aboutsummaryrefslogtreecommitdiff
path: root/weed/worker/tasks/base/task_definition.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/task_definition.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/task_definition.go')
-rw-r--r--weed/worker/tasks/base/task_definition.go272
1 files changed, 272 insertions, 0 deletions
diff --git a/weed/worker/tasks/base/task_definition.go b/weed/worker/tasks/base/task_definition.go
new file mode 100644
index 000000000..6689d9c81
--- /dev/null
+++ b/weed/worker/tasks/base/task_definition.go
@@ -0,0 +1,272 @@
+package base
+
+import (
+ "fmt"
+ "reflect"
+ "strings"
+ "time"
+
+ "github.com/seaweedfs/seaweedfs/weed/admin/config"
+ "github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
+ "github.com/seaweedfs/seaweedfs/weed/worker/types"
+)
+
+// TaskDefinition encapsulates everything needed to define a complete task type
+type TaskDefinition struct {
+ // Basic task information
+ Type types.TaskType
+ Name string
+ DisplayName string
+ Description string
+ Icon string
+ Capabilities []string
+
+ // Task configuration
+ Config TaskConfig
+ ConfigSpec ConfigSpec
+
+ // Task creation
+ CreateTask func(params types.TaskParams) (types.TaskInterface, error)
+
+ // Detection logic
+ DetectionFunc func(metrics []*types.VolumeHealthMetrics, info *types.ClusterInfo, config TaskConfig) ([]*types.TaskDetectionResult, error)
+ ScanInterval time.Duration
+
+ // Scheduling logic
+ SchedulingFunc func(task *types.Task, running []*types.Task, workers []*types.Worker, config TaskConfig) bool
+ MaxConcurrent int
+ RepeatInterval time.Duration
+}
+
+// TaskConfig provides a configuration interface that supports type-safe defaults
+type TaskConfig interface {
+ config.ConfigWithDefaults // Extends ConfigWithDefaults for type-safe schema operations
+ IsEnabled() bool
+ SetEnabled(bool)
+ ToTaskPolicy() *worker_pb.TaskPolicy
+ FromTaskPolicy(policy *worker_pb.TaskPolicy) error
+}
+
+// ConfigSpec defines the configuration schema
+type ConfigSpec struct {
+ Fields []*config.Field
+}
+
+// BaseConfig provides common configuration fields with reflection-based serialization
+type BaseConfig struct {
+ Enabled bool `json:"enabled"`
+ ScanIntervalSeconds int `json:"scan_interval_seconds"`
+ MaxConcurrent int `json:"max_concurrent"`
+}
+
+// IsEnabled returns whether the task is enabled
+func (c *BaseConfig) IsEnabled() bool {
+ return c.Enabled
+}
+
+// SetEnabled sets whether the task is enabled
+func (c *BaseConfig) SetEnabled(enabled bool) {
+ c.Enabled = enabled
+}
+
+// Validate validates the base configuration
+func (c *BaseConfig) Validate() error {
+ // Common validation logic
+ return nil
+}
+
+// StructToMap converts any struct to a map using reflection
+func StructToMap(obj interface{}) map[string]interface{} {
+ result := make(map[string]interface{})
+ val := reflect.ValueOf(obj)
+
+ // Handle pointer to struct
+ if val.Kind() == reflect.Ptr {
+ val = val.Elem()
+ }
+
+ if val.Kind() != reflect.Struct {
+ return result
+ }
+
+ typ := val.Type()
+
+ for i := 0; i < val.NumField(); i++ {
+ field := val.Field(i)
+ fieldType := typ.Field(i)
+
+ // Skip unexported fields
+ if !field.CanInterface() {
+ continue
+ }
+
+ // Handle embedded structs recursively (before JSON tag check)
+ if field.Kind() == reflect.Struct && fieldType.Anonymous {
+ embeddedMap := StructToMap(field.Interface())
+ for k, v := range embeddedMap {
+ result[k] = v
+ }
+ continue
+ }
+
+ // Get JSON tag name
+ jsonTag := fieldType.Tag.Get("json")
+ if jsonTag == "" || jsonTag == "-" {
+ continue
+ }
+
+ // Remove options like ",omitempty"
+ if commaIdx := strings.Index(jsonTag, ","); commaIdx >= 0 {
+ jsonTag = jsonTag[:commaIdx]
+ }
+
+ result[jsonTag] = field.Interface()
+ }
+ return result
+}
+
+// MapToStruct loads data from map into struct using reflection
+func MapToStruct(data map[string]interface{}, obj interface{}) error {
+ val := reflect.ValueOf(obj)
+
+ // Must be pointer to struct
+ if val.Kind() != reflect.Ptr || val.Elem().Kind() != reflect.Struct {
+ return fmt.Errorf("obj must be pointer to struct")
+ }
+
+ val = val.Elem()
+ typ := val.Type()
+
+ for i := 0; i < val.NumField(); i++ {
+ field := val.Field(i)
+ fieldType := typ.Field(i)
+
+ // Skip unexported fields
+ if !field.CanSet() {
+ continue
+ }
+
+ // Handle embedded structs recursively (before JSON tag check)
+ if field.Kind() == reflect.Struct && fieldType.Anonymous {
+ err := MapToStruct(data, field.Addr().Interface())
+ if err != nil {
+ return err
+ }
+ continue
+ }
+
+ // Get JSON tag name
+ jsonTag := fieldType.Tag.Get("json")
+ if jsonTag == "" || jsonTag == "-" {
+ continue
+ }
+
+ // Remove options like ",omitempty"
+ if commaIdx := strings.Index(jsonTag, ","); commaIdx >= 0 {
+ jsonTag = jsonTag[:commaIdx]
+ }
+
+ if value, exists := data[jsonTag]; exists {
+ err := setFieldValue(field, value)
+ if err != nil {
+ return fmt.Errorf("failed to set field %s: %v", jsonTag, err)
+ }
+ }
+ }
+
+ return nil
+}
+
+// ToMap converts config to map using reflection
+// ToTaskPolicy converts BaseConfig to protobuf (partial implementation)
+// Note: Concrete implementations should override this to include task-specific config
+func (c *BaseConfig) ToTaskPolicy() *worker_pb.TaskPolicy {
+ return &worker_pb.TaskPolicy{
+ Enabled: c.Enabled,
+ MaxConcurrent: int32(c.MaxConcurrent),
+ RepeatIntervalSeconds: int32(c.ScanIntervalSeconds),
+ CheckIntervalSeconds: int32(c.ScanIntervalSeconds),
+ // TaskConfig field should be set by concrete implementations
+ }
+}
+
+// FromTaskPolicy loads BaseConfig from protobuf (partial implementation)
+// Note: Concrete implementations should override this to handle task-specific config
+func (c *BaseConfig) FromTaskPolicy(policy *worker_pb.TaskPolicy) error {
+ if policy == nil {
+ return fmt.Errorf("policy is nil")
+ }
+ c.Enabled = policy.Enabled
+ c.MaxConcurrent = int(policy.MaxConcurrent)
+ c.ScanIntervalSeconds = int(policy.RepeatIntervalSeconds)
+ return nil
+}
+
+// ApplySchemaDefaults applies default values from schema using reflection
+func (c *BaseConfig) ApplySchemaDefaults(schema *config.Schema) error {
+ // Use reflection-based approach for BaseConfig since it needs to handle embedded structs
+ return schema.ApplyDefaultsToProtobuf(c)
+}
+
+// setFieldValue sets a field value with type conversion
+func setFieldValue(field reflect.Value, value interface{}) error {
+ if value == nil {
+ return nil
+ }
+
+ valueVal := reflect.ValueOf(value)
+ fieldType := field.Type()
+ valueType := valueVal.Type()
+
+ // Direct assignment if types match
+ if valueType.AssignableTo(fieldType) {
+ field.Set(valueVal)
+ return nil
+ }
+
+ // Type conversion for common cases
+ switch fieldType.Kind() {
+ case reflect.Bool:
+ if b, ok := value.(bool); ok {
+ field.SetBool(b)
+ } else {
+ return fmt.Errorf("cannot convert %T to bool", value)
+ }
+ case reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64:
+ switch v := value.(type) {
+ case int:
+ field.SetInt(int64(v))
+ case int32:
+ field.SetInt(int64(v))
+ case int64:
+ field.SetInt(v)
+ case float64:
+ field.SetInt(int64(v))
+ default:
+ return fmt.Errorf("cannot convert %T to int", value)
+ }
+ case reflect.Float32, reflect.Float64:
+ switch v := value.(type) {
+ case float32:
+ field.SetFloat(float64(v))
+ case float64:
+ field.SetFloat(v)
+ case int:
+ field.SetFloat(float64(v))
+ case int64:
+ field.SetFloat(float64(v))
+ default:
+ return fmt.Errorf("cannot convert %T to float", value)
+ }
+ case reflect.String:
+ if s, ok := value.(string); ok {
+ field.SetString(s)
+ } else {
+ return fmt.Errorf("cannot convert %T to string", value)
+ }
+ default:
+ return fmt.Errorf("unsupported field type %s", fieldType.Kind())
+ }
+
+ return nil
+}