mirror of
https://github.com/ethereum/go-ethereum.git
synced 2026-08-19 18:32:23 +00:00
pathdb: add bloomfilter to pathdb difflayer
This commit is contained in:
parent
3e896c875a
commit
f31105d285
4 changed files with 197 additions and 1 deletions
|
|
@ -17,15 +17,91 @@
|
|||
package pathdb
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"fmt"
|
||||
"math"
|
||||
"math/rand"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/ethereum/go-ethereum/common"
|
||||
"github.com/ethereum/go-ethereum/log"
|
||||
"github.com/ethereum/go-ethereum/trie/trienode"
|
||||
"github.com/ethereum/go-ethereum/trie/triestate"
|
||||
bloomfilter "github.com/holiman/bloomfilter/v2"
|
||||
)
|
||||
|
||||
var (
|
||||
// aggregatorMemoryLimit is the maximum size of the bottom-most diff layer
|
||||
// that aggregates the writes from above until it's flushed into the disk
|
||||
// layer.
|
||||
//
|
||||
// Note, bumping this up might drastically increase the size of the bloom
|
||||
// filters that's stored in every diff layer. Don't do that without fully
|
||||
// understanding all the implications.
|
||||
aggregatorMemoryLimit = uint64(4 * 1024 * 1024)
|
||||
|
||||
// aggregatorItemLimit is an approximate number of items that will end up
|
||||
// in the aggregator layer before it's flushed out to disk. A plain account
|
||||
// weighs around 14B (+hash), a storage slot 32B (+hash), a deleted slot
|
||||
// 0B (+hash). Slots are mostly set/unset in lockstep, so that average at
|
||||
// 16B (+hash). All in all, the average entry seems to be 15+32=47B. Use a
|
||||
// smaller number to be on the safe side.
|
||||
aggregatorItemLimit = aggregatorMemoryLimit / 42
|
||||
|
||||
// bloomTargetError is the target false positive rate when the aggregator
|
||||
// layer is at its fullest. The actual value will probably move around up
|
||||
// and down from this number, it's mostly a ballpark figure.
|
||||
//
|
||||
// Note, dropping this down might drastically increase the size of the bloom
|
||||
// filters that's stored in every diff layer. Don't do that without fully
|
||||
// understanding all the implications.
|
||||
bloomTargetError = 0.02
|
||||
|
||||
// bloomSize is the ideal bloom filter size given the maximum number of items
|
||||
// it's expected to hold and the target false positive error rate.
|
||||
bloomSize = math.Ceil(float64(aggregatorItemLimit) * math.Log(bloomTargetError) / math.Log(1/math.Pow(2, math.Log(2))))
|
||||
|
||||
// bloomFuncs is the ideal number of bits a single entry should set in the
|
||||
// bloom filter to keep its size to a minimum (given it's size and maximum
|
||||
// entry count).
|
||||
bloomFuncs = math.Round((bloomSize / float64(aggregatorItemLimit)) * math.Log(2))
|
||||
|
||||
// the bloom offsets are runtime constants which determines which part of the
|
||||
// account/storage hash the hasher functions looks at, to determine the
|
||||
// bloom key for an account/slot. This is randomized at init(), so that the
|
||||
// global population of nodes do not all display the exact same behaviour with
|
||||
// regards to bloom content
|
||||
bloomNodeHasherOffset = 0
|
||||
)
|
||||
|
||||
func init() {
|
||||
// Init the bloom offsets in the range [0:24] (requires 8 bytes)
|
||||
bloomNodeHasherOffset = rand.Intn(25)
|
||||
}
|
||||
|
||||
func nodeBloomHash(h common.Hash, p []byte) uint64 {
|
||||
return binary.BigEndian.Uint64(h[bloomNodeHasherOffset:bloomNodeHasherOffset+8]) ^ pathBloomHash(p)
|
||||
}
|
||||
|
||||
func pathBloomHash(p []byte) uint64 {
|
||||
if len(p)&1 != 0 {
|
||||
panic("can't convert hex key of odd length")
|
||||
}
|
||||
hashLen := len(p) / 2
|
||||
if hashLen > 8 {
|
||||
panic("hash value too long")
|
||||
}
|
||||
|
||||
var hashValue uint64
|
||||
for i := 0; i < hashLen; i++ {
|
||||
hashValue <<= 8
|
||||
hashValue |= uint64(p[i*2])<<4 | uint64(p[i*2+1])
|
||||
}
|
||||
|
||||
return (uint64(hashLen) << 32) | (hashValue << 1)
|
||||
}
|
||||
|
||||
// diffLayer represents a collection of modifications made to the in-memory tries
|
||||
// along with associated state changes after running a block on top.
|
||||
//
|
||||
|
|
@ -42,6 +118,10 @@ type diffLayer struct {
|
|||
|
||||
parent layer // Parent layer modified by this one, never nil, **can be changed**
|
||||
lock sync.RWMutex // Lock used to protect parent
|
||||
|
||||
origin *diskLayer
|
||||
diffed *bloomfilter.Filter // Bloom filter tracking all the diffed items up to the disk layer
|
||||
selfDiffed *bloomfilter.Filter // Bloom filter tracking all the diffed items of its own
|
||||
}
|
||||
|
||||
// newDiffLayer creates a new diff layer on top of an existing layer.
|
||||
|
|
@ -58,6 +138,15 @@ func newDiffLayer(parent layer, root common.Hash, id uint64, block uint64, nodes
|
|||
states: states,
|
||||
parent: parent,
|
||||
}
|
||||
switch l := parent.(type) {
|
||||
case *diskLayer:
|
||||
dl.rebloom(l)
|
||||
case *diffLayer:
|
||||
dl.rebloom(l.origin)
|
||||
default:
|
||||
panic("unknown parent type")
|
||||
}
|
||||
|
||||
for _, subset := range nodes {
|
||||
for path, n := range subset {
|
||||
dl.memory += uint64(n.Size() + len(path))
|
||||
|
|
@ -75,6 +164,53 @@ func newDiffLayer(parent layer, root common.Hash, id uint64, block uint64, nodes
|
|||
return dl
|
||||
}
|
||||
|
||||
// rebloom discards the layer's current bloom and rebuilds it from scratch based
|
||||
// on the parent's and the local diffs.
|
||||
func (dl *diffLayer) rebloom(origin *diskLayer) {
|
||||
dl.lock.Lock()
|
||||
defer dl.lock.Unlock()
|
||||
|
||||
defer func(start time.Time) {
|
||||
bloomIndexTimer.Update(time.Since(start))
|
||||
}(time.Now())
|
||||
|
||||
// Inject the new origin that triggered the rebloom
|
||||
dl.origin = origin
|
||||
|
||||
// Retrieve the parent bloom or create a fresh empty one
|
||||
if parent, ok := dl.parent.(*diffLayer); ok {
|
||||
parent.lock.RLock()
|
||||
dl.diffed, _ = parent.diffed.Copy()
|
||||
parent.lock.RUnlock()
|
||||
} else {
|
||||
if dl.selfDiffed == nil {
|
||||
dl.diffed, _ = bloomfilter.New(uint64(bloomSize), uint64(bloomFuncs))
|
||||
} else {
|
||||
dl.diffed, _ = dl.selfDiffed.NewCompatible()
|
||||
}
|
||||
}
|
||||
|
||||
if dl.selfDiffed == nil {
|
||||
dl.selfDiffed, _ = dl.diffed.NewCompatible()
|
||||
for owner, subset := range dl.nodes {
|
||||
for path, _ := range subset {
|
||||
dl.selfDiffed.AddHash(nodeBloomHash(owner, []byte(path)))
|
||||
}
|
||||
}
|
||||
}
|
||||
err := dl.diffed.UnionInPlace(dl.selfDiffed)
|
||||
if err != nil {
|
||||
log.Error("diff layer bloom filter failed to union in place", "id", dl.id, "err", err)
|
||||
}
|
||||
// Calculate the current false positive rate and update the error rate meter.
|
||||
// This is a bit cheating because subsequent layers will overwrite it, but it
|
||||
// should be fine, we're only interested in ballpark figures.
|
||||
k := float64(dl.diffed.K())
|
||||
n := float64(dl.diffed.N())
|
||||
m := float64(dl.diffed.M())
|
||||
bloomErrorGauge.Update(math.Pow(1.0-math.Exp((-k)*(n+0.5)/(m-1)), k))
|
||||
}
|
||||
|
||||
// rootHash implements the layer interface, returning the root hash of
|
||||
// corresponding state.
|
||||
func (dl *diffLayer) rootHash() common.Hash {
|
||||
|
|
@ -97,7 +233,7 @@ func (dl *diffLayer) parentLayer() layer {
|
|||
|
||||
// node implements the layer interface, retrieving the trie node blob with the
|
||||
// provided node information. No error will be returned if the node is not found.
|
||||
func (dl *diffLayer) node(owner common.Hash, path []byte, depth int) ([]byte, common.Hash, *nodeLoc, error) {
|
||||
func (dl *diffLayer) nodeInternal(owner common.Hash, path []byte, depth int) ([]byte, common.Hash, *nodeLoc, error) {
|
||||
// Hold the lock, ensure the parent won't be changed during the
|
||||
// state accessing.
|
||||
dl.lock.RLock()
|
||||
|
|
@ -114,10 +250,33 @@ func (dl *diffLayer) node(owner common.Hash, path []byte, depth int) ([]byte, co
|
|||
return n.Blob, n.Hash, &nodeLoc{loc: locDiffLayer, depth: depth}, nil
|
||||
}
|
||||
}
|
||||
|
||||
// Trie node unknown to this layer, resolve from parent
|
||||
if diff, ok := dl.parent.(*diffLayer); ok {
|
||||
return diff.nodeInternal(owner, path, depth+1)
|
||||
}
|
||||
// Failed to resolve through diff layers, fallback to disk layer
|
||||
return dl.parent.node(owner, path, depth+1)
|
||||
}
|
||||
|
||||
// Node implements the layer interface, retrieving the trie node blob with the
|
||||
// provided node information. No error will be returned if the node is not found.
|
||||
func (dl *diffLayer) node(owner common.Hash, path []byte, depth int) ([]byte, common.Hash, *nodeLoc, error) {
|
||||
dl.lock.RLock()
|
||||
defer dl.lock.RUnlock()
|
||||
|
||||
var origin *diskLayer
|
||||
hit := dl.diffed.ContainsHash(nodeBloomHash(owner, path))
|
||||
if !hit {
|
||||
origin = dl.origin // extract origin while holding the lock
|
||||
}
|
||||
|
||||
if origin != nil {
|
||||
return origin.node(owner, path, depth+1)
|
||||
}
|
||||
return dl.nodeInternal(owner, path, 0)
|
||||
}
|
||||
|
||||
// update implements the layer interface, creating a new layer on top of the
|
||||
// existing layer tree with the specified data items.
|
||||
func (dl *diffLayer) update(root common.Hash, id uint64, block uint64, nodes map[common.Hash]map[string]*trienode.Node, states *triestate.Set) *diffLayer {
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ package pathdb
|
|||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"testing"
|
||||
|
||||
"github.com/ethereum/go-ethereum/common"
|
||||
|
|
@ -25,6 +26,7 @@ import (
|
|||
"github.com/ethereum/go-ethereum/crypto"
|
||||
"github.com/ethereum/go-ethereum/internal/testrand"
|
||||
"github.com/ethereum/go-ethereum/trie/trienode"
|
||||
"github.com/stretchr/testify/assert"
|
||||
)
|
||||
|
||||
func emptyLayer() *diskLayer {
|
||||
|
|
@ -170,3 +172,20 @@ func BenchmarkJournal(b *testing.B) {
|
|||
layer.journal(new(bytes.Buffer))
|
||||
}
|
||||
}
|
||||
|
||||
func TestBloomHash(t *testing.T) {
|
||||
n1 := nodeBloomHash(common.Hash{}, common.Hex2Bytes("0101"))
|
||||
n2 := nodeBloomHash(common.Hash{}, common.Hex2Bytes("00000101"))
|
||||
n3 := nodeBloomHash(common.Hash{}, common.Hex2Bytes("0000000000000000000000000101"))
|
||||
n4 := nodeBloomHash(common.HexToHash("0xfffffffffffffffffffffffffffffffffffffffffffffff1ffffdfffffffffaf"), common.Hex2Bytes("0101"))
|
||||
n5 := nodeBloomHash(common.HexToHash("0xf1234ffffffffffffffffffffffffffffffffffffffffff1ffffdfffffffffaf"), common.Hex2Bytes("00000101"))
|
||||
fmt.Printf("hash: %x\n", n1)
|
||||
fmt.Printf("hash: %x\n", n2)
|
||||
fmt.Printf("hash: %x\n", n3)
|
||||
fmt.Printf("hash: %x\n", n4)
|
||||
fmt.Printf("hash: %x\n", n5)
|
||||
assert.NotEqual(t, n1, n2)
|
||||
assert.NotEqual(t, n1, n3)
|
||||
assert.NotEqual(t, n1, n4)
|
||||
assert.NotEqual(t, n4, n5)
|
||||
}
|
||||
|
|
|
|||
|
|
@ -145,6 +145,7 @@ func (tree *layerTree) cap(root common.Hash, layers int) error {
|
|||
return nil
|
||||
}
|
||||
}
|
||||
var persisted *diskLayer
|
||||
// We're out of layers, flatten anything below, stopping if it's the disk or if
|
||||
// the memory limit is not yet exceeded.
|
||||
switch parent := diff.parentLayer().(type) {
|
||||
|
|
@ -163,6 +164,7 @@ func (tree *layerTree) cap(root common.Hash, layers int) error {
|
|||
}
|
||||
tree.layers[base.rootHash()] = base
|
||||
diff.parent = base
|
||||
persisted = base.(*diskLayer)
|
||||
|
||||
diff.lock.Unlock()
|
||||
|
||||
|
|
@ -190,6 +192,19 @@ func (tree *layerTree) cap(root common.Hash, layers int) error {
|
|||
remove(root)
|
||||
}
|
||||
}
|
||||
// If the disk layer was modified, regenerate all the cumulative blooms
|
||||
if persisted != nil {
|
||||
var rebloom func(root common.Hash)
|
||||
rebloom = func(root common.Hash) {
|
||||
if diff, ok := tree.layers[root].(*diffLayer); ok {
|
||||
diff.rebloom(persisted)
|
||||
}
|
||||
for _, child := range children[root] {
|
||||
rebloom(child)
|
||||
}
|
||||
}
|
||||
rebloom(persisted.root)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -48,4 +48,7 @@ var (
|
|||
historyBuildTimeMeter = metrics.NewRegisteredTimer("pathdb/history/time", nil)
|
||||
historyDataBytesMeter = metrics.NewRegisteredMeter("pathdb/history/bytes/data", nil)
|
||||
historyIndexBytesMeter = metrics.NewRegisteredMeter("pathdb/history/bytes/index", nil)
|
||||
|
||||
bloomIndexTimer = metrics.NewRegisteredResettingTimer("pathdb/bloom/index", nil)
|
||||
bloomErrorGauge = metrics.NewRegisteredGaugeFloat64("pathdb/bloom/error", nil)
|
||||
)
|
||||
|
|
|
|||
Loading…
Reference in a new issue