* 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>
232 lines
5.7 KiB
Go
232 lines
5.7 KiB
Go
package plugin
|
|
|
|
import (
|
|
"encoding/base64"
|
|
"sort"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/erasure_coding"
|
|
"google.golang.org/protobuf/proto"
|
|
)
|
|
|
|
func enrichTrackedJobParameters(jobType string, parameters map[string]interface{}) map[string]interface{} {
|
|
if len(parameters) == 0 {
|
|
return parameters
|
|
}
|
|
if _, exists := parameters["execution_plan"]; exists {
|
|
return parameters
|
|
}
|
|
|
|
taskParams, ok := decodeTaskParamsFromPlainParameters(parameters)
|
|
if !ok || taskParams == nil {
|
|
return parameters
|
|
}
|
|
|
|
plan := buildExecutionPlan(strings.TrimSpace(jobType), taskParams)
|
|
if plan == nil {
|
|
return parameters
|
|
}
|
|
|
|
enriched := make(map[string]interface{}, len(parameters)+1)
|
|
for key, value := range parameters {
|
|
enriched[key] = value
|
|
}
|
|
enriched["execution_plan"] = plan
|
|
return enriched
|
|
}
|
|
|
|
func decodeTaskParamsFromPlainParameters(parameters map[string]interface{}) (*worker_pb.TaskParams, bool) {
|
|
rawField, ok := parameters["task_params_pb"]
|
|
if !ok || rawField == nil {
|
|
return nil, false
|
|
}
|
|
|
|
fieldMap, ok := rawField.(map[string]interface{})
|
|
if !ok {
|
|
return nil, false
|
|
}
|
|
|
|
bytesValue, _ := fieldMap["bytes_value"].(string)
|
|
bytesValue = strings.TrimSpace(bytesValue)
|
|
if bytesValue == "" {
|
|
return nil, false
|
|
}
|
|
|
|
payload, err := base64.StdEncoding.DecodeString(bytesValue)
|
|
if err != nil {
|
|
return nil, false
|
|
}
|
|
|
|
params := &worker_pb.TaskParams{}
|
|
if err := proto.Unmarshal(payload, params); err != nil {
|
|
return nil, false
|
|
}
|
|
|
|
return params, true
|
|
}
|
|
|
|
func buildExecutionPlan(jobType string, params *worker_pb.TaskParams) map[string]interface{} {
|
|
if params == nil {
|
|
return nil
|
|
}
|
|
|
|
normalizedJobType := strings.TrimSpace(jobType)
|
|
if normalizedJobType == "" && params.GetErasureCodingParams() != nil {
|
|
normalizedJobType = "erasure_coding"
|
|
}
|
|
|
|
switch normalizedJobType {
|
|
case "erasure_coding":
|
|
return buildErasureCodingExecutionPlan(params)
|
|
default:
|
|
return nil
|
|
}
|
|
}
|
|
|
|
func buildErasureCodingExecutionPlan(params *worker_pb.TaskParams) map[string]interface{} {
|
|
if params == nil {
|
|
return nil
|
|
}
|
|
|
|
ecParams := params.GetErasureCodingParams()
|
|
if ecParams == nil {
|
|
return nil
|
|
}
|
|
|
|
dataShards := int(ecParams.DataShards)
|
|
if dataShards <= 0 {
|
|
dataShards = int(erasure_coding.DataShardsCount)
|
|
}
|
|
parityShards := int(ecParams.ParityShards)
|
|
if parityShards <= 0 {
|
|
parityShards = int(erasure_coding.ParityShardsCount)
|
|
}
|
|
totalShards := dataShards + parityShards
|
|
|
|
sources := make([]map[string]interface{}, 0, len(params.Sources))
|
|
for _, source := range params.Sources {
|
|
if source == nil {
|
|
continue
|
|
}
|
|
sources = append(sources, buildExecutionEndpoint(
|
|
source.Node,
|
|
source.DataCenter,
|
|
source.Rack,
|
|
source.VolumeId,
|
|
source.ShardIds,
|
|
dataShards,
|
|
))
|
|
}
|
|
|
|
targets := make([]map[string]interface{}, 0, len(params.Targets))
|
|
shardAssignments := make([]map[string]interface{}, 0, totalShards)
|
|
for targetIndex, target := range params.Targets {
|
|
if target == nil {
|
|
continue
|
|
}
|
|
|
|
targets = append(targets, buildExecutionEndpoint(
|
|
target.Node,
|
|
target.DataCenter,
|
|
target.Rack,
|
|
target.VolumeId,
|
|
target.ShardIds,
|
|
dataShards,
|
|
))
|
|
|
|
for _, shardID := range normalizeShardIDs(target.ShardIds) {
|
|
kind, label := classifyShardID(shardID, dataShards)
|
|
shardAssignments = append(shardAssignments, map[string]interface{}{
|
|
"shard_id": shardID,
|
|
"kind": kind,
|
|
"label": label,
|
|
"target_index": targetIndex + 1,
|
|
"target_node": strings.TrimSpace(target.Node),
|
|
"target_data_center": strings.TrimSpace(target.DataCenter),
|
|
"target_rack": strings.TrimSpace(target.Rack),
|
|
"target_volume_id": int(target.VolumeId),
|
|
})
|
|
}
|
|
}
|
|
sort.Slice(shardAssignments, func(i, j int) bool {
|
|
left, _ := shardAssignments[i]["shard_id"].(int)
|
|
right, _ := shardAssignments[j]["shard_id"].(int)
|
|
return left < right
|
|
})
|
|
|
|
plan := map[string]interface{}{
|
|
"job_type": "erasure_coding",
|
|
"task_id": strings.TrimSpace(params.TaskId),
|
|
"volume_id": int(params.VolumeId),
|
|
"collection": strings.TrimSpace(params.Collection),
|
|
"data_shards": dataShards,
|
|
"parity_shards": parityShards,
|
|
"total_shards": totalShards,
|
|
"sources": sources,
|
|
"targets": targets,
|
|
"source_count": len(sources),
|
|
"target_count": len(targets),
|
|
}
|
|
|
|
if len(shardAssignments) > 0 {
|
|
plan["shard_assignments"] = shardAssignments
|
|
}
|
|
|
|
return plan
|
|
}
|
|
|
|
func buildExecutionEndpoint(
|
|
node string,
|
|
dataCenter string,
|
|
rack string,
|
|
volumeID uint32,
|
|
shardIDs []uint32,
|
|
dataShardCount int,
|
|
) map[string]interface{} {
|
|
allShards := normalizeShardIDs(shardIDs)
|
|
dataShards := make([]int, 0, len(allShards))
|
|
parityShards := make([]int, 0, len(allShards))
|
|
for _, shardID := range allShards {
|
|
if shardID < dataShardCount {
|
|
dataShards = append(dataShards, shardID)
|
|
} else {
|
|
parityShards = append(parityShards, shardID)
|
|
}
|
|
}
|
|
|
|
return map[string]interface{}{
|
|
"node": strings.TrimSpace(node),
|
|
"data_center": strings.TrimSpace(dataCenter),
|
|
"rack": strings.TrimSpace(rack),
|
|
"volume_id": int(volumeID),
|
|
"shard_ids": allShards,
|
|
"data_shard_ids": dataShards,
|
|
"parity_shard_ids": parityShards,
|
|
}
|
|
}
|
|
|
|
func normalizeShardIDs(shardIDs []uint32) []int {
|
|
if len(shardIDs) == 0 {
|
|
return nil
|
|
}
|
|
|
|
out := make([]int, 0, len(shardIDs))
|
|
for _, shardID := range shardIDs {
|
|
out = append(out, int(shardID))
|
|
}
|
|
sort.Ints(out)
|
|
return out
|
|
}
|
|
|
|
func classifyShardID(shardID int, dataShardCount int) (kind string, label string) {
|
|
if dataShardCount <= 0 {
|
|
dataShardCount = int(erasure_coding.DataShardsCount)
|
|
}
|
|
if shardID < dataShardCount {
|
|
return "data", "D" + strconv.Itoa(shardID)
|
|
}
|
|
return "parity", "P" + strconv.Itoa(shardID)
|
|
}
|