seaweedfs/go/storage/needle_map_boltdb.go
chrislusf 1b6ab2f6af Add boltdb for volume needle map
boltdb is fairly slow to write, about 6 minutes for recreating index
for 1553934 files. Boltdb loads 1,553,934 x 16 = 24,862,944bytes from
disk, and generate the boltdb as large as 134,217,728 bytes in 6
minutes.

To compare, for leveldb, it recreates index in leveldb as large as
27,188,148 bytes in 8 seconds.
For in memory version, it loads the index in

To test the memory consumption, the leveldb or boltdb index are
created. And the server is restarted. Using the benchmark tool to read
lots of files. There are 7 volumes in benchmark collection, each with
about 1553K files.
For leveldb, the memory starts at 142,884KB, and stays at 179,340KB.
For boltdb, the memory starts at 73,756KB, and stays at 144,564KB.
For in-memory, the memory starts at 368,152KB, and stays at 448,032KB.
2015-03-29 11:04:32 -07:00

183 lines
4.4 KiB
Go

package storage
import (
"fmt"
"os"
"github.com/boltdb/bolt"
"github.com/chrislusf/weed-fs/go/glog"
"github.com/chrislusf/weed-fs/go/util"
)
type BoltDbNeedleMap struct {
dbFileName string
indexFile *os.File
db *bolt.DB
mapMetric
}
var boltdbBucket = []byte("weed")
func NewBoltDbNeedleMap(dbFileName string, indexFile *os.File) (m *BoltDbNeedleMap, err error) {
m = &BoltDbNeedleMap{indexFile: indexFile, dbFileName: dbFileName}
if !isBoltDbFresh(dbFileName, indexFile) {
glog.V(1).Infof("Start to Generate %s from %s", dbFileName, indexFile.Name())
generateBoltDbFile(dbFileName, indexFile)
glog.V(1).Infof("Finished Generating %s from %s", dbFileName, indexFile.Name())
}
glog.V(1).Infof("Opening %s...", dbFileName)
if m.db, err = bolt.Open(dbFileName, 0644, nil); err != nil {
return
}
glog.V(1).Infof("Loading %s...", indexFile.Name())
nm, indexLoadError := LoadNeedleMap(indexFile)
if indexLoadError != nil {
return nil, indexLoadError
}
m.mapMetric = nm.mapMetric
return
}
func isBoltDbFresh(dbFileName string, indexFile *os.File) bool {
// normally we always write to index file first
dbLogFile, err := os.Open(dbFileName)
if err != nil {
return false
}
defer dbLogFile.Close()
dbStat, dbStatErr := dbLogFile.Stat()
indexStat, indexStatErr := indexFile.Stat()
if dbStatErr != nil || indexStatErr != nil {
glog.V(0).Infof("Can not stat file: %v and %v", dbStatErr, indexStatErr)
return false
}
return dbStat.ModTime().After(indexStat.ModTime())
}
func generateBoltDbFile(dbFileName string, indexFile *os.File) error {
db, err := bolt.Open(dbFileName, 0644, nil)
if err != nil {
return err
}
defer db.Close()
return WalkIndexFile(indexFile, func(key uint64, offset, size uint32) error {
if offset > 0 {
boltDbWrite(db, key, offset, size)
} else {
boltDbDelete(db, key)
}
return nil
})
}
func (m *BoltDbNeedleMap) Get(key uint64) (element *NeedleValue, ok bool) {
bytes := make([]byte, 8)
var data []byte
util.Uint64toBytes(bytes, key)
err := m.db.View(func(tx *bolt.Tx) error {
bucket := tx.Bucket(boltdbBucket)
if bucket == nil {
return fmt.Errorf("Bucket %q not found!", boltdbBucket)
}
data = bucket.Get(bytes)
return nil
})
if err != nil || len(data) != 8 {
glog.V(0).Infof("Failed to get %d %v", key, err)
return nil, false
}
offset := util.BytesToUint32(data[0:4])
size := util.BytesToUint32(data[4:8])
return &NeedleValue{Key: Key(key), Offset: offset, Size: size}, true
}
func (m *BoltDbNeedleMap) Put(key uint64, offset uint32, size uint32) error {
var oldSize uint32
if oldNeedle, ok := m.Get(key); ok {
oldSize = oldNeedle.Size
}
m.logPut(key, oldSize, size)
// write to index file first
if err := appendToIndexFile(m.indexFile, key, offset, size); err != nil {
return fmt.Errorf("cannot write to indexfile %s: %v", m.indexFile.Name(), err)
}
return boltDbWrite(m.db, key, offset, size)
}
func boltDbWrite(db *bolt.DB,
key uint64, offset uint32, size uint32) error {
bytes := make([]byte, 16)
util.Uint64toBytes(bytes[0:8], key)
util.Uint32toBytes(bytes[8:12], offset)
util.Uint32toBytes(bytes[12:16], size)
return db.Update(func(tx *bolt.Tx) error {
bucket, err := tx.CreateBucketIfNotExists(boltdbBucket)
if err != nil {
return err
}
err = bucket.Put(bytes[0:8], bytes[8:16])
if err != nil {
return err
}
return nil
})
}
func boltDbDelete(db *bolt.DB, key uint64) error {
bytes := make([]byte, 8)
util.Uint64toBytes(bytes, key)
return db.Update(func(tx *bolt.Tx) error {
bucket, err := tx.CreateBucketIfNotExists(boltdbBucket)
if err != nil {
return err
}
err = bucket.Delete(bytes)
if err != nil {
return err
}
return nil
})
}
func (m *BoltDbNeedleMap) Delete(key uint64) error {
if oldNeedle, ok := m.Get(key); ok {
m.logDelete(oldNeedle.Size)
}
// write to index file first
if err := appendToIndexFile(m.indexFile, key, 0, 0); err != nil {
return err
}
return boltDbDelete(m.db, key)
}
func (m *BoltDbNeedleMap) Close() {
m.db.Close()
}
func (m *BoltDbNeedleMap) Destroy() error {
m.Close()
os.Remove(m.indexFile.Name())
return os.Remove(m.dbFileName)
}
func (m *BoltDbNeedleMap) ContentSize() uint64 {
return m.FileByteCounter
}
func (m *BoltDbNeedleMap) DeletedSize() uint64 {
return m.DeletionByteCounter
}
func (m *BoltDbNeedleMap) FileCount() int {
return m.FileCounter
}
func (m *BoltDbNeedleMap) DeletedCount() int {
return m.DeletionCounter
}
func (m *BoltDbNeedleMap) MaxFileKey() uint64 {
return m.MaximumFileKey
}