Files
seaweedFS/weed/plugin/worker/erasure_coding_handler_test.go
Chris Lu 8ec9ff4a12 Refactor plugin system and migrate worker runtime (#8369)
* admin: add plugin runtime UI page and route wiring

* pb: add plugin gRPC contract and generated bindings

* admin/plugin: implement worker registry, runtime, monitoring, and config store

* admin/dash: wire plugin runtime and expose plugin workflow APIs

* command: add flags to enable plugin runtime

* admin: rename remaining plugin v2 wording to plugin

* admin/plugin: add detectable job type registry helper

* admin/plugin: add scheduled detection and dispatch orchestration

* admin/plugin: prefetch job type descriptors when workers connect

* admin/plugin: add known job type discovery API and UI

* admin/plugin: refresh design doc to match current implementation

* admin/plugin: enforce per-worker scheduler concurrency limits

* admin/plugin: use descriptor runtime defaults for scheduler policy

* admin/ui: auto-load first known plugin job type on page open

* admin/plugin: bootstrap persisted config from descriptor defaults

* admin/plugin: dedupe scheduled proposals by dedupe key

* admin/ui: add job type and state filters for plugin monitoring

* admin/ui: add per-job-type plugin activity summary

* admin/plugin: split descriptor read API from schema refresh

* admin/ui: keep plugin summary metrics global while tables are filtered

* admin/plugin: retry executor reservation before timing out

* admin/plugin: expose scheduler states for monitoring

* admin/ui: show per-job-type scheduler states in plugin monitor

* pb/plugin: rename protobuf package to plugin

* admin/plugin: rename pluginRuntime wiring to plugin

* admin/plugin: remove runtime naming from plugin APIs and UI

* admin/plugin: rename runtime files to plugin naming

* admin/plugin: persist jobs and activities for monitor recovery

* admin/plugin: lease one detector worker per job type

* admin/ui: show worker load from plugin heartbeats

* admin/plugin: skip stale workers for detector and executor picks

* plugin/worker: add plugin worker command and stream runtime scaffold

* plugin/worker: implement vacuum detect and execute handlers

* admin/plugin: document external vacuum plugin worker starter

* command: update plugin.worker help to reflect implemented flow

* command/admin: drop legacy Plugin V2 label

* plugin/worker: validate vacuum job type and respect min interval

* plugin/worker: test no-op detect when min interval not elapsed

* command/admin: document plugin.worker external process

* plugin/worker: advertise configured concurrency in hello

* command/plugin.worker: add jobType handler selection

* command/plugin.worker: test handler selection by job type

* command/plugin.worker: persist worker id in workingDir

* admin/plugin: document plugin.worker jobType and workingDir flags

* plugin/worker: support cancel request for in-flight work

* plugin/worker: test cancel request acknowledgements

* command/plugin.worker: document workingDir and jobType behavior

* plugin/worker: emit executor activity events for monitor

* plugin/worker: test executor activity builder

* admin/plugin: send last successful run in detection request

* admin/plugin: send cancel request when detect or execute context ends

* admin/plugin: document worker cancel request responsibility

* admin/handlers: expose plugin scheduler states API in no-auth mode

* admin/handlers: test plugin scheduler states route registration

* admin/plugin: keep worker id on worker-generated activity records

* admin/plugin: test worker id propagation in monitor activities

* admin/dash: always initialize plugin service

* command/admin: remove plugin enable flags and default to enabled

* admin/dash: drop pluginEnabled constructor parameter

* admin/plugin UI: stop checking plugin enabled state

* admin/plugin: remove docs for plugin enable flags

* admin/dash: remove unused plugin enabled check method

* admin/dash: fallback to in-memory plugin init when dataDir fails

* admin/plugin API: expose worker gRPC port in status

* command/plugin.worker: resolve admin gRPC port via plugin status

* split plugin UI into overview/configuration/monitoring pages

* Update layout_templ.go

* add volume_balance plugin worker handler

* wire plugin.worker CLI for volume_balance job type

* add erasure_coding plugin worker handler

* wire plugin.worker CLI for erasure_coding job type

* support multi-job handlers in plugin worker runtime

* allow plugin.worker jobType as comma-separated list

* admin/plugin UI: rename to Workers and simplify config view

* plugin worker: queue detection requests instead of capacity reject

* Update plugin_worker.go

* plugin volume_balance: remove force_move/timeout from worker config UI

* plugin erasure_coding: enforce local working dir and cleanup

* admin/plugin UI: rename admin settings to job scheduling

* admin/plugin UI: persist and robustly render detection results

* admin/plugin: record and return detection trace metadata

* admin/plugin UI: show detection process and decision trace

* plugin: surface detector decision trace as activities

* mini: start a plugin worker by default

* admin/plugin UI: split monitoring into detection and execution tabs

* plugin worker: emit detection decision trace for EC and balance

* admin workers UI: split monitoring into detection and execution pages

* plugin scheduler: skip proposals for active assigned/running jobs

* admin workers UI: add job queue tab

* plugin worker: add dummy stress detector and executor job type

* admin workers UI: reorder tabs to detection queue execution

* admin workers UI: regenerate plugin template

* plugin defaults: include dummy stress and add stress tests

* plugin dummy stress: rotate detection selections across runs

* plugin scheduler: remove cross-run proposal dedupe

* plugin queue: track pending scheduled jobs

* plugin scheduler: wait for executor capacity before dispatch

* plugin scheduler: skip detection when waiting backlog is high

* plugin: add disk-backed job detail API and persistence

* admin ui: show plugin job detail modal from job id links

* plugin: generate unique job ids instead of reusing proposal ids

* plugin worker: emit heartbeats on work state changes

* plugin registry: round-robin tied executor and detector picks

* add temporary EC overnight stress runner

* plugin job details: persist and render EC execution plans

* ec volume details: color data and parity shard badges

* shard labels: keep parity ids numeric and color-only distinction

* admin: remove legacy maintenance UI routes and templates

* admin: remove dead maintenance endpoint helpers

* Update layout_templ.go

* remove dummy_stress worker and command support

* refactor plugin UI to job-type top tabs and sub-tabs

* migrate weed worker command to plugin runtime

* remove plugin.worker command and keep worker runtime with metrics

* update helm worker args for jobType and execution flags

* set plugin scheduling defaults to global 16 and per-worker 4

* stress: fix RPC context reuse and remove redundant variables in ec_stress_runner

* admin/plugin: fix lifecycle races, safe channel operations, and terminal state constants

* admin/dash: randomize job IDs and fix priority zero-value overwrite in plugin API

* admin/handlers: implement buffered rendering to prevent response corruption

* admin/plugin: implement debounced persistence flusher and optimize BuildJobDetail memory lookups

* admin/plugin: fix priority overwrite and implement bounded wait in scheduler reserve

* admin/plugin: implement atomic file writes and fix run record side effects

* admin/plugin: use P prefix for parity shard labels in execution plans

* admin/plugin: enable parallel execution for cancellation tests

* admin: refactor time.Time fields to pointers for better JSON omitempty support

* admin/plugin: implement pointer-safe time assignments and comparisons in plugin core

* admin/plugin: fix time assignment and sorting logic in plugin monitor after pointer refactor

* admin/plugin: update scheduler activity tracking to use time pointers

* admin/plugin: fix time-based run history trimming after pointer refactor

* admin/dash: fix JobSpec struct literal in plugin API after pointer refactor

* admin/view: add D/P prefixes to EC shard badges for UI consistency

* admin/plugin: use lifecycle-aware context for schema prefetching

* Update ec_volume_details_templ.go

* admin/stress: fix proposal sorting and log volume cleanup errors

* stress: refine ec stress runner with math/rand and collection name

- Added Collection field to VolumeEcShardsDeleteRequest for correct filename construction.
- Replaced crypto/rand with seeded math/rand PRNG for bulk payloads.
- Added documentation for EcMinAge zero-value behavior.
- Added logging for ignored errors in volume/shard deletion.

* admin: return internal server error for plugin store failures

Changed error status code from 400 Bad Request to 500 Internal Server Error for failures in GetPluginJobDetail to correctly reflect server-side errors.

* admin: implement safe channel sends and graceful shutdown sync

- Added sync.WaitGroup to Plugin struct to manage background goroutines.
- Implemented safeSendCh helper using recover() to prevent panics on closed channels.
- Ensured Shutdown() waits for all background operations to complete.

* admin: robustify plugin monitor with nil-safe time and record init

- Standardized nil-safe assignment for *time.Time pointers (CreatedAt, UpdatedAt, CompletedAt).
- Ensured persistJobDetailSnapshot initializes new records correctly if they don't exist on disk.
- Fixed debounced persistence to trigger immediate write on job completion.

* admin: improve scheduler shutdown behavior and logic guards

- Replaced brittle error string matching with explicit r.shutdownCh selection for shutdown detection.
- Removed redundant nil guard in buildScheduledJobSpec.
- Standardized WaitGroup usage for schedulerLoop.

* admin: implement deep copy for job parameters and atomic write fixes

- Implemented deepCopyGenericValue and used it in cloneTrackedJob to prevent shared state.
- Ensured atomicWriteFile creates parent directories before writing.

* admin: remove unreachable branch in shard classification

Removed an unreachable 'totalShards <= 0' check in classifyShardID as dataShards and parityShards are already guarded.

* admin: secure UI links and use canonical shard constants

- Added rel="noopener noreferrer" to external links for security.
- Replaced magic number 14 with erasure_coding.TotalShardsCount.
- Used renderEcShardBadge for missing shard list consistency.

* admin: stabilize plugin tests and fix regressions

- Composed a robust plugin_monitor_test.go to handle asynchronous persistence.
- Updated all time.Time literals to use timeToPtr helper.
- Added explicit Shutdown() calls in tests to synchronize with debounced writes.
- Fixed syntax errors and orphaned struct literals in tests.

* Potential fix for code scanning alert no. 278: Slice memory allocation with excessive size value

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* Potential fix for code scanning alert no. 283: Uncontrolled data used in path expression

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* admin: finalize refinements for error handling, scheduler, and race fixes

- Standardized HTTP 500 status codes for store failures in plugin_api.go.
- Tracked scheduled detection goroutines with sync.WaitGroup for safe shutdown.
- Fixed race condition in safeSendDetectionComplete by extracting channel under lock.
- Implemented deep copy for JobActivity details.
- Used defaultDirPerm constant in atomicWriteFile.

* test(ec): migrate admin dockertest to plugin APIs

* admin/plugin_api: fix RunPluginJobTypeAPI to return 500 for server-side detection/filter errors

* admin/plugin_api: fix ExecutePluginJobAPI to return 500 for job execution failures

* admin/plugin_api: limit parseProtoJSONBody request body to 1MB to prevent unbounded memory usage

* admin/plugin: consolidate regex to package-level validJobTypePattern; add char validation to sanitizeJobID

* admin/plugin: fix racy Shutdown channel close with sync.Once

* admin/plugin: track sendLoop and recv goroutines in WorkerStream with r.wg

* admin/plugin: document writeProtoFiles atomicity — .pb is source of truth, .json is human-readable only

* admin/plugin: extract activityLess helper to deduplicate nil-safe OccurredAt sort comparators

* test/ec: check http.NewRequest errors to prevent nil req panics

* test/ec: replace deprecated ioutil/math/rand, fix stale step comment 5.1→3.1

* plugin(ec): raise default detection and scheduling throughput limits

* topology: include empty disks in volume list and EC capacity fallback

* topology: remove hard 10-task cap for detection planning

* Update ec_volume_details_templ.go

* adjust default

* fix tests

---------

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2026-02-18 13:42:41 -08:00

330 lines
10 KiB
Go

package pluginworker
import (
"context"
"strings"
"testing"
"time"
"github.com/seaweedfs/seaweedfs/weed/pb/plugin_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
ecstorage "github.com/seaweedfs/seaweedfs/weed/storage/erasure_coding"
erasurecodingtask "github.com/seaweedfs/seaweedfs/weed/worker/tasks/erasure_coding"
workertypes "github.com/seaweedfs/seaweedfs/weed/worker/types"
"google.golang.org/protobuf/proto"
"google.golang.org/protobuf/types/known/timestamppb"
)
func TestDecodeErasureCodingTaskParamsFromPayload(t *testing.T) {
expected := &worker_pb.TaskParams{
TaskId: "task-ec-1",
VolumeId: 88,
Collection: "images",
Sources: []*worker_pb.TaskSource{
{
Node: "10.0.0.1:8080",
VolumeId: 88,
},
},
Targets: []*worker_pb.TaskTarget{
{
Node: "10.0.0.2:8080",
VolumeId: 88,
ShardIds: []uint32{0, 10},
},
},
TaskParams: &worker_pb.TaskParams_ErasureCodingParams{
ErasureCodingParams: &worker_pb.ErasureCodingTaskParams{
DataShards: ecstorage.DataShardsCount,
ParityShards: ecstorage.ParityShardsCount,
WorkingDir: "/tmp/ec-work",
CleanupSource: 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 := decodeErasureCodingTaskParams(job)
if err != nil {
t.Fatalf("decodeErasureCodingTaskParams() err = %v", err)
}
if !proto.Equal(expected, actual) {
t.Fatalf("decoded params mismatch\nexpected: %+v\nactual: %+v", expected, actual)
}
}
func TestDecodeErasureCodingTaskParamsFallback(t *testing.T) {
targetServers := make([]string, 0, ecstorage.TotalShardsCount)
for i := 0; i < ecstorage.TotalShardsCount; i++ {
targetServers = append(targetServers, "10.0.0."+string(rune('a'+i))+":8080")
}
job := &plugin_pb.JobSpec{
JobId: "job-ec-2",
Parameters: map[string]*plugin_pb.ConfigValue{
"volume_id": {
Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 7},
},
"source_server": {
Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "127.0.0.1:8080"},
},
"target_servers": {
Kind: &plugin_pb.ConfigValue_StringList{
StringList: &plugin_pb.StringList{Values: targetServers},
},
},
"collection": {
Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "videos"},
},
},
}
params, err := decodeErasureCodingTaskParams(job)
if err != nil {
t.Fatalf("decodeErasureCodingTaskParams() err = %v", err)
}
if params.TaskId != "job-ec-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 len(params.Targets) != ecstorage.TotalShardsCount {
t.Fatalf("unexpected target count: %d", len(params.Targets))
}
if params.GetErasureCodingParams() == nil {
t.Fatalf("expected fallback erasure coding params")
}
}
func TestDeriveErasureCodingWorkerConfig(t *testing.T) {
values := map[string]*plugin_pb.ConfigValue{
"quiet_for_seconds": {
Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 720},
},
"fullness_ratio": {
Kind: &plugin_pb.ConfigValue_DoubleValue{DoubleValue: 0.92},
},
"min_size_mb": {
Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 128},
},
"min_interval_seconds": {
Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 55},
},
}
cfg := deriveErasureCodingWorkerConfig(values)
if cfg.TaskConfig.QuietForSeconds != 720 {
t.Fatalf("expected quiet_for_seconds 720, got %d", cfg.TaskConfig.QuietForSeconds)
}
if cfg.TaskConfig.FullnessRatio != 0.92 {
t.Fatalf("expected fullness_ratio 0.92, got %v", cfg.TaskConfig.FullnessRatio)
}
if cfg.TaskConfig.MinSizeMB != 128 {
t.Fatalf("expected min_size_mb 128, got %d", cfg.TaskConfig.MinSizeMB)
}
if cfg.MinIntervalSeconds != 55 {
t.Fatalf("expected min_interval_seconds 55, got %d", cfg.MinIntervalSeconds)
}
}
func TestBuildErasureCodingProposal(t *testing.T) {
params := &worker_pb.TaskParams{
TaskId: "ec-task-1",
VolumeId: 99,
Collection: "c1",
Sources: []*worker_pb.TaskSource{
{
Node: "source-a:8080",
VolumeId: 99,
},
},
Targets: []*worker_pb.TaskTarget{
{
Node: "target-a:8080",
VolumeId: 99,
ShardIds: []uint32{0, 10},
},
{
Node: "target-b:8080",
VolumeId: 99,
ShardIds: []uint32{1, 11},
},
},
TaskParams: &worker_pb.TaskParams_ErasureCodingParams{
ErasureCodingParams: &worker_pb.ErasureCodingTaskParams{
DataShards: ecstorage.DataShardsCount,
ParityShards: ecstorage.ParityShardsCount,
},
},
}
result := &workertypes.TaskDetectionResult{
TaskID: "ec-task-1",
TaskType: workertypes.TaskTypeErasureCoding,
VolumeID: 99,
Server: "source-a",
Collection: "c1",
Priority: workertypes.TaskPriorityLow,
Reason: "quiet and full",
TypedParams: params,
}
proposal, err := buildErasureCodingProposal(result)
if err != nil {
t.Fatalf("buildErasureCodingProposal() err = %v", err)
}
if proposal.JobType != "erasure_coding" {
t.Fatalf("unexpected job type %q", proposal.JobType)
}
if proposal.Parameters["task_params_pb"] == nil {
t.Fatalf("expected serialized task params")
}
if proposal.Labels["source_node"] != "source-a:8080" {
t.Fatalf("unexpected source label %q", proposal.Labels["source_node"])
}
}
func TestErasureCodingHandlerRejectsUnsupportedJobType(t *testing.T) {
handler := NewErasureCodingHandler(nil)
err := handler.Detect(context.Background(), &plugin_pb.RunDetectionRequest{
JobType: "vacuum",
}, 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: "vacuum"},
}, noopExecutionSender{})
if err == nil {
t.Fatalf("expected execute job type mismatch error")
}
}
func TestErasureCodingHandlerDetectSkipsByMinInterval(t *testing.T) {
handler := NewErasureCodingHandler(nil)
sender := &recordingDetectionSender{}
err := handler.Detect(context.Background(), &plugin_pb.RunDetectionRequest{
JobType: "erasure_coding",
LastSuccessfulRun: timestamppb.New(time.Now().Add(-3 * time.Second)),
WorkerConfigValues: map[string]*plugin_pb.ConfigValue{
"min_interval_seconds": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 10}},
},
}, sender)
if err != nil {
t.Fatalf("detect returned err = %v", err)
}
if sender.proposals == nil {
t.Fatalf("expected proposals message")
}
if len(sender.proposals.Proposals) != 0 {
t.Fatalf("expected zero proposals, got %d", len(sender.proposals.Proposals))
}
if sender.complete == nil || !sender.complete.Success {
t.Fatalf("expected successful completion message")
}
if len(sender.events) == 0 {
t.Fatalf("expected detector activity events")
}
if !strings.Contains(sender.events[0].Message, "min interval") {
t.Fatalf("unexpected skip-by-interval message: %q", sender.events[0].Message)
}
}
func TestEmitErasureCodingDetectionDecisionTraceNoTasks(t *testing.T) {
sender := &recordingDetectionSender{}
config := erasurecodingtask.NewDefaultConfig()
config.QuietForSeconds = 5 * 60
config.MinSizeMB = 30
config.FullnessRatio = 0.91
metrics := []*workertypes.VolumeHealthMetrics{
{
VolumeID: 20,
Size: 0,
Age: 218*time.Hour + 41*time.Minute,
FullnessRatio: 0,
},
{
VolumeID: 27,
Size: uint64(16 * 1024 * 1024 / 10),
Age: 91*time.Hour + time.Minute,
FullnessRatio: 0.002,
},
{
VolumeID: 12,
Size: 0,
Age: 219*time.Hour + 49*time.Minute,
FullnessRatio: 0,
},
}
if err := emitErasureCodingDetectionDecisionTrace(sender, metrics, config, nil); err != nil {
t.Fatalf("emitErasureCodingDetectionDecisionTrace 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, "EC detection: No tasks created for 3 volumes") {
t.Fatalf("unexpected summary message: %q", sender.events[0].Message)
}
if !strings.Contains(sender.events[1].Message, "ERASURE CODING: Volume 20: size=0.0MB") {
t.Fatalf("unexpected first detail message: %q", sender.events[1].Message)
}
}
func TestErasureCodingDescriptorOmitsLocalExecutionFields(t *testing.T) {
descriptor := NewErasureCodingHandler(nil).Descriptor()
if descriptor == nil || descriptor.WorkerConfigForm == nil {
t.Fatalf("expected worker config form in descriptor")
}
if workerConfigFormHasField(descriptor.WorkerConfigForm, "working_dir") {
t.Fatalf("unexpected working_dir in erasure coding worker config form")
}
if workerConfigFormHasField(descriptor.WorkerConfigForm, "cleanup_source") {
t.Fatalf("unexpected cleanup_source in erasure coding worker config form")
}
}
func TestApplyErasureCodingExecutionDefaultsForcesLocalFields(t *testing.T) {
params := &worker_pb.TaskParams{
TaskId: "ec-test",
VolumeId: 100,
TaskParams: &worker_pb.TaskParams_ErasureCodingParams{
ErasureCodingParams: &worker_pb.ErasureCodingTaskParams{
DataShards: ecstorage.DataShardsCount,
ParityShards: ecstorage.ParityShardsCount,
WorkingDir: "/tmp/custom-from-job",
CleanupSource: false,
},
},
}
applyErasureCodingExecutionDefaults(params, nil)
ecParams := params.GetErasureCodingParams()
if ecParams == nil {
t.Fatalf("expected erasure coding params")
}
if ecParams.WorkingDir != defaultErasureCodingWorkingDir() {
t.Fatalf("expected local working_dir %q, got %q", defaultErasureCodingWorkingDir(), ecParams.WorkingDir)
}
if !ecParams.CleanupSource {
t.Fatalf("expected cleanup_source true")
}
}