mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2025-09-24 03:03:36 +08:00
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
140
weed/worker/tasks/erasure_coding/detection.go
Normal file
140
weed/worker/tasks/erasure_coding/detection.go
Normal file
@@ -0,0 +1,140 @@
|
||||
package erasure_coding
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/seaweedfs/seaweedfs/weed/glog"
|
||||
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/base"
|
||||
"github.com/seaweedfs/seaweedfs/weed/worker/types"
|
||||
)
|
||||
|
||||
// Detection implements the detection logic for erasure coding tasks
|
||||
func Detection(metrics []*types.VolumeHealthMetrics, clusterInfo *types.ClusterInfo, config base.TaskConfig) ([]*types.TaskDetectionResult, error) {
|
||||
if !config.IsEnabled() {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
ecConfig := config.(*Config)
|
||||
var results []*types.TaskDetectionResult
|
||||
now := time.Now()
|
||||
quietThreshold := time.Duration(ecConfig.QuietForSeconds) * time.Second
|
||||
minSizeBytes := uint64(ecConfig.MinSizeMB) * 1024 * 1024 // Configurable minimum
|
||||
|
||||
debugCount := 0
|
||||
skippedAlreadyEC := 0
|
||||
skippedTooSmall := 0
|
||||
skippedCollectionFilter := 0
|
||||
skippedQuietTime := 0
|
||||
skippedFullness := 0
|
||||
|
||||
for _, metric := range metrics {
|
||||
// Skip if already EC volume
|
||||
if metric.IsECVolume {
|
||||
skippedAlreadyEC++
|
||||
continue
|
||||
}
|
||||
|
||||
// Check minimum size requirement
|
||||
if metric.Size < minSizeBytes {
|
||||
skippedTooSmall++
|
||||
continue
|
||||
}
|
||||
|
||||
// Check collection filter if specified
|
||||
if ecConfig.CollectionFilter != "" {
|
||||
// Parse comma-separated collections
|
||||
allowedCollections := make(map[string]bool)
|
||||
for _, collection := range strings.Split(ecConfig.CollectionFilter, ",") {
|
||||
allowedCollections[strings.TrimSpace(collection)] = true
|
||||
}
|
||||
// Skip if volume's collection is not in the allowed list
|
||||
if !allowedCollections[metric.Collection] {
|
||||
skippedCollectionFilter++
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
// Check quiet duration and fullness criteria
|
||||
if metric.Age >= quietThreshold && metric.FullnessRatio >= ecConfig.FullnessRatio {
|
||||
result := &types.TaskDetectionResult{
|
||||
TaskType: types.TaskTypeErasureCoding,
|
||||
VolumeID: metric.VolumeID,
|
||||
Server: metric.Server,
|
||||
Collection: metric.Collection,
|
||||
Priority: types.TaskPriorityLow, // EC is not urgent
|
||||
Reason: fmt.Sprintf("Volume meets EC criteria: quiet for %.1fs (>%ds), fullness=%.1f%% (>%.1f%%), size=%.1fMB (>100MB)",
|
||||
metric.Age.Seconds(), ecConfig.QuietForSeconds, metric.FullnessRatio*100, ecConfig.FullnessRatio*100,
|
||||
float64(metric.Size)/(1024*1024)),
|
||||
ScheduleAt: now,
|
||||
}
|
||||
results = append(results, result)
|
||||
} else {
|
||||
// Count debug reasons
|
||||
if debugCount < 5 { // Limit to avoid spam
|
||||
if metric.Age < quietThreshold {
|
||||
skippedQuietTime++
|
||||
}
|
||||
if metric.FullnessRatio < ecConfig.FullnessRatio {
|
||||
skippedFullness++
|
||||
}
|
||||
}
|
||||
debugCount++
|
||||
}
|
||||
}
|
||||
|
||||
// Log debug summary if no tasks were created
|
||||
if len(results) == 0 && len(metrics) > 0 {
|
||||
totalVolumes := len(metrics)
|
||||
glog.V(1).Infof("EC detection: No tasks created for %d volumes (skipped: %d already EC, %d too small, %d filtered, %d not quiet, %d not full)",
|
||||
totalVolumes, skippedAlreadyEC, skippedTooSmall, skippedCollectionFilter, skippedQuietTime, skippedFullness)
|
||||
|
||||
// Show details for first few volumes
|
||||
for i, metric := range metrics {
|
||||
if i >= 3 || metric.IsECVolume { // Limit to first 3 non-EC volumes
|
||||
continue
|
||||
}
|
||||
sizeMB := float64(metric.Size) / (1024 * 1024)
|
||||
glog.Infof("ERASURE CODING: Volume %d: size=%.1fMB (need ≥%dMB), age=%s (need ≥%s), fullness=%.1f%% (need ≥%.1f%%)",
|
||||
metric.VolumeID, sizeMB, ecConfig.MinSizeMB, metric.Age.Truncate(time.Minute), quietThreshold.Truncate(time.Minute),
|
||||
metric.FullnessRatio*100, ecConfig.FullnessRatio*100)
|
||||
}
|
||||
}
|
||||
|
||||
return results, nil
|
||||
}
|
||||
|
||||
// Scheduling implements the scheduling logic for erasure coding tasks
|
||||
func Scheduling(task *types.Task, runningTasks []*types.Task, availableWorkers []*types.Worker, config base.TaskConfig) bool {
|
||||
ecConfig := config.(*Config)
|
||||
|
||||
// Check if we have available workers
|
||||
if len(availableWorkers) == 0 {
|
||||
return false
|
||||
}
|
||||
|
||||
// Count running EC tasks
|
||||
runningCount := 0
|
||||
for _, runningTask := range runningTasks {
|
||||
if runningTask.Type == types.TaskTypeErasureCoding {
|
||||
runningCount++
|
||||
}
|
||||
}
|
||||
|
||||
// Check concurrency limit
|
||||
if runningCount >= ecConfig.MaxConcurrent {
|
||||
return false
|
||||
}
|
||||
|
||||
// Check if any worker can handle EC tasks
|
||||
for _, worker := range availableWorkers {
|
||||
for _, capability := range worker.Capabilities {
|
||||
if capability == types.TaskTypeErasureCoding {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
Reference in New Issue
Block a user