2016-06-03 09:09:14 +08:00
|
|
|
package command
|
2013-09-29 13:18:52 +08:00
|
|
|
|
|
|
|
import (
|
2019-09-12 21:18:21 +08:00
|
|
|
"github.com/chrislusf/seaweedfs/weed/glog"
|
|
|
|
"github.com/chrislusf/seaweedfs/weed/storage"
|
|
|
|
"github.com/chrislusf/seaweedfs/weed/storage/needle"
|
2013-09-29 13:18:52 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
func init() {
|
|
|
|
cmdCompact.Run = runCompact // break init cycle
|
|
|
|
}
|
|
|
|
|
|
|
|
var cmdCompact = &Command{
|
|
|
|
UsageLine: "compact -dir=/tmp -volumeId=234",
|
2014-10-21 16:27:40 +08:00
|
|
|
Short: "run weed tool compact on volume file",
|
2013-09-29 13:18:52 +08:00
|
|
|
Long: `Force an compaction to remove deleted files from volume files.
|
|
|
|
The compacted .dat file is stored as .cpd file.
|
|
|
|
The compacted .idx file is stored as .cpx file.
|
|
|
|
|
2019-12-25 06:55:50 +08:00
|
|
|
For method=0, it compacts based on the .dat file, works if .idx file is corrupted.
|
|
|
|
For method=1, it compacts based on the .idx file, works if deletion happened but not written to .dat files.
|
|
|
|
|
2013-09-29 13:18:52 +08:00
|
|
|
`,
|
|
|
|
}
|
|
|
|
|
|
|
|
var (
|
2017-01-09 03:01:46 +08:00
|
|
|
compactVolumePath = cmdCompact.Flag.String("dir", ".", "data directory to store files")
|
|
|
|
compactVolumeCollection = cmdCompact.Flag.String("collection", "", "volume collection name")
|
|
|
|
compactVolumeId = cmdCompact.Flag.Int("volumeId", -1, "a volume id. The volume should already exist in the dir.")
|
|
|
|
compactMethod = cmdCompact.Flag.Int("method", 0, "option to choose which compact method. use 0 or 1.")
|
2017-01-09 06:57:32 +08:00
|
|
|
compactVolumePreallocate = cmdCompact.Flag.Int64("preallocateMB", 0, "preallocate volume disk space")
|
2013-09-29 13:18:52 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
func runCompact(cmd *Command, args []string) bool {
|
|
|
|
|
|
|
|
if *compactVolumeId == -1 {
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
|
2017-08-30 14:59:53 +08:00
|
|
|
preallocate := *compactVolumePreallocate * (1 << 20)
|
|
|
|
|
2019-04-19 12:43:36 +08:00
|
|
|
vid := needle.VolumeId(*compactVolumeId)
|
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.
2015-03-30 02:04:32 +08:00
|
|
|
v, err := storage.NewVolume(*compactVolumePath, *compactVolumeCollection, vid,
|
2019-09-04 22:27:14 +08:00
|
|
|
storage.NeedleMapInMemory, nil, nil, preallocate, 0)
|
2013-09-29 13:18:52 +08:00
|
|
|
if err != nil {
|
|
|
|
glog.Fatalf("Load Volume [ERROR] %s\n", err)
|
|
|
|
}
|
2016-09-23 11:31:17 +08:00
|
|
|
if *compactMethod == 0 {
|
2019-09-04 00:00:59 +08:00
|
|
|
if err = v.Compact(preallocate, 0); err != nil {
|
2016-09-23 11:31:17 +08:00
|
|
|
glog.Fatalf("Compact Volume [ERROR] %s\n", err)
|
|
|
|
}
|
|
|
|
} else {
|
2020-03-12 01:32:17 +08:00
|
|
|
if err = v.Compact2(preallocate, 0); err != nil {
|
2016-09-23 11:31:17 +08:00
|
|
|
glog.Fatalf("Compact Volume [ERROR] %s\n", err)
|
|
|
|
}
|
2013-09-29 13:18:52 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return true
|
|
|
|
}
|