Files
seaweedFS/weed/plugin/worker/ec_balance_handler_test.go
Chris Lu a838661b83 feat(plugin): EC shard balance handler for plugin worker (#8629)
* feat(ec_balance): add TaskTypeECBalance constant and protobuf definitions

Add the ec_balance task type constant to both topology and worker type
systems. Define EcBalanceTaskParams, EcShardMoveSpec, and
EcBalanceTaskConfig protobuf messages for EC shard balance operations.

* feat(ec_balance): add configuration for EC shard balance task

Config includes imbalance threshold, min server count, collection
filter, disk type, and preferred tags for tag-aware placement.

* feat(ec_balance): add multi-phase EC shard balance detection algorithm

Implements four detection phases adapted from the ec.balance shell
command:
1. Duplicate shard detection and removal proposals
2. Cross-rack shard distribution balancing
3. Within-rack node-level shard balancing
4. Global shard count equalization across nodes

Detection is side-effect-free: it builds an EC topology view from
ActiveTopology and generates move proposals without executing them.

* feat(ec_balance): add EC shard move task execution

Implements the shard move sequence using the same VolumeEcShardsCopy,
VolumeEcShardsMount, VolumeEcShardsUnmount, and VolumeEcShardsDelete
RPCs as the shell ec.balance command. Supports both regular shard
moves and dedup-phase deletions (unmount+delete without copy).

* feat(ec_balance): add task registration and scheduling

Register EC balance task definition with auto-config update support.
Scheduling respects max concurrent limits and worker capabilities.

* feat(ec_balance): add plugin handler for EC shard balance

Implements the full plugin handler with detection, execution, admin
and worker config forms, proposal building, and decision trace
reporting. Supports collection/DC/disk type filtering, preferred tag
placement, and configurable detection intervals. Auto-registered via
init() with the handler registry.

* test(ec_balance): add tests for detection algorithm and plugin handler

Detection tests cover: duplicate shard detection, cross-rack imbalance,
within-rack imbalance, global rebalancing, topology building, collection
filtering, and edge cases. Handler tests cover: config derivation with
clamping, proposal building, protobuf encode/decode round-trip, fallback
parameter decoding, capability, and config policy round-trip.

* fix(ec_balance): address PR review feedback and fix CI test failure

- Update TestWorkerDefaultJobTypes to expect 6 handlers (was 5)
- Extract threshold constants (ecBalanceMinImbalanceThreshold, etc.)
  to eliminate magic numbers in Descriptor and config derivation
- Remove duplicate ShardIdsToUint32 helper (use erasure_coding package)
- Add bounds checks for int64→int/uint32 conversions to fix CodeQL
  integer conversion warnings

* fix(ec_balance): address code review findings

storage_impact.go:
- Add TaskTypeECBalance case returning shard-level reservation
  (ShardSlots: -1/+1) instead of falling through to default which
  incorrectly reserves a full volume slot on target.

detection.go:
- Use dc:rack composite key to avoid cross-DC rack name collisions.
  Only create rack entries after confirming node has matching disks.
- Add exceedsImbalanceThreshold check to cross-rack, within-rack,
  and global phases so trivial skews below the configured threshold
  are ignored. Dedup phase always runs since duplicates are errors.
- Reserve destination capacity after each planned move (decrement
  destNode.freeSlots, update rackShardCount/nodeShardCount) to
  prevent overbooking the same destination.
- Skip nodes with freeSlots <= 0 when selecting minNode in global
  balance to avoid proposing moves to full nodes.
- Include loop index and source/target node IDs in TaskID to
  guarantee uniqueness across moves with the same volumeID/shardID.

ec_balance_handler.go:
- Fail fast with error when shard_id is absent in fallback parameter
  decoding instead of silently defaulting to shard 0.

ec_balance_task.go:
- Delegate GetProgress() to BaseTask.GetProgress() so progress
  updates from ReportProgressWithStage are visible to callers.
- Add fail-fast guard rejecting multiple sources/targets until
  batch execution is implemented.

Findings verified but not changed (matches existing codebase pattern
in vacuum/balance/erasure_coding handlers):
- register.go globalTaskDef.Config race: same unsynchronized pattern
  in all 4 task packages.
- CreateTask using generated ID: same fmt.Sprintf pattern in all 4
  task packages.

* fix(ec_balance): harden parameter decoding, progress tracking, and validation

ec_balance_handler.go (decodeECBalanceTaskParams):
- Validate execution-critical fields (Sources[0].Node, ShardIds,
  Targets[0].Node, ShardIds) after protobuf deserialization.
- Require source_disk_id and target_disk_id in legacy fallback path
  so Targets[0].DiskId is populated for VolumeEcShardsCopyRequest.
- All error messages reference decodeECBalanceTaskParams and the
  specific missing field (TaskParams, shard_id, Targets[0].DiskId,
  EcBalanceTaskParams) for debuggability.

ec_balance_task.go:
- Track progress in ECBalanceTask.progress field, updated via
  reportProgress() helper called before ReportProgressWithStage(),
  so GetProgress() returns real stage progress instead of stale 0.
- Validate: require exactly 1 source and 1 target (mirrors Execute
  guard), require ShardIds on both, with error messages referencing
  ECBalanceTask.Validate and the specific field.

* fix(ec_balance): fix dedup execution path, stale topology, collection filter, timeout, and dedupeKey

detection.go:
- Dedup moves now set target=source so isDedupPhase() triggers the
  unmount+delete-only execution path instead of attempting a copy.
- Apply moves to in-memory topology between phases via
  applyMovesToTopology() so subsequent phases see updated shard
  placement and don't conflict with already-planned moves.
- detectGlobalImbalance now accepts allowedVids and filters both
  shard counting and shard selection to respect CollectionFilter.

ec_balance_task.go:
- Apply EcBalanceTaskParams.TimeoutSeconds to the context via
  context.WithTimeout so all RPC operations respect the configured
  timeout instead of hanging indefinitely.

ec_balance_handler.go:
- Include source node ID in dedupeKey so dedup deletions from
  different source nodes for the same shard aren't collapsed.
- Clamp minServerCountRaw and minIntervalRaw lower bounds on int64
  before narrowing to int, preventing undefined overflow on 32-bit.

* fix(ec_balance): log warning before cancelling on progress send failure

Log the error, job ID, job type, progress percentage, and stage
before calling execCancel() in the progress callback so failed
progress sends are diagnosable instead of silently cancelling.
2026-03-14 21:34:53 -07:00

326 lines
10 KiB
Go

package pluginworker
import (
"testing"
"github.com/seaweedfs/seaweedfs/weed/pb/plugin_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
ecbalancetask "github.com/seaweedfs/seaweedfs/weed/worker/tasks/ec_balance"
workertypes "github.com/seaweedfs/seaweedfs/weed/worker/types"
"google.golang.org/protobuf/proto"
)
func TestDeriveECBalanceWorkerConfig(t *testing.T) {
tests := []struct {
name string
values map[string]*plugin_pb.ConfigValue
check func(t *testing.T, config *ecBalanceWorkerConfig)
}{
{
name: "nil values uses defaults",
values: nil,
check: func(t *testing.T, config *ecBalanceWorkerConfig) {
if config.TaskConfig.ImbalanceThreshold != 0.2 {
t.Errorf("expected default threshold 0.2, got %f", config.TaskConfig.ImbalanceThreshold)
}
if config.TaskConfig.MinServerCount != 3 {
t.Errorf("expected default min_server_count 3, got %d", config.TaskConfig.MinServerCount)
}
},
},
{
name: "custom threshold",
values: map[string]*plugin_pb.ConfigValue{
"imbalance_threshold": {Kind: &plugin_pb.ConfigValue_DoubleValue{DoubleValue: 0.3}},
"min_server_count": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 5}},
},
check: func(t *testing.T, config *ecBalanceWorkerConfig) {
if config.TaskConfig.ImbalanceThreshold != 0.3 {
t.Errorf("expected threshold 0.3, got %f", config.TaskConfig.ImbalanceThreshold)
}
if config.TaskConfig.MinServerCount != 5 {
t.Errorf("expected min_server_count 5, got %d", config.TaskConfig.MinServerCount)
}
},
},
{
name: "threshold clamped to min",
values: map[string]*plugin_pb.ConfigValue{
"imbalance_threshold": {Kind: &plugin_pb.ConfigValue_DoubleValue{DoubleValue: 0.01}},
},
check: func(t *testing.T, config *ecBalanceWorkerConfig) {
if config.TaskConfig.ImbalanceThreshold != 0.05 {
t.Errorf("expected clamped threshold 0.05, got %f", config.TaskConfig.ImbalanceThreshold)
}
},
},
{
name: "threshold clamped to max",
values: map[string]*plugin_pb.ConfigValue{
"imbalance_threshold": {Kind: &plugin_pb.ConfigValue_DoubleValue{DoubleValue: 0.9}},
},
check: func(t *testing.T, config *ecBalanceWorkerConfig) {
if config.TaskConfig.ImbalanceThreshold != 0.5 {
t.Errorf("expected clamped threshold 0.5, got %f", config.TaskConfig.ImbalanceThreshold)
}
},
},
{
name: "min_server_count clamped to 2",
values: map[string]*plugin_pb.ConfigValue{
"min_server_count": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 1}},
},
check: func(t *testing.T, config *ecBalanceWorkerConfig) {
if config.TaskConfig.MinServerCount != 2 {
t.Errorf("expected min_server_count 2, got %d", config.TaskConfig.MinServerCount)
}
},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
config := deriveECBalanceWorkerConfig(tt.values)
tt.check(t, config)
})
}
}
func TestBuildECBalanceProposal(t *testing.T) {
result := &workertypes.TaskDetectionResult{
TaskID: "test-task-123",
TaskType: workertypes.TaskTypeECBalance,
VolumeID: 42,
Collection: "test-col",
Priority: workertypes.TaskPriorityMedium,
Reason: "cross_rack balance",
TypedParams: &worker_pb.TaskParams{
VolumeId: 42,
Collection: "test-col",
Sources: []*worker_pb.TaskSource{{
Node: "source:8080",
ShardIds: []uint32{5},
}},
Targets: []*worker_pb.TaskTarget{{
Node: "target:8080",
ShardIds: []uint32{5},
}},
},
}
proposal, err := buildECBalanceProposal(result)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if proposal.JobType != "ec_balance" {
t.Errorf("expected job type ec_balance, got %s", proposal.JobType)
}
if proposal.ProposalId != "test-task-123" {
t.Errorf("expected proposal ID test-task-123, got %s", proposal.ProposalId)
}
if proposal.DedupeKey != "ec_balance:42:5:source:8080:test-col" {
t.Errorf("expected dedupe key ec_balance:42:5:source:8080:test-col, got %s", proposal.DedupeKey)
}
if proposal.Labels["source_node"] != "source:8080" {
t.Errorf("expected source_node label source:8080, got %s", proposal.Labels["source_node"])
}
if proposal.Labels["target_node"] != "target:8080" {
t.Errorf("expected target_node label target:8080, got %s", proposal.Labels["target_node"])
}
}
func TestBuildECBalanceProposalNilResult(t *testing.T) {
_, err := buildECBalanceProposal(nil)
if err == nil {
t.Fatal("expected error for nil result")
}
}
func TestDecodeECBalanceTaskParamsFromProtobuf(t *testing.T) {
originalParams := &worker_pb.TaskParams{
TaskId: "test-id",
VolumeId: 100,
Collection: "test-col",
Sources: []*worker_pb.TaskSource{{
Node: "source:8080",
ShardIds: []uint32{3},
}},
Targets: []*worker_pb.TaskTarget{{
Node: "target:8080",
ShardIds: []uint32{3},
}},
TaskParams: &worker_pb.TaskParams_EcBalanceParams{
EcBalanceParams: &worker_pb.EcBalanceTaskParams{
DiskType: "hdd",
TimeoutSeconds: 300,
},
},
}
payload, err := proto.Marshal(originalParams)
if err != nil {
t.Fatalf("failed to marshal: %v", err)
}
job := &plugin_pb.JobSpec{
JobId: "job-1",
Parameters: map[string]*plugin_pb.ConfigValue{
"task_params_pb": {Kind: &plugin_pb.ConfigValue_BytesValue{BytesValue: payload}},
},
}
decoded, err := decodeECBalanceTaskParams(job)
if err != nil {
t.Fatalf("failed to decode: %v", err)
}
if decoded.VolumeId != 100 {
t.Errorf("expected volume_id 100, got %d", decoded.VolumeId)
}
if decoded.Collection != "test-col" {
t.Errorf("expected collection test-col, got %s", decoded.Collection)
}
if len(decoded.Sources) != 1 || decoded.Sources[0].Node != "source:8080" {
t.Error("source mismatch")
}
if len(decoded.Targets) != 1 || decoded.Targets[0].Node != "target:8080" {
t.Error("target mismatch")
}
ecParams := decoded.GetEcBalanceParams()
if ecParams == nil {
t.Fatal("expected ec_balance_params")
}
if ecParams.DiskType != "hdd" {
t.Errorf("expected disk_type hdd, got %s", ecParams.DiskType)
}
}
func TestDecodeECBalanceTaskParamsFallback(t *testing.T) {
job := &plugin_pb.JobSpec{
JobId: "job-2",
Parameters: map[string]*plugin_pb.ConfigValue{
"volume_id": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 200}},
"source_server": {Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "src:8080"}},
"target_server": {Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "dst:8080"}},
"collection": {Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "fallback-col"}},
"shard_id": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 7}},
"source_disk_id": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 1}},
"target_disk_id": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 2}},
},
}
decoded, err := decodeECBalanceTaskParams(job)
if err != nil {
t.Fatalf("failed to decode fallback: %v", err)
}
if decoded.VolumeId != 200 {
t.Errorf("expected volume_id 200, got %d", decoded.VolumeId)
}
if len(decoded.Sources) != 1 || decoded.Sources[0].Node != "src:8080" {
t.Error("source mismatch")
}
if decoded.Sources[0].ShardIds[0] != 7 {
t.Errorf("expected shard_id 7, got %d", decoded.Sources[0].ShardIds[0])
}
if decoded.Sources[0].DiskId != 1 {
t.Errorf("expected source disk_id 1, got %d", decoded.Sources[0].DiskId)
}
if decoded.Targets[0].DiskId != 2 {
t.Errorf("expected target disk_id 2, got %d", decoded.Targets[0].DiskId)
}
}
func TestDecodeECBalanceTaskParamsProtobufValidation(t *testing.T) {
// Protobuf payload with missing ShardIds should fail validation
badParams := &worker_pb.TaskParams{
TaskId: "test-id",
VolumeId: 100,
Sources: []*worker_pb.TaskSource{{Node: "source:8080"}}, // no ShardIds
Targets: []*worker_pb.TaskTarget{{Node: "target:8080", ShardIds: []uint32{3}}},
}
payload, _ := proto.Marshal(badParams)
job := &plugin_pb.JobSpec{
JobId: "job-validate",
Parameters: map[string]*plugin_pb.ConfigValue{
"task_params_pb": {Kind: &plugin_pb.ConfigValue_BytesValue{BytesValue: payload}},
},
}
_, err := decodeECBalanceTaskParams(job)
if err == nil {
t.Fatal("expected error for missing Sources[0].ShardIds in protobuf")
}
}
func TestDecodeECBalanceTaskParamsMissingShardID(t *testing.T) {
job := &plugin_pb.JobSpec{
JobId: "job-3",
Parameters: map[string]*plugin_pb.ConfigValue{
"volume_id": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 300}},
"source_server": {Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "src:8080"}},
"target_server": {Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "dst:8080"}},
"collection": {Kind: &plugin_pb.ConfigValue_StringValue{StringValue: "test-col"}},
// shard_id deliberately missing
},
}
_, err := decodeECBalanceTaskParams(job)
if err == nil {
t.Fatal("expected error for missing shard_id")
}
}
func TestECBalanceHandlerCapability(t *testing.T) {
handler := NewECBalanceHandler(nil)
cap := handler.Capability()
if cap.JobType != "ec_balance" {
t.Errorf("expected job type ec_balance, got %s", cap.JobType)
}
if !cap.CanDetect {
t.Error("expected CanDetect=true")
}
if !cap.CanExecute {
t.Error("expected CanExecute=true")
}
if cap.Weight != 60 {
t.Errorf("expected weight 60, got %d", cap.Weight)
}
}
func TestECBalanceConfigRoundTrip(t *testing.T) {
config := ecbalancetask.NewDefaultConfig()
config.ImbalanceThreshold = 0.3
config.MinServerCount = 5
config.CollectionFilter = "my_col"
config.DiskType = "ssd"
config.PreferredTags = []string{"fast", "ssd"}
policy := config.ToTaskPolicy()
if policy == nil {
t.Fatal("expected non-nil policy")
}
config2 := ecbalancetask.NewDefaultConfig()
if err := config2.FromTaskPolicy(policy); err != nil {
t.Fatalf("failed to load from policy: %v", err)
}
if config2.ImbalanceThreshold != 0.3 {
t.Errorf("expected threshold 0.3, got %f", config2.ImbalanceThreshold)
}
if config2.MinServerCount != 5 {
t.Errorf("expected min_server_count 5, got %d", config2.MinServerCount)
}
if config2.CollectionFilter != "my_col" {
t.Errorf("expected collection_filter my_col, got %s", config2.CollectionFilter)
}
if config2.DiskType != "ssd" {
t.Errorf("expected disk_type ssd, got %s", config2.DiskType)
}
if len(config2.PreferredTags) != 2 || config2.PreferredTags[0] != "fast" {
t.Errorf("expected preferred_tags [fast ssd], got %v", config2.PreferredTags)
}
}