mirror of
https://gitlab.com/pulsechaincom/erigon-pulse.git
synced 2024-12-25 13:07:17 +00:00
0042f13d47
* eth/downloader: separate state sync from queue Scheduling of state node downloads hogged the downloader queue lock when new requests were scheduled. This caused timeouts for other requests. With this change, state sync is fully independent of all other downloads and doesn't involve the queue at all. State sync is started and checked on in processContent. This is slightly awkward because processContent doesn't have a select loop. Instead, the queue is closed by an auxiliary goroutine when state sync fails. We tried several alternatives to this but settled on the current approach because it's the least amount of change overall. Handling of the pivot block has changed slightly: the queue previously prevented import of pivot block receipts before the state of the pivot block was available. In this commit, the receipt will be imported before the state. This causes an annoyance where the pivot block is committed as fast block head even when state downloads fail. Stay tuned for more updates in this area ;) * eth/downloader: remove cancelTimeout channel * eth/downloader: retry state requests on timeout * eth/downloader: improve comment * eth/downloader: mark peers idle when state sync is done * eth/downloader: move pivot block splitting to processContent This change also ensures that pivot block receipts aren't imported before the pivot block itself. * eth/downloader: limit state node retries * eth/downloader: improve state node error handling and retry check * eth/downloader: remove maxStateNodeRetries It fails the sync too much. * eth/downloader: remove last use of cancelCh in statesync.go Fixes TestDeliverHeadersHang*Fast and (hopefully) the weird cancellation behaviour at the end of fast sync. * eth/downloader: fix leak in runStateSync * eth/downloader: don't run processFullSyncContent in LightSync mode * eth/downloader: improve comments * eth/downloader: fix vet, megacheck * eth/downloader: remove unrequested tasks anyway * eth/downloader, trie: various polishes around duplicate items This commit explicitly tracks duplicate and unexpected state delieveries done against a trie Sync structure, also adding there to import info logs. The commit moves the db batch used to commit trie changes one level deeper so its flushed after every node insertion. This is needed to avoid a lot of duplicate retrievals caused by inconsistencies between Sync internals and database. A better approach is to track not-yet-written states in trie.Sync and flush on commit, but I'm focuing on correctness first now. The commit fixes a regression around pivot block fail count. The counter previously was reset to 1 if and only if a sync cycle progressed (inserted at least 1 entry to the database). The current code reset it already if a node was delivered, which is not stong enough, because unless it ends up written to disk, an attacker can just loop and attack ad infinitum. The commit also fixes a regression around state deliveries and timeouts. The old downloader tracked if a delivery is stale (none of the deliveries were requestedt), in which case it didn't mark the node idle and did not send further requests, since it signals a past timeout. The current code did mark it idle even on stale deliveries, which eventually caused two requests to be in flight at the same time, making the deliveries always stale and mass duplicating retrievals between multiple peers. * eth/downloader: fix state request leak This commit fixes the hang seen sometimes while doing the state sync. The cause of the hang was a rare combination of events: request state data from peer, peer drops and reconnects almost immediately. This caused a new download task to be assigned to the peer, overwriting the old one still waiting for a timeout, which in turned leaked the requests out, never to be retried. The fix is to ensure that a task assignment moves any pending one back into the retry queue. The commit also fixes a regression with peer dropping due to stalls. The current code considered a peer stalling if they timed out delivering 1 item. However, the downloader never requests only one, the minimum is 2 (attempt to fine tune estimated latency/bandwidth). The fix is simply to drop if a timeout is detected at 2 items. Apart from the above bugfixes, the commit contains some code polishes I made while debugging the hang. * core, eth, trie: support batched trie sync db writes * trie: rename SyncMemCache to syncMemBatch
78 lines
2.7 KiB
Go
78 lines
2.7 KiB
Go
// Copyright 2015 The go-ethereum Authors
|
|
// This file is part of the go-ethereum library.
|
|
//
|
|
// The go-ethereum library is free software: you can redistribute it and/or modify
|
|
// it under the terms of the GNU Lesser General Public License as published by
|
|
// the Free Software Foundation, either version 3 of the License, or
|
|
// (at your option) any later version.
|
|
//
|
|
// The go-ethereum library is distributed in the hope that it will be useful,
|
|
// but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
// GNU Lesser General Public License for more details.
|
|
//
|
|
// You should have received a copy of the GNU Lesser General Public License
|
|
// along with the go-ethereum library. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
package state
|
|
|
|
import (
|
|
"bytes"
|
|
"math/big"
|
|
|
|
"github.com/ethereum/go-ethereum/common"
|
|
"github.com/ethereum/go-ethereum/rlp"
|
|
"github.com/ethereum/go-ethereum/trie"
|
|
)
|
|
|
|
// StateSync is the main state synchronisation scheduler, which provides yet the
|
|
// unknown state hashes to retrieve, accepts node data associated with said hashes
|
|
// and reconstructs the state database step by step until all is done.
|
|
type StateSync trie.TrieSync
|
|
|
|
// NewStateSync create a new state trie download scheduler.
|
|
func NewStateSync(root common.Hash, database trie.DatabaseReader) *StateSync {
|
|
var syncer *trie.TrieSync
|
|
|
|
callback := func(leaf []byte, parent common.Hash) error {
|
|
var obj struct {
|
|
Nonce uint64
|
|
Balance *big.Int
|
|
Root common.Hash
|
|
CodeHash []byte
|
|
}
|
|
if err := rlp.Decode(bytes.NewReader(leaf), &obj); err != nil {
|
|
return err
|
|
}
|
|
syncer.AddSubTrie(obj.Root, 64, parent, nil)
|
|
syncer.AddRawEntry(common.BytesToHash(obj.CodeHash), 64, parent)
|
|
|
|
return nil
|
|
}
|
|
syncer = trie.NewTrieSync(root, database, callback)
|
|
return (*StateSync)(syncer)
|
|
}
|
|
|
|
// Missing retrieves the known missing nodes from the state trie for retrieval.
|
|
func (s *StateSync) Missing(max int) []common.Hash {
|
|
return (*trie.TrieSync)(s).Missing(max)
|
|
}
|
|
|
|
// Process injects a batch of retrieved trie nodes data, returning if something
|
|
// was committed to the memcache and also the index of an entry if processing of
|
|
// it failed.
|
|
func (s *StateSync) Process(list []trie.SyncResult) (bool, int, error) {
|
|
return (*trie.TrieSync)(s).Process(list)
|
|
}
|
|
|
|
// Commit flushes the data stored in the internal memcache out to persistent
|
|
// storage, returning th enumber of items written and any occurred error.
|
|
func (s *StateSync) Commit(dbw trie.DatabaseWriter) (int, error) {
|
|
return (*trie.TrieSync)(s).Commit(dbw)
|
|
}
|
|
|
|
// Pending returns the number of state entries currently pending for download.
|
|
func (s *StateSync) Pending() int {
|
|
return (*trie.TrieSync)(s).Pending()
|
|
}
|