Files
Chris LuandGitHub 944d967502 refactor: extract EC orchestration into a shared weed/ec package (#10760)
* shell: move ErrorWaitGroup to weed/util

* shell: remove unused CandidateEcNode and EcRack types

* ec: extract EC orchestration logic from weed/shell into weed/ec

Move the EC node/topology model, balance engine, encode pipeline, decode
pipeline, and rebuild engine into a new weed/ec package so shell commands
and maintenance workers can share the logic. Shell commands keep flag
parsing and delegate through a small ec.Env (dial option, topology fetch,
volume locations, lock check). Tests move along with the code.

* shell: remove unused proportional-rebalance type stubs

* ec: move scrub, replication check, and shard unmount engines into weed/ec

* worker: share the EC generation-aware shard counter from weed/ec

* ec: gofmt

* shell: drop EC aliases with no remaining callers

* ec: guard a missing topology hook and nil disk entries in topology helpers

* ec: drop trailing newlines from decode error strings

* ec: re-check the shell lock before applying shard unmounts

* shell: trim -node entries in ec.scrub
2026-08-14 13:54:12 -07:00

82 lines
2.8 KiB
Go

package ec
import (
"context"
"fmt"
"io"
"strings"
"sync"
"github.com/seaweedfs/seaweedfs/weed/operation"
"github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
"github.com/seaweedfs/seaweedfs/weed/util"
)
// ScrubEcVolumes asks each volume server to scrub its EC volumes (optionally
// narrowed to volumeIds) in the given mode, aggregating and reporting results.
func ScrubEcVolumes(env *Env, writer io.Writer, volumeServerAddrs []pb.ServerAddress, volumeIds []uint32, mode volume_server_pb.VolumeScrubMode, forceDeletedNeedlesCheck bool, maxParallelization int, showDetails bool) error {
var brokenVolumesStr, brokenShardsStr []string
var details []string
var totalVolumes, brokenVolumes, brokenShards, totalFiles uint64
var mu sync.Mutex
ewg := util.NewErrorWaitGroup(maxParallelization)
count := 0
for _, addr := range volumeServerAddrs {
ewg.Add(func() error {
mu.Lock()
count++
fmt.Fprintf(writer, "Scrubbing %s (%d/%d)...\n", addr.String(), count, len(volumeServerAddrs))
mu.Unlock()
err := operation.WithVolumeServerClient(false, addr, env.GrpcDialOption, func(volumeServerClient volume_server_pb.VolumeServerClient) error {
res, err := volumeServerClient.ScrubEcVolume(context.Background(), &volume_server_pb.ScrubEcVolumeRequest{
Mode: mode,
VolumeIds: volumeIds,
ForceDeletedNeedlesCheck: forceDeletedNeedlesCheck,
})
if err != nil {
return err
}
mu.Lock()
defer mu.Unlock()
totalVolumes += res.GetTotalVolumes()
totalFiles += res.GetTotalFiles()
brokenVolumes += uint64(len(res.GetBrokenVolumeIds()))
brokenShards += uint64(len(res.GetBrokenShardInfos()))
for _, d := range res.GetDetails() {
details = append(details, fmt.Sprintf("[%s] %s", addr, d))
}
for _, vid := range res.GetBrokenVolumeIds() {
brokenVolumesStr = append(brokenVolumesStr, fmt.Sprintf("%s:%v", addr, vid))
}
for _, si := range res.GetBrokenShardInfos() {
brokenShardsStr = append(brokenShardsStr, fmt.Sprintf("%s:%v:%v", addr, si.VolumeId, si.ShardId))
}
return nil
})
return err
})
}
if err := ewg.Wait(); err != nil {
return err
}
fmt.Fprintf(writer, "Scrubbed %d EC files and %d volumes on %d nodes\n", totalFiles, totalVolumes, len(volumeServerAddrs))
if brokenVolumes != 0 {
fmt.Fprintf(writer, "\nGot scrub failures on %d EC volumes and %d EC shards :(\n", brokenVolumes, brokenShards)
fmt.Fprintf(writer, "Affected volumes: %s\n", strings.Join(brokenVolumesStr, ", "))
if len(brokenShardsStr) != 0 {
fmt.Fprintf(writer, "Affected shards: %s\n", strings.Join(brokenShardsStr, ", "))
}
if showDetails && len(details) != 0 {
fmt.Fprintf(writer, "Details:\n\t%s\n", strings.Join(details, "\n\t"))
}
}
return nil
}