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

197 lines
8.1 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 rootcoord
import (
"context"
"fmt"
"github.com/cockroachdb/errors"
"github.com/milvus-io/milvus/internal/streamingcoord/server/balancer/balance"
"github.com/milvus-io/milvus/internal/streamingcoord/server/broadcaster"
"github.com/milvus-io/milvus/internal/streamingcoord/server/broadcaster/broadcast"
"github.com/milvus-io/milvus/internal/streamingcoord/server/broadcaster/registry"
"github.com/milvus-io/milvus/internal/util/proxyutil"
"github.com/milvus-io/milvus/pkg/v3/proto/messagespb"
"github.com/milvus-io/milvus/pkg/v3/streaming/util/message"
"github.com/milvus-io/milvus/pkg/v3/streaming/util/message/ce"
"github.com/milvus-io/milvus/pkg/v3/util/merr"
"github.com/milvus-io/milvus/pkg/v3/util/typeutil"
)
// RegisterDDLCallbacks registers the ddl callbacks.
func RegisterDDLCallbacks(core *Core) {
ddlCallback := &DDLCallback{
Core: core,
}
ddlCallback.registerCollectionCallbacks()
ddlCallback.registerPartitionCallbacks()
ddlCallback.registerRBACCallbacks()
ddlCallback.registerDatabaseCallbacks()
ddlCallback.registerAliasCallbacks()
}
// registerRBACCallbacks registers the rbac callbacks.
func (c *DDLCallback) registerRBACCallbacks() {
registry.RegisterAlterUserV2AckCallback(c.alterUserV2AckCallback)
registry.RegisterDropUserV2AckCallback(c.dropUserV2AckCallback)
registry.RegisterAlterRoleV2AckCallback(c.alterRoleV2AckCallback)
registry.RegisterDropRoleV2AckCallback(c.dropRoleV2AckCallback)
registry.RegisterAlterUserRoleV2AckCallback(c.alterUserRoleV2AckCallback)
registry.RegisterDropUserRoleV2AckCallback(c.dropUserRoleV2AckCallback)
registry.RegisterAlterPrivilegeV2AckCallback(c.alterPrivilegeV2AckCallback)
registry.RegisterDropPrivilegeV2AckCallback(c.dropPrivilegeV2AckCallback)
registry.RegisterAlterPrivilegeGroupV2AckCallback(c.alterPrivilegeGroupV2AckCallback)
registry.RegisterDropPrivilegeGroupV2AckCallback(c.dropPrivilegeGroupV2AckCallback)
registry.RegisterRestoreRBACV2AckCallback(c.restoreRBACV2AckCallback)
}
// registerDatabaseCallbacks registers the database callbacks.
func (c *DDLCallback) registerDatabaseCallbacks() {
registry.RegisterCreateDatabaseV2AckCallback(c.createDatabaseV1AckCallback)
registry.RegisterAlterDatabaseV2AckCallback(c.alterDatabaseV1AckCallback)
registry.RegisterDropDatabaseV2AckCallback(c.dropDatabaseV1AckCallback)
}
// registerAliasCallbacks registers the alias callbacks.
func (c *DDLCallback) registerAliasCallbacks() {
registry.RegisterAlterAliasV2AckCallback(c.alterAliasV2AckCallback)
registry.RegisterDropAliasV2AckCallback(c.dropAliasV2AckCallback)
}
// registerCollectionCallbacks registers the collection callbacks.
func (c *DDLCallback) registerCollectionCallbacks() {
registry.RegisterCreateCollectionV1AckCallback(c.createCollectionV1AckCallback)
registry.RegisterAlterCollectionV2AckCallback(c.alterCollectionV2AckCallback)
registry.RegisterDropCollectionV1AckCallback(c.dropCollectionV1AckCallback)
registry.RegisterTruncateCollectionV2AckCallback(c.truncateCollectionV2AckCallback)
registry.RegisterTruncateCollectionV2AckOnceCallback(c.truncateCollectionV2AckOnceCallback)
}
// registerPartitionCallbacks registers the partition callbacks.
func (c *DDLCallback) registerPartitionCallbacks() {
registry.RegisterCreatePartitionV1AckCallback(c.createPartitionV1AckCallback)
registry.RegisterDropPartitionV1AckCallback(c.dropPartitionV1AckCallback)
}
// DDLCallback is the callback of ddl.
type DDLCallback struct {
*Core
}
// CacheExpirationsGetter is the getter of cache expirations.
type CacheExpirationsGetter interface {
GetCacheExpirations() *message.CacheExpirations
}
// ExpireCaches handles the cache
func (c *DDLCallback) ExpireCaches(ctx context.Context, expirations any) error {
var cacheExpirations *message.CacheExpirations
if g, ok := expirations.(CacheExpirationsGetter); ok {
cacheExpirations = g.GetCacheExpirations()
} else if g, ok := expirations.(*message.CacheExpirations); ok {
cacheExpirations = g
} else if g, ok := expirations.(*ce.CacheExpirationsBuilder); ok {
cacheExpirations = g.Build()
} else {
panic(fmt.Sprintf("invalid getter type: %T", expirations))
}
for _, cacheExpiration := range cacheExpirations.CacheExpirations {
if err := c.expireCache(ctx, cacheExpiration); err != nil {
return err
}
}
return nil
}
func (c *DDLCallback) expireCache(ctx context.Context, cacheExpiration *message.CacheExpiration) error {
ts, err := c.tsoAllocator.GenerateTSO(1)
if err != nil {
return merr.Wrap(err, "failed to generate timestamp")
}
switch cacheExpiration.Cache.(type) {
case *messagespb.CacheExpiration_LegacyProxyCollectionMetaCache:
legacyProxyCollectionMetaCache := cacheExpiration.GetLegacyProxyCollectionMetaCache()
return c.ExpireMetaCache(
ctx,
legacyProxyCollectionMetaCache.DbName,
[]string{legacyProxyCollectionMetaCache.CollectionName},
legacyProxyCollectionMetaCache.CollectionId,
legacyProxyCollectionMetaCache.PartitionName,
ts,
proxyutil.SetMsgType(legacyProxyCollectionMetaCache.MsgType))
}
return nil
}
// startBroadcastWithRBACLock starts a broadcast for rbac.
func startBroadcastWithRBACLock(ctx context.Context) (broadcaster.BroadcastAPI, error) {
api, err := broadcast.StartBroadcastWithResourceKeys(ctx, message.NewExclusivePrivilegeResourceKey())
if err != nil {
return nil, merr.Wrap(err, "failed to start broadcast with rbac lock")
}
return api, nil
}
// startBroadcastWithDatabaseLock starts a broadcast with database lock.
func startBroadcastWithDatabaseLock(ctx context.Context, dbName string) (broadcaster.BroadcastAPI, error) {
broadcaster, err := broadcast.StartBroadcastWithResourceKeys(ctx, message.NewExclusiveDBNameResourceKey(dbName))
if err != nil {
return nil, merr.Wrap(err, "failed to start broadcast with database lock")
}
return broadcaster, nil
}
// startBroadcastWithCollectionLock starts a broadcast with collection lock.
// CreateCollection and DropCollection can only be called with collection name itself, not alias.
// So it's safe to use collection name directly for those API.
func (*Core) startBroadcastWithCollectionLock(ctx context.Context, dbName string, collectionName string) (broadcaster.BroadcastAPI, error) {
broadcaster, err := broadcast.StartBroadcastWithResourceKeys(ctx,
message.NewSharedDBNameResourceKey(dbName),
message.NewExclusiveCollectionNameResourceKey(dbName, collectionName),
)
if err != nil {
return nil, merr.Wrap(err, "failed to start broadcast with collection lock")
}
return broadcaster, nil
}
func waitUntilSchemaDropReady(ctx context.Context) error {
balancer, err := balance.GetWithContext(ctx)
if err != nil {
return err
}
if err := balancer.WaitUntilSchemaDropReady(ctx); err != nil {
return errors.Wrap(err, "failed to wait until schema drop ready")
}
return nil
}
// startBroadcastWithAliasOrCollectionLock starts a broadcast with alias or collection lock.
// Some API like AlterCollection can be called with alias or collection name,
// so we need to get the real collection name to add resource key lock.
func (c *Core) startBroadcastWithAliasOrCollectionLock(ctx context.Context, dbName string, collectionNameOrAlias string) (broadcaster.BroadcastAPI, error) {
coll, err := c.meta.GetCollectionByName(ctx, dbName, collectionNameOrAlias, typeutil.MaxTimestamp, true)
if err != nil {
return nil, merr.Wrap(err, "failed to get collection by name")
}
return c.startBroadcastWithCollectionLock(ctx, dbName, coll.Name)
}