Files
milvus/internal/datanode/importv2/task_preimport.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

237 lines
7.0 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 importv2
import (
"context"
"fmt"
"io"
"runtime/debug"
"time"
"github.com/cockroachdb/errors"
"github.com/samber/lo"
"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/storage"
"github.com/milvus-io/milvus/internal/util/importutilv2"
"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/internalpb"
"github.com/milvus-io/milvus/pkg/v3/util/conc"
"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 PreImportTask struct {
*datapb.PreImportTask
ctx context.Context
cancel context.CancelFunc
partitionIDs []int64
vchannels []string
schema *schemapb.CollectionSchema
options []*commonpb.KeyValuePair
req *datapb.PreImportRequest
manager TaskManager
cm storage.ChunkManager
}
func NewPreImportTask(req *datapb.PreImportRequest,
manager TaskManager,
cm storage.ChunkManager,
) Task {
fileStats := lo.Map(req.GetImportFiles(), func(file *internalpb.ImportFile, _ int) *datapb.ImportFileStats {
return &datapb.ImportFileStats{
ImportFile: file,
}
})
ctx, cancel := context.WithCancel(context.Background())
// During binlog import, even if the primary key's autoID is set to true,
// the primary key from the binlog should be used instead of being reassigned.
if importutilv2.IsBackup(req.GetOptions()) {
UnsetAutoID(req.GetSchema())
}
return &PreImportTask{
PreImportTask: &datapb.PreImportTask{
JobID: req.GetJobID(),
TaskID: req.GetTaskID(),
CollectionID: req.GetCollectionID(),
State: datapb.ImportTaskStateV2_Pending,
FileStats: fileStats,
},
ctx: ctx,
cancel: cancel,
partitionIDs: req.GetPartitionIDs(),
vchannels: req.GetVchannels(),
schema: req.GetSchema(),
options: req.GetOptions(),
req: req,
manager: manager,
cm: cm,
}
}
func (t *PreImportTask) GetPartitionIDs() []int64 {
return t.partitionIDs
}
func (t *PreImportTask) GetVchannels() []string {
return t.vchannels
}
func (t *PreImportTask) GetType() TaskType {
return PreImportTaskType
}
func (t *PreImportTask) GetSchema() *schemapb.CollectionSchema {
return t.schema
}
func (t *PreImportTask) GetSlots() int64 {
return t.req.GetTaskSlot()
}
// PreImportTask buffer size is fixed
func (t *PreImportTask) GetBufferSize() int64 {
return paramtable.Get().DataNodeCfg.ImportBaseBufferSize.GetAsInt64()
}
func (t *PreImportTask) Cancel() {
t.cancel()
}
func (t *PreImportTask) Clone() Task {
ctx, cancel := context.WithCancel(t.ctx)
return &PreImportTask{
PreImportTask: typeutil.Clone(t.PreImportTask),
ctx: ctx,
cancel: cancel,
partitionIDs: t.GetPartitionIDs(),
vchannels: t.GetVchannels(),
schema: t.GetSchema(),
options: t.options,
req: t.req,
manager: t.manager,
cm: t.cm,
}
}
func (t *PreImportTask) Execute() []*conc.Future[any] {
bufferSize := int(t.GetBufferSize())
log.Info("start to preimport", WrapLogFields(t,
zap.Int("bufferSize", bufferSize),
zap.Int64("taskSlot", t.GetSlots()),
zap.Any("files", t.req.GetImportFiles()),
zap.Any("schema", t.GetSchema()),
)...)
t.manager.Update(t.GetTaskID(), UpdateState(datapb.ImportTaskStateV2_InProgress))
files := lo.Map(t.GetFileStats(),
func(fileStat *datapb.ImportFileStats, _ int) *internalpb.ImportFile {
return fileStat.GetImportFile()
})
fn := func(i int, file *internalpb.ImportFile) error {
reader, err := importutilv2.NewReader(t.ctx, t.cm, t.GetSchema(), file, t.options, bufferSize, t.req.GetStorageConfig())
if err != nil {
log.Warn("new reader failed", WrapLogFields(t, zap.String("file", file.String()), zap.Error(err))...)
reason := fmt.Sprintf("error: %v, file: %s", err, file.String())
t.manager.Update(t.GetTaskID(), UpdateState(datapb.ImportTaskStateV2_Failed), UpdateReason(reason))
return err
}
defer reader.Close()
start := time.Now()
err = t.readFileStat(reader, i)
if err != nil {
log.Warn("preimport failed", WrapLogFields(t, zap.String("file", file.String()), zap.Error(err))...)
reason := fmt.Sprintf("error: %v, file: %s", err, file.String())
t.manager.Update(t.GetTaskID(), UpdateState(datapb.ImportTaskStateV2_Failed), UpdateReason(reason))
return err
}
log.Info("read file stat done", WrapLogFields(t, zap.Strings("files", file.GetPaths()),
zap.Duration("dur", time.Since(start)))...)
return nil
}
futures := make([]*conc.Future[any], 0, len(files))
for i, file := range files {
i := i
file := file
f := GetExecPool().Submit(func() (any, error) {
defer func() {
debug.FreeOSMemory()
}()
err := fn(i, file)
return err, err
})
futures = append(futures, f)
}
return futures
}
func (t *PreImportTask) readFileStat(reader importutilv2.Reader, fileIdx int) error {
fileSize, err := reader.Size()
if err != nil {
return err
}
maxSize := paramtable.Get().DataNodeCfg.MaxImportFileSizeInGB.GetAsFloat() * 1024 * 1024 * 1024
if fileSize > int64(maxSize) {
return merr.WrapErrParameterInvalidMsg(
"The import file size has reached the maximum limit allowed for importing, "+
"fileSize=%d, maxSize=%d", fileSize, int64(maxSize))
}
totalRows := 0
totalSize := 0
hashedStats := make(map[string]*datapb.PartitionImportStats)
for {
data, err := reader.Read()
if err != nil {
if errors.Is(err, io.EOF) {
break
}
return err
}
err = CheckRowsEqual(t.GetSchema(), data)
if err != nil {
return err
}
rowsCount, err := GetRowsStats(t, data)
if err != nil {
return err
}
MergeHashedStats(rowsCount, hashedStats)
rows := data.GetRowNum()
size := data.GetMemorySize()
totalRows += rows
totalSize += size
log.Info("reading file stat...", WrapLogFields(t, zap.Int("readRows", rows), zap.Int("readSize", size))...)
}
stat := &datapb.ImportFileStats{
FileSize: fileSize,
TotalRows: int64(totalRows),
TotalMemorySize: int64(totalSize),
HashedStats: hashedStats,
}
t.manager.Update(t.GetTaskID(), UpdateFileStat(fileIdx, stat))
return nil
}