Files
milvus/internal/datanode/external/manager.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

295 lines
8.4 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 external
import (
"context"
"fmt"
"runtime/debug"
"sync"
"go.uber.org/zap"
"google.golang.org/protobuf/proto"
"github.com/milvus-io/milvus/pkg/v3/log"
"github.com/milvus-io/milvus/pkg/v3/proto/datapb"
"github.com/milvus-io/milvus/pkg/v3/proto/indexpb"
"github.com/milvus-io/milvus/pkg/v3/util/conc"
"github.com/milvus-io/milvus/pkg/v3/util/merr"
)
// TaskKey uniquely identifies an external collection task.
type TaskKey struct {
ClusterID string
TaskID int64
}
// TaskInfo stores the mutable state of an external collection task.
type TaskInfo struct {
Cancel context.CancelFunc
State indexpb.JobState
FailReason string
CollID int64
KeptSegments []int64
UpdatedSegments []*datapb.SegmentInfo
}
// Clone creates a deep copy so callers can freely mutate the result.
func (t *TaskInfo) Clone() *TaskInfo {
return &TaskInfo{
Cancel: t.Cancel,
State: t.State,
FailReason: t.FailReason,
CollID: t.CollID,
KeptSegments: cloneSegmentIDs(t.KeptSegments),
UpdatedSegments: cloneSegments(t.UpdatedSegments),
}
}
func makeTaskKey(clusterID string, taskID int64) TaskKey {
return TaskKey{
ClusterID: clusterID,
TaskID: taskID,
}
}
func cloneSegmentIDs(src []int64) []int64 {
if len(src) == 0 {
return nil
}
dst := make([]int64, len(src))
copy(dst, src)
return dst
}
func extractSegmentIDs(segments []*datapb.SegmentInfo) []int64 {
if len(segments) == 0 {
return nil
}
result := make([]int64, 0, len(segments))
for _, seg := range segments {
if seg == nil {
continue
}
result = append(result, seg.GetID())
}
return result
}
// cloneSegments returns deep copies of SegmentInfo slices.
func cloneSegments(src []*datapb.SegmentInfo) []*datapb.SegmentInfo {
if len(src) == 0 {
return nil
}
cloned := make([]*datapb.SegmentInfo, len(src))
for i, seg := range src {
if seg == nil {
continue
}
cloned[i] = proto.Clone(seg).(*datapb.SegmentInfo)
}
return cloned
}
// ExternalCollectionManager supervises the lifecycle of external collection tasks
// within a single datanode.
type ExternalCollectionManager struct {
ctx context.Context
mu sync.RWMutex
tasks map[TaskKey]*TaskInfo
pool *conc.Pool[any]
closeOnce sync.Once
}
// NewExternalCollectionManager constructs a manager with the provided worker pool size.
func NewExternalCollectionManager(ctx context.Context, poolSize int) *ExternalCollectionManager {
return &ExternalCollectionManager{
ctx: ctx,
tasks: make(map[TaskKey]*TaskInfo),
pool: conc.NewPool[any](poolSize),
}
}
// Close releases all background resources.
func (m *ExternalCollectionManager) Close() {
m.closeOnce.Do(func() {
if m.pool != nil {
m.pool.Release()
}
log.Info("external collection manager closed")
})
}
// LoadOrStore adds a task entry if absent and returns the existing entry if present.
func (m *ExternalCollectionManager) LoadOrStore(clusterID string, taskID int64, info *TaskInfo) *TaskInfo {
m.mu.Lock()
defer m.mu.Unlock()
key := makeTaskKey(clusterID, taskID)
if oldInfo, ok := m.tasks[key]; ok {
return oldInfo
}
m.tasks[key] = info
return nil
}
// Get returns a cloned snapshot of a task.
func (m *ExternalCollectionManager) Get(clusterID string, taskID int64) *TaskInfo {
m.mu.RLock()
defer m.mu.RUnlock()
key := makeTaskKey(clusterID, taskID)
if info, ok := m.tasks[key]; ok {
return info.Clone()
}
return nil
}
// Delete removes the task entry and returns the previous value.
func (m *ExternalCollectionManager) Delete(clusterID string, taskID int64) *TaskInfo {
m.mu.Lock()
defer m.mu.Unlock()
key := makeTaskKey(clusterID, taskID)
if info, ok := m.tasks[key]; ok {
delete(m.tasks, key)
return info
}
return nil
}
// UpdateState updates only the state/failReason fields.
func (m *ExternalCollectionManager) UpdateState(clusterID string, taskID int64, state indexpb.JobState, failReason string) {
m.mu.Lock()
defer m.mu.Unlock()
key := makeTaskKey(clusterID, taskID)
if info, ok := m.tasks[key]; ok {
info.State = state
info.FailReason = failReason
}
}
// UpdateResult commits the latest state plus kept/updated segments atomically.
func (m *ExternalCollectionManager) UpdateResult(clusterID string, taskID int64,
state indexpb.JobState,
failReason string,
keptSegments []int64,
updatedSegments []*datapb.SegmentInfo,
) {
m.mu.Lock()
defer m.mu.Unlock()
key := makeTaskKey(clusterID, taskID)
if info, ok := m.tasks[key]; ok {
info.State = state
info.FailReason = failReason
info.KeptSegments = append([]int64(nil), keptSegments...)
info.UpdatedSegments = cloneSegments(updatedSegments)
}
}
// CancelTask triggers the context cancellation for a task if it exists.
func (m *ExternalCollectionManager) CancelTask(clusterID string, taskID int64) bool {
key := makeTaskKey(clusterID, taskID)
m.mu.RLock()
info, ok := m.tasks[key]
var cancel context.CancelFunc
if ok {
cancel = info.Cancel
}
m.mu.RUnlock()
if cancel != nil {
cancel()
}
return ok
}
// SubmitTask registers and runs a task asynchronously in the manager pool.
func (m *ExternalCollectionManager) SubmitTask(
clusterID string,
req *datapb.RefreshExternalCollectionTaskRequest,
taskFunc func(context.Context) (*datapb.RefreshExternalCollectionTaskResponse, error),
) error {
taskID := req.GetTaskID()
taskCtx, cancel := context.WithCancel(m.ctx)
keptSegments := extractSegmentIDs(req.GetCurrentSegments())
info := &TaskInfo{
Cancel: cancel,
State: indexpb.JobState_JobStateInProgress,
FailReason: "",
CollID: req.GetCollectionID(),
KeptSegments: keptSegments,
UpdatedSegments: nil,
}
if oldInfo := m.LoadOrStore(clusterID, taskID, info); oldInfo != nil {
// Task already exists — this is a duplicate dispatch (e.g. from
// scheduler TOCTOU race between Enqueue dedup check and Push).
// Treat as idempotent success since the task is already running.
log.Info("task already exists, treating as idempotent success",
zap.Int64("taskID", taskID),
zap.Int64("collectionID", req.GetCollectionID()))
return nil
}
// Submit to pool
m.pool.Submit(func() (_ any, retErr error) {
defer cancel()
// Defense-in-depth: isolate panics in a single task so a buggy
// external source cannot crash the whole datanode process (e.g.
// divide-by-zero from a zero-row parquet, fix for #49225).
defer func() {
if r := recover(); r != nil {
stack := debug.Stack()
log.Error("external collection task panicked",
zap.Int64("taskID", taskID),
zap.Int64("collectionID", req.GetCollectionID()),
zap.Any("panic", r),
zap.ByteString("stack", stack))
reason := fmt.Sprintf("task panicked: %v", r)
m.UpdateResult(clusterID, taskID, indexpb.JobState_JobStateFailed, reason, info.KeptSegments, nil)
// A recovered panic is a server-side failure, never caller input.
retErr = merr.WrapErrServiceInternalMsg("%s", reason)
}
}()
log.Info("executing external collection task in pool",
zap.Int64("taskID", taskID),
zap.Int64("collectionID", req.GetCollectionID()))
// Execute the task
resp, err := taskFunc(taskCtx)
if err != nil {
m.UpdateResult(clusterID, taskID, indexpb.JobState_JobStateFailed, err.Error(), info.KeptSegments, nil)
log.Warn("external collection task failed",
zap.Int64("taskID", taskID),
zap.Error(err))
return nil, err
}
state := resp.GetState()
if state == indexpb.JobState_JobStateNone {
state = indexpb.JobState_JobStateFinished
}
failReason := resp.GetFailReason()
kept := resp.GetKeptSegments()
m.UpdateResult(clusterID, taskID, state, failReason, kept, resp.GetUpdatedSegments())
log.Info("external collection task completed",
zap.Int64("taskID", taskID))
return nil, nil
})
return nil
}