Files
milvus/internal/datacoord/metrics_info.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

391 lines
13 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"
"sync"
"github.com/tidwall/gjson"
"go.uber.org/zap"
"golang.org/x/sync/errgroup"
"github.com/milvus-io/milvus-proto/go-api/v3/commonpb"
"github.com/milvus-io/milvus-proto/go-api/v3/milvuspb"
"github.com/milvus-io/milvus/internal/json"
"github.com/milvus-io/milvus/internal/types"
"github.com/milvus-io/milvus/pkg/v3/log"
"github.com/milvus-io/milvus/pkg/v3/proto/datapb"
"github.com/milvus-io/milvus/pkg/v3/util/hardware"
"github.com/milvus-io/milvus/pkg/v3/util/merr"
"github.com/milvus-io/milvus/pkg/v3/util/metricsinfo"
"github.com/milvus-io/milvus/pkg/v3/util/paramtable"
"github.com/milvus-io/milvus/pkg/v3/util/tsoutil"
"github.com/milvus-io/milvus/pkg/v3/util/typeutil"
"github.com/milvus-io/milvus/pkg/v3/util/uniquegenerator"
)
// getQuotaMetrics returns DataCoordQuotaMetrics.
func (s *Server) getQuotaMetrics() *metricsinfo.DataCoordQuotaMetrics {
info := s.meta.GetQuotaInfo()
return info
}
func (s *Server) getCollectionMetrics(ctx context.Context) *metricsinfo.DataCoordCollectionMetrics {
totalNumRows := s.meta.GetAllCollectionNumRows()
ret := &metricsinfo.DataCoordCollectionMetrics{
Collections: make(map[int64]*metricsinfo.DataCoordCollectionInfo, len(totalNumRows)),
}
for collectionID, total := range totalNumRows {
if _, ok := ret.Collections[collectionID]; !ok {
ret.Collections[collectionID] = &metricsinfo.DataCoordCollectionInfo{
NumEntitiesTotal: 0,
IndexInfo: make([]*metricsinfo.DataCoordIndexInfo, 0),
}
}
ret.Collections[collectionID].NumEntitiesTotal = total
}
return ret
}
func (s *Server) getChannelsJSON(ctx context.Context, req *milvuspb.GetMetricsRequest) (string, error) {
channels, err := getMetrics[*metricsinfo.Channel](ctx, s, req)
// fill checkpoint timestamp
channel2Checkpoints := s.meta.GetChannelCheckpoints()
for _, channel := range channels {
if cp, ok := channel2Checkpoints[channel.Name]; ok {
channel.CheckpointTS = tsoutil.PhysicalTimeFormat(cp.GetTimestamp())
} else {
log.Warn("channel not found in meta cache", zap.String("channel", channel.Name))
}
}
return metricsinfo.MarshalGetMetricsValues(channels, err)
}
// mergeChannels merges the channel metrics from data nodes and channel watch infos from channel manager
// dnChannels: a slice of Channel metrics from data nodes
// dcChannels: a map of channel watch infos from the channel manager, keyed by node ID and channel name
func mergeChannels(dnChannels []*metricsinfo.Channel, dcChannels map[int64]map[string]*datapb.ChannelWatchInfo) []*metricsinfo.Channel {
mergedChannels := make([]*metricsinfo.Channel, 0)
// Add or update channels from data nodes
for _, dnChannel := range dnChannels {
if dcChannelMap, ok := dcChannels[dnChannel.NodeID]; ok {
if dcChannel, ok := dcChannelMap[dnChannel.Name]; ok {
dnChannel.WatchState = dcChannel.State.String()
delete(dcChannelMap, dnChannel.Name)
}
}
mergedChannels = append(mergedChannels, dnChannel)
}
// Add remaining channels from channel manager
for nodeID, dcChannelMap := range dcChannels {
for _, dcChannel := range dcChannelMap {
mergedChannels = append(mergedChannels, &metricsinfo.Channel{
Name: dcChannel.Vchan.ChannelName,
CollectionID: dcChannel.Vchan.CollectionID,
WatchState: dcChannel.State.String(),
NodeID: nodeID,
})
}
}
return mergedChannels
}
func (s *Server) getSegmentsJSON(ctx context.Context, req *milvuspb.GetMetricsRequest, jsonReq gjson.Result) (string, error) {
v := jsonReq.Get(metricsinfo.MetricRequestParamINKey)
if !v.Exists() {
// default to get all segments from datanode
return s.getDataNodeSegmentsJSON(ctx, req)
}
in := v.String()
if in == metricsinfo.MetricsRequestParamsInDN {
return s.getDataNodeSegmentsJSON(ctx, req)
}
if in == metricsinfo.MetricsRequestParamsInDC {
collectionID := metricsinfo.GetCollectionIDFromRequest(jsonReq)
segments := s.meta.getSegmentsMetrics(collectionID)
for _, seg := range segments {
isIndexed, indexedFields := s.meta.indexMeta.GetSegmentIndexedFields(seg.CollectionID, seg.SegmentID)
seg.IndexedFields = indexedFields
seg.IsIndexed = isIndexed
}
bs, err := json.Marshal(segments)
if err != nil {
log.Ctx(ctx).Warn("marshal segment value failed", zap.Int64("collectionID", collectionID), zap.String("err", err.Error()))
return "", nil
}
return string(bs), nil
}
return "", merr.WrapErrParameterInvalidMsg("invalid param value in=[%s], it should be dc or dn", in)
}
func (s *Server) getDistJSON(ctx context.Context, req *milvuspb.GetMetricsRequest) string {
segments := s.meta.getSegmentsMetrics(-1)
dist := &metricsinfo.DataCoordDist{
Segments: segments,
}
bs, err := json.Marshal(dist)
if err != nil {
log.Warn("marshal dist value failed", zap.String("err", err.Error()))
return ""
}
return string(bs)
}
func (s *Server) getDataNodeSegmentsJSON(ctx context.Context, req *milvuspb.GetMetricsRequest) (string, error) {
ret, err := getMetrics[*metricsinfo.Segment](ctx, s, req)
return metricsinfo.MarshalGetMetricsValues(ret, err)
}
func (s *Server) getSyncTaskJSON(ctx context.Context, req *milvuspb.GetMetricsRequest) (string, error) {
ret, err := getMetrics[*metricsinfo.SyncTask](ctx, s, req)
return metricsinfo.MarshalGetMetricsValues(ret, err)
}
// getSystemInfoMetrics composes data cluster metrics
func (s *Server) getSystemInfoMetrics(
ctx context.Context,
req *milvuspb.GetMetricsRequest,
) (string, error) {
coordTopology := s.getDataCoordTopology(ctx, req)
ret, err := metricsinfo.MarshalTopology(coordTopology)
if err != nil {
return "", err
}
return ret, nil
}
// getDataCoordTopology returns DataCoord topology directly without JSON serialization
// This is optimized for in-process calls in MixCoord mode to avoid marshal/unmarshal overhead
func (s *Server) getDataCoordTopology(
ctx context.Context,
req *milvuspb.GetMetricsRequest,
) metricsinfo.DataCoordTopology {
// TODO(dragondriver): add more detail metrics
// get datacoord info
nodes := s.nodeManager.GetClientIDs()
clusterTopology := metricsinfo.DataClusterTopology{
Self: s.getDataCoordMetrics(ctx),
ConnectedDataNodes: make([]metricsinfo.DataNodeInfos, 0, len(nodes)),
}
// for each data node, fetch metrics info
for _, node := range nodes {
infos, err := s.getDataNodeMetrics(ctx, req, node)
if err != nil {
log.Warn("fails to get DataNode metrics", zap.Error(err))
continue
}
clusterTopology.ConnectedDataNodes = append(clusterTopology.ConnectedDataNodes, infos)
}
// compose topology struct
return metricsinfo.DataCoordTopology{
Cluster: clusterTopology,
Connections: metricsinfo.ConnTopology{
Name: metricsinfo.ConstructComponentName(typeutil.DataCoordRole, paramtable.GetNodeID()),
// TODO(dragondriver): fill ConnectedComponents if necessary
ConnectedComponents: []metricsinfo.ConnectionInfo{},
},
}
}
// getDataCoordMetrics composes datacoord infos
func (s *Server) getDataCoordMetrics(ctx context.Context) metricsinfo.DataCoordInfos {
used, total, err := hardware.GetDiskUsage(paramtable.Get().LocalStorageCfg.Path.GetValue())
if err != nil {
log.Ctx(ctx).Warn("get disk usage failed", zap.Error(err))
}
ioWait, err := hardware.GetIOWait()
if err != nil {
log.Ctx(ctx).Warn("get iowait failed", zap.Error(err))
}
ret := metricsinfo.DataCoordInfos{
BaseComponentInfos: metricsinfo.BaseComponentInfos{
Name: metricsinfo.ConstructComponentName(typeutil.DataCoordRole, paramtable.GetNodeID()),
HardwareInfos: metricsinfo.HardwareMetrics{
IP: s.session.GetAddress(),
CPUCoreCount: hardware.GetCPUNum(),
CPUCoreUsage: hardware.GetCPUUsage(),
Memory: hardware.GetMemoryCount(),
MemoryUsage: hardware.GetUsedMemoryCount(),
Disk: total,
DiskUsage: used,
IOWaitPercentage: ioWait,
},
SystemInfo: metricsinfo.DeployMetrics{},
CreatedTime: paramtable.GetCreateTime().String(),
UpdatedTime: paramtable.GetUpdateTime().String(),
Type: typeutil.DataCoordRole,
ID: paramtable.GetNodeID(),
},
SystemConfigurations: metricsinfo.DataCoordConfiguration{
SegmentMaxSize: Params.DataCoordCfg.SegmentMaxSize.GetAsFloat(),
},
QuotaMetrics: s.getQuotaMetrics(),
CollectionMetrics: s.getCollectionMetrics(ctx),
}
metricsinfo.FillDeployMetricsWithEnv(&ret.SystemInfo)
return ret
}
// getDataNodeMetrics composes DataNode infos
// this function will invoke GetMetrics with DataNode specified in NodeInfo
func (s *Server) getDataNodeMetrics(ctx context.Context, req *milvuspb.GetMetricsRequest, node int64) (metricsinfo.DataNodeInfos, error) {
infos := metricsinfo.DataNodeInfos{
BaseComponentInfos: metricsinfo.BaseComponentInfos{
HasError: true,
ID: int64(uniquegenerator.GetUniqueIntGeneratorIns().GetInt()),
},
}
cli, err := s.nodeManager.GetClient(node)
if err != nil {
return infos, err
}
metrics, err := cli.GetMetrics(ctx, req)
if err != nil {
log.Warn("invalid metrics of DataNode was found",
zap.Error(err))
infos.ErrorReason = err.Error()
// err handled, returns nil
return infos, nil
}
infos.Name = metrics.GetComponentName()
if metrics.GetStatus().GetErrorCode() != commonpb.ErrorCode_Success {
log.Warn("invalid metrics of DataNode was found",
zap.Any("error_code", metrics.GetStatus().GetErrorCode()),
zap.Any("error_reason", metrics.GetStatus().GetReason()))
infos.ErrorReason = metrics.GetStatus().GetReason()
return infos, nil
}
err = metricsinfo.UnmarshalComponentInfos(metrics.GetResponse(), &infos)
if err != nil {
log.Warn("invalid metrics of DataNode found",
zap.Error(err))
infos.ErrorReason = err.Error()
return infos, nil
}
infos.HasError = false
return infos, nil
}
func (s *Server) getIndexNodeMetrics(ctx context.Context, req *milvuspb.GetMetricsRequest, node types.DataNodeClient) (metricsinfo.DataNodeInfos, error) {
infos := metricsinfo.DataNodeInfos{
BaseComponentInfos: metricsinfo.BaseComponentInfos{
HasError: true,
ID: int64(uniquegenerator.GetUniqueIntGeneratorIns().GetInt()),
},
}
if node == nil {
return infos, merr.WrapErrServiceInternalMsg("index node is nil")
}
metrics, err := node.GetMetrics(ctx, req)
if err != nil {
log.Warn("invalid metrics of IndexNode was found",
zap.Error(err))
infos.ErrorReason = err.Error()
// err handled, returns nil
return infos, nil
}
infos.Name = metrics.GetComponentName()
if metrics.GetStatus().GetErrorCode() != commonpb.ErrorCode_Success {
log.Warn("invalid metrics of DataNode was found",
zap.Any("error_code", metrics.GetStatus().GetErrorCode()),
zap.Any("error_reason", metrics.GetStatus().GetReason()))
infos.ErrorReason = metrics.GetStatus().GetReason()
return infos, nil
}
err = metricsinfo.UnmarshalComponentInfos(metrics.GetResponse(), &infos)
if err != nil {
log.Warn("invalid metrics of DataNode found",
zap.Error(err))
infos.ErrorReason = err.Error()
return infos, nil
}
infos.HasError = false
return infos, nil
}
// getMetrics retrieves and aggregates the metrics of the datanode to a slice
func getMetrics[T any](ctx context.Context, s *Server, req *milvuspb.GetMetricsRequest) ([]T, error) {
var metrics []T
var mu sync.Mutex
errorGroup, ctx := errgroup.WithContext(ctx)
nodes := s.nodeManager.GetClientIDs()
for _, node := range nodes {
errorGroup.Go(func() error {
cli, err := s.nodeManager.GetClient(node)
if err != nil {
return err
}
resp, err := cli.GetMetrics(ctx, req)
if err != nil {
log.Warn("failed to get metric from DataNode", zap.Int64("nodeID", node))
return err
}
if resp.Response == "" {
return nil
}
var infos []T
err = json.Unmarshal([]byte(resp.Response), &infos)
if err != nil {
log.Warn("invalid metrics of data node was found", zap.Error(err))
return err
}
mu.Lock()
metrics = append(metrics, infos...)
mu.Unlock()
return nil
})
}
err := errorGroup.Wait()
return metrics, err
}
// GetDataCoordTopology returns DataCoord topology directly without JSON serialization
// This is optimized for in-process calls in MixCoord mode to avoid marshal/unmarshal overhead
func (s *Server) GetDataCoordTopology(ctx context.Context, req *milvuspb.GetMetricsRequest) (*metricsinfo.DataCoordTopology, error) {
if err := merr.CheckHealthy(s.GetStateCode()); err != nil {
return nil, err
}
topology := s.getDataCoordTopology(ctx, req)
return &topology, nil
}