Files
seaweedfs/weed/worker/tasks/vacuum/plugin_handler_test.go
T
Chris LuandGitHub 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

374 lines
11 KiB
Go

package vacuum
import (
"context"
"strings"
"testing"
"time"
"github.com/seaweedfs/seaweedfs/weed/pb/plugin_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
pluginworker "github.com/seaweedfs/seaweedfs/weed/plugin/worker"
workertypes "github.com/seaweedfs/seaweedfs/weed/worker/types"
"google.golang.org/protobuf/proto"
"google.golang.org/protobuf/types/known/timestamppb"
)
func TestDecodeVacuumTaskParamsFromPayload(t *testing.T) {
expected := &worker_pb.TaskParams{
TaskId: "task-1",
VolumeId: 42,
Collection: "photos",
Sources: []*worker_pb.TaskSource{
{
Node: "10.0.0.1:8080",
VolumeId: 42,
},
},
TaskParams: &worker_pb.TaskParams_VacuumParams{
VacuumParams: &worker_pb.VacuumTaskParams{
GarbageThreshold: 0.33,
BatchSize: 500,
VerifyChecksum: true,
},
},
}
payload, err := proto.Marshal(expected)
if err != nil {
t.Fatalf("marshal payload: %v", err)
}
job := &plugin_pb.JobSpec{
JobId: "job-from-admin",
Parameters: map[string]*plugin_pb.ConfigValue{
"task_params_pb": {Kind: &plugin_pb.ConfigValue_BytesValue{BytesValue: payload}},
},
}
actual, err := decodeVacuumTaskParams(job)
if err != nil {
t.Fatalf("decodeVacuumTaskParams() err = %v", err)
}
if !proto.Equal(expected, actual) {
t.Fatalf("decoded params mismatch\nexpected: %+v\nactual: %+v", expected, actual)
}
}
func TestDecodeVacuumTaskParamsFallback(t *testing.T) {
job := &plugin_pb.JobSpec{
JobId: "job-2",
Parameters: map[string]*plugin_pb.ConfigValue{
"volume_id": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 7}},
"server": {Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "127.0.0.1:8080"}},
"collection": {Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "videos"}},
},
}
params, err := decodeVacuumTaskParams(job)
if err != nil {
t.Fatalf("decodeVacuumTaskParams() err = %v", err)
}
if params.TaskId != "job-2" || params.VolumeId != 7 || params.Collection != "videos" {
t.Fatalf("unexpected basic params: %+v", params)
}
if len(params.Sources) != 1 || params.Sources[0].Node != "127.0.0.1:8080" {
t.Fatalf("unexpected sources: %+v", params.Sources)
}
if params.GetVacuumParams() == nil {
t.Fatalf("expected fallback vacuum params")
}
}
func TestDeriveVacuumConfigAllowsZeroValues(t *testing.T) {
values := map[string]*plugin_pb.ConfigValue{
"garbage_threshold": {
Kind: &plugin_pb.ConfigValue_DoubleValue{DoubleValue: 0},
},
}
cfg := deriveVacuumConfig(values)
if cfg.GarbageThreshold != 0 {
t.Fatalf("expected garbage_threshold 0, got %v", cfg.GarbageThreshold)
}
}
func TestMasterAddressCandidates(t *testing.T) {
candidates := pluginworker.MasterAddressCandidates("localhost:9333")
if len(candidates) != 2 {
t.Fatalf("expected 2 candidates, got %d: %v", len(candidates), candidates)
}
seen := map[string]bool{}
for _, candidate := range candidates {
seen[candidate] = true
}
if !seen["localhost:9333"] {
t.Fatalf("expected original address in candidates: %v", candidates)
}
if !seen["localhost:19333"] {
t.Fatalf("expected grpc address in candidates: %v", candidates)
}
}
func TestShouldSkipDetectionByInterval(t *testing.T) {
if pluginworker.ShouldSkipDetectionByInterval(nil, 10) {
t.Fatalf("expected false when timestamp is nil")
}
if pluginworker.ShouldSkipDetectionByInterval(timestamppb.Now(), 0) {
t.Fatalf("expected false when min interval is zero")
}
recent := timestamppb.New(time.Now().Add(-5 * time.Second))
if !pluginworker.ShouldSkipDetectionByInterval(recent, 10) {
t.Fatalf("expected true for recent successful run")
}
old := timestamppb.New(time.Now().Add(-30 * time.Second))
if pluginworker.ShouldSkipDetectionByInterval(old, 10) {
t.Fatalf("expected false for old successful run")
}
}
func TestVacuumHandlerRejectsUnsupportedJobType(t *testing.T) {
handler := NewVacuumHandler(nil, 0)
err := handler.Detect(context.Background(), &plugin_pb.RunDetectionRequest{
JobType: "balance",
}, noopDetectionSender{})
if err == nil {
t.Fatalf("expected detect job type mismatch error")
}
err = handler.Execute(context.Background(), &plugin_pb.ExecuteJobRequest{
Job: &plugin_pb.JobSpec{JobId: "job-1", JobType: "balance"},
}, noopExecutionSender{})
if err == nil {
t.Fatalf("expected execute job type mismatch error")
}
}
func TestBuildExecutorActivity(t *testing.T) {
activity := pluginworker.BuildExecutorActivity("running", "vacuum in progress")
if activity == nil {
t.Fatalf("expected non-nil activity")
}
if activity.Source != plugin_pb.ActivitySource_ACTIVITY_SOURCE_EXECUTOR {
t.Fatalf("unexpected source: %v", activity.Source)
}
if activity.Stage != "running" {
t.Fatalf("unexpected stage: %q", activity.Stage)
}
if activity.Message != "vacuum in progress" {
t.Fatalf("unexpected message: %q", activity.Message)
}
if activity.CreatedAt == nil {
t.Fatalf("expected created_at timestamp")
}
}
func TestEmitVacuumDetectionDecisionTraceNoTasks(t *testing.T) {
sender := &recordingDetectionSender{}
config := NewDefaultConfig()
config.GarbageThreshold = 0.3
config.MinVolumeAgeSeconds = 0
metrics := []*workertypes.VolumeHealthMetrics{
{
VolumeID: 17,
GarbageRatio: 0,
Age: 218*time.Hour + 23*time.Minute,
},
{
VolumeID: 16,
GarbageRatio: 0,
Age: 218*time.Hour + 22*time.Minute,
},
{
VolumeID: 6,
GarbageRatio: 0,
Age: 90*time.Hour + 42*time.Minute,
},
}
if err := emitVacuumDetectionDecisionTrace(sender, metrics, config, nil); err != nil {
t.Fatalf("emitVacuumDetectionDecisionTrace error: %v", err)
}
if len(sender.events) < 4 {
t.Fatalf("expected at least 4 detection events, got %d", len(sender.events))
}
if sender.events[0].Source != plugin_pb.ActivitySource_ACTIVITY_SOURCE_DETECTOR {
t.Fatalf("expected detector source, got %v", sender.events[0].Source)
}
if !strings.Contains(sender.events[0].Message, "VACUUM: No tasks created for 3 volumes") {
t.Fatalf("unexpected summary message: %q", sender.events[0].Message)
}
if !strings.Contains(sender.events[1].Message, "VACUUM: Volume 17: garbage=0.00%") {
t.Fatalf("unexpected first detail message: %q", sender.events[1].Message)
}
}
func TestVacuumDescriptorHasNewFields(t *testing.T) {
handler := NewVacuumHandler(nil, 2)
desc := handler.Descriptor()
if desc == nil {
t.Fatal("descriptor is nil")
}
adminForm := desc.AdminConfigForm
if adminForm == nil {
t.Fatal("admin config form is nil")
}
if len(adminForm.Sections) == 0 {
t.Fatal("admin config form has no sections")
}
scopeSection := adminForm.Sections[0]
fieldNames := make(map[string]*plugin_pb.ConfigField)
for _, f := range scopeSection.Fields {
fieldNames[f.Name] = f
}
requiredFields := []string{
"collection_filter",
"volume_state",
"data_center_filter",
"rack_filter",
"node_filter",
}
for _, name := range requiredFields {
if _, ok := fieldNames[name]; !ok {
t.Errorf("missing field %q in admin config scope section", name)
}
}
// Verify volume_state is an enum with correct options.
vsField := fieldNames["volume_state"]
if vsField.FieldType != plugin_pb.ConfigFieldType_CONFIG_FIELD_TYPE_ENUM {
t.Errorf("volume_state field type = %v, want ENUM", vsField.FieldType)
}
if len(vsField.Options) != 3 {
t.Errorf("volume_state options count = %d, want 3", len(vsField.Options))
}
// Verify default values exist for new fields.
defaultKeys := []string{"volume_state", "data_center_filter", "rack_filter", "node_filter"}
for _, key := range defaultKeys {
if _, ok := adminForm.DefaultValues[key]; !ok {
t.Errorf("missing default value for %q", key)
}
}
// Verify volume_state default is ALL.
vsDefault := adminForm.DefaultValues["volume_state"]
if sv, ok := vsDefault.Kind.(*plugin_pb.ConfigValue_StringValue); !ok || sv.StringValue != "ALL" {
t.Errorf("volume_state default = %v, want ALL", vsDefault)
}
// Verify collection_filter description mentions ALL_COLLECTIONS.
cfField := fieldNames["collection_filter"]
if cfField.Placeholder != "ALL_COLLECTIONS" {
t.Errorf("collection_filter placeholder = %q, want ALL_COLLECTIONS", cfField.Placeholder)
}
}
func TestVacuumFiltersVolumeState(t *testing.T) {
metrics := []*workertypes.VolumeHealthMetrics{
{VolumeID: 1, FullnessRatio: 0.5}, // active
{VolumeID: 2, FullnessRatio: 1.5}, // full
{VolumeID: 3, FullnessRatio: 0.9}, // active
{VolumeID: 4, FullnessRatio: 1.01}, // full (at threshold)
}
tests := []struct {
name string
state pluginworker.VolumeState
wantIDs []uint32
}{
{"ALL returns all", pluginworker.VolumeStateAll, []uint32{1, 2, 3, 4}},
{"ACTIVE returns writable", pluginworker.VolumeStateActive, []uint32{1, 3}},
{"FULL returns read-only", pluginworker.VolumeStateFull, []uint32{2, 4}},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
filtered := pluginworker.FilterMetricsByVolumeState(metrics, tt.state)
if len(filtered) != len(tt.wantIDs) {
t.Fatalf("got %d metrics, want %d", len(filtered), len(tt.wantIDs))
}
for i, m := range filtered {
if m.VolumeID != tt.wantIDs[i] {
t.Errorf("filtered[%d].VolumeID = %d, want %d", i, m.VolumeID, tt.wantIDs[i])
}
}
})
}
}
func TestVacuumFiltersLocation(t *testing.T) {
metrics := []*workertypes.VolumeHealthMetrics{
{VolumeID: 1, DataCenter: "dc1", Rack: "r1", Server: "s1"},
{VolumeID: 2, DataCenter: "dc1", Rack: "r2", Server: "s2"},
{VolumeID: 3, DataCenter: "dc2", Rack: "r1", Server: "s3"},
{VolumeID: 4, DataCenter: "dc2", Rack: "r3", Server: "s4"},
}
tests := []struct {
name string
dc string
rack string
node string
wantIDs []uint32
}{
{"dc filter", "dc1", "", "", []uint32{1, 2}},
{"rack filter", "", "r1", "", []uint32{1, 3}},
{"node filter", "", "", "s2,s4", []uint32{2, 4}},
{"dc + rack", "dc1", "r1", "", []uint32{1}},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
filtered := pluginworker.FilterMetricsByLocation(metrics, tt.dc, tt.rack, tt.node)
if len(filtered) != len(tt.wantIDs) {
t.Fatalf("got %d metrics, want %d", len(filtered), len(tt.wantIDs))
}
for i, m := range filtered {
if m.VolumeID != tt.wantIDs[i] {
t.Errorf("filtered[%d].VolumeID = %d, want %d", i, m.VolumeID, tt.wantIDs[i])
}
}
})
}
}
type noopDetectionSender struct{}
func (noopDetectionSender) SendProposals(*plugin_pb.DetectionProposals) error { return nil }
func (noopDetectionSender) SendComplete(*plugin_pb.DetectionComplete) error { return nil }
func (noopDetectionSender) SendActivity(*plugin_pb.ActivityEvent) error { return nil }
type noopExecutionSender struct{}
func (noopExecutionSender) SendProgress(*plugin_pb.JobProgressUpdate) error { return nil }
func (noopExecutionSender) SendCompleted(*plugin_pb.JobCompleted) error { return nil }
type recordingDetectionSender struct {
proposals *plugin_pb.DetectionProposals
complete *plugin_pb.DetectionComplete
events []*plugin_pb.ActivityEvent
}
func (r *recordingDetectionSender) SendProposals(proposals *plugin_pb.DetectionProposals) error {
r.proposals = proposals
return nil
}
func (r *recordingDetectionSender) SendComplete(complete *plugin_pb.DetectionComplete) error {
r.complete = complete
return nil
}
func (r *recordingDetectionSender) SendActivity(event *plugin_pb.ActivityEvent) error {
if event != nil {
r.events = append(r.events, event)
}
return nil
}