mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-08 23:37:43 +02:00
* ec: strict_placement option so encode only runs while guarantees hold Shard placement during encode was best-effort (PlaceDurabilityFirst): when the cluster could not satisfy the per-disk caps, anti-affinity, replica-placement or per-rack caps, the constraints were relaxed and the volume was encoded anyway, weaker than configured. A strict_placement option on the erasure coding task switches planning to PlaceStrict so the volume's planning fails instead, and the encode is retried when capacity allows the guarantee. Also documents the resilience rule in ec.encode help: a volume survives losing any nodes or racks holding at most parity-shards shards between them, and how -shardReplicaPlacement's rack and node digits bound that loss. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * ec: expose strict_placement through the plugin form and persisted task policy The admin UI, the admin.toml maintenance mapping, and the TaskPolicy serialization all dropped the new flag; add the bool field to ErasureCodingTaskConfig, the worker config form, and both conversion directions. * shell: describe shardReplicaPlacement as requested limits, not guarantees ec.encode places shards best-effort, so the configured rack/node caps only bound shard loss when the final placement actually satisfies them. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
271 lines
10 KiB
Go
271 lines
10 KiB
Go
package erasure_coding
|
|
|
|
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 erasure coding specific settings
|
|
type Config struct {
|
|
base.BaseConfig
|
|
QuietForSeconds int `json:"quiet_for_seconds"`
|
|
FullnessRatio float64 `json:"fullness_ratio"`
|
|
CollectionFilter string `json:"collection_filter"`
|
|
MinSizeMB int `json:"min_size_mb"`
|
|
PreferredTags []string `json:"preferred_tags"`
|
|
ReplicaPlacement string `json:"replica_placement"` // e.g. "020"; empty falls back to the master default replication
|
|
StrictPlacement bool `json:"strict_placement"` // fail planning instead of relaxing placement constraints
|
|
}
|
|
|
|
// NewDefaultConfig creates a new default erasure coding configuration
|
|
func NewDefaultConfig() *Config {
|
|
return &Config{
|
|
BaseConfig: base.BaseConfig{
|
|
Enabled: true,
|
|
ScanIntervalSeconds: 60 * 60, // 1 hour
|
|
MaxConcurrent: 1,
|
|
},
|
|
QuietForSeconds: 3600, // 1 hour, matching the shell ec.encode -quietFor default
|
|
FullnessRatio: 0.95, // 95%, matching the shell ec.encode -fullPercent default
|
|
CollectionFilter: "",
|
|
MinSizeMB: 30, // 30MB (more reasonable than 100MB)
|
|
PreferredTags: nil,
|
|
}
|
|
}
|
|
|
|
// GetConfigSpec returns the configuration schema for erasure coding tasks
|
|
func GetConfigSpec() base.ConfigSpec {
|
|
return base.ConfigSpec{
|
|
Fields: []*config.Field{
|
|
{
|
|
Name: "enabled",
|
|
JSONName: "enabled",
|
|
Type: config.FieldTypeBool,
|
|
DefaultValue: true,
|
|
Required: false,
|
|
DisplayName: "Enable Erasure Coding Tasks",
|
|
Description: "Whether erasure coding tasks should be automatically created",
|
|
HelpText: "Toggle this to enable or disable automatic erasure coding task generation",
|
|
InputType: "checkbox",
|
|
CSSClasses: "form-check-input",
|
|
},
|
|
{
|
|
Name: "scan_interval_seconds",
|
|
JSONName: "scan_interval_seconds",
|
|
Type: config.FieldTypeInterval,
|
|
DefaultValue: 60 * 60,
|
|
MinValue: 10 * 60,
|
|
MaxValue: 24 * 60 * 60,
|
|
Required: true,
|
|
DisplayName: "Scan Interval",
|
|
Description: "How often to scan for volumes needing erasure coding",
|
|
HelpText: "The system will check for volumes that need erasure coding at this interval",
|
|
Placeholder: "1",
|
|
Unit: config.UnitHours,
|
|
InputType: "interval",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "max_concurrent",
|
|
JSONName: "max_concurrent",
|
|
Type: config.FieldTypeInt,
|
|
DefaultValue: 1,
|
|
MinValue: 1,
|
|
MaxValue: 5,
|
|
Required: true,
|
|
DisplayName: "Max Concurrent Tasks",
|
|
Description: "Maximum number of erasure coding tasks that can run simultaneously",
|
|
HelpText: "Limits the number of erasure coding operations running at the same time",
|
|
Placeholder: "1 (default)",
|
|
Unit: config.UnitCount,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "quiet_for_seconds",
|
|
JSONName: "quiet_for_seconds",
|
|
Type: config.FieldTypeInterval,
|
|
DefaultValue: 3600,
|
|
MinValue: 1,
|
|
MaxValue: 3600,
|
|
Required: true,
|
|
DisplayName: "Quiet Period",
|
|
Description: "Minimum time volume must be quiet before erasure coding",
|
|
HelpText: "Volume must not be modified for this duration before erasure coding",
|
|
Placeholder: "60",
|
|
Unit: config.UnitMinutes,
|
|
InputType: "interval",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "fullness_ratio",
|
|
JSONName: "fullness_ratio",
|
|
Type: config.FieldTypeFloat,
|
|
DefaultValue: 0.95,
|
|
MinValue: 0.0001,
|
|
MaxValue: 1.0,
|
|
Required: true,
|
|
DisplayName: "Fullness Ratio",
|
|
Description: "Minimum fullness ratio to trigger erasure coding",
|
|
HelpText: "Only volumes with this fullness ratio or higher will be erasure coded",
|
|
Placeholder: "0.80 (80%)",
|
|
Unit: config.UnitNone,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "collection_filter",
|
|
JSONName: "collection_filter",
|
|
Type: config.FieldTypeString,
|
|
DefaultValue: "",
|
|
Required: false,
|
|
DisplayName: "Collection Filter",
|
|
Description: "Only process volumes from specific collections (comma-separated names, wildcards, or regex patterns)",
|
|
HelpText: "Leave empty to process all collections, or list the collections to process",
|
|
Placeholder: "pictures,videos",
|
|
InputType: "text",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "min_size_mb",
|
|
JSONName: "min_size_mb",
|
|
Type: config.FieldTypeInt,
|
|
DefaultValue: 30,
|
|
MinValue: 1,
|
|
MaxValue: 1000,
|
|
Required: true,
|
|
DisplayName: "Minimum Size (MB)",
|
|
Description: "Minimum volume size to consider for erasure coding",
|
|
HelpText: "Only volumes larger than this size will be considered for erasure coding",
|
|
Placeholder: "30",
|
|
Unit: config.UnitNone,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "preferred_tags",
|
|
JSONName: "preferred_tags",
|
|
Type: config.FieldTypeString,
|
|
DefaultValue: "",
|
|
Required: false,
|
|
DisplayName: "Preferred Disk Tags",
|
|
Description: "Comma-separated disk tags to prioritize for EC shard placement",
|
|
HelpText: "EC shards will be placed on disks with these tags first, then fall back to other disks if needed",
|
|
Placeholder: "fast,ssd",
|
|
InputType: "text",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "replica_placement",
|
|
JSONName: "replica_placement",
|
|
Type: config.FieldTypeString,
|
|
DefaultValue: "",
|
|
Required: false,
|
|
DisplayName: "Replica Placement",
|
|
Description: "EC shard replica placement constraint (e.g. 020)",
|
|
HelpText: "Leave empty to use the master default replication. When set, the 2nd/3rd digits cap EC shards per rack and per node (best-effort during encode: relaxed rather than failing if the cluster can't satisfy them, then enforced by rebalancing). The 1st (data-center) digit is ignored for EC placement",
|
|
Placeholder: "020",
|
|
InputType: "text",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "strict_placement",
|
|
JSONName: "strict_placement",
|
|
Type: config.FieldTypeBool,
|
|
DefaultValue: false,
|
|
Required: false,
|
|
DisplayName: "Strict Placement",
|
|
Description: "Refuse to encode a volume when the placement constraints can't be satisfied",
|
|
HelpText: "When enabled, a volume is only encoded if every shard can be placed within the per-disk, anti-affinity, replica-placement and per-rack caps, so the configured resilience is preserved. When disabled (default), unsatisfiable constraints are relaxed and noted in the log",
|
|
InputType: "checkbox",
|
|
CSSClasses: "form-check-input",
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
// ToTaskPolicy converts configuration to a TaskPolicy protobuf message
|
|
func (c *Config) ToTaskPolicy() *worker_pb.TaskPolicy {
|
|
// Defensive copy of PreferredTags to prevent external mutation
|
|
preferredTagsCopy := append([]string(nil), c.PreferredTags...)
|
|
return &worker_pb.TaskPolicy{
|
|
Enabled: c.Enabled,
|
|
MaxConcurrent: int32(c.MaxConcurrent),
|
|
RepeatIntervalSeconds: int32(c.ScanIntervalSeconds),
|
|
CheckIntervalSeconds: int32(c.ScanIntervalSeconds),
|
|
TaskConfig: &worker_pb.TaskPolicy_ErasureCodingConfig{
|
|
ErasureCodingConfig: &worker_pb.ErasureCodingTaskConfig{
|
|
FullnessRatio: float64(c.FullnessRatio),
|
|
QuietForSeconds: int32(c.QuietForSeconds),
|
|
MinVolumeSizeMb: int32(c.MinSizeMB),
|
|
CollectionFilter: c.CollectionFilter,
|
|
PreferredTags: preferredTagsCopy,
|
|
ReplicaPlacement: c.ReplicaPlacement,
|
|
StrictPlacement: c.StrictPlacement,
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
// 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 erasure coding-specific fields from the task config
|
|
if ecConfig := policy.GetErasureCodingConfig(); ecConfig != nil {
|
|
c.FullnessRatio = float64(ecConfig.FullnessRatio)
|
|
c.QuietForSeconds = int(ecConfig.QuietForSeconds)
|
|
c.MinSizeMB = int(ecConfig.MinVolumeSizeMb)
|
|
c.CollectionFilter = ecConfig.CollectionFilter
|
|
c.PreferredTags = append([]string(nil), ecConfig.PreferredTags...)
|
|
c.ReplicaPlacement = ecConfig.ReplicaPlacement
|
|
c.StrictPlacement = ecConfig.StrictPlacement
|
|
}
|
|
|
|
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 {
|
|
LoadErasureCodingTaskPolicy() (*worker_pb.TaskPolicy, error)
|
|
}); ok {
|
|
policy, err := persistence.LoadErasureCodingTaskPolicy()
|
|
switch {
|
|
case err != nil:
|
|
glog.Warningf("Could not read the persisted erasure coding configuration, falling back to defaults: %v", err)
|
|
case policy == nil:
|
|
glog.V(1).Infof("No erasure coding configuration persisted yet, using defaults")
|
|
default:
|
|
if err := config.FromTaskPolicy(policy); err != nil {
|
|
glog.Warningf("Could not apply the persisted erasure coding configuration, falling back to defaults: %v", err)
|
|
} else {
|
|
glog.V(1).Infof("Loaded erasure coding configuration from persistence")
|
|
return config
|
|
}
|
|
}
|
|
} else if configPersistence != nil {
|
|
// A store was handed in but does not expose the accessor, so the persisted
|
|
// settings are silently ignored - always a wiring bug, never a normal state.
|
|
glog.Warningf("%T cannot provide the persisted erasure coding configuration: it has no LoadErasureCodingTaskPolicy() method, "+
|
|
"so the compiled-in defaults are used and any saved erasure coding settings are ignored", configPersistence)
|
|
}
|
|
|
|
glog.V(1).Infof("Using default erasure coding configuration")
|
|
return config
|
|
}
|