mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-30 12:47:00 +00:00
fcc2ea61d3
* Introduce a new `READS` scrub mode. `READS` performs a full volume scrub but, unlike `FULL`, it will attempt to reconstruct data for missing/damaged shard intervals from other shards in the cluster when necessary. The goal of this check is to ensure that EC volume contents _are readable by Seaweed_ even on a degraded storage state, by exercising parity data which is not read in `FULL` mode. This is useful not only to validate data is user-readable, but also to detect potential parity shard issues which may be difficult to pinpoint otherwise - particularly for older volumes lacking sidecar data, and hence unaffected by `CHECKSUM` scrubs. For regular volumes, this operation is equivalent to `FULL`. Example: ``` > ec.shard.unmount --volumeId=1 --shardId=0,3,11 --delete --apply Live shard topology for volume ID 1 (14 shards): 0@10.200.18.89:9001 1@10.200.18.89:9002 2@10.200.18.89:9003 3@10.200.18.89:9004 4@10.200.18.89:9005 5@10.200.18.89:9006 6@10.200.18.89:9007 7@10.200.18.89:9008 8@10.200.18.89:9009 9@10.200.18.89:9013 10@10.200.18.89:9010 11@10.200.18.89:9011 12@10.200.18.89:9012 13@10.200.18.89:9020 Will unmount + delete 3 shard(s): 0@10.200.18.89:9001 3@10.200.18.89:9004 11@10.200.18.89:9011 Unmounting shard 0@10.200.18.89:9001 for volume ID 1... Deleting shard 0@10.200.18.89:9001 for volume ID 1... Unmounting shard 3@10.200.18.89:9004 for volume ID 1... Deleting shard 3@10.200.18.89:9004 for volume ID 1... Unmounting shard 11@10.200.18.89:9011 for volume ID 1... Deleting shard 11@10.200.18.89:9011 for volume ID 1... All done! > ec.scrub --volumeId=1 --node=10.200.18.89:9002 --mode=full using FULL mode Scrubbing 10.200.18.89:9002 (1/1)... Scrubbed 6 EC files and 1 volumes on 1 nodes Got scrub failures on 1 EC volumes and 1 EC shards :( Affected volumes: 10.200.18.89:9002:1 Affected shards: 10.200.18.89:9002:1:0 > ec.scrub --volumeId=1 --node=10.200.18.89:9002 --mode=reads using READS mode Scrubbing 10.200.18.89:9002 (1/1)... Scrubbed 6 EC files and 1 volumes on 1 nodes ``` * ec: report the shards a READS scrub had to rebuild A READS scrub that recovers an interval was recording nothing, so a volume missing three shards came back clean and nobody repaired it. The unreadable shard is now recorded before the rebuild is attempted: READS reports the same broken shards as FULL and differs only in whether the needles themselves failed, which is the signal worth having - shards are gone, data is still there. forceDeletedNeedlesCheck now applies to READS as well, in the shell and in the RPC guard: it runs the same needle walk as FULL. Regenerated the proto instead of hand-editing it, so the pancis typo (which protoc-gen-go-grpc emits into eight other files here) and the header whitespace stay as generated. Mirrors into the Rust volume server, which also now honors force_deleted_needles_check rather than hardcoding it off. Claude-Session: https://claude.ai/code/session_014yMNebkUjSbx9sfUCWJJtq * ec: answer a deleted needle from a READS rebuild as deleted #11020 gave the Rust recovery a deleted flag alongside its bytes, and it answers a deleted needle with no bytes at all. The READS scrub appended that empty answer, which does not compile against the new signature and, once it did, would leave the needle short and report the size mismatch as damage. Zero-fill the interval instead, the way the direct read beside it already does: the assembled needle then reaches read_bytes as the delete-state mismatch the walk already tolerates. Go takes the same branch off the flag its recovery returns, rather than discarding it. Claude-Session: https://claude.ai/code/session_014yMNebkUjSbx9sfUCWJJtq --------- Co-authored-by: Lisandro Pin <lisandro.pin@proton.ch>
113 lines
3.6 KiB
Go
113 lines
3.6 KiB
Go
package shell
|
|
|
|
import (
|
|
"flag"
|
|
"fmt"
|
|
"io"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/ec"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
|
|
)
|
|
|
|
func init() {
|
|
Commands = append(Commands, &commandEcVolumeScrub{})
|
|
}
|
|
|
|
type commandEcVolumeScrub struct {
|
|
}
|
|
|
|
func (c *commandEcVolumeScrub) Name() string {
|
|
return "ec.scrub"
|
|
}
|
|
|
|
func (c *commandEcVolumeScrub) Help() string {
|
|
return `scrubs EC volume contents on volume servers.
|
|
|
|
Supports either scrubbing only needle data, or deep scrubbing file contents as well.
|
|
|
|
Scrubbing can be limited to specific EC volume IDs for specific volume servers.
|
|
By default, all volume IDs across all servers are processed.
|
|
`
|
|
}
|
|
|
|
func (c *commandEcVolumeScrub) HasTag(CommandTag) bool {
|
|
return false
|
|
}
|
|
|
|
func (c *commandEcVolumeScrub) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
|
|
volScrubCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
|
|
nodesStr := volScrubCommand.String("node", "", "comma-separated list of volume server <host>:<port> (optional)")
|
|
volumeIDsStr := volScrubCommand.String("volumeId", "", "comma-separated EC volume IDs to process (optional)")
|
|
mode := volScrubCommand.String("mode", "local", "scrubbing mode (index/local/full/reads/checksum)")
|
|
maxParallelization := volScrubCommand.Int("maxParallelization", DefaultMaxParallelization, "run up to X tasks in parallel, whenever possible")
|
|
showDetails := volScrubCommand.Bool("details", false, "display scrub result details, if available")
|
|
forceDeletedNeedlesCheck := volScrubCommand.Bool("forceDeletedNeedlesCheck", false, "force strict verification of deleted needles (full and reads modes only); may report false positives when EC indexes disagree")
|
|
|
|
if err = volScrubCommand.Parse(args); err != nil {
|
|
return err
|
|
}
|
|
if err = commandEnv.confirmIsLocked(args); err != nil {
|
|
return
|
|
}
|
|
|
|
volumeServerAddrs := []pb.ServerAddress{}
|
|
if *nodesStr != "" {
|
|
for _, addr := range strings.Split(*nodesStr, ",") {
|
|
addr = strings.TrimSpace(addr)
|
|
if addr == "" {
|
|
continue
|
|
}
|
|
volumeServerAddrs = append(volumeServerAddrs, pb.ServerAddress(addr))
|
|
}
|
|
} else {
|
|
dns, err := collectDataNodes(commandEnv, 0)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
for _, dn := range dns {
|
|
volumeServerAddrs = append(volumeServerAddrs, pb.ServerAddress(dn.Address))
|
|
}
|
|
}
|
|
|
|
volumeIDs := []uint32{}
|
|
if *volumeIDsStr != "" {
|
|
for _, vids := range strings.Split(*volumeIDsStr, ",") {
|
|
vids = strings.TrimSpace(vids)
|
|
if vids == "" {
|
|
continue
|
|
}
|
|
if vid, err := strconv.ParseUint(vids, 10, 32); err == nil {
|
|
volumeIDs = append(volumeIDs, uint32(vid))
|
|
} else {
|
|
return fmt.Errorf("invalid volume ID %q", vids)
|
|
}
|
|
}
|
|
}
|
|
|
|
var scrubMode volume_server_pb.VolumeScrubMode
|
|
switch strings.ToUpper(*mode) {
|
|
case "INDEX":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_INDEX
|
|
case "LOCAL":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_LOCAL
|
|
case "FULL":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_FULL
|
|
case "CHECKSUM":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_CHECKSUM
|
|
case "READS":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_READS
|
|
default:
|
|
return fmt.Errorf("unsupported scrubbing mode %q", *mode)
|
|
}
|
|
fmt.Fprintf(writer, "using %s mode\n", scrubMode.String())
|
|
if *forceDeletedNeedlesCheck &&
|
|
scrubMode != volume_server_pb.VolumeScrubMode_FULL && scrubMode != volume_server_pb.VolumeScrubMode_READS {
|
|
return fmt.Errorf("deleted needle checks are only supported for FULL and READS scrubs")
|
|
}
|
|
|
|
return ec.ScrubEcVolumes(commandEnv.ecEnv(), writer, volumeServerAddrs, volumeIDs, scrubMode, *forceDeletedNeedlesCheck, *maxParallelization, *showDetails)
|
|
}
|