Files
milvus/internal/datanode/index/scheduler.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

300 lines
7.4 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 index
import (
"container/list"
"context"
"runtime/debug"
"sync"
"github.com/cockroachdb/errors"
"go.uber.org/atomic"
"go.uber.org/zap"
"github.com/milvus-io/milvus/internal/storagev2"
"github.com/milvus-io/milvus/pkg/v3/log"
"github.com/milvus-io/milvus/pkg/v3/proto/indexpb"
"github.com/milvus-io/milvus/pkg/v3/util/merr"
)
// TaskQueue is a queue used to store tasks.
type TaskQueue interface {
utChan() <-chan struct{}
utEmpty() bool
utFull() bool
addUnissuedTask(t Task) error
PopUnissuedTask() Task
AddActiveTask(t Task)
PopActiveTask(tName string) Task
Enqueue(t Task) error
GetTaskNum() (int, int)
GetUsingSlot() int64
GetActiveSlot() int64
}
// BaseTaskQueue is a basic instance of TaskQueue.
type IndexTaskQueue struct {
unissuedTasks *list.List
activeTasks map[string]Task
utLock sync.Mutex
atLock sync.Mutex
// maxTaskNum should keep still
maxTaskNum int64
utBufChan chan struct{} // to block scheduler
usingSlot atomic.Int64
sched *TaskScheduler
}
func (queue *IndexTaskQueue) utChan() <-chan struct{} {
return queue.utBufChan
}
func (queue *IndexTaskQueue) utEmpty() bool {
return queue.unissuedTasks.Len() == 0
}
func (queue *IndexTaskQueue) utFull() bool {
return int64(queue.unissuedTasks.Len()) >= queue.maxTaskNum
}
func (queue *IndexTaskQueue) addUnissuedTask(t Task) error {
queue.utLock.Lock()
defer queue.utLock.Unlock()
if queue.utFull() {
return merr.Wrap(merr.ErrServiceResourceInsufficient, "index task queue is full")
}
queue.unissuedTasks.PushBack(t)
select {
case queue.utBufChan <- struct{}{}:
default:
}
return nil
}
func (queue *IndexTaskQueue) GetUsingSlot() int64 {
return queue.usingSlot.Load()
}
func (queue *IndexTaskQueue) GetActiveSlot() int64 {
queue.atLock.Lock()
defer queue.atLock.Unlock()
slots := int64(0)
for _, t := range queue.activeTasks {
slots += t.GetSlot()
}
return slots
}
// PopUnissuedTask pops a task from tasks queue.
func (queue *IndexTaskQueue) PopUnissuedTask() Task {
queue.utLock.Lock()
defer queue.utLock.Unlock()
if queue.unissuedTasks.Len() <= 0 {
return nil
}
ft := queue.unissuedTasks.Front()
queue.unissuedTasks.Remove(ft)
return ft.Value.(Task)
}
// AddActiveTask adds a task to activeTasks.
func (queue *IndexTaskQueue) AddActiveTask(t Task) {
queue.atLock.Lock()
defer queue.atLock.Unlock()
tName := t.Name()
_, ok := queue.activeTasks[tName]
if ok {
log.Ctx(context.TODO()).Debug("task already in active task list", zap.String("TaskID", tName))
}
queue.activeTasks[tName] = t
}
// PopActiveTask pops a task from activateTask and the task will be executed.
func (queue *IndexTaskQueue) PopActiveTask(tName string) Task {
queue.atLock.Lock()
defer queue.atLock.Unlock()
t, ok := queue.activeTasks[tName]
if ok {
delete(queue.activeTasks, tName)
queue.usingSlot.Sub(t.GetSlot())
return t
}
log.Ctx(queue.sched.ctx).Debug("task was not found in the active task list", zap.String("TaskName", tName))
return nil
}
// Enqueue adds a task to TaskQueue.
func (queue *IndexTaskQueue) Enqueue(t Task) error {
err := t.OnEnqueue(t.Ctx())
if err != nil {
return err
}
if err = queue.addUnissuedTask(t); err != nil {
return err
}
queue.usingSlot.Add(t.GetSlot())
return nil
}
func (queue *IndexTaskQueue) GetTaskNum() (int, int) {
queue.utLock.Lock()
defer queue.utLock.Unlock()
queue.atLock.Lock()
defer queue.atLock.Unlock()
utNum := queue.unissuedTasks.Len()
atNum := 0
// remove the finished task
for _, task := range queue.activeTasks {
if task.GetState() != indexpb.JobState_JobStateFinished && task.GetState() != indexpb.JobState_JobStateFailed {
atNum++
}
}
return utNum, atNum
}
// NewIndexBuildTaskQueue creates a new IndexBuildTaskQueue.
func NewIndexBuildTaskQueue(sched *TaskScheduler) *IndexTaskQueue {
return &IndexTaskQueue{
unissuedTasks: list.New(),
activeTasks: make(map[string]Task),
maxTaskNum: 1024,
utBufChan: make(chan struct{}, 1024),
sched: sched,
usingSlot: atomic.Int64{},
}
}
// TaskScheduler is a scheduler of indexing tasks.
type TaskScheduler struct {
TaskQueue TaskQueue
wg sync.WaitGroup
ctx context.Context
cancel context.CancelFunc
}
// NewTaskScheduler creates a new task scheduler of indexing tasks.
func NewTaskScheduler(ctx context.Context) *TaskScheduler {
ctx1, cancel := context.WithCancel(ctx)
s := &TaskScheduler{
ctx: ctx1,
cancel: cancel,
}
s.TaskQueue = NewIndexBuildTaskQueue(s)
return s
}
func getStateFromError(err error) indexpb.JobState {
if errors.Is(err, errCancel) {
return indexpb.JobState_JobStateRetry
} else if errors.Is(err, merr.ErrIoKeyNotFound) || errors.Is(err, merr.ErrSegcoreUnsupported) {
// NoSuchKey or unsupported error
return indexpb.JobState_JobStateFailed
} else if errors.Is(err, merr.ErrSegcorePretendFinished) {
return indexpb.JobState_JobStateFinished
}
return indexpb.JobState_JobStateRetry
}
func (sched *TaskScheduler) processTask(t Task) {
wrap := func(fn func(ctx context.Context) error) error {
select {
case <-t.Ctx().Done():
return errCancel
default:
return fn(t.Ctx())
}
}
defer func() {
t.Reset()
debug.FreeOSMemory()
}()
sched.TaskQueue.AddActiveTask(t)
defer sched.TaskQueue.PopActiveTask(t.Name())
log.Ctx(t.Ctx()).Debug("process task", zap.String("task", t.Name()))
pipelines := []func(context.Context) error{t.PreExecute, t.Execute, t.PostExecute}
for _, fn := range pipelines {
if err := wrap(fn); err != nil {
log.Ctx(t.Ctx()).Warn("process task failed", zap.Error(err))
t.SetState(getStateFromError(err), err.Error())
return
}
}
t.SetState(indexpb.JobState_JobStateFinished, "")
// Publish filesystem metrics after index task completion
if indexTask, ok := t.(*indexBuildTask); ok {
if indexTask.req != nil && indexTask.req.GetStorageConfig() != nil {
storagev2.PublishFilesystemMetricsWithConfig(indexTask.req.GetStorageConfig())
}
}
}
func (sched *TaskScheduler) indexBuildLoop() {
log.Ctx(sched.ctx).Debug("TaskScheduler start build loop ...")
defer sched.wg.Done()
for {
select {
case <-sched.ctx.Done():
return
case <-sched.TaskQueue.utChan():
t := sched.TaskQueue.PopUnissuedTask()
go func(t Task) {
if t.IsVectorIndex() {
GetVecIndexBuildPool().Submit(func() (any, error) {
sched.processTask(t)
return nil, nil
})
} else {
sched.processTask(t)
}
}(t)
}
}
}
// Start stats the task scheduler of indexing tasks.
func (sched *TaskScheduler) Start() error {
sched.wg.Add(1)
go sched.indexBuildLoop()
return nil
}
// Close closes the task scheduler of indexing tasks.
func (sched *TaskScheduler) Close() {
sched.cancel()
sched.wg.Wait()
}