mirror of
https://github.com/milvus-io/milvus.git
synced 2026-07-21 10:15:43 +00:00
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>
276 lines
9.9 KiB
Go
276 lines
9.9 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"
|
|
|
|
"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/msgpb"
|
|
"github.com/milvus-io/milvus-proto/go-api/v3/schemapb"
|
|
"github.com/milvus-io/milvus/internal/streamingcoord/server/balancer/balance"
|
|
"github.com/milvus-io/milvus/internal/streamingcoord/server/broadcaster/registry"
|
|
"github.com/milvus-io/milvus/internal/util/importutilv2"
|
|
"github.com/milvus-io/milvus/pkg/v3/log"
|
|
"github.com/milvus-io/milvus/pkg/v3/proto/internalpb"
|
|
"github.com/milvus-io/milvus/pkg/v3/streaming/util/message"
|
|
"github.com/milvus-io/milvus/pkg/v3/util/funcutil"
|
|
"github.com/milvus-io/milvus/pkg/v3/util/merr"
|
|
"github.com/milvus-io/milvus/pkg/v3/util/paramtable"
|
|
)
|
|
|
|
// importV1AckCallback handles the ack callback for import messages.
|
|
func (c *DDLCallbacks) importV1AckCallback(ctx context.Context, result message.BroadcastResultImportMessageV1) error {
|
|
body := result.Message.MustBody()
|
|
|
|
// Ensure Schema.DbName is populated from the broadcast message's DbName,
|
|
// matching the behavior in master where this was set before calling ImportV2.
|
|
if body.Schema != nil {
|
|
body.Schema.DbName = body.DbName
|
|
}
|
|
|
|
// Process each vchannel with its own TimeTick (not deprecated MsgBase)
|
|
// Each vchannel gets its own import job with the corresponding TimeTick
|
|
vchannels := make([]string, 0, len(result.Results))
|
|
for vchannel := range result.Results {
|
|
if funcutil.IsControlChannel(vchannel) {
|
|
continue
|
|
}
|
|
vchannels = append(vchannels, vchannel)
|
|
}
|
|
|
|
// Call createImportJobFromAck directly instead of ImportV2
|
|
// ImportV2 is only for proxy broadcast, not for ack callback
|
|
importResp, err := c.createImportJobFromAck(ctx, &internalpb.ImportRequestInternal{
|
|
DbID: 0, // already deprecated.
|
|
CollectionID: body.GetCollectionID(),
|
|
CollectionName: body.GetCollectionName(),
|
|
PartitionIDs: body.GetPartitionIDs(),
|
|
ChannelNames: vchannels,
|
|
Schema: body.GetSchema(),
|
|
Files: lo.Map(body.GetFiles(), func(file *msgpb.ImportFile, _ int) *internalpb.ImportFile {
|
|
return &internalpb.ImportFile{
|
|
Id: file.GetId(),
|
|
Paths: file.GetPaths(),
|
|
}
|
|
}),
|
|
Options: funcutil.Map2KeyValuePair(body.GetOptions()),
|
|
DataTimestamp: result.GetMaxTimeTick(), // TODO: use per-vchannel TimeTick in future, must be supported for CDC.
|
|
JobID: body.GetJobID(),
|
|
})
|
|
|
|
err = merr.CheckRPCCall(importResp, err)
|
|
if errors.Is(err, merr.ErrCollectionNotFound) {
|
|
log.Ctx(ctx).Warn("import job creation failed because of collection not found, skip it",
|
|
zap.Strings("vchannels", vchannels),
|
|
zap.String("job_id", importResp.GetJobID()), zap.Error(err))
|
|
return nil
|
|
}
|
|
return err
|
|
}
|
|
|
|
// validateImportRequest validates the import request before broadcasting.
|
|
// This includes all validation logic previously done in CheckCallback and Proxy.
|
|
func (s *Server) validateImportRequest(ctx context.Context, files []*msgpb.ImportFile, options []*commonpb.KeyValuePair) error {
|
|
// Validate timeout
|
|
_, err := importutilv2.GetTimeoutTs(options)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
// Validate binlog import files if it's a backup
|
|
if importutilv2.IsBackup(options) {
|
|
err = ValidateBinlogImportRequest(ctx, s.meta.chunkManager, files, options)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
|
|
// Validate max import job count
|
|
err = ValidateMaxImportJobExceed(ctx, s.importMeta)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
if err := s.validateImportReplication(ctx, options); err != nil {
|
|
return err
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func (s *Server) validateImportReplication(ctx context.Context, options []*commonpb.KeyValuePair) error {
|
|
balancer, err := balance.GetWithContext(ctx)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
assignment, err := balancer.GetLatestChannelAssignment()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if assignment == nil {
|
|
return nil
|
|
}
|
|
if !isReplicatingCluster(assignment.ReplicateConfiguration) {
|
|
return nil
|
|
}
|
|
|
|
if !paramtable.Get().DataCoordCfg.ImportInReplicatingCluster.GetAsBool() {
|
|
return merr.WrapErrOperationNotSupportedMsg("import in replicating cluster is not supported yet")
|
|
}
|
|
if importutilv2.IsAutoCommit(options) {
|
|
return merr.WrapErrOperationNotSupportedMsg("auto_commit=true import in replicating cluster is not supported")
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func isReplicatingCluster(cfg *commonpb.ReplicateConfiguration) bool {
|
|
return cfg != nil && (len(cfg.GetCrossClusterTopology()) > 0 || len(cfg.GetClusters()) > 1)
|
|
}
|
|
|
|
// broadcastImport broadcasts the import message to all vchannels.
|
|
// This method is called from the new ImportV2 flow where proxy calls DataCoord directly.
|
|
func (s *Server) broadcastImport(ctx context.Context,
|
|
collectionName string,
|
|
collectionID int64,
|
|
partitionIDs []int64,
|
|
files []*internalpb.ImportFile,
|
|
options []*commonpb.KeyValuePair,
|
|
schema *schemapb.CollectionSchema,
|
|
jobID int64,
|
|
vchannels []string,
|
|
) error {
|
|
// Convert files to msgpb format for validation
|
|
msgFiles := lo.Map(files, func(file *internalpb.ImportFile, _ int) *msgpb.ImportFile {
|
|
return &msgpb.ImportFile{
|
|
Id: file.GetId(),
|
|
Paths: file.GetPaths(),
|
|
}
|
|
})
|
|
|
|
// Validate the request before broadcasting
|
|
if err := s.validateImportRequest(ctx, msgFiles, options); err != nil {
|
|
return merr.Wrap(err, "failed to validate import request")
|
|
}
|
|
|
|
// Get database name from collection metadata via broker
|
|
// This is safer than extracting from schema which may be stale
|
|
broadcaster, err := s.startBroadcastWithCollectionID(ctx, collectionID)
|
|
if err != nil {
|
|
return merr.Wrap(err, "failed to start broadcast with collection id")
|
|
}
|
|
defer broadcaster.Close()
|
|
|
|
coll, err := s.broker.DescribeCollectionInternal(ctx, collectionID)
|
|
if err := merr.CheckRPCCall(coll, err); err != nil {
|
|
return err
|
|
}
|
|
// Build import message without deprecated MsgBase
|
|
msg := message.NewImportMessageBuilderV1().
|
|
WithHeader(&message.ImportMessageHeader{}).
|
|
WithBody(&msgpb.ImportMsg{
|
|
Base: &commonpb.MsgBase{
|
|
MsgType: commonpb.MsgType_Import,
|
|
Timestamp: 0,
|
|
},
|
|
DbName: coll.DbName,
|
|
CollectionName: collectionName,
|
|
CollectionID: collectionID,
|
|
PartitionIDs: partitionIDs,
|
|
Options: funcutil.KeyValuePair2Map(options),
|
|
Files: msgFiles,
|
|
Schema: schema, // TODO: should we use the schema from the collection?
|
|
JobID: jobID,
|
|
}).
|
|
WithBroadcast(vchannels).
|
|
MustBuildBroadcast()
|
|
|
|
// Broadcast the message
|
|
_, err = broadcaster.Broadcast(ctx, msg)
|
|
return err
|
|
}
|
|
|
|
func (c *DDLCallbacks) registerImportCallbacks() {
|
|
registry.RegisterImportV1AckCallback(c.importV1AckCallback)
|
|
registry.RegisterCommitImportV2AckCallback(c.commitImportV2AckCallback)
|
|
registry.RegisterRollbackImportV2AckCallback(c.rollbackImportV2AckCallback)
|
|
}
|
|
|
|
// commitImportV2AckCallback handles the ack callback for CommitImport WAL message.
|
|
// It transitions the import job from Uncommitted → Committing state.
|
|
// Concurrency safety is guaranteed by the broadcaster framework's resource key lock
|
|
// (exclusive collection-level lock), so no CAS is needed here.
|
|
func (c *DDLCallbacks) commitImportV2AckCallback(ctx context.Context, result message.BroadcastResultCommitImportMessageV2) error {
|
|
header := result.Message.Header()
|
|
jobID := header.GetJobId()
|
|
log.Ctx(ctx).Info("CommitImport broadcast ack received", zap.Int64("jobID", jobID))
|
|
|
|
job := c.importMeta.GetJob(ctx, jobID)
|
|
if job == nil {
|
|
log.Ctx(ctx).Warn("CommitImport: job not found, skipping", zap.Int64("jobID", jobID))
|
|
return nil
|
|
}
|
|
if job.GetState() != internalpb.ImportJobState_Uncommitted {
|
|
log.Ctx(ctx).Info("CommitImport: job not in Uncommitted state, no-op",
|
|
zap.Int64("jobID", jobID), zap.String("state", job.GetState().String()))
|
|
return nil
|
|
}
|
|
|
|
if err := c.importMeta.UpdateJob(ctx, jobID,
|
|
UpdateJobState(internalpb.ImportJobState_Committing),
|
|
); err != nil {
|
|
return err
|
|
}
|
|
|
|
uncommittedDuration := job.GetTR().RecordSpan()
|
|
log.Ctx(ctx).Info("import job uncommitted stage done",
|
|
zap.Int64("jobID", jobID),
|
|
zap.Duration("jobTimeCost/uncommitted", uncommittedDuration))
|
|
return nil
|
|
}
|
|
|
|
// rollbackImportV2AckCallback handles the ack callback for RollbackImport WAL message.
|
|
// It transitions the import job to Failed state.
|
|
// Concurrency safety is guaranteed by the broadcaster framework's resource key lock
|
|
// (exclusive collection-level lock), so no CAS is needed here.
|
|
// Segment cleanup is handled by the import inspector (processFailed), not here.
|
|
func (c *DDLCallbacks) rollbackImportV2AckCallback(ctx context.Context, result message.BroadcastResultRollbackImportMessageV2) error {
|
|
header := result.Message.Header()
|
|
jobID := header.GetJobId()
|
|
log.Ctx(ctx).Info("RollbackImport broadcast ack received", zap.Int64("jobID", jobID))
|
|
|
|
job := c.importMeta.GetJob(ctx, jobID)
|
|
if job == nil {
|
|
log.Ctx(ctx).Warn("RollbackImport: job not found, skipping", zap.Int64("jobID", jobID))
|
|
return nil
|
|
}
|
|
state := job.GetState()
|
|
if state == internalpb.ImportJobState_Committing ||
|
|
state == internalpb.ImportJobState_Completed ||
|
|
state == internalpb.ImportJobState_Failed {
|
|
log.Ctx(ctx).Info("RollbackImport: job already in terminal/committed state, no-op",
|
|
zap.Int64("jobID", jobID), zap.String("state", state.String()))
|
|
return nil
|
|
}
|
|
|
|
return c.importMeta.UpdateJob(ctx, jobID, UpdateJobState(internalpb.ImportJobState_Failed))
|
|
}
|