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>
This commit is contained in:
Chris Lu
@@ -2,80 +2,71 @@ package erasure_coding
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"github.com/seaweedfs/seaweedfs/weed/glog"
|
||||
"github.com/seaweedfs/seaweedfs/weed/worker/tasks"
|
||||
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/base"
|
||||
"github.com/seaweedfs/seaweedfs/weed/worker/types"
|
||||
)
|
||||
|
||||
// Factory creates erasure coding task instances
|
||||
type Factory struct {
|
||||
*tasks.BaseTaskFactory
|
||||
}
|
||||
|
||||
// NewFactory creates a new erasure coding task factory
|
||||
func NewFactory() *Factory {
|
||||
return &Factory{
|
||||
BaseTaskFactory: tasks.NewBaseTaskFactory(
|
||||
types.TaskTypeErasureCoding,
|
||||
[]string{"erasure_coding", "storage", "durability"},
|
||||
"Convert volumes to erasure coded format for improved durability",
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
// Create creates a new erasure coding task instance
|
||||
func (f *Factory) Create(params types.TaskParams) (types.TaskInterface, error) {
|
||||
// Validate parameters
|
||||
if params.VolumeID == 0 {
|
||||
return nil, fmt.Errorf("volume_id is required")
|
||||
}
|
||||
if params.Server == "" {
|
||||
return nil, fmt.Errorf("server is required")
|
||||
}
|
||||
|
||||
task := NewTask(params.Server, params.VolumeID)
|
||||
task.SetEstimatedDuration(task.EstimateTime(params))
|
||||
|
||||
return task, nil
|
||||
}
|
||||
|
||||
// Shared detector and scheduler instances
|
||||
var (
|
||||
sharedDetector *EcDetector
|
||||
sharedScheduler *Scheduler
|
||||
)
|
||||
|
||||
// getSharedInstances returns the shared detector and scheduler instances
|
||||
func getSharedInstances() (*EcDetector, *Scheduler) {
|
||||
if sharedDetector == nil {
|
||||
sharedDetector = NewEcDetector()
|
||||
}
|
||||
if sharedScheduler == nil {
|
||||
sharedScheduler = NewScheduler()
|
||||
}
|
||||
return sharedDetector, sharedScheduler
|
||||
}
|
||||
|
||||
// GetSharedInstances returns the shared detector and scheduler instances (public access)
|
||||
func GetSharedInstances() (*EcDetector, *Scheduler) {
|
||||
return getSharedInstances()
|
||||
}
|
||||
// Global variable to hold the task definition for configuration updates
|
||||
var globalTaskDef *base.TaskDefinition
|
||||
|
||||
// Auto-register this task when the package is imported
|
||||
func init() {
|
||||
factory := NewFactory()
|
||||
tasks.AutoRegister(types.TaskTypeErasureCoding, factory)
|
||||
RegisterErasureCodingTask()
|
||||
|
||||
// Get shared instances for all registrations
|
||||
detector, scheduler := getSharedInstances()
|
||||
|
||||
// Register with types registry
|
||||
tasks.AutoRegisterTypes(func(registry *types.TaskRegistry) {
|
||||
registry.RegisterTask(detector, scheduler)
|
||||
})
|
||||
|
||||
// Register with UI registry using the same instances
|
||||
tasks.AutoRegisterUI(func(uiRegistry *types.UIRegistry) {
|
||||
RegisterUI(uiRegistry, detector, scheduler)
|
||||
})
|
||||
// Register config updater
|
||||
tasks.AutoRegisterConfigUpdater(types.TaskTypeErasureCoding, UpdateConfigFromPersistence)
|
||||
}
|
||||
|
||||
// RegisterErasureCodingTask registers the erasure coding task with the new architecture
|
||||
func RegisterErasureCodingTask() {
|
||||
// Create configuration instance
|
||||
config := NewDefaultConfig()
|
||||
|
||||
// Create complete task definition
|
||||
taskDef := &base.TaskDefinition{
|
||||
Type: types.TaskTypeErasureCoding,
|
||||
Name: "erasure_coding",
|
||||
DisplayName: "Erasure Coding",
|
||||
Description: "Applies erasure coding to volumes for data protection",
|
||||
Icon: "fas fa-shield-alt text-success",
|
||||
Capabilities: []string{"erasure_coding", "data_protection"},
|
||||
|
||||
Config: config,
|
||||
ConfigSpec: GetConfigSpec(),
|
||||
CreateTask: nil, // Uses typed task system - see init() in ec.go
|
||||
DetectionFunc: Detection,
|
||||
ScanInterval: 1 * time.Hour,
|
||||
SchedulingFunc: Scheduling,
|
||||
MaxConcurrent: 1,
|
||||
RepeatInterval: 24 * time.Hour,
|
||||
}
|
||||
|
||||
// Store task definition globally for configuration updates
|
||||
globalTaskDef = taskDef
|
||||
|
||||
// Register everything with a single function call!
|
||||
base.RegisterTask(taskDef)
|
||||
}
|
||||
|
||||
// UpdateConfigFromPersistence updates the erasure coding configuration from persistence
|
||||
func UpdateConfigFromPersistence(configPersistence interface{}) error {
|
||||
if globalTaskDef == nil {
|
||||
return fmt.Errorf("erasure coding task not registered")
|
||||
}
|
||||
|
||||
// Load configuration from persistence
|
||||
newConfig := LoadConfigFromPersistence(configPersistence)
|
||||
if newConfig == nil {
|
||||
return fmt.Errorf("failed to load configuration from persistence")
|
||||
}
|
||||
|
||||
// Update the task definition's config
|
||||
globalTaskDef.Config = newConfig
|
||||
|
||||
glog.V(1).Infof("Updated erasure coding task configuration from persistence")
|
||||
return nil
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user