Some checks failed
go: build dev binaries / cleanup (push) Successful in 4s
Codespell / Check for spelling errors (push) Failing after 3s
docker: build dev containers / build-rust-binaries (amd64, x86_64-unknown-linux-musl) (push) Failing after 3s
docker: build dev containers / build-dev-containers (push) Has been skipped
docker: build dev containers / build-rust-binaries (arm64, true, aarch64-unknown-linux-musl) (push) Failing after 3s
End to End / FUSE Mount (push) Failing after 2s
EC Integration Tests / EC Integration Tests (push) Failing after 30s
FUSE DLM Integration Tests / FUSE DLM Integration Tests (push) Failing after 3s
FUSE Volume Server Failover Tests / FUSE Volume Server Failover (push) Failing after 3s
FUSE Integration Tests / FUSE Integration Testing (push) Failing after 2s
FUSE P2P Peer Chunk Sharing Integration Tests / FUSE P2P Peer Chunk Sharing (push) Failing after 3s
go: build binary / Go Vet (push) Failing after 2s
go: build binary / Go Vet 32-bit (push) Failing after 3s
go: build binary / Build (push) Failing after 4s
go: build binary / Build cross-platform (freebsd/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (darwin/arm64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/arm64) (push) Failing after 3s
go: build binary / Test (push) Failing after 2s
go: build binary / Test 32-bit (push) Failing after 3s
helm: lint and test charts / lint-test (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (11) (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (17) (push) Failing after 3s
go: build dev binaries / build_dev_linux_windows (amd64, linux) (push) Failing after 2s
go: build dev binaries / build_dev_linux_windows (amd64, windows) (push) Failing after 3s
go: build dev binaries / build_dev_darwin (amd64, darwin) (push) Has been skipped
go: build dev binaries / build_dev_darwin (arm64, darwin) (push) Has been skipped
Java Client Unit Tests / Java Unit Tests (11) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (17) (push) Failing after 2s
Java Client Unit Tests / Java Unit Tests (21) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (8) (push) Failing after 3s
Kafka Quick Test (Load Test with Schema Registry) / Kafka Client Load Test (Quick) (push) Failing after 3s
Kafka Gateway Tests / Kafka Unit Tests (unit-tests-1) (push) Failing after 11s
Kafka Gateway Tests / Kafka Integration Tests (Critical) (integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka End-to-End Tests (with SMQ) (e2e-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Consumer Group Tests (Highly Isolated) (consumer-group-1) (push) Failing after 2s
Kafka Gateway Tests / Kafka Client Compatibility (with SMQ) (client-compat-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka SMQ Integration Tests (Full Stack) (smq-integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Protocol Tests (Isolated) (protocol-1) (push) Failing after 3s
KMS Tests / KMS Provider Integration Tests (push) Failing after 2s
KMS Tests / S3 KMS End-to-End Tests (push) Failing after 3s
Master Cold Start Tests / Master Cold Start Tests (push) Failing after 4s
Metadata Subscribe Integration Tests / Metadata Subscribe Integration Tests (push) Failing after 3s
Multi-Master Tests / Multi-Master Failover Tests (push) Failing after 3s
Performance / CPU and Heap Profile (push) Failing after 2s
Performance / S3 Read/Write Benchmark (rust volume) (push) Failing after 3s
pjdfstest POSIX Compliance / pjdfstest (push) Failing after 2s
Plugin Worker Integration Tests / Plugin Worker: erasure_coding (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: vacuum (push) Failing after 3s
Rust Volume Server Tests / Rust Integration Tests (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 1) (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 1) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 3) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Distributed Tests (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Performance Tests (push) Failing after 3s
Performance / Throughput Benchmark (go volume) (push) Failing after 3s
Performance / Throughput Benchmark (rust volume) (push) Failing after 2s
Performance / S3 Read/Write Benchmark (go volume) (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: volume_balance (push) Failing after 3s
PostgreSQL Gateway Tests / PostgreSQL Basic Tests (push) Failing after 3s
Rust Volume Server Tests / Rust Unit Tests (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 3) (push) Failing after 3s
Rust Plugin Worker Tests / Rust Plugin Worker Build and Unit Tests (push) Failing after 3s
rust: build dev volume server binaries / cleanup (push) Successful in 3s
S3 ETag and ACL Tests / S3 ETag + ACL Integration Tests (push) Failing after 3s
S3 IAM Integration Tests / IAM Unit Tests (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (advanced) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (basic) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (group) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (policy-enforcement) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (sts) (push) Failing after 4s
S3 Keycloak Integration Tests / S3 Keycloak Integration Tests (push) Failing after 3s
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.11) (push) Failing after 3s
S3 PyArrow Parquet Tests / Go Unit Tests (Implicit Directory) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.12) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-amd64, x86_64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-arm64, aarch64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-linux (linux-amd64, x86_64-unknown-linux-gnu) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.9) (push) Has been cancelled
S3 Proxy Signature Tests / S3 Proxy Signature Verification Tests (push) Has been cancelled
S3 SDK V2 Route Disambiguation Tests / S3 SDK V2 Routing Tests (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (quick) (push) Has been cancelled
S3 SSE Tests / S3 SSE Compatibility Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Metadata Persistence Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Copy Operations Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Multipart Upload Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Performance Test (push) Has been cancelled
S3 SSE Tests / S3 Volume Encryption Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (comprehensive) (push) Has been cancelled
Spark Integration Tests / Spark Integration Tests (push) Failing after 2s
Telemetry Integration Tests / telemetry-integration-test (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 1) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 1) (push) Failing after 3s
Ceph S3 tests / Basic S3 tests (KV store) (push) Has been cancelled
Ceph S3 tests / S3 Versioning & Object Lock tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Unit Tests (push) Failing after 3s
Ceph S3 tests / S3 CORS tests (push) Has been cancelled
Ceph S3 tests / SeaweedFS Custom S3 Copy tests (push) Has been cancelled
Ceph S3 tests / Basic S3 tests (SQL store) (push) Has been cancelled
test s3 over https using aws-cli / awscli-tests (push) Has been cancelled
TLS Rotation Integration Tests / TLS Rotation Integration Tests (push) Has been cancelled
Vacuum Integration Tests / Vacuum Integration Tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Variables Integration Tests (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (advanced-policy) (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (basic-policy) (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (contextual-policy) (push) Failing after 4s
S3 Policy Integration Tests / Trusted Proxy Detection Tests (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Shell Integration Tests (push) Failing after 3s
Samba on FUSE Integration / samba-integration (push) Failing after 2s
SFTP Integration Tests / SFTP Integration Testing (push) Failing after 3s
terraform: validate and test modules / fmt, validate, plan-level tests (push) Failing after 3s
terraform: validate and test modules / local cluster smoke test (real weed) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 3) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 2) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 2) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 3) (push) Failing after 5s
mount: windows conformance / WinFsp conformance (push) Has been cancelled
mount: windows / Mount on Windows (push) Has been cancelled
268 lines
9.7 KiB
Go
268 lines
9.7 KiB
Go
package ec_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 EC balance specific settings
|
|
type Config struct {
|
|
base.BaseConfig
|
|
ImbalanceThreshold float64 `json:"imbalance_threshold"`
|
|
MinServerCount int `json:"min_server_count"`
|
|
CollectionFilter string `json:"collection_filter"`
|
|
DiskType string `json:"disk_type"`
|
|
PreferredTags []string `json:"preferred_tags"`
|
|
ReplicaPlacement string `json:"replica_placement"` // e.g. "020"; empty falls back to the master default replication (even spread only when that default is empty or zero)
|
|
IoBytePerSecond int64 `json:"io_byte_per_second"` // limit each shard copy's rate; 0 falls back to the volume server's maintenance rate
|
|
DataCenterFilter string `json:"-"` // per-detection-run, not persisted
|
|
}
|
|
|
|
// NewDefaultConfig creates a new default EC balance configuration
|
|
func NewDefaultConfig() *Config {
|
|
return &Config{
|
|
BaseConfig: base.BaseConfig{
|
|
Enabled: true,
|
|
ScanIntervalSeconds: 60 * 60, // 1 hour
|
|
MaxConcurrent: 1,
|
|
},
|
|
ImbalanceThreshold: 0.2, // 20%
|
|
MinServerCount: 3,
|
|
CollectionFilter: "",
|
|
DiskType: "",
|
|
PreferredTags: nil,
|
|
}
|
|
}
|
|
|
|
// GetConfigSpec returns the configuration schema for EC 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 EC Shard Balance Tasks",
|
|
Description: "Whether EC shard balance tasks should be automatically created",
|
|
HelpText: "Toggle this to enable or disable automatic EC shard balancing",
|
|
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 EC shard imbalances",
|
|
HelpText: "The system will check for EC shard distribution imbalances 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 EC shard balance tasks that can run simultaneously",
|
|
HelpText: "Limits the number of EC shard balancing 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 shard count imbalance ratio to trigger balancing",
|
|
HelpText: "EC shard distribution imbalances above this threshold will trigger rebalancing",
|
|
Placeholder: "0.20 (20%)",
|
|
Unit: config.UnitNone,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "min_server_count",
|
|
JSONName: "min_server_count",
|
|
Type: config.FieldTypeInt,
|
|
DefaultValue: 3,
|
|
MinValue: 2,
|
|
MaxValue: 100,
|
|
Required: true,
|
|
DisplayName: "Minimum Server Count",
|
|
Description: "Minimum number of servers required for EC shard balancing",
|
|
HelpText: "EC shard balancing will only occur if there are at least this many servers",
|
|
Placeholder: "3 (default)",
|
|
Unit: config.UnitCount,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "collection_filter",
|
|
JSONName: "collection_filter",
|
|
Type: config.FieldTypeString,
|
|
DefaultValue: "",
|
|
Required: false,
|
|
DisplayName: "Collection Filter",
|
|
Description: "Only balance EC shards from specific collections (comma-separated names, wildcards, or regex patterns)",
|
|
HelpText: "Leave empty to balance all collections, or list the collections to balance",
|
|
Placeholder: "pictures,videos",
|
|
InputType: "text",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "disk_type",
|
|
JSONName: "disk_type",
|
|
Type: config.FieldTypeString,
|
|
DefaultValue: "",
|
|
Required: false,
|
|
DisplayName: "Disk Type",
|
|
Description: "Only balance EC shards on this disk type",
|
|
HelpText: "Leave empty for all disk types, or specify hdd or ssd",
|
|
Placeholder: "hdd",
|
|
InputType: "text",
|
|
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 shard placement",
|
|
HelpText: "EC shards will be placed on disks with these tags first, ordered by preference",
|
|
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 (even spread only when that default is empty or zero). When set, limits shards per rack/node per the placement digits (dc/rack/node)",
|
|
Placeholder: "020",
|
|
InputType: "text",
|
|
CSSClasses: "form-control",
|
|
},
|
|
{
|
|
Name: "io_byte_per_second",
|
|
JSONName: "io_byte_per_second",
|
|
Type: config.FieldTypeInt,
|
|
DefaultValue: 0,
|
|
MinValue: 0,
|
|
Required: false,
|
|
DisplayName: "Shard Copy IO Limit (bytes/sec)",
|
|
Description: "Limit each EC shard copy's rate",
|
|
HelpText: "0 falls back to each volume server's own maintenance rate (-maintenanceBytePerSecond)",
|
|
Placeholder: "0 (server maintenance rate)",
|
|
Unit: config.UnitNone,
|
|
InputType: "number",
|
|
CSSClasses: "form-control",
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
// ToTaskPolicy converts configuration to a TaskPolicy protobuf message
|
|
func (c *Config) ToTaskPolicy() *worker_pb.TaskPolicy {
|
|
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_EcBalanceConfig{
|
|
EcBalanceConfig: &worker_pb.EcBalanceTaskConfig{
|
|
ImbalanceThreshold: c.ImbalanceThreshold,
|
|
MinServerCount: int32(c.MinServerCount),
|
|
CollectionFilter: c.CollectionFilter,
|
|
DiskType: c.DiskType,
|
|
PreferredTags: preferredTagsCopy,
|
|
ReplicaPlacement: c.ReplicaPlacement,
|
|
IoBytePerSecond: c.IoBytePerSecond,
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
// 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")
|
|
}
|
|
|
|
c.Enabled = policy.Enabled
|
|
c.MaxConcurrent = int(policy.MaxConcurrent)
|
|
c.ScanIntervalSeconds = int(policy.RepeatIntervalSeconds)
|
|
|
|
if ecbConfig := policy.GetEcBalanceConfig(); ecbConfig != nil {
|
|
c.ImbalanceThreshold = ecbConfig.ImbalanceThreshold
|
|
c.MinServerCount = int(ecbConfig.MinServerCount)
|
|
c.CollectionFilter = ecbConfig.CollectionFilter
|
|
c.DiskType = ecbConfig.DiskType
|
|
c.PreferredTags = append([]string(nil), ecbConfig.PreferredTags...)
|
|
c.ReplicaPlacement = ecbConfig.ReplicaPlacement
|
|
c.IoBytePerSecond = ecbConfig.IoBytePerSecond
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
// LoadConfigFromPersistence loads configuration from the persistence layer if available
|
|
func LoadConfigFromPersistence(configPersistence interface{}) *Config {
|
|
cfg := NewDefaultConfig()
|
|
|
|
if persistence, ok := configPersistence.(interface {
|
|
LoadEcBalanceTaskPolicy() (*worker_pb.TaskPolicy, error)
|
|
}); ok {
|
|
policy, err := persistence.LoadEcBalanceTaskPolicy()
|
|
switch {
|
|
case err != nil:
|
|
glog.Warningf("Could not read the persisted EC balance configuration, falling back to defaults: %v", err)
|
|
case policy == nil:
|
|
glog.V(1).Infof("No EC balance configuration persisted yet, using defaults")
|
|
default:
|
|
if err := cfg.FromTaskPolicy(policy); err != nil {
|
|
glog.Warningf("Could not apply the persisted EC balance configuration, falling back to defaults: %v", err)
|
|
} else {
|
|
glog.V(1).Infof("Loaded EC balance configuration from persistence")
|
|
return cfg
|
|
}
|
|
}
|
|
} 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 EC balance configuration: it has no LoadEcBalanceTaskPolicy() method, "+
|
|
"so the compiled-in defaults are used and any saved EC balance settings are ignored", configPersistence)
|
|
}
|
|
|
|
glog.V(1).Infof("Using default EC balance configuration")
|
|
return cfg
|
|
}
|