Files
milvus/internal/datacoord/stats_task_meta.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

384 lines
12 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"
"fmt"
"strconv"
"go.uber.org/zap"
"google.golang.org/protobuf/proto"
"github.com/milvus-io/milvus/internal/metastore"
"github.com/milvus-io/milvus/pkg/v3/log"
"github.com/milvus-io/milvus/pkg/v3/metrics"
"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/util/lock"
"github.com/milvus-io/milvus/pkg/v3/util/merr"
"github.com/milvus-io/milvus/pkg/v3/util/timerecord"
"github.com/milvus-io/milvus/pkg/v3/util/typeutil"
)
type statsTaskMeta struct {
ctx context.Context
catalog metastore.DataCoordCatalog
keyLock *lock.KeyLock[UniqueID]
// taskID -> statsTask
tasks *typeutil.ConcurrentMap[UniqueID, *indexpb.StatsTask]
// segmentID + SubJobType -> statsTask
segmentID2Tasks *typeutil.ConcurrentMap[string, *indexpb.StatsTask]
}
func newStatsTaskMeta(ctx context.Context, catalog metastore.DataCoordCatalog) (*statsTaskMeta, error) {
stm := &statsTaskMeta{
ctx: ctx,
catalog: catalog,
keyLock: lock.NewKeyLock[UniqueID](),
tasks: typeutil.NewConcurrentMap[UniqueID, *indexpb.StatsTask](),
segmentID2Tasks: typeutil.NewConcurrentMap[string, *indexpb.StatsTask](),
}
if err := stm.reloadFromKV(); err != nil {
return nil, err
}
return stm, nil
}
func createSecondaryIndexKey(segmentID UniqueID, subJobType string) string {
return strconv.FormatUint(uint64(segmentID), 10) + "-" + subJobType
}
func (stm *statsTaskMeta) reloadFromKV() error {
record := timerecord.NewTimeRecorder("statsTaskMeta-reloadFromKV")
// load stats task
statsTasks, err := stm.catalog.ListStatsTasks(stm.ctx)
if err != nil {
log.Error("statsTaskMeta reloadFromKV load stats tasks failed", zap.Error(err))
return err
}
for _, t := range statsTasks {
// sort stats task no need to reload
if t.GetSubJobType() == indexpb.StatsSubJob_Sort {
if err := stm.catalog.DropStatsTask(stm.ctx, t.GetTaskID()); err != nil {
log.Warn("drop stats task failed",
zap.Int64("taskID", t.GetTaskID()),
zap.Int64("segmentID", t.GetSegmentID()),
zap.Error(err))
}
continue
}
stm.tasks.Insert(t.GetTaskID(), t)
secondaryKey := createSecondaryIndexKey(t.GetSegmentID(), t.GetSubJobType().String())
stm.segmentID2Tasks.Insert(secondaryKey, t)
}
log.Info("statsTaskMeta reloadFromKV done", zap.Duration("duration", record.ElapseSpan()))
return nil
}
func (stm *statsTaskMeta) updateMetrics() {
taskMetrics := make(map[indexpb.JobState]int)
taskMetrics[indexpb.JobState_JobStateNone] = 0
taskMetrics[indexpb.JobState_JobStateInit] = 0
taskMetrics[indexpb.JobState_JobStateInProgress] = 0
taskMetrics[indexpb.JobState_JobStateFinished] = 0
taskMetrics[indexpb.JobState_JobStateFailed] = 0
taskMetrics[indexpb.JobState_JobStateRetry] = 0
allTasks := stm.tasks.Values()
for _, t := range allTasks {
taskMetrics[t.GetState()]++
}
jobType := indexpb.JobType_JobTypeStatsJob.String()
for k, v := range taskMetrics {
metrics.IndexStatsTaskNum.WithLabelValues(jobType, k.String()).Set(float64(v))
}
}
func (stm *statsTaskMeta) AddStatsTask(t *indexpb.StatsTask) error {
taskID := t.GetTaskID()
secondaryKey := createSecondaryIndexKey(t.GetSegmentID(), t.GetSubJobType().String())
task, alreadyExist := stm.segmentID2Tasks.Get(secondaryKey)
if alreadyExist {
msg := fmt.Sprintf("stats task already exist in meta of segment %d with subJobType: %s",
t.GetSegmentID(), t.GetSubJobType().String())
log.RatedWarn(10, msg, zap.Int64("taskID", t.GetTaskID()), zap.Int64("exist taskID", task.GetTaskID()))
return merr.WrapErrTaskDuplicate(indexpb.JobType_JobTypeStatsJob.String(), msg)
}
stm.keyLock.Lock(taskID)
defer stm.keyLock.Unlock(taskID)
log.Info("add stats task", zap.Int64("taskID", t.GetTaskID()), zap.Int64("originSegmentID", t.GetSegmentID()),
zap.Int64("targetSegmentID", t.GetTargetSegmentID()), zap.String("subJobType", t.GetSubJobType().String()))
t.State = indexpb.JobState_JobStateInit
if err := stm.catalog.SaveStatsTask(stm.ctx, t); err != nil {
log.Warn("adding stats task failed",
zap.Int64("taskID", taskID),
zap.Int64("segmentID", t.GetSegmentID()),
zap.String("subJobType", t.GetSubJobType().String()),
zap.Error(err))
return err
}
stm.tasks.Insert(taskID, t)
stm.segmentID2Tasks.Insert(secondaryKey, t)
log.Info("add stats task success", zap.Int64("taskID", t.GetTaskID()), zap.Int64("originSegmentID", t.GetSegmentID()),
zap.Int64("targetSegmentID", t.GetTargetSegmentID()), zap.String("subJobType", t.GetSubJobType().String()))
return nil
}
func (stm *statsTaskMeta) DropStatsTask(ctx context.Context, taskID int64) error {
stm.keyLock.Lock(taskID)
defer stm.keyLock.Unlock(taskID)
log.Ctx(ctx).Info("drop stats task by taskID", zap.Int64("taskID", taskID))
t, ok := stm.tasks.Get(taskID)
if !ok {
log.Info("remove stats task success, task already not exist", zap.Int64("taskID", taskID))
return nil
}
if err := stm.catalog.DropStatsTask(ctx, taskID); err != nil {
log.Warn("drop stats task failed",
zap.Int64("taskID", taskID),
zap.Int64("segmentID", t.GetSegmentID()),
zap.Error(err))
return err
}
stm.tasks.Remove(taskID)
secondaryKey := createSecondaryIndexKey(t.GetSegmentID(), t.GetSubJobType().String())
stm.segmentID2Tasks.Remove(secondaryKey)
log.Info("remove stats task success", zap.Int64("taskID", taskID))
return nil
}
func (stm *statsTaskMeta) UpdateVersion(taskID, nodeID int64) error {
stm.keyLock.Lock(taskID)
defer stm.keyLock.Unlock(taskID)
t, ok := stm.tasks.Get(taskID)
if !ok {
return merr.WrapErrServiceInternalMsg("task %d not found", taskID)
}
cloneT := proto.Clone(t).(*indexpb.StatsTask)
cloneT.Version++
cloneT.NodeID = nodeID
if err := stm.catalog.SaveStatsTask(stm.ctx, cloneT); err != nil {
log.Warn("update stats task version failed",
zap.Int64("taskID", t.GetTaskID()),
zap.Int64("segmentID", t.GetSegmentID()),
zap.Int64("nodeID", nodeID),
zap.Error(err))
return err
}
stm.tasks.Insert(taskID, cloneT)
secondaryKey := createSecondaryIndexKey(t.GetSegmentID(), t.GetSubJobType().String())
stm.segmentID2Tasks.Insert(secondaryKey, cloneT)
log.Info("update stats task version success", zap.Int64("taskID", taskID), zap.Int64("nodeID", nodeID),
zap.Int64("newVersion", cloneT.GetVersion()))
return nil
}
func (stm *statsTaskMeta) UpdateTaskState(taskID int64, state indexpb.JobState, failReason string) error {
stm.keyLock.Lock(taskID)
defer stm.keyLock.Unlock(taskID)
t, ok := stm.tasks.Get(taskID)
if !ok {
return merr.WrapErrServiceInternalMsg("task %d not found", taskID)
}
cloneT := proto.Clone(t).(*indexpb.StatsTask)
cloneT.State = state
cloneT.FailReason = failReason
if err := stm.catalog.SaveStatsTask(stm.ctx, cloneT); err != nil {
log.Warn("update stats task state failed",
zap.Int64("taskID", t.GetTaskID()),
zap.Error(err))
return err
}
stm.tasks.Insert(taskID, cloneT)
secondaryKey := createSecondaryIndexKey(t.GetSegmentID(), t.GetSubJobType().String())
stm.segmentID2Tasks.Insert(secondaryKey, cloneT)
return nil
}
func (stm *statsTaskMeta) UpdateBuildingTask(taskID int64) error {
stm.keyLock.Lock(taskID)
defer stm.keyLock.Unlock(taskID)
t, ok := stm.tasks.Get(taskID)
if !ok {
return merr.WrapErrServiceInternalMsg("task %d not found", taskID)
}
cloneT := proto.Clone(t).(*indexpb.StatsTask)
cloneT.State = indexpb.JobState_JobStateInProgress
if err := stm.catalog.SaveStatsTask(stm.ctx, cloneT); err != nil {
log.Warn("update stats task state building failed",
zap.Int64("taskID", t.GetTaskID()),
zap.Int64("segmentID", t.GetSegmentID()),
zap.Error(err))
return err
}
stm.tasks.Insert(taskID, cloneT)
secondaryKey := createSecondaryIndexKey(t.GetSegmentID(), t.GetSubJobType().String())
stm.segmentID2Tasks.Insert(secondaryKey, cloneT)
log.Info("update building stats task success", zap.Int64("taskID", taskID))
return nil
}
func (stm *statsTaskMeta) FinishTask(taskID int64, result *workerpb.StatsResult) error {
stm.keyLock.Lock(taskID)
defer stm.keyLock.Unlock(taskID)
t, ok := stm.tasks.Get(taskID)
if !ok {
return merr.WrapErrServiceInternalMsg("task %d not found", taskID)
}
cloneT := proto.Clone(t).(*indexpb.StatsTask)
cloneT.State = result.GetState()
cloneT.FailReason = result.GetFailReason()
if err := stm.catalog.SaveStatsTask(stm.ctx, cloneT); err != nil {
log.Warn("finish stats task state failed",
zap.Int64("taskID", t.GetTaskID()),
zap.Int64("segmentID", t.GetSegmentID()),
zap.Error(err))
return err
}
stm.tasks.Insert(taskID, cloneT)
secondaryKey := createSecondaryIndexKey(t.GetSegmentID(), t.GetSubJobType().String())
stm.segmentID2Tasks.Insert(secondaryKey, cloneT)
log.Info("finish stats task meta success", zap.Int64("taskID", taskID), zap.Int64("segmentID", t.SegmentID),
zap.String("state", result.GetState().String()), zap.String("failReason", t.GetFailReason()))
return nil
}
func (stm *statsTaskMeta) GetStatsTask(taskID int64) *indexpb.StatsTask {
t, _ := stm.tasks.Get(taskID)
return t
}
func (stm *statsTaskMeta) GetStatsTaskState(taskID int64) indexpb.JobState {
t, ok := stm.tasks.Get(taskID)
if !ok {
return indexpb.JobState_JobStateNone
}
return t.GetState()
}
func (stm *statsTaskMeta) GetStatsTaskStateBySegmentID(segmentID int64, subJobType indexpb.StatsSubJob) indexpb.JobState {
state := indexpb.JobState_JobStateNone
secondaryKey := createSecondaryIndexKey(segmentID, subJobType.String())
t, exists := stm.segmentID2Tasks.Get(secondaryKey)
if exists {
state = t.GetState()
}
return state
}
func (stm *statsTaskMeta) CanCleanedTasks() []int64 {
needCleanedTaskIDs := make([]int64, 0)
stm.tasks.Range(func(key UniqueID, value *indexpb.StatsTask) bool {
if value.GetCanRecycle() && (value.GetState() == indexpb.JobState_JobStateFinished ||
value.GetState() == indexpb.JobState_JobStateFailed) {
needCleanedTaskIDs = append(needCleanedTaskIDs, key)
}
return true
})
return needCleanedTaskIDs
}
func (stm *statsTaskMeta) GetAllTasks() map[int64]*indexpb.StatsTask {
tasks := make(map[int64]*indexpb.StatsTask)
allTasks := stm.tasks.Values()
for _, v := range allTasks {
tasks[v.GetTaskID()] = proto.Clone(v).(*indexpb.StatsTask)
}
return tasks
}
func (stm *statsTaskMeta) GetStatsTaskBySegmentID(segmentID int64, subJobType indexpb.StatsSubJob) *indexpb.StatsTask {
secondaryKey := createSecondaryIndexKey(segmentID, subJobType.String())
t, exists := stm.segmentID2Tasks.Get(secondaryKey)
if exists {
log.Info("get stats task by segmentID success",
zap.Int64("taskID", t.GetTaskID()),
zap.Int64("segmentID", segmentID),
zap.String("subJobType", subJobType.String()))
return t
}
log.Info("get stats task by segmentID failed, task not exist", zap.Int64("segmentID", segmentID),
zap.String("subJobType", subJobType.String()))
return nil
}
func (stm *statsTaskMeta) MarkTaskCanRecycle(taskID int64) error {
log.Info("mark stats task can recycle", zap.Int64("taskID", taskID))
t, ok := stm.tasks.Get(taskID)
if !ok {
return merr.WrapErrServiceInternalMsg("task %d not found", taskID)
}
cloneT := proto.Clone(t).(*indexpb.StatsTask)
cloneT.CanRecycle = true
if err := stm.catalog.SaveStatsTask(stm.ctx, cloneT); err != nil {
log.Warn("mark stats task can recycle failed",
zap.Int64("taskID", taskID),
zap.Int64("segmentID", t.GetSegmentID()),
zap.Error(err))
return err
}
stm.tasks.Insert(taskID, cloneT)
secondaryKey := createSecondaryIndexKey(t.GetSegmentID(), t.GetSubJobType().String())
stm.segmentID2Tasks.Insert(secondaryKey, cloneT)
log.Info("mark stats task can recycle success", zap.Int64("taskID", taskID),
zap.Int64("segmentID", t.SegmentID),
zap.String("subJobType", t.GetSubJobType().String()))
return nil
}