Files
s3/weed/worker/tasks/vacuum/config.go
zooqueen dd74d3e6d6 Replace AGPL MinIO fork with Apache-2.0 SeaweedFS fork; rebrand CLI weed->s3
hanzoai/s3 was an AGPL-3.0 MinIO fork whose network-copyleft blocks embedding
and reselling as a managed service. Replace it wholesale with a fork of
SeaweedFS (github.com/seaweedfs/seaweedfs, Apache-2.0, Go) which ships a
built-in S3 gateway + Filer.

- License: AGPL-3.0 -> Apache-2.0 (upstream LICENSE kept verbatim, incl.
  "Copyright 2025 Chris Lu"); NOTICE added crediting SeaweedFS. No AGPL/BUSL/
  SSPL/GPL or enterprise ("ee") files remain.
- Module: go.mod path set to github.com/hanzoai/s3 with a self-replace
  (replace github.com/seaweedfs/seaweedfs => ./) so the ~1800 internal Go files
  keep their upstream import paths with zero churn. Internal identifiers and
  import paths are intentionally NOT renamed.
- CLI rebrand: the binary is built as `s3` (was `weed`); root usage, per-command
  help/usage/flag strings, shell autocomplete program name, and the product name
  in CLI output now read "Hanzo S3" / `s3`. Users never see `weed`.
  (e.g. `s3 server`, `s3 filer`, `s3 master`, `s3 volume`, `s3 s3`, `s3 mount`.)
- Build: `make` (or `go build -o s3 ./weed`) builds the `s3` binary green;
  `cmd/weed-db` and `cmd/weed-sql` also build; `go vet ./weed/command/` clean.
- README/LLM.md rewritten for Hanzo S3; AGENTS.md/CLAUDE.md symlinks preserved.
- Dropped a 33MB prebuilt Mach-O `stress` binary upstream had committed; `.gitignore`
  updated to ignore the `s3` build output.
2026-06-18 23:41:25 -07:00

171 lines
5.6 KiB
Go

package vacuum
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 vacuum-specific settings
type Config struct {
base.BaseConfig
GarbageThreshold float64 `json:"garbage_threshold"`
MinVolumeAgeSeconds int `json:"min_volume_age_seconds"`
}
// NewDefaultConfig creates a new default vacuum configuration
func NewDefaultConfig() *Config {
return &Config{
BaseConfig: base.BaseConfig{
Enabled: true,
ScanIntervalSeconds: 2 * 60 * 60, // 2 hours
MaxConcurrent: 2,
},
GarbageThreshold: 0.3, // 30%
MinVolumeAgeSeconds: 24 * 60 * 60, // 24 hours
}
}
// 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_VacuumConfig{
VacuumConfig: &worker_pb.VacuumTaskConfig{
GarbageThreshold: float64(c.GarbageThreshold),
MinVolumeAgeHours: int32((c.MinVolumeAgeSeconds + 3599) / 3600), // round up so sub-hour values don't become 0
},
},
}
}
// 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 vacuum-specific fields from the task config
if vacuumConfig := policy.GetVacuumConfig(); vacuumConfig != nil {
c.GarbageThreshold = float64(vacuumConfig.GarbageThreshold)
c.MinVolumeAgeSeconds = int(vacuumConfig.MinVolumeAgeHours * 3600) // Convert hours to seconds
}
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 {
LoadVacuumTaskPolicy() (*worker_pb.TaskPolicy, error)
}); ok {
if policy, err := persistence.LoadVacuumTaskPolicy(); err == nil && policy != nil {
if err := config.FromTaskPolicy(policy); err == nil {
glog.V(1).Infof("Loaded vacuum configuration from persistence")
return config
}
}
}
glog.V(1).Infof("Using default vacuum configuration")
return config
}
// GetConfigSpec returns the configuration schema for vacuum tasks
func GetConfigSpec() base.ConfigSpec {
return base.ConfigSpec{
Fields: []*config.Field{
{
Name: "enabled",
JSONName: "enabled",
Type: config.FieldTypeBool,
DefaultValue: true,
Required: false,
DisplayName: "Enable Vacuum Tasks",
Description: "Whether vacuum tasks should be automatically created",
HelpText: "Toggle this to enable or disable automatic vacuum task generation",
InputType: "checkbox",
CSSClasses: "form-check-input",
},
{
Name: "scan_interval_seconds",
JSONName: "scan_interval_seconds",
Type: config.FieldTypeInterval,
DefaultValue: 2 * 60 * 60,
MinValue: 10 * 60,
MaxValue: 24 * 60 * 60,
Required: true,
DisplayName: "Scan Interval",
Description: "How often to scan for volumes needing vacuum",
HelpText: "The system will check for volumes that need vacuuming at this interval",
Placeholder: "2",
Unit: config.UnitHours,
InputType: "interval",
CSSClasses: "form-control",
},
{
Name: "max_concurrent",
JSONName: "max_concurrent",
Type: config.FieldTypeInt,
DefaultValue: 2,
MinValue: 1,
MaxValue: 10,
Required: true,
DisplayName: "Max Concurrent Tasks",
Description: "Maximum number of vacuum tasks that can run simultaneously",
HelpText: "Limits the number of vacuum operations running at the same time to control system load",
Placeholder: "2 (default)",
Unit: config.UnitCount,
InputType: "number",
CSSClasses: "form-control",
},
{
Name: "garbage_threshold",
JSONName: "garbage_threshold",
Type: config.FieldTypeFloat,
DefaultValue: 0.3,
MinValue: 0.0,
MaxValue: 1.0,
Required: true,
DisplayName: "Garbage Percentage Threshold",
Description: "Trigger vacuum when garbage ratio exceeds this percentage",
HelpText: "Volumes with more deleted content than this threshold will be vacuumed",
Placeholder: "0.30 (30%)",
Unit: config.UnitNone,
InputType: "number",
CSSClasses: "form-control",
},
{
Name: "min_volume_age_seconds",
JSONName: "min_volume_age_seconds",
Type: config.FieldTypeInterval,
DefaultValue: 24 * 60 * 60,
MinValue: 1 * 60 * 60,
MaxValue: 7 * 24 * 60 * 60,
Required: true,
DisplayName: "Minimum Volume Age",
Description: "Only vacuum volumes older than this duration",
HelpText: "Prevents vacuuming of recently created volumes that may still be actively written to",
Placeholder: "24",
Unit: config.UnitHours,
InputType: "interval",
CSSClasses: "form-control",
},
},
}
}