Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

core/state/snapshot: reuse memory data instead of hitting disk when generating #22667

Merged
merged 4 commits into from
Apr 23, 2021
Merged

core/state/snapshot: reuse memory data instead of hitting disk when generating #22667

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a8facbf
core/state/snapshot: reuse memory data instead of hitting disk when g…
holiman Apr 14, 2021
4897e10
trie: minor nitpicks wrt the resolver optimization
karalabe Apr 22, 2021
1acfe92
core/state/snapshot, trie: use key/value store for resolver
karalabe Apr 23, 2021
b32edf9
trie: fix linter
karalabe Apr 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 19 additions & 1 deletion core/state/snapshot/generate.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ import (
"github.com/ethereum/go-ethereum/core/rawdb"
"github.com/ethereum/go-ethereum/crypto"
"github.com/ethereum/go-ethereum/ethdb"
"github.com/ethereum/go-ethereum/ethdb/memorydb"
"github.com/ethereum/go-ethereum/log"
"github.com/ethereum/go-ethereum/metrics"
"github.com/ethereum/go-ethereum/rlp"
Expand Down Expand Up @@ -434,6 +435,20 @@ func (dl *diskLayer) generateRange(root common.Hash, prefix []byte, kind string,
}
meter.Mark(1)
}

// We use the snap data to build up a cache which can be used by the
// main account trie as a primary lookup when resolving hashes
var snapNodeCache ethdb.KeyValueStore
if len(result.keys) > 0 {
snapNodeCache = memorydb.New()
snapTrieDb := trie.NewDatabase(snapNodeCache)
snapTrie, _ := trie.New(common.Hash{}, snapTrieDb)
for i, key := range result.keys {
snapTrie.Update(key, result.vals[i])
}
root, _ := snapTrie.Commit(nil)
snapTrieDb.Commit(root, false, nil)
}
tr := result.tr
if tr == nil {
tr, err = trie.New(root, dl.triedb)
Expand All @@ -442,9 +457,11 @@ func (dl *diskLayer) generateRange(root common.Hash, prefix []byte, kind string,
return false, nil, errMissingTrie
}
}

var (
trieMore bool
iter = trie.NewIterator(tr.NodeIterator(origin))
nodeIt = tr.NodeIterator(origin)
iter = trie.NewIterator(nodeIt)
kvkeys, kvvals = result.keys, result.vals

// counters
Expand All @@ -458,6 +475,7 @@ func (dl *diskLayer) generateRange(root common.Hash, prefix []byte, kind string,
start = time.Now()
internal time.Duration
)
nodeIt.AddResolver(snapNodeCache)
for iter.Next() {
if last != nil && bytes.Compare(iter.Key, last) > 0 {
trieMore = true
Expand Down
50 changes: 45 additions & 5 deletions trie/iterator.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@ import (
"errors"

"github.com/ethereum/go-ethereum/common"
"github.com/ethereum/go-ethereum/ethdb"
"github.com/ethereum/go-ethereum/rlp"
)

Expand Down Expand Up @@ -102,6 +103,19 @@ type NodeIterator interface {
// iterator is not positioned at a leaf. Callers must not retain references
// to the value after calling Next.
LeafProof() [][]byte

// AddResolver sets an intermediate database to use for looking up trie nodes
// before reaching into the real persistent layer.
//
// This is not required for normal operation, rather is an optimization for
// cases where trie nodes can be recovered from some external mechanism without
// reading from disk. In those cases, this resolver allows short circuiting
// accesses and returning them from memory.
//
// Before adding a similar mechanism to any other place in Geth, consider
// making trie.Database an interface and wrapping at that level. It's a huge
// refactor, but it could be worth it if another occurrence arises.
AddResolver(ethdb.KeyValueStore)
}

// nodeIteratorState represents the iteration state at one particular node of the
Expand All @@ -119,6 +133,8 @@ type nodeIterator struct {
stack []*nodeIteratorState // Hierarchy of trie nodes persisting the iteration state
path []byte // Path to the current node
err error // Failure set in case of an internal error in the iterator

resolver ethdb.KeyValueStore // Optional intermediate resolver above the disk layer
}

// errIteratorEnd is stored in nodeIterator.err when iteration is done.
Expand All @@ -143,6 +159,10 @@ func newNodeIterator(trie *Trie, start []byte) NodeIterator {
return it
}

func (it *nodeIterator) AddResolver(resolver ethdb.KeyValueStore) {
it.resolver = resolver
}

func (it *nodeIterator) Hash() common.Hash {
if len(it.stack) == 0 {
return common.Hash{}
Expand Down Expand Up @@ -262,7 +282,7 @@ func (it *nodeIterator) init() (*nodeIteratorState, error) {
if root != emptyRoot {
state.hash = root
}
return state, state.resolve(it.trie, nil)
return state, state.resolve(it, nil)
}

// peek creates the next state of the iterator.
Expand All @@ -286,7 +306,7 @@ func (it *nodeIterator) peek(descend bool) (*nodeIteratorState, *int, []byte, er
}
state, path, ok := it.nextChild(parent, ancestor)
if ok {
if err := state.resolve(it.trie, path); err != nil {
if err := state.resolve(it, path); err != nil {
return parent, &parent.index, path, err
}
return state, &parent.index, path, nil
Expand Down Expand Up @@ -319,7 +339,7 @@ func (it *nodeIterator) peekSeek(seekKey []byte) (*nodeIteratorState, *int, []by
}
state, path, ok := it.nextChildAt(parent, ancestor, seekKey)
if ok {
if err := state.resolve(it.trie, path); err != nil {
if err := state.resolve(it, path); err != nil {
return parent, &parent.index, path, err
}
return state, &parent.index, path, nil
Expand All @@ -330,9 +350,21 @@ func (it *nodeIterator) peekSeek(seekKey []byte) (*nodeIteratorState, *int, []by
return nil, nil, nil, errIteratorEnd
}

func (st *nodeIteratorState) resolve(tr *Trie, path []byte) error {
func (it *nodeIterator) resolveHash(hash hashNode, path []byte) (node, error) {
if it.resolver != nil {
if blob, err := it.resolver.Get(hash); err == nil && len(blob) > 0 {
if resolved, err := decodeNode(hash, blob); err == nil {
return resolved, nil
}
}
}
resolved, err := it.trie.resolveHash(hash, path)
return resolved, err
}

func (st *nodeIteratorState) resolve(it *nodeIterator, path []byte) error {
if hash, ok := st.node.(hashNode); ok {
resolved, err := tr.resolveHash(hash, path)
resolved, err := it.resolveHash(hash, path)
if err != nil {
return err
}
Expand Down Expand Up @@ -517,6 +549,10 @@ func (it *differenceIterator) Path() []byte {
return it.b.Path()
}

func (it *differenceIterator) AddResolver(resolver ethdb.KeyValueStore) {
panic("not implemented")
}

func (it *differenceIterator) Next(bool) bool {
// Invariants:
// - We always advance at least one element in b.
Expand Down Expand Up @@ -624,6 +660,10 @@ func (it *unionIterator) Path() []byte {
return (*it.items)[0].Path()
}

func (it *unionIterator) AddResolver(resolver ethdb.KeyValueStore) {
panic("not implemented")
}

// Next returns the next node in the union of tries being iterated over.
//
// It does this by maintaining a heap of iterators, sorted by the iteration
Expand Down