Files
milvus/internal/datacoord/task_index.go
T
e2787d3981 enhance: standardize error handling on merr + Sys/Input classification (#50221)
issue: #47420

## What this PR does

Project-wide migration of raw `fmt.Errorf` / `errors.New` in function
bodies onto
the `merr` framework, plus the Sys-vs-Input error classification and the
machinery it drives (retriability, fine-grained metrics, segcore
unification),
plus the convention docs and a linter that keeps it from regressing.

Scope: storage, proxy, coordinators (root/data/query), query node, data
node,
`pkg/util` & `internal/util`, expression parser, message queue,
streaming, and
misc packages. Bare raw-error usages went from ~3000 to a ~340 allowlist
(package-level sentinels / build-tag / test sites).

---

## How to review this PR

It is large but the vast majority is mechanical. Changes fall into three
tiers;
spend review budget on Part 2 and Part 3.

### Part 1 — Mechanical standardization (low risk, verify by rule)

Each converted call follows one of a small fixed set of rules. To
review, check
that each site obeys the matching rule rather than reading every line:

| Pattern | Rule |
|---|---|
| `fmt.Errorf("...")` originating a new error | →
`merr.WrapErrXxxMsg("...")` with a code matching the failure's meaning |
| Adding context to an existing typed error | → `merr.Wrap(err, "...")`
/ `merr.Wrapf(...)` — **preserves** the inner code (never `WrapErr*Err`,
which overwrites it) |
| Errors inside the streaming subsystem | → `status.New*` factories
(StreamingError), **not** merr — this is the component-internal dialect
(see `docs/dev/error_handling_guide.md`) |
| Low-level / control-flow signal caught by `errors.Is` | → kept as a
package-level `errors.New` sentinel (lowercase, same-package) |

Conventions are documented in `docs/dev/error_handling_guide.md`
(how-to) and
`docs/dev/error_sentinel_convention.md` (rules + audit). A
`gocritic`/`ruleguard`
rule (`rawmerrerror`, in `rules.go`) enforces "no raw `return
errors.New/fmt.Errorf`"
under `make verifiers`.

### Part 2 — Behavior changes (review these closely)

These are the sites where the wire contract or runtime behavior changes,
not just
the source text. Listed by category; representative locations given,
full set in
the diff.

**A. gRPC wire-code shifts: `UnexpectedError(1)/Code 65535` → typed
code.**
Where a handler previously returned a raw error (collapsed to
`Code=65535` on the
wire), it now returns a typed merr, so the client sees a real code. The
most
common shift is to `IllegalArgument(5)/Code 1100` (ParameterInvalid).
Touch
points include datanode task handlers (CreateTask/Query/Drop), proxy
Upsert,
querynode GetMetrics, datacoord CreateIndex, httpserver query-response
builder,
and typeutil schema validation. One code refinement: an index-param
validation
moved `1100` → `1101` (ParameterMissing). **Client/SDK assertions and
any code
that switched on `Code=65535` for these paths must be re-checked** (the
go_client
e2e assertions were already aligned in this PR).

**B. Prometheus `status` label contract change (externally visible).**
The proxy metric's coarse `fail` / `rejected` values are split into
`fail_input` / `fail_system` and `rejected_user` / `rejected_system` (in
`requestutil.ParseMetricLabel`; auth/privilege rejections count as
`rejected_user`), so dashboards can attribute a failure to caller vs
operator.
**Dashboards/alerts querying `status="fail"` must migrate to
`status=~"fail_.*"`, and `status="rejected"` to
`status=~"rejected_.*"`.** The
in-repo Grafana dashboard is already migrated; external dashboards built
on the
old values silently go empty after upgrade. This is the one change that
requires an ops-side migration.

**C. Retriability semantics.**
- C1: `merr.Status(err)` now forces `Retriable=false` when the error is
an
`InputError` — a malformed request can never succeed on blind retry, so
clients
never get the self-contradictory "your input is wrong but you may
retry".
- C2: `retry.Do` short-circuits an `InputError` (non-retriable) — **but
only when
  the caller did not pass a `RetryErr` predicate**. The check is an
`if c.isRetryErr != nil { ... } else if InputError { ... }` *mutually
exclusive*
branch (`pkg/util/retry/retry.go`): an explicit `RetryErr` takes
precedence and
bypasses the InputError abort. `retry.Handle` deliberately does **not**
apply
the InputError abort (its callers signal abort via `shouldRetry=false`).
Four
flusher startup callsites that must retry through transient "not ready"
errors
  were given explicit `RetryErr` escape hatches.

**D. segcore (C++→Go) error classification.**
A single shared Go-side table (`pkg/util/merr/segcore.go`) maps each
segcore code
to a merr sentinel + InputError/signal category, replacing scattered
hand-written
`if errorCode == ...` switches in the cgo wrappers. **Wire `Code` values
change
for every segcore pass-through error, not just the remapped ones.**
Named
sentinels remap (C++ `2003` → merr `2001`, `2033` → `2002`,
Folly/Knowhere codes
likewise); **all remaining pass-through codes (`2004`–`2043`, previously
surfaced to clients as raw C++ enum values) now serialize as `2000`**
(`ErrSegcore`), with the original C++ code preserved in the `Reason`
text
(`segcoreCode=...`); unknown/future codes collapse to `2000` as well
(pinned by
the `wire_code_projection` test). Transient segcore classes (object
storage /
file IO / OOM / mmap / FieldNotLoaded — 11 codes) now report
`Retriable=true`.
**Any client switching on raw segcore codes in the `2004`–`2043` range
must be
re-checked**; the in-Reason code remains available for diagnostics.
Signal
codes (PretendFinished / FollyCancel) are recognized centrally.
`errors.Is`-based
control flow on these (e.g. scheduler skip/retry) is preserved.

**E. InputError classification (25 sentinels + dynamic marks).**
25 sentinels in `errors.go` carry `WithErrorType(InputError)` (the
Collection /
ResourceGroup / Database families, `ErrIndexDuplicate`,
`ErrParameterInvalid`,
`ErrPrivilegeNotAuthenticated`, `ErrImportFailed`, `ErrQueryPlan`, ...),
plus dynamic
marks for the 8 segcore input codes (ExprInvalid, DimNotMatch,
MetricTypeInvalid, FieldIDInvalid, ...) and
`WrapErrAsInputError`. The widest blast radius is `ErrParameterInvalid`
(1100):
~2335 `WrapErrParameterInvalid*` callsites now classify as input /
non-retriable. Because of C1/C2 this changes retriability for
any path that returns these. **The audit to confirm no transient path
was
mis-marked is the single most important review item** (see Part 3). One
reverse
correction: storage field-stats parsing moved from `ErrParameterInvalid`
(input)
to `ErrDataIntegrity` — a corrupted stored stat is data corruption, not
user
input.

### Part 3 — Known risks & traps (called out proactively)

1. **`merr.Wrap` vs `WrapErr*Err` (code-masking).** `WrapErr*Err` builds
a
`wrappedMilvusError{sentinel: ErrServiceInternal}` whose `code()`
returns the
*outer* sentinel — it overwrites the inner typed code and hides the
`errors.Is`
chain. This is intentional (use it to *deliberately* downgrade), but it
was a
recurring conversion defect; the rule "add context with `merr.Wrap`,
downgrade
with `WrapErr*Err`" is enforced by convention and reviewed across the
diff.
2. **InputError × `retry.Do` blast radius.** Marking a sentinel
`InputError` makes
any `retry.Do(...)` without a `RetryErr` predicate stop retrying it.
Reviewers
should sanity-check that no transient use of the 19 newly-marked
sentinels
(especially `ErrParameterInvalid`) sits inside a retry loop that needed
to keep
   spinning. The known flusher cases were handled (see C2).
3. **The ~340 raw-error allowlist.** What remains as bare `errors.New`
is, by
design: package-level sentinels (caught by `errors.Is`), `//go:build
test`
sites, and out-of-band trees (`cmd/`, `tests/`, codegen, walimpls). The
linter
only bans the *direct-return* form; assignment-then-return escapes and
the full
no-exceptions ban are deferred to an AST-based linter (Tier 2,
documented).
4. **segcore C++ second step deferred.** This PR unifies classification
on the Go
side; splitting the dual-semantic C++ codes at the source is a
follow-up.

---

## Validation

- `make verifiers`: Go side clean (gofmt + static-check across modules,
including
  the new `rawmerrerror` rule with a 0-hit baseline repo-wide).
- `make test-go`: passing; the one real regression introduced (a
datanode
`invalid_task_type` assertion shifting `1` → `5` from a ParameterInvalid
  conversion) was fixed in-tree.
- go_client e2e CreateIndex assertions aligned to the new merr messages.

---------

Signed-off-by: zhenshan.cao <zhenshan.cao@zilliz.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-12 15:04:51 -07:00

440 lines
16 KiB
Go

// Licensed to the LF AI & Data foundation under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package datacoord
import (
"context"
"path"
"time"
"github.com/cockroachdb/errors"
"go.uber.org/zap"
"github.com/milvus-io/milvus-proto/go-api/v3/commonpb"
"github.com/milvus-io/milvus-proto/go-api/v3/schemapb"
"github.com/milvus-io/milvus/internal/datacoord/session"
globalTask "github.com/milvus-io/milvus/internal/datacoord/task"
"github.com/milvus-io/milvus/internal/metastore/model"
"github.com/milvus-io/milvus/internal/storage"
"github.com/milvus-io/milvus/internal/util/segmentutil"
"github.com/milvus-io/milvus/internal/util/vecindexmgr"
"github.com/milvus-io/milvus/pkg/v3/common"
"github.com/milvus-io/milvus/pkg/v3/log"
"github.com/milvus-io/milvus/pkg/v3/proto/indexpb"
"github.com/milvus-io/milvus/pkg/v3/proto/workerpb"
"github.com/milvus-io/milvus/pkg/v3/taskcommon"
"github.com/milvus-io/milvus/pkg/v3/util/indexparams"
"github.com/milvus-io/milvus/pkg/v3/util/merr"
"github.com/milvus-io/milvus/pkg/v3/util/paramtable"
"github.com/milvus-io/milvus/pkg/v3/util/typeutil"
)
type indexBuildTask struct {
*model.SegmentIndex
taskSlot int64
times *taskcommon.Times
meta *meta
handler Handler
chunkManager storage.ChunkManager
indexEngineVersionManager IndexEngineVersionManager
}
var _ globalTask.Task = (*indexBuildTask)(nil)
func newIndexBuildTask(segIndex *model.SegmentIndex,
taskSlot int64,
meta *meta,
handler Handler,
chunkManager storage.ChunkManager,
indexEngineVersionManager IndexEngineVersionManager,
) *indexBuildTask {
return &indexBuildTask{
SegmentIndex: segIndex,
taskSlot: taskSlot,
times: taskcommon.NewTimes(),
meta: meta,
handler: handler,
chunkManager: chunkManager,
indexEngineVersionManager: indexEngineVersionManager,
}
}
func (it *indexBuildTask) GetTaskID() int64 {
return it.BuildID
}
func (it *indexBuildTask) GetTaskSlot() int64 {
return it.taskSlot
}
func (it *indexBuildTask) GetTaskState() taskcommon.State {
return taskcommon.State(it.IndexState)
}
func (it *indexBuildTask) SetTaskTime(timeType taskcommon.TimeType, time time.Time) {
it.times.SetTaskTime(timeType, time)
}
func (it *indexBuildTask) GetTaskTime(timeType taskcommon.TimeType) time.Time {
return timeType.GetTaskTime(it.times)
}
func (it *indexBuildTask) GetTaskType() taskcommon.Type {
return taskcommon.Index
}
func (it *indexBuildTask) GetTaskVersion() int64 {
return it.IndexVersion
}
func (it *indexBuildTask) SetState(state indexpb.JobState, failReason string) {
it.IndexState = commonpb.IndexState(state)
it.FailReason = failReason
}
func (it *indexBuildTask) UpdateStateWithMeta(state indexpb.JobState, failReason string) error {
if err := it.meta.indexMeta.UpdateIndexState(it.BuildID, commonpb.IndexState(state), failReason); err != nil {
return err
}
it.SetState(state, failReason)
return nil
}
func (it *indexBuildTask) UpdateTaskVersion(nodeID int64) error {
if err := it.meta.indexMeta.UpdateVersion(it.BuildID, nodeID); err != nil {
return err
}
it.IndexVersion++
it.NodeID = nodeID
return nil
}
func (it *indexBuildTask) setJobInfo(result *workerpb.IndexTaskInfo) error {
if err := it.meta.indexMeta.FinishTask(result); err != nil {
return err
}
it.SetState(indexpb.JobState(result.GetState()), result.GetFailReason())
return nil
}
func (it *indexBuildTask) resetTask(reason string) {
it.UpdateStateWithMeta(indexpb.JobState_JobStateInit, reason)
}
func (it *indexBuildTask) dropAndResetTaskOnWorker(cluster session.Cluster, reason string) {
if err := it.tryDropTaskOnWorker(cluster); err != nil {
return
}
it.resetTask(reason)
}
func (it *indexBuildTask) CreateTaskOnWorker(nodeID int64, cluster session.Cluster) {
ctx := context.TODO()
log := log.Ctx(ctx).With(zap.Int64("taskID", it.BuildID), zap.Int64("segmentID", it.SegmentID))
// Check if task exists in meta
segIndex, exist := it.meta.indexMeta.GetIndexJob(it.BuildID)
if !exist || segIndex == nil {
log.Info("index task has not exist in meta table, removing task")
it.SetState(indexpb.JobState_JobStateNone, "index task has not exist in meta table")
return
}
// Check segment health and index existence
segment := it.meta.GetSegment(ctx, segIndex.SegmentID)
if !isSegmentHealthy(segment) || !it.meta.indexMeta.IsIndexExist(segIndex.CollectionID, segIndex.IndexID) {
log.Info("task is no need to build index, removing it")
it.SetState(indexpb.JobState_JobStateNone, "task is no need to build index")
return
}
// Handle special cases for certain index types or small segments
indexParams := it.meta.indexMeta.GetIndexParams(segIndex.CollectionID, segIndex.IndexID)
indexType := GetIndexType(indexParams)
effectiveRows := segIndex.NumRows
if fieldID := it.meta.indexMeta.GetFieldIDByIndexID(segIndex.CollectionID, segIndex.IndexID); fieldID > 0 {
if collectionInfo, err := it.handler.GetCollection(ctx, segIndex.CollectionID); err == nil {
for _, f := range typeutil.GetAllFieldSchemas(collectionInfo.Schema) {
if f.FieldID == fieldID && f.GetNullable() && typeutil.IsVectorType(f.GetDataType()) {
effectiveRows = segmentutil.CalcValidRowCountFromFieldBinLog(segment.SegmentInfo, fieldID)
break
}
}
}
}
if isNoTrainIndex(indexType) || effectiveRows < Params.DataCoordCfg.MinSegmentNumRowsToEnableIndex.GetAsInt64() {
log.Info("segment does not need index really, marking as finished", zap.Int64("numRows", segIndex.NumRows), zap.Int64("effectiveRows", effectiveRows))
now := time.Now()
it.SetTaskTime(taskcommon.TimeStart, now)
it.SetTaskTime(taskcommon.TimeEnd, now)
it.UpdateStateWithMeta(indexpb.JobState_JobStateFinished, "fake finished index success")
return
}
// Create job request
req, err := it.prepareJobRequest(ctx, segment, segIndex, indexParams, indexType)
if err != nil {
log.Warn("failed to prepare job request", zap.Error(err))
return
}
// Update task version
if err := it.UpdateTaskVersion(nodeID); err != nil {
log.Warn("failed to update task version", zap.Error(err))
return
}
defer func() {
if err != nil {
it.tryDropTaskOnWorker(cluster)
}
}()
// Send request to worker
if err = cluster.CreateIndex(nodeID, req); err != nil {
log.Warn("failed to send job to worker", zap.Error(err))
return
}
// Update state to in progress
if err = it.UpdateStateWithMeta(indexpb.JobState_JobStateInProgress, ""); err != nil {
log.Warn("failed to update task state", zap.Error(err))
return
}
log.Info("index task assigned successfully")
}
// Helper method to prepare job request
func (it *indexBuildTask) prepareJobRequest(ctx context.Context, segment *SegmentInfo, segIndex *model.SegmentIndex,
indexParams []*commonpb.KeyValuePair, indexType string,
) (*workerpb.CreateJobRequest, error) {
log := log.Ctx(ctx).With(zap.Int64("taskID", it.BuildID), zap.Int64("segmentID", segment.GetID()))
typeParams := it.meta.indexMeta.GetTypeParams(segIndex.CollectionID, segIndex.IndexID)
fieldID := it.meta.indexMeta.GetFieldIDByIndexID(segIndex.CollectionID, segIndex.IndexID)
binlogIDs := getBinLogIDs(segment, fieldID)
totalRows := getTotalBinlogRows(segment, fieldID)
// Update index parameters as needed
params := indexParams
if vecindexmgr.GetVecIndexMgrInstance().IsVecIndex(indexType) && Params.KnowhereConfig.Enable.GetAsBool() {
var err error
params, err = Params.KnowhereConfig.UpdateIndexParams(GetIndexType(params), paramtable.BuildStage, params)
if err != nil {
return nil, merr.WrapErrServiceInternalErr(err, "failed to update index build params")
}
}
if isDiskANNIndex(GetIndexType(params)) {
var err error
params, err = indexparams.UpdateDiskIndexBuildParams(Params, params)
if err != nil {
return nil, merr.WrapErrServiceInternalErr(err, "failed to append index build params")
}
}
// Get collection info and field
collectionInfo, err := it.handler.GetCollection(ctx, segment.GetCollectionID())
if err != nil {
return nil, merr.Wrap(err, "failed to get collection info")
}
schema := collectionInfo.Schema
var field *schemapb.FieldSchema
allFields := typeutil.GetAllFieldSchemas(schema)
for _, f := range allFields {
if f.FieldID == fieldID {
field = f
break
}
}
if field == nil {
return nil, merr.WrapErrFieldNotFound(fieldID)
}
// Extract dim only for vector types to avoid unnecessary warnings
dim := -1
dataType := field.GetDataType()
if typeutil.IsVectorArrayType(dataType) {
dataType = field.GetElementType()
}
if typeutil.IsFixDimVectorType(dataType) {
if dimVal, err := storage.GetDimFromParams(field.GetTypeParams()); err != nil {
log.Warn("failed to get dim from field type params",
zap.String("field type", field.GetDataType().String()), zap.Error(err))
} else {
dim = dimVal
}
}
// Prepare optional fields for vector index
optionalFields, partitionKeyIsolation := it.prepareOptionalFields(ctx, collectionInfo, segment, schema, indexType, field)
indexNonEncoding := "false"
if it.indexEngineVersionManager.GetIndexNonEncoding() {
indexNonEncoding = "true"
}
params = append(params, &commonpb.KeyValuePair{
Key: common.IndexNonEncoding,
Value: indexNonEncoding,
})
currentVecIndexVersion := it.indexEngineVersionManager.ResolveVecIndexVersion()
currentScalarIndexVersion := it.indexEngineVersionManager.ResolveScalarIndexVersion()
// Create the job request. The path layout (v0/v1) is propagated via
// IndexStorePathVersion; C++ indexbuilder assembles the remote prefix locally.
// external_source is passed raw (AWS-form or Milvus-form). C++ indexbuilder
// InjectExternalSpecProperties handles Tier-1/2 endpoint derivation + AWS-form swap.
req := &workerpb.CreateJobRequest{
ClusterID: Params.CommonCfg.ClusterPrefix.GetValue(),
IndexFilePrefix: path.Join(it.chunkManager.RootPath(), common.SegmentIndexV0Path),
BuildID: it.BuildID,
IndexStorePathVersion: segIndex.IndexStorePathVersion,
IndexVersion: segIndex.IndexVersion + 1,
StorageConfig: createStorageConfig(),
IndexParams: params,
TypeParams: typeParams,
NumRows: segIndex.NumRows,
CurrentIndexVersion: currentVecIndexVersion,
CurrentScalarIndexVersion: currentScalarIndexVersion,
CollectionID: segment.GetCollectionID(),
PartitionID: segment.GetPartitionID(),
SegmentID: segment.GetID(),
FieldID: fieldID,
FieldName: field.GetName(),
FieldType: field.GetDataType(),
Dim: int64(dim),
DataIds: binlogIDs,
OptionalScalarFields: optionalFields,
Field: field,
PartitionKeyIsolation: partitionKeyIsolation,
StorageVersion: segment.GetStorageVersion(),
TaskSlot: it.taskSlot,
LackBinlogRows: segIndex.NumRows - totalRows,
InsertLogs: segment.GetBinlogs(),
Manifest: segment.GetManifestPath(),
ExternalSource: schema.GetExternalSource(),
ExternalSpec: schema.GetExternalSpec(),
}
WrapPluginContext(segment.GetCollectionID(), schema.GetProperties(), req)
return req, nil
}
// Helper method to prepare optional fields
func (it *indexBuildTask) prepareOptionalFields(ctx context.Context, collectionInfo *collectionInfo,
segment *SegmentInfo, schema *schemapb.CollectionSchema, indexType string, field *schemapb.FieldSchema,
) ([]*indexpb.OptionalFieldInfo, bool) {
optionalFields := make([]*indexpb.OptionalFieldInfo, 0)
partitionKeyIsolation := false
isVectorTypeSupported := typeutil.IsDenseFloatVectorType(field.DataType) || typeutil.IsBinaryVectorType(field.DataType)
if Params.CommonCfg.EnableMaterializedView.GetAsBool() && isVectorTypeSupported && isMvSupported(indexType) {
partitionKeyField, _ := typeutil.GetPartitionKeyFieldSchema(schema)
if partitionKeyField != nil && typeutil.IsFieldDataTypeSupportMaterializedView(partitionKeyField) {
optionalFields = append(optionalFields, &indexpb.OptionalFieldInfo{
FieldID: partitionKeyField.FieldID,
FieldName: partitionKeyField.Name,
FieldType: int32(partitionKeyField.DataType),
ElementType: int32(partitionKeyField.GetElementType()),
DataIds: getBinLogIDs(segment, partitionKeyField.FieldID),
})
iso, isoErr := common.IsPartitionKeyIsolationPropEnabled(collectionInfo.Properties)
if isoErr != nil {
log.Ctx(ctx).Warn("failed to parse partition key isolation", zap.Error(isoErr))
}
if iso {
partitionKeyIsolation = true
}
}
}
return optionalFields, partitionKeyIsolation
}
func (it *indexBuildTask) QueryTaskOnWorker(cluster session.Cluster) {
log := log.Ctx(context.TODO()).With(zap.Int64("taskID", it.BuildID), zap.Int64("segmentID", it.SegmentID), zap.Int64("nodeID", it.NodeID))
// Check if task exists in meta
segIndex, exist := it.meta.indexMeta.GetIndexJob(it.BuildID)
if !exist || segIndex == nil {
log.Info("index task has not exist in meta table, removing task")
if it.tryDropTaskOnWorker(cluster) != nil {
return
}
it.SetState(indexpb.JobState_JobStateNone, "index task has not exist in meta table")
return
}
results, err := cluster.QueryIndex(it.NodeID, &workerpb.QueryJobsRequest{
ClusterID: Params.CommonCfg.ClusterPrefix.GetValue(),
TaskIDs: []UniqueID{it.BuildID},
})
if err != nil {
log.Warn("query index task result from worker failed", zap.Error(err))
it.dropAndResetTaskOnWorker(cluster, err.Error())
return
}
// indexInfos length is always one.
for _, info := range results.GetResults() {
if info.GetBuildID() == it.BuildID {
switch info.GetState() {
case commonpb.IndexState_Finished, commonpb.IndexState_Failed:
log.Info("query task index info successfully",
zap.Int64("taskID", it.BuildID), zap.String("result state", info.GetState().String()),
zap.String("failReason", info.GetFailReason()))
it.setJobInfo(info)
case commonpb.IndexState_Retry, commonpb.IndexState_IndexStateNone:
log.Info("query task index info successfully",
zap.Int64("taskID", it.BuildID), zap.String("result state", info.GetState().String()),
zap.String("failReason", info.GetFailReason()))
it.dropAndResetTaskOnWorker(cluster, info.GetFailReason())
}
// inProgress or unissued, keep InProgress state
return
}
}
it.UpdateStateWithMeta(indexpb.JobState_JobStateInit, "index is not in info response")
// Task not found in results will be return error
}
func (it *indexBuildTask) tryDropTaskOnWorker(cluster session.Cluster) error {
log := log.Ctx(context.TODO()).With(zap.Int64("taskID", it.BuildID), zap.Int64("segmentID", it.SegmentID), zap.Int64("nodeID", it.NodeID))
if err := cluster.DropIndex(it.NodeID, it.BuildID); err != nil && !errors.Is(err, merr.ErrNodeNotFound) {
log.Warn("notify worker drop the index task failed", zap.Error(err))
return err
}
log.Info("index task dropped successfully")
return nil
}
func (it *indexBuildTask) DropTaskOnWorker(cluster session.Cluster) {
it.tryDropTaskOnWorker(cluster)
}