Merge pull request #2585 from karalabe/trie-dirty-tracking

core, core/state, trie: enterprise hand-tuned multi-level caching

core/blockchain.go

@@ -819,6 +819,7 @@ func (self *BlockChain) InsertChain(chain types.Blocks) (int, error) {
 		tstart        = time.Now()
 
 		nonceChecked = make([]bool, len(chain))
+		statedb      *state.StateDB
 	)
 
 	// Start the parallel nonce verifier.
@@ -885,7 +886,11 @@ func (self *BlockChain) InsertChain(chain types.Blocks) (int, error) {
 
 		// Create a new statedb using the parent block and report an
 		// error if it fails.
-		statedb, err := state.New(self.GetBlock(block.ParentHash()).Root(), self.chainDb)
+		if statedb == nil {
+			statedb, err = state.New(self.GetBlock(block.ParentHash()).Root(), self.chainDb)
+		} else {
+			err = statedb.Reset(chain[i-1].Root())
+		}
 		if err != nil {
 			reportBlock(block, err)
 			return i, err

core/state/statedb.go

@@ -68,6 +68,28 @@ func New(root common.Hash, db ethdb.Database) (*StateDB, error) {
 	}, nil
 }
 
+// Reset clears out all emphemeral state objects from the state db, but keeps
+// the underlying state trie to avoid reloading data for the next operations.
+func (self *StateDB) Reset(root common.Hash) error {
+	var (
+		err error
+		tr  = self.trie
+	)
+	if self.trie.Hash() != root {
+		if tr, err = trie.NewSecure(root, self.db); err != nil {
+			return err
+		}
+	}
+	*self = StateDB{
+		db:           self.db,
+		trie:         tr,
+		stateObjects: make(map[string]*StateObject),
+		refund:       new(big.Int),
+		logs:         make(map[common.Hash]vm.Logs),
+	}
+	return nil
+}
+
 func (self *StateDB) StartRecord(thash, bhash common.Hash, ti int) {
 	self.thash = thash
 	self.bhash = bhash

trie/iterator.go

@@ -62,7 +62,7 @@ func (self *Iterator) next(node interface{}, key []byte, isIterStart bool) []byt
 	switch node := node.(type) {
 	case fullNode:
 		if len(key) > 0 {
-			k := self.next(node[key[0]], key[1:], isIterStart)
+			k := self.next(node.Children[key[0]], key[1:], isIterStart)
 			if k != nil {
 				return append([]byte{key[0]}, k...)
 			}
@@ -74,7 +74,7 @@ func (self *Iterator) next(node interface{}, key []byte, isIterStart bool) []byt
 		}
 
 		for i := r; i < 16; i++ {
-			k := self.key(node[i])
+			k := self.key(node.Children[i])
 			if k != nil {
 				return append([]byte{i}, k...)
 			}
@@ -130,12 +130,12 @@ func (self *Iterator) key(node interface{}) []byte {
 		}
 		return append(k, self.key(node.Val)...)
 	case fullNode:
-		if node[16] != nil {
-			self.Value = node[16].(valueNode)
+		if node.Children[16] != nil {
+			self.Value = node.Children[16].(valueNode)
 			return []byte{16}
 		}
 		for i := 0; i < 16; i++ {
-			k := self.key(node[i])
+			k := self.key(node.Children[i])
 			if k != nil {
 				return append([]byte{byte(i)}, k...)
 			}
@@ -175,7 +175,7 @@ type NodeIterator struct {
 
 // NewNodeIterator creates an post-order trie iterator.
 func NewNodeIterator(trie *Trie) *NodeIterator {
-	if bytes.Compare(trie.Root(), emptyRoot.Bytes()) == 0 {
+	if trie.Hash() == emptyState {
 		return new(NodeIterator)
 	}
 	return &NodeIterator{trie: trie}
@@ -205,9 +205,11 @@ func (it *NodeIterator) step() error {
 	}
 	// Initialize the iterator if we've just started, or pop off the old node otherwise
 	if len(it.stack) == 0 {
-		it.stack = append(it.stack, &nodeIteratorState{node: it.trie.root, child: -1})
+		// Always start with a collapsed root
+		root := it.trie.Hash()
+		it.stack = append(it.stack, &nodeIteratorState{node: hashNode(root[:]), child: -1})
 		if it.stack[0].node == nil {
-			return fmt.Errorf("root node missing: %x", it.trie.Root())
+			return fmt.Errorf("root node missing: %x", it.trie.Hash())
 		}
 	} else {
 		it.stack = it.stack[:len(it.stack)-1]
@@ -225,11 +227,11 @@ func (it *NodeIterator) step() error {
 		}
 		if node, ok := parent.node.(fullNode); ok {
 			// Full node, traverse all children, then the node itself
-			if parent.child >= len(node) {
+			if parent.child >= len(node.Children) {
 				break
 			}
-			for parent.child++; parent.child < len(node); parent.child++ {
-				if current := node[parent.child]; current != nil {
+			for parent.child++; parent.child < len(node.Children); parent.child++ {
+				if current := node.Children[parent.child]; current != nil {
 					it.stack = append(it.stack, &nodeIteratorState{node: current, parent: ancestor, child: -1})
 					break
 				}

trie/node.go

@@ -29,18 +29,36 @@ var indices = []string{"0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "a", "b
 
 type node interface {
 	fstring(string) string
+	cache() (hashNode, bool)
 }
 
 type (
-	fullNode  [17]node
+	fullNode struct {
+		Children [17]node // Actual trie node data to encode/decode (needs custom encoder)
+		hash     hashNode // Cached hash of the node to prevent rehashing (may be nil)
+		dirty    bool     // Cached flag whether the node's new or already stored
+	}
 	shortNode struct {
-		Key []byte
-		Val node
+		Key   []byte
+		Val   node
+		hash  hashNode // Cached hash of the node to prevent rehashing (may be nil)
+		dirty bool     // Cached flag whether the node's new or already stored
 	}
 	hashNode  []byte
 	valueNode []byte
 )
 
+// EncodeRLP encodes a full node into the consensus RLP format.
+func (n fullNode) EncodeRLP(w io.Writer) error {
+	return rlp.Encode(w, n.Children)
+}
+
+// Cache accessors to retrieve precalculated values (avoid lengthy type switches).
+func (n fullNode) cache() (hashNode, bool)  { return n.hash, n.dirty }
+func (n shortNode) cache() (hashNode, bool) { return n.hash, n.dirty }
+func (n hashNode) cache() (hashNode, bool)  { return nil, true }
+func (n valueNode) cache() (hashNode, bool) { return nil, true }
+
 // Pretty printing.
 func (n fullNode) String() string  { return n.fstring("") }
 func (n shortNode) String() string { return n.fstring("") }
@@ -49,7 +67,7 @@ func (n valueNode) String() string { return n.fstring("") }
 
 func (n fullNode) fstring(ind string) string {
 	resp := fmt.Sprintf("[\n%s  ", ind)
-	for i, node := range n {
+	for i, node := range n.Children {
 		if node == nil {
 			resp += fmt.Sprintf("%s: <nil> ", indices[i])
 		} else {
@@ -68,16 +86,16 @@ func (n valueNode) fstring(ind string) string {
 	return fmt.Sprintf("%x ", []byte(n))
 }
 
-func mustDecodeNode(dbkey, buf []byte) node {
-	n, err := decodeNode(buf)
+func mustDecodeNode(hash, buf []byte) node {
+	n, err := decodeNode(hash, buf)
 	if err != nil {
-		panic(fmt.Sprintf("node %x: %v", dbkey, err))
+		panic(fmt.Sprintf("node %x: %v", hash, err))
 	}
 	return n
 }
 
 // decodeNode parses the RLP encoding of a trie node.
-func decodeNode(buf []byte) (node, error) {
+func decodeNode(hash, buf []byte) (node, error) {
 	if len(buf) == 0 {
 		return nil, io.ErrUnexpectedEOF
 	}
@@ -87,18 +105,18 @@ func decodeNode(buf []byte) (node, error) {
 	}
 	switch c, _ := rlp.CountValues(elems); c {
 	case 2:
-		n, err := decodeShort(elems)
+		n, err := decodeShort(hash, buf, elems)
 		return n, wrapError(err, "short")
 	case 17:
-		n, err := decodeFull(elems)
+		n, err := decodeFull(hash, buf, elems)
 		return n, wrapError(err, "full")
 	default:
 		return nil, fmt.Errorf("invalid number of list elements: %v", c)
 	}
 }
 
-func decodeShort(buf []byte) (node, error) {
-	kbuf, rest, err := rlp.SplitString(buf)
+func decodeShort(hash, buf, elems []byte) (node, error) {
+	kbuf, rest, err := rlp.SplitString(elems)
 	if err != nil {
 		return nil, err
 	}
@@ -109,30 +127,30 @@ func decodeShort(buf []byte) (node, error) {
 		if err != nil {
 			return nil, fmt.Errorf("invalid value node: %v", err)
 		}
-		return shortNode{key, valueNode(val)}, nil
+		return shortNode{key, valueNode(val), hash, false}, nil
 	}
 	r, _, err := decodeRef(rest)
 	if err != nil {
 		return nil, wrapError(err, "val")
 	}
-	return shortNode{key, r}, nil
+	return shortNode{key, r, hash, false}, nil
 }
 
-func decodeFull(buf []byte) (fullNode, error) {
-	var n fullNode
+func decodeFull(hash, buf, elems []byte) (fullNode, error) {
+	n := fullNode{hash: hash}
 	for i := 0; i < 16; i++ {
-		cld, rest, err := decodeRef(buf)
+		cld, rest, err := decodeRef(elems)
 		if err != nil {
 			return n, wrapError(err, fmt.Sprintf("[%d]", i))
 		}
-		n[i], buf = cld, rest
+		n.Children[i], elems = cld, rest
 	}
-	val, _, err := rlp.SplitString(buf)
+	val, _, err := rlp.SplitString(elems)
 	if err != nil {
 		return n, err
 	}
 	if len(val) > 0 {
-		n[16] = valueNode(val)
+		n.Children[16] = valueNode(val)
 	}
 	return n, nil
 }
@@ -152,7 +170,7 @@ func decodeRef(buf []byte) (node, []byte, error) {
 			err := fmt.Errorf("oversized embedded node (size is %d bytes, want size < %d)", size, hashLen)
 			return nil, buf, err
 		}
-		n, err := decodeNode(buf)
+		n, err := decodeNode(nil, buf)
 		return n, rest, err
 	case kind == rlp.String && len(val) == 0:
 		// empty node

trie/proof.go

@@ -54,7 +54,7 @@ func (t *Trie) Prove(key []byte) []rlp.RawValue {
 			}
 			nodes = append(nodes, n)
 		case fullNode:
-			tn = n[key[0]]
+			tn = n.Children[key[0]]
 			key = key[1:]
 			nodes = append(nodes, n)
 		case hashNode:
@@ -77,7 +77,7 @@ func (t *Trie) Prove(key []byte) []rlp.RawValue {
 	for i, n := range nodes {
 		// Don't bother checking for errors here since hasher panics
 		// if encoding doesn't work and we're not writing to any database.
-		n, _ = t.hasher.replaceChildren(n, nil)
+		n, _, _ = t.hasher.hashChildren(n, nil)
 		hn, _ := t.hasher.store(n, nil, false)
 		if _, ok := hn.(hashNode); ok || i == 0 {
 			// If the node's database encoding is a hash (or is the
@@ -103,7 +103,7 @@ func VerifyProof(rootHash common.Hash, key []byte, proof []rlp.RawValue) (value
 		if !bytes.Equal(sha.Sum(nil), wantHash) {
 			return nil, fmt.Errorf("bad proof node %d: hash mismatch", i)
 		}
-		n, err := decodeNode(buf)
+		n, err := decodeNode(wantHash, buf)
 		if err != nil {
 			return nil, fmt.Errorf("bad proof node %d: %v", i, err)
 		}
@@ -139,7 +139,7 @@ func get(tn node, key []byte) ([]byte, node) {
 			tn = n.Val
 			key = key[len(n.Key):]
 		case fullNode:
-			tn = n[key[0]]
+			tn = n.Children[key[0]]
 			key = key[1:]
 		case hashNode:
 			return key, n

trie/secure_trie.go

@@ -162,11 +162,11 @@ func (t *SecureTrie) CommitTo(db DatabaseWriter) (root common.Hash, err error) {
 		}
 		t.secKeyCache = make(map[string][]byte)
 	}
-	n, err := t.hashRoot(db)
+	n, clean, err := t.hashRoot(db)
 	if err != nil {
 		return (common.Hash{}), err
 	}
-	t.root = n
+	t.root = clean
 	return common.BytesToHash(n.(hashNode)), nil
 }
 

trie/sync.go

@@ -75,8 +75,9 @@ func (s *TrieSync) AddSubTrie(root common.Hash, depth int, parent common.Hash, c
 	if root == emptyRoot {
 		return
 	}
-	blob, _ := s.database.Get(root.Bytes())
-	if local, err := decodeNode(blob); local != nil && err == nil {
+	key := root.Bytes()
+	blob, _ := s.database.Get(key)
+	if local, err := decodeNode(key, blob); local != nil && err == nil {
 		return
 	}
 	// Assemble the new sub-trie sync request
@@ -152,7 +153,7 @@ func (s *TrieSync) Process(results []SyncResult) (int, error) {
 			continue
 		}
 		// Decode the node data content and update the request
-		node, err := decodeNode(item.Data)
+		node, err := decodeNode(item.Hash[:], item.Data)
 		if err != nil {
 			return i, err
 		}
@@ -213,9 +214,9 @@ func (s *TrieSync) children(req *request) ([]*request, error) {
 		}}
 	case fullNode:
 		for i := 0; i < 17; i++ {
-			if node[i] != nil {
+			if node.Children[i] != nil {
 				children = append(children, child{
-					node:  &node[i],
+					node:  &node.Children[i],
 					depth: req.depth + 1,
 				})
 			}
@@ -238,7 +239,7 @@ func (s *TrieSync) children(req *request) ([]*request, error) {
 		if node, ok := (*child.node).(hashNode); ok {
 			// Try to resolve the node from the local database
 			blob, _ := s.database.Get(node)
-			if local, err := decodeNode(blob); local != nil && err == nil {
+			if local, err := decodeNode(node[:], blob); local != nil && err == nil {
 				*child.node = local
 				continue
 			}

trie/trie_test.go

@@ -295,7 +295,7 @@ func TestReplication(t *testing.T) {
 	for _, val := range vals2 {
 		updateString(trie2, val.k, val.v)
 	}
-	if trie2.Hash() != exp {
+	if hash := trie2.Hash(); hash != exp {
 		t.Errorf("root failure. expected %x got %x", exp, hash)
 	}
 }