Files
seaweedfs/weed/plugin/worker/volume_metrics.go
T
Chris Lu 1f6f473995 refactor(worker): co-locate plugin handlers with their task packages (#9301)
* refactor(worker): co-locate plugin handlers with their task packages

Move every per-task plugin handler from weed/plugin/worker/ into the
matching weed/worker/tasks/<name>/ package, so each task owns its
detection, scheduling, execution, and plugin handler in one place.

Step 0 (within pluginworker, no behavior change): extract shared helpers
that previously lived inside individual handler files into dedicated
files and export the ones now consumed across packages.

  - activity.go: BuildExecutorActivity, BuildDetectorActivity
  - config.go: ReadStringConfig/Double/Int64/Bytes/StringList, MapTaskPriority
  - interval.go: ShouldSkipDetectionByInterval
  - volume_state.go: VolumeState + consts, FilterMetricsByVolumeState/Location
  - collection_filter.go: CollectionFilterMode + consts
  - volume_metrics.go: export CollectVolumeMetricsFromMasters,
    MasterAddressCandidates, FetchVolumeList
  - testing_senders_test.go: shared test stubs

Phase 1: move the per-task plugin handlers (and the iceberg subpackage)
into their task packages.

  weed/plugin/worker/vacuum_handler.go         -> weed/worker/tasks/vacuum/plugin_handler.go
  weed/plugin/worker/ec_balance_handler.go     -> weed/worker/tasks/ec_balance/plugin_handler.go
  weed/plugin/worker/erasure_coding_handler.go -> weed/worker/tasks/erasure_coding/plugin_handler.go
  weed/plugin/worker/volume_balance_handler.go -> weed/worker/tasks/balance/plugin_handler.go
  weed/plugin/worker/iceberg/                   -> weed/worker/tasks/iceberg/

  weed/plugin/worker/handlers/handlers.go now blank-imports all five
  task subpackages so their init() registrations fire.

  weed/command/mini.go and the worker tests construct the handler with
  vacuum.DefaultMaxExecutionConcurrency (the constant moved with the
  vacuum handler).

admin_script remains in weed/plugin/worker/ because there is no
underlying weed/worker/tasks/admin_script/ package to merge with.

* refactor(worker): update test/plugin_workers imports for moved handlers

Three handler constructors moved out of pluginworker into their task
packages — update the integration test files in test/plugin_workers/
to import from the new locations:

  pluginworker.NewVacuumHandler        -> vacuum.NewVacuumHandler
  pluginworker.NewVolumeBalanceHandler -> balance.NewVolumeBalanceHandler
  pluginworker.NewErasureCodingHandler -> erasure_coding.NewErasureCodingHandler

The pluginworker import is kept where the file still uses
pluginworker.WorkerOptions / pluginworker.JobHandler.

* refactor(worker): update test/s3tables iceberg import path

The iceberg subpackage moved from weed/plugin/worker/iceberg/ to
weed/worker/tasks/iceberg/. test/s3tables/maintenance/maintenance_integration_test.go
still imported the old path, breaking S3 Tables / RisingWave / Trino /
Spark / Iceberg-catalog / STS integration test builds.

Mirrors the OSS-side fix needed by every job in the run that
transitively imports test/s3tables/maintenance.

* chore: gofmt PR-touched files

The S3 Tables Format Check job runs `gofmt -l` over weed/s3api/s3tables
and test/s3tables, then fails if anything is unformatted. Files this
PR moved or modified had import-grouping and trailing-spacing issues
introduced by perl-based renames; reformat them with gofmt -w.

Touched files:
  test/plugin_workers/erasure_coding/{detection,execution}_test.go
  test/s3tables/maintenance/maintenance_integration_test.go
  weed/plugin/worker/handlers/handlers.go
  weed/worker/tasks/{balance,ec_balance,erasure_coding,vacuum}/plugin_handler*.go

* refactor(worker): bounds-checked int conversions for plugin config values

CodeQL flagged 18 go/incorrect-integer-conversion warnings on the moved
plugin handler files: results of pluginworker.ReadInt64Config (which
ultimately calls strconv.ParseInt with bit size 64) were being narrowed
to int32/uint32/int without an upper-bound check, so a malicious or
malformed admin/worker config value could overflow the target type.

Add three helpers in weed/plugin/worker/config.go that wrap
ReadInt64Config and clamp out-of-range values back to the caller's
fallback:

  ReadInt32Config (math.MinInt32 .. math.MaxInt32)
  ReadUint32Config (0 .. math.MaxUint32)
  ReadIntConfig    (math.MinInt32 .. math.MaxInt32, platform-portable)

Update each flagged call site in the four moved task packages to use
the bounds-checked helper. For protobuf uint32 fields (volume IDs)
the variable type also becomes uint32, removing the trailing
uint32(volumeID) casts and changing the "missing volume_id" check
from `<= 0` to `== 0`.

Touched files:
  weed/plugin/worker/config.go
  weed/worker/tasks/balance/plugin_handler.go
  weed/worker/tasks/erasure_coding/plugin_handler.go
  weed/worker/tasks/vacuum/plugin_handler.go

* refactor(worker): use ReadIntConfig for clamped derive-worker-config helpers

CodeQL still flagged three call sites where ReadInt64Config was being
narrowed to int after a value-range clamp (max_concurrent_moves <= 50,
batch_size <= 100, min_server_count >= 2). The clamp is correct but
CodeQL's flow analysis didn't recognize the bound, so it flagged them
as unbounded narrowing.

Switch to ReadIntConfig (already int32-bounded by the helper) for
those three sites, drop the now-redundant int64 intermediate variables.

Also drops the now-unused `> math.MaxInt32` clamp in
ec_balance.deriveECBalanceWorkerConfig (the helper covers it).
2026-05-02 18:03:13 -07:00

216 lines
7.0 KiB
Go

package pluginworker
import (
"context"
"errors"
"fmt"
"regexp"
"sort"
"strings"
"time"
"github.com/seaweedfs/seaweedfs/weed/admin/topology"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
workertypes "github.com/seaweedfs/seaweedfs/weed/worker/types"
"google.golang.org/grpc"
)
// CollectVolumeMetricsFromMasters dials the provided master addresses in order
// until one returns a usable volume list, then converts that into per-volume
// health metrics, an active-topology view, and a replica-location map.
func CollectVolumeMetricsFromMasters(
ctx context.Context,
masterAddresses []string,
collectionFilter string,
grpcDialOption grpc.DialOption,
) ([]*workertypes.VolumeHealthMetrics, *topology.ActiveTopology, map[uint32][]workertypes.ReplicaLocation, error) {
if grpcDialOption == nil {
return nil, nil, nil, fmt.Errorf("grpc dial option is not configured")
}
if len(masterAddresses) == 0 {
return nil, nil, nil, fmt.Errorf("no master addresses provided in cluster context")
}
for _, masterAddress := range masterAddresses {
response, err := FetchVolumeList(ctx, masterAddress, grpcDialOption)
if err != nil {
glog.Warningf("Plugin worker failed master volume list at %s: %v", masterAddress, err)
continue
}
metrics, activeTopology, replicaMap, buildErr := buildVolumeMetrics(response, collectionFilter)
if buildErr != nil {
// Configuration errors (e.g. invalid regex) will fail on every master,
// so return immediately instead of masking them with retries.
if isConfigError(buildErr) {
return nil, nil, nil, buildErr
}
glog.Warningf("Plugin worker failed to build metrics from master %s: %v", masterAddress, buildErr)
continue
}
return metrics, activeTopology, replicaMap, nil
}
return nil, nil, nil, fmt.Errorf("failed to load topology from all provided masters")
}
// FetchVolumeList dials the given master address (trying both the address as
// given and the gRPC port variant) and returns the master's volume list. Used
// by detection helpers that already know which master address to talk to.
func FetchVolumeList(ctx context.Context, address string, grpcDialOption grpc.DialOption) (*master_pb.VolumeListResponse, error) {
var lastErr error
for _, candidate := range MasterAddressCandidates(address) {
if ctx.Err() != nil {
return nil, ctx.Err()
}
dialCtx, cancelDial := context.WithTimeout(ctx, 5*time.Second)
conn, err := pb.GrpcDial(dialCtx, candidate, false, grpcDialOption)
cancelDial()
if err != nil {
lastErr = err
continue
}
client := master_pb.NewSeaweedClient(conn)
callCtx, cancelCall := context.WithTimeout(ctx, 10*time.Second)
response, callErr := client.VolumeList(callCtx, &master_pb.VolumeListRequest{})
cancelCall()
_ = conn.Close()
if callErr == nil {
return response, nil
}
lastErr = callErr
}
if lastErr == nil {
lastErr = fmt.Errorf("no valid master address candidate")
}
return nil, lastErr
}
func buildVolumeMetrics(
response *master_pb.VolumeListResponse,
collectionFilter string,
) ([]*workertypes.VolumeHealthMetrics, *topology.ActiveTopology, map[uint32][]workertypes.ReplicaLocation, error) {
if response == nil || response.TopologyInfo == nil {
return nil, nil, nil, fmt.Errorf("volume list response has no topology info")
}
activeTopology := topology.NewActiveTopology(10)
if err := activeTopology.UpdateTopology(response.TopologyInfo); err != nil {
return nil, nil, nil, err
}
var collectionRegex *regexp.Regexp
trimmedFilter := strings.TrimSpace(collectionFilter)
filterMode := CollectionFilterMode(trimmedFilter)
if trimmedFilter != "" && filterMode != CollectionFilterAll && filterMode != CollectionFilterEach && trimmedFilter != "*" {
var err error
collectionRegex, err = regexp.Compile(trimmedFilter)
if err != nil {
return nil, nil, nil, &configError{err: fmt.Errorf("invalid collection_filter regex %q: %w", trimmedFilter, err)}
}
}
volumeSizeLimitBytes := uint64(response.VolumeSizeLimitMb) * 1024 * 1024
now := time.Now()
metrics := make([]*workertypes.VolumeHealthMetrics, 0, 256)
replicaMap := make(map[uint32][]workertypes.ReplicaLocation)
for _, dc := range response.TopologyInfo.DataCenterInfos {
for _, rack := range dc.RackInfos {
for _, node := range rack.DataNodeInfos {
for diskType, diskInfo := range node.DiskInfos {
for _, volume := range diskInfo.VolumeInfos {
// Build replica map from ALL volumes BEFORE collection filtering,
// since replicas may span filtered/unfiltered nodes.
replicaMap[volume.Id] = append(replicaMap[volume.Id], workertypes.ReplicaLocation{
DataCenter: dc.Id,
Rack: rack.Id,
NodeID: node.Id,
})
if collectionRegex != nil && !collectionRegex.MatchString(volume.Collection) {
continue
}
metric := &workertypes.VolumeHealthMetrics{
VolumeID: volume.Id,
Server: node.Id,
ServerAddress: string(pb.NewServerAddressFromDataNode(node)),
DiskType: diskType,
DiskId: volume.DiskId,
DataCenter: dc.Id,
Rack: rack.Id,
Collection: volume.Collection,
Size: volume.Size,
DeletedBytes: volume.DeletedByteCount,
LastModified: time.Unix(volume.ModifiedAtSecond, 0),
ReplicaCount: 1,
ExpectedReplicas: int(volume.ReplicaPlacement),
IsReadOnly: volume.ReadOnly,
}
if metric.Size > 0 {
metric.GarbageRatio = float64(metric.DeletedBytes) / float64(metric.Size)
}
if volumeSizeLimitBytes > 0 {
metric.FullnessRatio = float64(metric.Size) / float64(volumeSizeLimitBytes)
}
metric.Age = now.Sub(metric.LastModified)
metrics = append(metrics, metric)
}
}
}
}
}
replicaCounts := make(map[uint32]int)
for _, metric := range metrics {
replicaCounts[metric.VolumeID]++
}
for _, metric := range metrics {
metric.ReplicaCount = replicaCounts[metric.VolumeID]
}
return metrics, activeTopology, replicaMap, nil
}
// configError wraps configuration errors that should not be retried across masters.
type configError struct {
err error
}
func (e *configError) Error() string { return e.err.Error() }
func (e *configError) Unwrap() error { return e.err }
func isConfigError(err error) bool {
var ce *configError
return errors.As(err, &ce)
}
// MasterAddressCandidates returns address forms to try when dialing a master:
// the address as given plus the gRPC variant (port + 10000). Both are tried
// because callers may pass either an HTTP-port or gRPC-port address.
func MasterAddressCandidates(address string) []string {
trimmed := strings.TrimSpace(address)
if trimmed == "" {
return nil
}
candidateSet := map[string]struct{}{
trimmed: {},
}
converted := pb.ServerToGrpcAddress(trimmed)
candidateSet[converted] = struct{}{}
candidates := make([]string, 0, len(candidateSet))
for candidate := range candidateSet {
candidates = append(candidates, candidate)
}
sort.Strings(candidates)
return candidates
}