Files
seaweedFS/weed/worker/tasks/balance/balance.go
Chris Lu 891a2fb6eb 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>
2025-07-30 12:38:03 -07:00

142 lines
3.9 KiB
Go

package balance
import (
"context"
"fmt"
"time"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/worker/tasks"
"github.com/seaweedfs/seaweedfs/weed/worker/types"
)
// Task implements balance operation to redistribute volumes across volume servers
type Task struct {
*tasks.BaseTask
server string
volumeID uint32
collection string
// Task parameters for accessing planned destinations
taskParams types.TaskParams
}
// NewTask creates a new balance task instance
func NewTask(server string, volumeID uint32, collection string) *Task {
task := &Task{
BaseTask: tasks.NewBaseTask(types.TaskTypeBalance),
server: server,
volumeID: volumeID,
collection: collection,
}
return task
}
// Execute executes the balance task
func (t *Task) Execute(params types.TaskParams) error {
// Use BaseTask.ExecuteTask to handle logging initialization
return t.ExecuteTask(context.Background(), params, t.executeImpl)
}
// executeImpl is the actual balance implementation
func (t *Task) executeImpl(ctx context.Context, params types.TaskParams) error {
// Store task parameters for accessing planned destinations
t.taskParams = params
// Get planned destination
destNode := t.getPlannedDestination()
if destNode != "" {
t.LogWithFields("INFO", "Starting balance task with planned destination", map[string]interface{}{
"volume_id": t.volumeID,
"source": t.server,
"destination": destNode,
"collection": t.collection,
})
} else {
t.LogWithFields("INFO", "Starting balance task without specific destination", map[string]interface{}{
"volume_id": t.volumeID,
"server": t.server,
"collection": t.collection,
})
}
// Simulate balance operation with progress updates
steps := []struct {
name string
duration time.Duration
progress float64
}{
{"Analyzing cluster state", 2 * time.Second, 15},
{"Identifying optimal placement", 3 * time.Second, 35},
{"Moving volume data", 6 * time.Second, 75},
{"Updating cluster metadata", 2 * time.Second, 95},
{"Verifying balance", 1 * time.Second, 100},
}
for _, step := range steps {
select {
case <-ctx.Done():
t.LogWarning("Balance task cancelled during step: %s", step.name)
return ctx.Err()
default:
}
if t.IsCancelled() {
t.LogWarning("Balance task cancelled by request during step: %s", step.name)
return fmt.Errorf("balance task cancelled")
}
t.LogWithFields("INFO", "Executing balance step", map[string]interface{}{
"step": step.name,
"progress": step.progress,
"duration": step.duration.String(),
"volume_id": t.volumeID,
})
t.SetProgress(step.progress)
// Simulate work
time.Sleep(step.duration)
}
t.LogWithFields("INFO", "Balance task completed successfully", map[string]interface{}{
"volume_id": t.volumeID,
"server": t.server,
"collection": t.collection,
"final_progress": 100.0,
})
return nil
}
// Validate validates the task parameters
func (t *Task) Validate(params types.TaskParams) error {
if params.VolumeID == 0 {
return fmt.Errorf("volume_id is required")
}
if params.Server == "" {
return fmt.Errorf("server is required")
}
return nil
}
// getPlannedDestination extracts the planned destination node from task parameters
func (t *Task) getPlannedDestination() string {
if t.taskParams.TypedParams != nil {
if balanceParams := t.taskParams.TypedParams.GetBalanceParams(); balanceParams != nil {
if balanceParams.DestNode != "" {
glog.V(2).Infof("Found planned destination for volume %d: %s", t.volumeID, balanceParams.DestNode)
return balanceParams.DestNode
}
}
}
return ""
}
// EstimateTime estimates the time needed for the task
func (t *Task) EstimateTime(params types.TaskParams) time.Duration {
// Base time for balance operation
baseTime := 35 * time.Second
// Could adjust based on volume size or cluster state
return baseTime
}