Files
milvus/internal/allocator/cached_allocator.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

305 lines
6.7 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 allocator
import (
"context"
"sync"
"time"
"go.uber.org/zap"
"github.com/milvus-io/milvus/pkg/v3/log"
"github.com/milvus-io/milvus/pkg/v3/util/merr"
)
const (
maxConcurrentRequests = 10000
)
// Request defines an interface which has Wait and Notify methods.
type Request interface {
Wait() error
Notify(error)
}
// BaseRequest implements Request interface.
type BaseRequest struct {
Done chan error
Valid bool
}
// Wait is blocked until the request is allocated or an error occurs.
func (req *BaseRequest) Wait() error {
err := <-req.Done
return err
}
// Notify is used to send error to the requester.
func (req *BaseRequest) Notify(err error) {
req.Done <- err
}
// IDRequest implements Request and is used to get global unique Identities.
type IDRequest struct {
BaseRequest
id UniqueID
count uint32
}
// SyncRequest embeds BaseRequest and is used to force synchronize from RootCoordinator.
type SyncRequest struct {
BaseRequest
}
// TickerChan defines an interface.
type TickerChan interface {
Chan() <-chan time.Time
Close()
Init()
Reset()
}
// EmptyTicker implements TickerChan, but it will never issue a signal in Chan.
type EmptyTicker struct {
tChan <-chan time.Time
}
// Chan returns a read-only channel from which you can only receive time.Time type data.
// As for EmptyTicker, you will never read data from Chan.
func (t *EmptyTicker) Chan() <-chan time.Time {
return t.tChan
}
// Init does nothing.
func (t *EmptyTicker) Init() {
}
// Reset does nothing.
func (t *EmptyTicker) Reset() {
}
// Close does nothing.
func (t *EmptyTicker) Close() {
}
// Ticker implements TickerChan and is a simple wrapper for time.TimeTicker.
type Ticker struct {
ticker *time.Ticker
UpdateInterval time.Duration
}
// Init initialize the inner member `ticker` whose type is a pointer to time.Ticker.
func (t *Ticker) Init() {
t.ticker = time.NewTicker(t.UpdateInterval)
}
// Reset resets the inner member `ticker`.
func (t *Ticker) Reset() {
t.ticker.Reset(t.UpdateInterval)
}
// Close closes the inner member `ticker`.
func (t *Ticker) Close() {
t.ticker.Stop()
}
// Chan return a read-only channel from which you can only receive time.Time type data
func (t *Ticker) Chan() <-chan time.Time {
return t.ticker.C
}
// Allocator allocates from a global allocator by its given member functions
type CachedAllocator struct {
Ctx context.Context
CancelFunc context.CancelFunc
wg sync.WaitGroup
Reqs chan Request
ToDoReqs []Request
CanDoReqs []Request
SyncReqs []Request
TChan TickerChan
ForceSyncChan chan Request
SyncFunc func() (bool, error)
ProcessFunc func(req Request) error
CheckSyncFunc func(timeout bool) bool
PickCanDoFunc func()
SyncErr error
Role string
}
// Start starts the loop of checking whether to synchronize with the global allocator.
func (ta *CachedAllocator) Start() error {
ta.TChan.Init()
ta.wg.Add(1)
go ta.mainLoop()
return nil
}
// Init mainly initialize internal members.
func (ta *CachedAllocator) Init() {
ta.ForceSyncChan = make(chan Request, maxConcurrentRequests)
ta.Reqs = make(chan Request, maxConcurrentRequests)
}
func (ta *CachedAllocator) mainLoop() {
defer ta.wg.Done()
loopCtx, loopCancel := context.WithCancel(ta.Ctx)
defer loopCancel()
for {
select {
case first := <-ta.ForceSyncChan:
ta.SyncReqs = append(ta.SyncReqs, first)
pending := len(ta.ForceSyncChan)
for i := 0; i < pending; i++ {
ta.SyncReqs = append(ta.SyncReqs, <-ta.ForceSyncChan)
}
ta.sync(true)
ta.finishSyncRequest()
case <-ta.TChan.Chan():
ta.pickCanDo()
ta.finishRequest()
if ta.sync(true) {
ta.pickCanDo()
ta.finishRequest()
}
ta.failRemainRequest()
case first := <-ta.Reqs:
ta.ToDoReqs = append(ta.ToDoReqs, first)
pending := len(ta.Reqs)
for i := 0; i < pending; i++ {
ta.ToDoReqs = append(ta.ToDoReqs, <-ta.Reqs)
}
ta.pickCanDo()
ta.finishRequest()
if ta.sync(false) {
ta.pickCanDo()
ta.finishRequest()
}
ta.failRemainRequest()
case <-loopCtx.Done():
return
}
}
}
func (ta *CachedAllocator) pickCanDo() {
if ta.PickCanDoFunc == nil {
return
}
ta.PickCanDoFunc()
}
func (ta *CachedAllocator) sync(timeout bool) bool {
if ta.SyncFunc == nil || ta.CheckSyncFunc == nil {
ta.CanDoReqs = ta.ToDoReqs
ta.ToDoReqs = nil
return true
}
if !timeout && len(ta.ToDoReqs) == 0 {
return false
}
if !ta.CheckSyncFunc(timeout) {
return false
}
var ret bool
ret, ta.SyncErr = ta.SyncFunc()
if !timeout {
ta.TChan.Reset()
}
return ret
}
func (ta *CachedAllocator) finishSyncRequest() {
for _, req := range ta.SyncReqs {
if req != nil {
req.Notify(nil)
}
}
ta.SyncReqs = nil
}
func (ta *CachedAllocator) failRemainRequest() {
var err error
if ta.SyncErr != nil {
err = merr.Wrapf(ta.SyncErr, "%s failRemainRequest", ta.Role)
} else {
err = merr.WrapErrServiceInternalMsg("%s failRemainRequest unexpected error", ta.Role)
}
if len(ta.ToDoReqs) > 0 {
log.Warn("Allocator has some reqs to fail",
zap.String("Role", ta.Role),
zap.Int("reqLen", len(ta.ToDoReqs)))
}
for _, req := range ta.ToDoReqs {
if req != nil {
req.Notify(err)
}
}
ta.ToDoReqs = nil
}
func (ta *CachedAllocator) finishRequest() {
for _, req := range ta.CanDoReqs {
if req != nil {
err := ta.ProcessFunc(req)
req.Notify(err)
}
}
ta.CanDoReqs = []Request{}
}
func (ta *CachedAllocator) revokeRequest(err error) {
n := len(ta.Reqs)
for i := 0; i < n; i++ {
req := <-ta.Reqs
req.Notify(err)
}
}
// Close mainly stop the internal coroutine and recover resources.
func (ta *CachedAllocator) Close() {
ta.CancelFunc()
ta.wg.Wait()
ta.TChan.Close()
ta.revokeRequest(merr.WrapErrServiceInternalMsg("%s is closing", ta.Role))
}
// CleanCache is used to force synchronize with global allocator.
func (ta *CachedAllocator) CleanCache() {
req := &SyncRequest{
BaseRequest: BaseRequest{
Done: make(chan error),
Valid: false,
},
}
ta.ForceSyncChan <- req
_ = req.Wait()
}