core, eth/downloader: commit block data using batches (#15115)

* ethdb: add Putter interface and Has method

* ethdb: improve docs and add IdealBatchSize

* ethdb: remove memory batch lock

Batches are not safe for concurrent use.

* core: use ethdb.Putter for Write* functions

This covers the easy cases.

* core/state: simplify StateSync

* trie: optimize local node check

* ethdb: add ValueSize to Batch

* core: optimize HasHeader check

This avoids one random database read get the block number. For many uses
of HasHeader, the expectation is that it's actually there. Using Has
avoids a load + decode of the value.

* core: write fast sync block data in batches

Collect writes into batches up to the ideal size instead of issuing many
small, concurrent writes.

* eth/downloader: commit larger state batches

Collect nodes into a batch up to the ideal size instead of committing
whenever a node is received.

* core: optimize HasBlock check

This avoids a random database read to get the number.

* core: use numberCache in HasHeader

numberCache has higher capacity, increasing the odds of finding the
header without a database lookup.

* core: write imported block data using a batch

Restore batch writes of state and add blocks, tx entries, receipts to
the same batch. The change also simplifies the miner.

This commit also removes posting of logs when a forked block is imported.

* core: fix DB write error handling

* ethdb: use RLock for Has

* core: fix HasBlock comment

1 files changed, 3 insertions, 39 deletions

diff --git a/core/state/sync.go b/core/state/sync.go
index 2c29d706a..28fcf6ae0 100644
--- a/core/state/sync.go
+++ b/core/state/sync.go
@@ -18,60 +18,24 @@ 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 {
+func NewStateSync(root common.Hash, database trie.DatabaseReader) *trie.TrieSync {
 	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
-		}
+		var obj Account
 		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()
+	return syncer
 }