aboutsummaryrefslogtreecommitdiff
path: root/weed/worker/tasks/base/generic_components.go
diff options
context:
space:
mode:
authorChris Lu <chrislusf@users.noreply.github.com>2025-07-30 12:38:03 -0700
committerGitHub <noreply@github.com>2025-07-30 12:38:03 -0700
commit891a2fb6ebc324329f5330a140b8cacff3899db4 (patch)
treed02aaa80a909e958aea831f206b3240b0237d7b7 /weed/worker/tasks/base/generic_components.go
parent64198dad8346fe284cbef944fe01ff0d062c147d (diff)
downloadseaweedfs-891a2fb6ebc324329f5330a140b8cacff3899db4.tar.xz
seaweedfs-891a2fb6ebc324329f5330a140b8cacff3899db4.zip
Admin: misc improvements on admin server and workers. EC now works. (#7055)
* initial design * added simulation as tests * reorganized the codebase to move the simulation framework and tests into their own dedicated package * integration test. ec worker task * remove "enhanced" reference * start master, volume servers, filer Current Status ✅ Master: Healthy and running (port 9333) ✅ Filer: Healthy and running (port 8888) ✅ Volume Servers: All 6 servers running (ports 8080-8085) 🔄 Admin/Workers: Will start when dependencies are ready * generate write load * tasks are assigned * admin start wtih grpc port. worker has its own working directory * Update .gitignore * working worker and admin. Task detection is not working yet. * compiles, detection uses volumeSizeLimitMB from master * compiles * worker retries connecting to admin * build and restart * rendering pending tasks * skip task ID column * sticky worker id * test canScheduleTaskNow * worker reconnect to admin * clean up logs * worker register itself first * worker can run ec work and report status but: 1. one volume should not be repeatedly worked on. 2. ec shards needs to be distributed and source data should be deleted. * move ec task logic * listing ec shards * local copy, ec. Need to distribute. * ec is mostly working now * distribution of ec shards needs improvement * need configuration to enable ec * show ec volumes * interval field UI component * rename * integration test with vauuming * garbage percentage threshold * fix warning * display ec shard sizes * fix ec volumes list * Update ui.go * show default values * ensure correct default value * MaintenanceConfig use ConfigField * use schema defined defaults * config * reduce duplication * refactor to use BaseUIProvider * each task register its schema * checkECEncodingCandidate use ecDetector * use vacuumDetector * use volumeSizeLimitMB * remove remove * remove unused * refactor * use new framework * remove v2 reference * refactor * left menu can scroll now * The maintenance manager was not being initialized when no data directory was configured for persistent storage. * saving config * Update task_config_schema_templ.go * enable/disable tasks * protobuf encoded task configurations * fix system settings * use ui component * remove logs * interface{} Reduction * reduce interface{} * reduce interface{} * avoid from/to map * reduce interface{} * refactor * keep it DRY * added logging * debug messages * debug level * debug * show the log caller line * use configured task policy * log level * handle admin heartbeat response * Update worker.go * fix EC rack and dc count * Report task status to admin server * fix task logging, simplify interface checking, use erasure_coding constants * factor in empty volume server during task planning * volume.list adds disk id * track disk id also * fix locking scheduled and manual scanning * add active topology * simplify task detector * ec task completed, but shards are not showing up * implement ec in ec_typed.go * adjust log level * dedup * implementing ec copying shards and only ecx files * use disk id when distributing ec shards 🎯 Planning: ActiveTopology creates DestinationPlan with specific TargetDisk 📦 Task Creation: maintenance_integration.go creates ECDestination with DiskId 🚀 Task Execution: EC task passes DiskId in VolumeEcShardsCopyRequest 💾 Volume Server: Receives disk_id and stores shards on specific disk (vs.store.Locations[req.DiskId]) 📂 File System: EC shards and metadata land in the exact disk directory planned * Delete original volume from all locations * clean up existing shard locations * local encoding and distributing * Update docker/admin_integration/EC-TESTING-README.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * check volume id range * simplify * fix tests * fix types * clean up logs and tests --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Diffstat (limited to 'weed/worker/tasks/base/generic_components.go')
-rw-r--r--weed/worker/tasks/base/generic_components.go129
1 files changed, 129 insertions, 0 deletions
diff --git a/weed/worker/tasks/base/generic_components.go b/weed/worker/tasks/base/generic_components.go
new file mode 100644
index 000000000..27ad1bb29
--- /dev/null
+++ b/weed/worker/tasks/base/generic_components.go
@@ -0,0 +1,129 @@
+package base
+
+import (
+ "time"
+
+ "github.com/seaweedfs/seaweedfs/weed/worker/types"
+)
+
+// GenericDetector implements TaskDetector using function-based logic
+type GenericDetector struct {
+ taskDef *TaskDefinition
+}
+
+// NewGenericDetector creates a detector from a task definition
+func NewGenericDetector(taskDef *TaskDefinition) *GenericDetector {
+ return &GenericDetector{taskDef: taskDef}
+}
+
+// GetTaskType returns the task type
+func (d *GenericDetector) GetTaskType() types.TaskType {
+ return d.taskDef.Type
+}
+
+// ScanForTasks scans using the task definition's detection function
+func (d *GenericDetector) ScanForTasks(volumeMetrics []*types.VolumeHealthMetrics, clusterInfo *types.ClusterInfo) ([]*types.TaskDetectionResult, error) {
+ if d.taskDef.DetectionFunc == nil {
+ return nil, nil
+ }
+ return d.taskDef.DetectionFunc(volumeMetrics, clusterInfo, d.taskDef.Config)
+}
+
+// ScanInterval returns the scan interval from task definition
+func (d *GenericDetector) ScanInterval() time.Duration {
+ if d.taskDef.ScanInterval > 0 {
+ return d.taskDef.ScanInterval
+ }
+ return 30 * time.Minute // Default
+}
+
+// IsEnabled returns whether this detector is enabled
+func (d *GenericDetector) IsEnabled() bool {
+ return d.taskDef.Config.IsEnabled()
+}
+
+// GenericScheduler implements TaskScheduler using function-based logic
+type GenericScheduler struct {
+ taskDef *TaskDefinition
+}
+
+// NewGenericScheduler creates a scheduler from a task definition
+func NewGenericScheduler(taskDef *TaskDefinition) *GenericScheduler {
+ return &GenericScheduler{taskDef: taskDef}
+}
+
+// GetTaskType returns the task type
+func (s *GenericScheduler) GetTaskType() types.TaskType {
+ return s.taskDef.Type
+}
+
+// CanScheduleNow determines if a task can be scheduled using the task definition's function
+func (s *GenericScheduler) CanScheduleNow(task *types.Task, runningTasks []*types.Task, availableWorkers []*types.Worker) bool {
+ if s.taskDef.SchedulingFunc == nil {
+ return s.defaultCanSchedule(task, runningTasks, availableWorkers)
+ }
+ return s.taskDef.SchedulingFunc(task, runningTasks, availableWorkers, s.taskDef.Config)
+}
+
+// defaultCanSchedule provides default scheduling logic
+func (s *GenericScheduler) defaultCanSchedule(task *types.Task, runningTasks []*types.Task, availableWorkers []*types.Worker) bool {
+ if !s.taskDef.Config.IsEnabled() {
+ return false
+ }
+
+ // Count running tasks of this type
+ runningCount := 0
+ for _, runningTask := range runningTasks {
+ if runningTask.Type == s.taskDef.Type {
+ runningCount++
+ }
+ }
+
+ // Check concurrency limit
+ maxConcurrent := s.taskDef.MaxConcurrent
+ if maxConcurrent <= 0 {
+ maxConcurrent = 1 // Default
+ }
+ if runningCount >= maxConcurrent {
+ return false
+ }
+
+ // Check if we have available workers
+ for _, worker := range availableWorkers {
+ if worker.CurrentLoad < worker.MaxConcurrent {
+ for _, capability := range worker.Capabilities {
+ if capability == s.taskDef.Type {
+ return true
+ }
+ }
+ }
+ }
+
+ return false
+}
+
+// GetPriority returns the priority for this task
+func (s *GenericScheduler) GetPriority(task *types.Task) types.TaskPriority {
+ return task.Priority
+}
+
+// GetMaxConcurrent returns max concurrent tasks
+func (s *GenericScheduler) GetMaxConcurrent() int {
+ if s.taskDef.MaxConcurrent > 0 {
+ return s.taskDef.MaxConcurrent
+ }
+ return 1 // Default
+}
+
+// GetDefaultRepeatInterval returns the default repeat interval
+func (s *GenericScheduler) GetDefaultRepeatInterval() time.Duration {
+ if s.taskDef.RepeatInterval > 0 {
+ return s.taskDef.RepeatInterval
+ }
+ return 24 * time.Hour // Default
+}
+
+// IsEnabled returns whether this scheduler is enabled
+func (s *GenericScheduler) IsEnabled() bool {
+ return s.taskDef.Config.IsEnabled()
+}