mirror of
https://github.com/chrislusf/seaweedfs
synced 2025-08-17 09:32:48 +02:00
* 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>
170 lines
5.4 KiB
Go
170 lines
5.4 KiB
Go
package balance
|
|
|
|
import (
|
|
"fmt"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/admin/config"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/base"
|
|
)
|
|
|
|
// Config extends BaseConfig with balance-specific settings
|
|
type Config struct {
|
|
base.BaseConfig
|
|
ImbalanceThreshold float64 `json:"imbalance_threshold"`
|
|
MinServerCount int `json:"min_server_count"`
|
|
}
|
|
|
|
// NewDefaultConfig creates a new default balance configuration
|
|
func NewDefaultConfig() *Config {
|
|
return &Config{
|
|
BaseConfig: base.BaseConfig{
|
|
Enabled: true,
|
|
ScanIntervalSeconds: 30 * 60, // 30 minutes
|
|
MaxConcurrent: 1,
|
|
},
|
|
ImbalanceThreshold: 0.2, // 20%
|
|
MinServerCount: 2,
|
|
}
|
|
}
|
|
|
|
// GetConfigSpec returns the configuration schema for balance tasks
|
|
func GetConfigSpec() base.ConfigSpec {
|
|
return base.ConfigSpec{
|
|
Fields: []*config.Field{
|
|
{
|
|
Name: "enabled",
|
|
JSONName: "enabled",
|
|
Type: config.FieldTypeBool,
|
|
DefaultValue: true,
|
|
Required: false,
|
|
DisplayName: "Enable Balance Tasks",
|
|
Description: "Whether balance tasks should be automatically created",
|
|
HelpText: "Toggle this to enable or disable automatic balance task generation",
|
|
InputType: "checkbox",
|
|
CSSClasses: "form-check-input",
|
|
},
|
|
{
|
|
Name: "scan_interval_seconds",
|
|
JSONName: "scan_interval_seconds",
|
|
Type: config.FieldTypeInterval,
|
|
DefaultValue: 30 * 60,
|
|
MinValue: 5 * 60,
|
|
MaxValue: 2 * 60 * 60,
|
|
Required: true,
|
|
DisplayName: "Scan Interval",
|
|
Description: "How often to scan for volume distribution imbalances",
|
|
HelpText: "The system will check for volume distribution imbalances at this interval",
|
|
Placeholder: "30",
|
|
Unit: config.UnitMinutes,
|
|
InputType: "interval",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "max_concurrent",
|
|
JSONName: "max_concurrent",
|
|
Type: config.FieldTypeInt,
|
|
DefaultValue: 1,
|
|
MinValue: 1,
|
|
MaxValue: 3,
|
|
Required: true,
|
|
DisplayName: "Max Concurrent Tasks",
|
|
Description: "Maximum number of balance tasks that can run simultaneously",
|
|
HelpText: "Limits the number of balance operations running at the same time",
|
|
Placeholder: "1 (default)",
|
|
Unit: config.UnitCount,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "imbalance_threshold",
|
|
JSONName: "imbalance_threshold",
|
|
Type: config.FieldTypeFloat,
|
|
DefaultValue: 0.2,
|
|
MinValue: 0.05,
|
|
MaxValue: 0.5,
|
|
Required: true,
|
|
DisplayName: "Imbalance Threshold",
|
|
Description: "Minimum imbalance ratio to trigger balancing",
|
|
HelpText: "Volume distribution imbalances above this threshold will trigger balancing",
|
|
Placeholder: "0.20 (20%)",
|
|
Unit: config.UnitNone,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "min_server_count",
|
|
JSONName: "min_server_count",
|
|
Type: config.FieldTypeInt,
|
|
DefaultValue: 2,
|
|
MinValue: 2,
|
|
MaxValue: 10,
|
|
Required: true,
|
|
DisplayName: "Minimum Server Count",
|
|
Description: "Minimum number of servers required for balancing",
|
|
HelpText: "Balancing will only occur if there are at least this many servers",
|
|
Placeholder: "2 (default)",
|
|
Unit: config.UnitCount,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
// ToTaskPolicy converts configuration to a TaskPolicy protobuf message
|
|
func (c *Config) ToTaskPolicy() *worker_pb.TaskPolicy {
|
|
return &worker_pb.TaskPolicy{
|
|
Enabled: c.Enabled,
|
|
MaxConcurrent: int32(c.MaxConcurrent),
|
|
RepeatIntervalSeconds: int32(c.ScanIntervalSeconds),
|
|
CheckIntervalSeconds: int32(c.ScanIntervalSeconds),
|
|
TaskConfig: &worker_pb.TaskPolicy_BalanceConfig{
|
|
BalanceConfig: &worker_pb.BalanceTaskConfig{
|
|
ImbalanceThreshold: float64(c.ImbalanceThreshold),
|
|
MinServerCount: int32(c.MinServerCount),
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
// FromTaskPolicy loads configuration from a TaskPolicy protobuf message
|
|
func (c *Config) FromTaskPolicy(policy *worker_pb.TaskPolicy) error {
|
|
if policy == nil {
|
|
return fmt.Errorf("policy is nil")
|
|
}
|
|
|
|
// Set general TaskPolicy fields
|
|
c.Enabled = policy.Enabled
|
|
c.MaxConcurrent = int(policy.MaxConcurrent)
|
|
c.ScanIntervalSeconds = int(policy.RepeatIntervalSeconds) // Direct seconds-to-seconds mapping
|
|
|
|
// Set balance-specific fields from the task config
|
|
if balanceConfig := policy.GetBalanceConfig(); balanceConfig != nil {
|
|
c.ImbalanceThreshold = float64(balanceConfig.ImbalanceThreshold)
|
|
c.MinServerCount = int(balanceConfig.MinServerCount)
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
// LoadConfigFromPersistence loads configuration from the persistence layer if available
|
|
func LoadConfigFromPersistence(configPersistence interface{}) *Config {
|
|
config := NewDefaultConfig()
|
|
|
|
// Try to load from persistence if available
|
|
if persistence, ok := configPersistence.(interface {
|
|
LoadBalanceTaskPolicy() (*worker_pb.TaskPolicy, error)
|
|
}); ok {
|
|
if policy, err := persistence.LoadBalanceTaskPolicy(); err == nil && policy != nil {
|
|
if err := config.FromTaskPolicy(policy); err == nil {
|
|
glog.V(1).Infof("Loaded balance configuration from persistence")
|
|
return config
|
|
}
|
|
}
|
|
}
|
|
|
|
glog.V(1).Infof("Using default balance configuration")
|
|
return config
|
|
}
|