@ -126,6 +137,11 @@ func wipeKeyRange(db ethdb.KeyValueStore, kind string, prefix []byte, keylen int
if err := batch.Write(); err != nil {
return err
}
log.Info("Deleted state snapshot leftovers", "kind", kind, "wiped", items, "elapsed", common.PrettyDuration(time.Since(start)))
if meter != nil {
meter.Mark(int64(items))
}
if report {
log.Info("Deleted state snapshot leftovers", "kind", kind, "wiped", items, "elapsed", common.PrettyDuration(time.Since(start)))
}
return nil
}