Files
milvus/internal/cdc/replication/replicatemanager/channel_replicator.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

231 lines
7.9 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 replicatemanager
import (
"context"
"fmt"
"time"
"github.com/cockroachdb/errors"
"go.uber.org/zap"
"github.com/milvus-io/milvus-proto/go-api/v3/milvuspb"
"github.com/milvus-io/milvus/internal/cdc/cluster"
"github.com/milvus-io/milvus/internal/cdc/meta"
"github.com/milvus-io/milvus/internal/cdc/replication/replicatestream"
"github.com/milvus-io/milvus/internal/cdc/util"
"github.com/milvus-io/milvus/internal/distributed/streaming"
"github.com/milvus-io/milvus/internal/streamingnode/server/wal/utility"
"github.com/milvus-io/milvus/pkg/v3/log"
"github.com/milvus-io/milvus/pkg/v3/streaming/util/message"
"github.com/milvus-io/milvus/pkg/v3/streaming/util/message/adaptor"
"github.com/milvus-io/milvus/pkg/v3/streaming/util/options"
"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/syncutil"
)
// Replicator is the client that replicates the message to the channel in the target cluster.
type Replicator interface {
// StartReplication starts the replicate for the channel.
StartReplication()
// StopReplication stops the replicate loop
// and wait for the loop to exit.
StopReplication()
}
var _ Replicator = (*channelReplicator)(nil)
// channelReplicator is the implementation of ChannelReplicator.
type channelReplicator struct {
channel *meta.ReplicateChannel
createRscFunc replicatestream.CreateReplicateStreamClientFunc
createMcFunc cluster.CreateMilvusClientFunc
targetClient cluster.MilvusClient
streamClient replicatestream.ReplicateStreamClient
msgScanner streaming.Scanner
msgChan adaptor.ChanMessageHandler
asyncNotifier *syncutil.AsyncTaskNotifier[struct{}]
}
// NewChannelReplicator creates a new ChannelReplicator.
func NewChannelReplicator(channel *meta.ReplicateChannel) Replicator {
createRscFunc := replicatestream.NewReplicateStreamClient
return &channelReplicator{
channel: channel,
createRscFunc: createRscFunc,
createMcFunc: cluster.NewMilvusClient,
asyncNotifier: syncutil.NewAsyncTaskNotifier[struct{}](),
}
}
func (r *channelReplicator) StartReplication() {
logger := log.With(zap.String("key", r.channel.Key), zap.Int64("modRevision", r.channel.ModRevision))
logger.Info("start replicate channel")
go func() {
defer func() {
if r.streamClient != nil {
r.streamClient.Close()
}
if r.msgScanner != nil {
r.msgScanner.Close()
}
if r.targetClient != nil {
r.targetClient.Close(r.asyncNotifier.Context())
}
r.asyncNotifier.Finish(struct{}{})
}()
INIT_LOOP:
for {
select {
case <-r.asyncNotifier.Context().Done():
return
default:
err := r.init()
if err != nil {
logger.Warn("initialize replicator failed", zap.Error(err))
continue
}
break INIT_LOOP
}
}
r.startConsumeLoop()
}()
}
func (r *channelReplicator) init() error {
logger := log.With(zap.String("key", r.channel.Key), zap.Int64("modRevision", r.channel.ModRevision))
// init target client
if r.targetClient == nil {
dialCtx, dialCancel := context.WithTimeout(r.asyncNotifier.Context(), 30*time.Second)
defer dialCancel()
milvusClient, err := r.createMcFunc(dialCtx, r.channel.Value.GetTargetCluster())
if err != nil {
return err
}
r.targetClient = milvusClient
logger.Info("target client initialized")
}
// init msg scanner
if r.msgScanner == nil {
cp, err := r.getReplicateCheckpoint()
if err != nil {
return err
}
ch := make(adaptor.ChanMessageHandler)
scanner := streaming.WAL().Read(r.asyncNotifier.Context(), streaming.ReadOption{
PChannel: r.channel.Value.GetSourceChannelName(),
DeliverPolicy: options.DeliverPolicyStartFrom(cp.MessageID),
DeliverFilters: []options.DeliverFilter{options.DeliverFilterTimeTickGT(cp.TimeTick)},
MessageHandler: ch,
IgnorePauseConsumption: true,
})
r.msgScanner = scanner
r.msgChan = ch
logger.Info("scanner initialized", zap.Any("checkpoint", cp))
}
// init replicate stream client
if r.streamClient == nil {
r.streamClient = r.createRscFunc(r.asyncNotifier.Context(), r.targetClient, r.channel)
logger.Info("stream client initialized")
}
return nil
}
// startConsumeLoop starts the replicate loop.
func (r *channelReplicator) startConsumeLoop() {
logger := log.With(zap.String("key", r.channel.Key), zap.Int64("modRevision", r.channel.ModRevision))
logger.Info("start consume loop")
for {
select {
case <-r.asyncNotifier.Context().Done():
logger.Info("consume loop stopped")
return
case msg := <-r.msgChan:
err := r.streamClient.Replicate(msg)
if err != nil {
if !errors.Is(err, replicatestream.ErrReplicateIgnored) {
panic(fmt.Sprintf("replicate message failed due to unrecoverable error: %v", err))
}
continue
}
logger.Debug("replicate message success", log.FieldMessage(msg))
if msg.MessageType() == message.MessageTypeAlterReplicateConfig {
if util.IsReplicationRemovedByAlterReplicateConfigMessage(msg, r.channel.Value) {
logger.Info("replication removed, stop consume loop")
r.streamClient.BlockUntilFinish()
return
}
}
}
}
}
func (r *channelReplicator) getReplicateCheckpoint() (*utility.ReplicateCheckpoint, error) {
logger := log.With(zap.String("key", r.channel.Key), zap.Int64("modRevision", r.channel.ModRevision))
// For pchannel-increasing tasks, the secondary WAL for new pchannels hasn't received the
// AlterReplicateConfig yet, so GetReplicateInfo would fail. Use InitializedCheckpoint directly.
if r.channel.Value.GetSkipGetReplicateCheckpoint() {
initializedCheckpoint := utility.NewReplicateCheckpointFromProto(r.channel.Value.InitializedCheckpoint)
logger.Info("skip get replicate checkpoint for pchannel-increasing task, use initialized checkpoint",
zap.Stringer("messageID", initializedCheckpoint.MessageID),
zap.Uint64("timeTick", initializedCheckpoint.TimeTick),
)
return initializedCheckpoint, nil
}
ctx, cancel := context.WithTimeout(r.asyncNotifier.Context(), 30*time.Second)
defer cancel()
sourceClusterID := paramtable.Get().CommonCfg.ClusterPrefix.GetValue()
req := &milvuspb.GetReplicateInfoRequest{
SourceClusterId: sourceClusterID,
TargetPchannel: r.channel.Value.GetTargetChannelName(),
}
replicateInfo, err := r.targetClient.GetReplicateInfo(ctx, req)
if err != nil {
return nil, merr.Wrap(err, "failed to get replicate info")
}
checkpoint := replicateInfo.GetCheckpoint()
if checkpoint == nil || checkpoint.MessageId == nil {
initializedCheckpoint := utility.NewReplicateCheckpointFromProto(r.channel.Value.InitializedCheckpoint)
logger.Info("channel not found in replicate info, will start from the beginning",
zap.Stringer("messageID", initializedCheckpoint.MessageID),
zap.Uint64("timeTick", initializedCheckpoint.TimeTick),
)
return initializedCheckpoint, nil
}
cp := utility.NewReplicateCheckpointFromProto(checkpoint)
logger.Info("replicate messages from position",
zap.Stringer("messageID", cp.MessageID),
zap.Uint64("timeTick", cp.TimeTick),
)
return cp, nil
}
func (r *channelReplicator) StopReplication() {
r.asyncNotifier.Cancel()
r.asyncNotifier.BlockUntilFinish()
}