Files
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

316 lines
11 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 embedding
import (
"context"
"strconv"
"sync"
"google.golang.org/protobuf/proto"
"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/storage"
"github.com/milvus-io/milvus/internal/util/function"
"github.com/milvus-io/milvus/internal/util/function/models"
"github.com/milvus-io/milvus/pkg/v3/metrics"
"github.com/milvus-io/milvus/pkg/v3/mq/msgstream"
"github.com/milvus-io/milvus/pkg/v3/proto/internalpb"
"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/timerecord"
)
type Runner interface {
GetSchema() *schemapb.FunctionSchema
GetOutputFields() []*schemapb.FieldSchema
GetCollectionName() string
GetFunctionTypeName() string
GetFunctionName() string
GetFunctionProvider() string
Check(ctx context.Context) error
MaxBatch() int
ProcessInsert(ctx context.Context, inputs []*schemapb.FieldData) ([]*schemapb.FieldData, error)
ProcessSearch(ctx context.Context, placeholderGroup *commonpb.PlaceholderGroup) (*commonpb.PlaceholderGroup, error)
ProcessBulkInsert(ctx context.Context, inputs []storage.FieldData) (map[storage.FieldID]storage.FieldData, error)
}
type FunctionExecutor struct {
runners map[int64]Runner
}
func createFunction(coll *schemapb.CollectionSchema, schema *schemapb.FunctionSchema, extraInfo *models.ModelExtraInfo) (Runner, error) {
switch schema.GetType() {
case schemapb.FunctionType_BM25: // ignore bm25 function
return nil, nil
case schemapb.FunctionType_TextEmbedding:
f, err := NewTextEmbeddingFunction(coll, schema, extraInfo)
if err != nil {
return nil, err
}
return f, nil
case schemapb.FunctionType_MinHash:
return nil, nil
default:
return nil, merr.WrapErrParameterInvalidMsg("unknown functionRunner type %s", schema.GetType().String())
}
}
// validateFunction validates a single function.
func validateFunction(schema *schemapb.CollectionSchema, fSchema *schemapb.FunctionSchema, extraInfo *models.ModelExtraInfo) error {
f, err := createFunction(schema, fSchema, extraInfo)
if err != nil {
return err
}
// BM25 or minhash function returns nil from createFunction
if f == nil {
if fSchema.GetType() == schemapb.FunctionType_MinHash {
err := function.ValidateMinHashFunction(schema, fSchema)
if err != nil {
return err
}
}
// bm25 or minhash validate pass
return nil
}
if err := f.Check(context.Background()); err != nil {
return merr.Wrapf(err, "check function [%s:%s] failed", fSchema.Name, fSchema.GetType().String())
}
return nil
}
// ValidateFunctions validates functions in the schema.
// If needValidateFunctionName is empty, all functions will be validated; otherwise, only the specified function will be validated.
func ValidateFunctions(schema *schemapb.CollectionSchema, needValidateFunctionName string, extraInfo *models.ModelExtraInfo) error {
if needValidateFunctionName == "" {
for _, fSchema := range schema.Functions {
if err := validateFunction(schema, fSchema, extraInfo); err != nil {
return err
}
}
return nil
}
for _, fSchema := range schema.Functions {
if fSchema.Name == needValidateFunctionName {
return validateFunction(schema, fSchema, extraInfo)
}
}
return merr.WrapErrParameterInvalidMsg("function [%s] not found in schema", needValidateFunctionName)
}
func NewFunctionExecutor(schema *schemapb.CollectionSchema, functions []*schemapb.FunctionSchema, extraInfo *models.ModelExtraInfo) (*FunctionExecutor, error) {
executor := &FunctionExecutor{
runners: make(map[int64]Runner),
}
if functions == nil {
functions = schema.Functions
}
for _, fSchema := range functions {
runner, err := createFunction(schema, fSchema, extraInfo)
if err != nil {
return nil, err
}
if runner != nil {
executor.runners[fSchema.GetOutputFieldIds()[0]] = runner
}
}
return executor, nil
}
func (executor *FunctionExecutor) processSingleFunction(ctx context.Context, runner Runner, msg *msgstream.InsertMsg) ([]*schemapb.FieldData, error) {
inputs := make([]*schemapb.FieldData, 0, len(runner.GetSchema().GetInputFieldNames()))
for _, name := range runner.GetSchema().GetInputFieldNames() {
for _, field := range msg.FieldsData {
if field.GetFieldName() == name {
inputs = append(inputs, field)
}
}
}
if len(inputs) != len(runner.GetSchema().InputFieldIds) {
return nil, merr.WrapErrParameterInvalidMsg("input field not found")
}
tr := timerecord.NewTimeRecorder("function ProcessInsert")
outputs, err := runner.ProcessInsert(ctx, inputs)
if err != nil {
return nil, err
}
metrics.ProxyFunctionlatency.WithLabelValues(strconv.FormatInt(paramtable.GetNodeID(), 10), runner.GetCollectionName(), runner.GetFunctionTypeName(), runner.GetFunctionProvider(), runner.GetFunctionName()).Observe(float64(tr.RecordSpan().Milliseconds()))
tr.CtxElapse(ctx, "function ProcessInsert done")
return outputs, nil
}
func (executor *FunctionExecutor) ProcessInsert(ctx context.Context, msg *msgstream.InsertMsg) error {
numRows := msg.NumRows
for _, runner := range executor.runners {
if numRows > uint64(runner.MaxBatch()) {
return merr.WrapErrParameterInvalidMsg("numRows [%d] > function [%s]'s max batch [%d]", numRows, runner.GetSchema().Name, runner.MaxBatch())
}
}
outputs := make(chan []*schemapb.FieldData, len(executor.runners))
errChan := make(chan error, len(executor.runners))
var wg sync.WaitGroup
for _, runner := range executor.runners {
wg.Add(1)
go func(runner Runner) {
defer wg.Done()
data, err := executor.processSingleFunction(ctx, runner, msg)
if err != nil {
errChan <- err
return
}
outputs <- data
}(runner)
}
wg.Wait()
close(errChan)
close(outputs)
// Collect all errors
var errs []error
for err := range errChan {
errs = append(errs, err)
}
if len(errs) > 0 {
return merr.WrapErrFunctionFailedMsg("function execution failed: %v", errs)
}
for output := range outputs {
msg.FieldsData = append(msg.FieldsData, output...)
}
return nil
}
func (executor *FunctionExecutor) processSingleSearch(ctx context.Context, runner Runner, placeholderGroup []byte) ([]byte, error) {
pb := &commonpb.PlaceholderGroup{}
proto.Unmarshal(placeholderGroup, pb)
if len(pb.Placeholders) != 1 {
return nil, merr.WrapErrParameterInvalidMsg("No placeholders founded")
}
if pb.Placeholders[0].Type != commonpb.PlaceholderType_VarChar {
return placeholderGroup, nil
}
tr := timerecord.NewTimeRecorder("function ProcessSearch")
res, err := runner.ProcessSearch(ctx, pb)
if err != nil {
return nil, err
}
metrics.ProxyFunctionlatency.WithLabelValues(strconv.FormatInt(paramtable.GetNodeID(), 10), runner.GetCollectionName(), runner.GetFunctionTypeName(), runner.GetFunctionProvider(), runner.GetFunctionName()).Observe(float64(tr.RecordSpan().Milliseconds()))
tr.CtxElapse(ctx, "function ProcessSearch done")
return proto.Marshal(res)
}
func (executor *FunctionExecutor) prcessSearch(ctx context.Context, req *internalpb.SearchRequest) error {
runner, exist := executor.runners[req.FieldId]
if !exist {
return merr.WrapErrParameterInvalidMsg("can not found function in field %d", req.FieldId)
}
if req.Nq > int64(runner.MaxBatch()) {
return merr.WrapErrParameterInvalidMsg("nq [%d] > function [%s]'s max batch [%d]", req.Nq, runner.GetSchema().Name, runner.MaxBatch())
}
if newHolder, err := executor.processSingleSearch(ctx, runner, req.GetPlaceholderGroup()); err != nil {
return err
} else {
req.PlaceholderGroup = newHolder
}
return nil
}
func (executor *FunctionExecutor) prcessAdvanceSearch(ctx context.Context, req *internalpb.SearchRequest) error {
outputs := make(chan map[int64][]byte, len(req.GetSubReqs()))
errChan := make(chan error, len(req.GetSubReqs()))
var wg sync.WaitGroup
for idx, sub := range req.GetSubReqs() {
if runner, exist := executor.runners[sub.FieldId]; exist {
if sub.Nq > int64(runner.MaxBatch()) {
return merr.WrapErrParameterInvalidMsg("nq [%d] > function [%s]'s max batch [%d]", sub.Nq, runner.GetSchema().Name, runner.MaxBatch())
}
wg.Add(1)
go func(runner Runner, idx int64, placeholderGroup []byte) {
defer wg.Done()
if newHolder, err := executor.processSingleSearch(ctx, runner, placeholderGroup); err != nil {
errChan <- err
} else {
outputs <- map[int64][]byte{idx: newHolder}
}
}(runner, int64(idx), sub.GetPlaceholderGroup())
}
}
wg.Wait()
close(errChan)
close(outputs)
for err := range errChan {
return err
}
for output := range outputs {
for idx, holder := range output {
req.SubReqs[idx].PlaceholderGroup = holder
}
}
return nil
}
func (executor *FunctionExecutor) ProcessSearch(ctx context.Context, req *internalpb.SearchRequest) error {
if !req.IsAdvanced {
return executor.prcessSearch(ctx, req)
}
return executor.prcessAdvanceSearch(ctx, req)
}
func (executor *FunctionExecutor) processSingleBulkInsert(ctx context.Context, runner Runner, data *storage.InsertData) (map[storage.FieldID]storage.FieldData, error) {
inputs := make([]storage.FieldData, 0, len(runner.GetSchema().InputFieldIds))
for idx, id := range runner.GetSchema().InputFieldIds {
field, exist := data.Data[id]
if !exist {
return nil, merr.WrapErrParameterInvalidMsg("can not find input field: [%s]", runner.GetSchema().GetInputFieldNames()[idx])
}
inputs = append(inputs, field)
}
outputs, err := runner.ProcessBulkInsert(ctx, inputs)
if err != nil {
return nil, err
}
return outputs, nil
}
func (executor *FunctionExecutor) ProcessBulkInsert(ctx context.Context, data *storage.InsertData) error {
// Since concurrency has already been used in the outer layer, only a serial logic access model is used here.
for _, runner := range executor.runners {
output, err := executor.processSingleBulkInsert(ctx, runner, data)
if err != nil {
return err
}
for k, v := range output {
data.Data[k] = v
}
}
return nil
}