mirror of
https://github.com/milvus-io/milvus.git
synced 2026-07-21 10:15:43 +00:00
issue: #51253 > Rebased on master after #51254 merged. The `db_name`/`db_id` part of the original PR is now covered by #51254; this PR is reduced to the two remaining gaps on the same query-by-id path. ## Problem When `DescribeCollection` is called with **only a `collectionID`** — no collection name, no db name (e.g. the HTTP management API on `:9091`) — two gaps remain after #51254: 1. **Top-level `collection_name` is empty** on both the cached provider path and the `describeCollectionTask` path. The response is initialized from the (empty) `request.CollectionName` before the name is resolved, and never backfilled. 2. **The cached provider discards the caller-provided collection id.** After deriving the name from the id, it re-resolves the id from that name via `GetCollectionID(db, name)`. Id-only lookups are cached under the request db name — empty here — so with same-name collections in different databases, a concurrent cache refresh can rebind the entry under the `""` key and the request would silently describe the wrong collection (the derived name matches, the id does not). ## Fix - `service_provider.go`: - Backfill `resp.CollectionName` from the resolved cached schema when the request carried no name. Requests that pass a name (including aliases) still echo it unchanged. - Skip the name→id re-resolution when the caller already supplied the id. `GetCollectionInfo` already validates the cache entry against the id (`collInfo.collID != collectionID` → refresh by id), so the caller-provided id is authoritative end to end. Name+id requests keep the existing name-precedence behavior. - Resolve identifiers on local copies instead of rewriting `request.CollectionName`/`CollectionID` in place — the access log interceptor and the success metric labels serialize the request after the handler returns, and previously recorded the resolved values instead of what the client sent. - `task.go`: backfill `t.result.CollectionName` from the coordinator result on the non-cached path. - `meta_cache.go`: fix a stale comment on `ResolveCollectionAlias` — `update()` now always keys `collInfo` by the real collection name (aliases live in the separate alias map), the old comment described pre-refactor behavior. - Tests: - `TestCachedProxyServiceProvider_DescribeCollection_ByIDFillsNameAndUsesRequestID`: drives the id-only path; `GetCollectionID` is deliberately not mocked, so any regression back to re-resolving the id panics the test. - `TestDescribeCollectionTask_FillsNameFromResultWhenQueriedByID`: same assertion for the non-cached path. - Removed the now-unused `GetCollectionID` expectation from the test added in #51254 (that call no longer happens on the id-only path). ## Follow-up commit: entity-keyed meta cache with a cluster-wide id index Reviewing this path surfaced a deeper issue in the proxy meta cache, fixed in the second commit: - By-id lookups (`GetCollectionName`, `GetCollectionInfo` with an empty name) linearly scanned a whole db bucket under the read lock, on every request even on cache hits. - The bucket scanned/filled was keyed by the *request* db name — empty for id-only calls — so entries landed in a bogus `""` bucket: a collection also cached under its real db was duplicated, and same-name collections of different databases evicted each other from the single `""`-keyed slot. The cache is now entity-keyed instead of request-keyed: - Fills land under the collection's **actual database** (carried in the describe response); the `""` bucket no longer exists. - A cluster-wide `collectionID → entry` index serves by-id lookups in **O(1)** regardless of the request db — matching rootcoord, which resolves by-id describes straight from `collID2Meta` without consulting the db name. - Name lookups normalize an empty db name to `default`, mirroring rootcoord's backward-compat normalization (`meta_table.getCollectionByNameInternal`). This also closes a latent cross-database mis-hit: a name lookup with an empty db could previously return whichever same-name collection was last id-cached under the `""` bucket. - All removal paths maintain the index (pointer-identity-guarded unindexing); invalidation sweeps stay exhaustive. ## Verification - Ran locally against a current master core build: the full `TestMetaCache*`, `TestCachedProxyServiceProvider*`, `TestDescribeCollectionTask*`, alias and partition test sets all pass, plus the **full `internal/proxy` suite** (only the pre-existing etcd-dependent `TestProxyRpcLimit` fails locally — it needs a live etcd, unrelated to this change). - New tests: `TestCachedProxyServiceProvider_DescribeCollection_ByIDFillsNameAndUsesRequestID` (id-only path; also asserts the request is not rewritten), `TestDescribeCollectionTask_FillsNameFromResultWhenQueriedByID`, `TestMetaCache_ByIDIndexRealDBBucket` (same-name collections in two databases filled by id: no eviction, entries under real dbs, by-name reuses by-id fill, every removal path cleans the index), `TestMetaCache_EmptyDBNameSharesDefaultEntry`. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --- ## Update: proxy meta cache rebuilt around an id-primary store (2 new commits) Following review discussions on invalidation cost and the alias-DDL races, this PR now also rebuilds the cache (issue: #51533, design doc: `docs/design-docs/design_docs/20260716-proxy-metacache-id-inverted-index.md` in this PR): 1. **`fix: forward the pre-alter alias target id in the AlterAlias expiration`** — rootcoord resolves the pre-alter target under its database lock and carries it in the new additive `AlterAliasMessageHeader.old_collection_id`; the ack callback emits a second expiration entry so proxies evict BOTH AlterAlias targets by id. Closes the race where a concurrent Describe re-points the proxy's alias resolution before the expiration arrives, leaving the old target permanently stale. Older rootcoords (field 0) fall back to the proxy's hint resolution. 2. **`enhance: rebuild the proxy meta cache around an id-primary store`** — the primary store is keyed by the cluster-unique collection id (single source of truth, with a per-database generation); name/alias resolution become hints validated against the primary on read; partition caches are keyed by id; fills are ordered against invalidations by a fill RWMutex (drain in-flight describes before evicting), replacing the per-collection timestamp floor. Every invalidation becomes O(1) — no more full-cache scans under the write lock on Load/Release/Drop/Rename/Alter broadcasts, and DropDatabase/AlterDatabase becomes a generation bump. Also removes a latent stale read (alias-keyed partition entries surviving DropCollection). Verification: targeted cache suites green (rename, alias re-point under concurrent describe, drop+recreate with a reused name, db-generation invalidation, cross-db isolation, gated-mock fill/invalidation ordering); three negative controls (hint validation / dbGen check / fill drain disabled) each fail exactly the test guarding them; full-package `-race` delegated to CI. --- ## Update: simplification series (final form) Following design review, the cache was iteratively simplified to an **id-primary store with declared hints** — every mechanism that could be replaced by an invariant was deleted (net-negative diffs throughout): - Primary store keyed by the cluster-unique collection id; liveness IS presence. Name/alias resolution are hints written ONLY together with their entry (declared aliases) and validated against the primary on every read — a stale hint can only cost one extra describe, never a stale read. - Fill/invalidation ordering via a fill RWMutex (drain in-flight describes before evicting); the per-collection timestamp floor, database generations, background GC, alias negative cache, per-partition cache, and the resolve-and-forget DescribeAlias path are all **deleted**. Evictions clean everything the entry owns synchronously; **no invalidation path performs any RPC**. - Old-rootcoord fallbacks: id-describes without DbName are served uncached; alias-DDL broadcasts without ids trigger hint resolution plus a holder scan **gated on that exact fingerprint** (dead code once rootcoords are upgraded), closing the ghost-alias case with no healing event. - **Accepted gaps (WONT-FIX)** are recorded in the design doc §6 — notably the upgrade-window new-target `Aliases` display lag (the association exists only at rootcoord; self-heals on first use; display-only). See `docs/design-docs/design_docs/20260716-proxy-metacache-id-inverted-index.md` for the full design, invariants and trade-offs. Signed-off-by: xiaofanluan <xf@hjjaq.com> Co-authored-by: xiaofanluan <xf@hjjaq.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
313 lines
12 KiB
Go
313 lines
12 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 proxy
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
|
|
"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-proto/go-api/v3/schemapb"
|
|
"github.com/milvus-io/milvus/internal/util/function/chain/types"
|
|
)
|
|
|
|
func TestValidateFunctionChainSearchRequest(t *testing.T) {
|
|
t.Run("ordinary function chains", func(t *testing.T) {
|
|
err := validateFunctionChainSearchRequest(&milvuspb.SearchRequest{
|
|
FunctionChains: []*schemapb.FunctionChain{l2FunctionChain(mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName)))},
|
|
}, false)
|
|
require.NoError(t, err)
|
|
})
|
|
|
|
t.Run("ordinary request without function chains", func(t *testing.T) {
|
|
err := validateFunctionChainSearchRequest(&milvuspb.SearchRequest{}, false)
|
|
require.NoError(t, err)
|
|
})
|
|
|
|
t.Run("function score and function chains", func(t *testing.T) {
|
|
err := validateFunctionChainSearchRequest(&milvuspb.SearchRequest{
|
|
FunctionScore: &schemapb.FunctionScore{},
|
|
FunctionChains: []*schemapb.FunctionChain{l2FunctionChain(mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName)))},
|
|
}, false)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "function_score and function_chains cannot be used together")
|
|
})
|
|
|
|
t.Run("hybrid function chains", func(t *testing.T) {
|
|
err := validateFunctionChainSearchRequest(&milvuspb.SearchRequest{
|
|
FunctionChains: []*schemapb.FunctionChain{l2FunctionChain(mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName)))},
|
|
}, true)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "function_chains is not supported for hybrid search yet")
|
|
})
|
|
}
|
|
|
|
func TestSplitFunctionChainsByStage(t *testing.T) {
|
|
t.Run("split l0 and l2 chains", func(t *testing.T) {
|
|
l0Chain := l0FunctionChain()
|
|
l2Chain := l2FunctionChain(mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName)))
|
|
|
|
l2Chains, querynodeChains, err := splitFunctionChainsByStage([]*schemapb.FunctionChain{l0Chain, l2Chain})
|
|
require.NoError(t, err)
|
|
assert.Equal(t, []*schemapb.FunctionChain{l2Chain}, l2Chains)
|
|
assert.Equal(t, []*schemapb.FunctionChain{l0Chain}, querynodeChains)
|
|
})
|
|
|
|
t.Run("l0 chain is shallow routed without op validation", func(t *testing.T) {
|
|
l0Chain := l0FunctionChain()
|
|
|
|
l2Chains, querynodeChains, err := splitFunctionChainsByStage([]*schemapb.FunctionChain{l0Chain})
|
|
require.NoError(t, err)
|
|
assert.Empty(t, l2Chains)
|
|
assert.Equal(t, []*schemapb.FunctionChain{l0Chain}, querynodeChains)
|
|
})
|
|
|
|
t.Run("nil chain", func(t *testing.T) {
|
|
_, _, err := splitFunctionChainsByStage([]*schemapb.FunctionChain{nil})
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "function chain[0] is nil")
|
|
})
|
|
|
|
t.Run("duplicate stage", func(t *testing.T) {
|
|
_, _, err := splitFunctionChainsByStage([]*schemapb.FunctionChain{
|
|
l0FunctionChain(),
|
|
l0FunctionChain(),
|
|
})
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "appears more than once")
|
|
})
|
|
|
|
t.Run("l1 is not supported yet", func(t *testing.T) {
|
|
_, _, err := splitFunctionChainsByStage([]*schemapb.FunctionChain{{
|
|
Stage: schemapb.FunctionChainStage_FunctionChainStageL1Rerank,
|
|
}})
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "is not supported yet")
|
|
})
|
|
}
|
|
|
|
func TestNewFunctionChainRerankMeta(t *testing.T) {
|
|
schema := newFunctionChainTestSchema()
|
|
|
|
t.Run("empty chains", func(t *testing.T) {
|
|
meta, err := newFunctionChainRerankMeta(nil, schema)
|
|
require.NoError(t, err)
|
|
assert.Nil(t, meta)
|
|
})
|
|
|
|
t.Run("score only chain", func(t *testing.T) {
|
|
chainPB := l2FunctionChain(mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName)))
|
|
|
|
meta, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{chainPB}, schema)
|
|
require.NoError(t, err)
|
|
require.NotNil(t, meta)
|
|
assert.Empty(t, meta.GetInputFieldNames())
|
|
assert.Empty(t, meta.GetInputFieldIDs())
|
|
assert.Equal(t, chainPB, meta.chainPB)
|
|
assert.NotNil(t, meta.repr)
|
|
})
|
|
|
|
t.Run("schema field and score", func(t *testing.T) {
|
|
chainPB := l2FunctionChain(
|
|
mapOp("score1", "decay", columnArg("ts")),
|
|
mapOp(types.ScoreFieldName, "sum", columnArg("score1"), columnArg(types.ScoreFieldName)),
|
|
)
|
|
|
|
meta, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{chainPB}, schema)
|
|
require.NoError(t, err)
|
|
require.NotNil(t, meta)
|
|
assert.Equal(t, []string{"ts"}, meta.GetInputFieldNames())
|
|
assert.Equal(t, []int64{101}, meta.GetInputFieldIDs())
|
|
})
|
|
|
|
t.Run("duplicate schema input is planned once", func(t *testing.T) {
|
|
chainPB := l2FunctionChain(
|
|
mapOp("score1", "expr", columnArg("ts"), columnArg(types.ScoreFieldName)),
|
|
mapOp(types.ScoreFieldName, "expr", columnArg("ts"), columnArg("score1")),
|
|
)
|
|
|
|
meta, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{chainPB}, schema)
|
|
require.NoError(t, err)
|
|
require.NotNil(t, meta)
|
|
assert.Equal(t, []string{"ts"}, meta.GetInputFieldNames())
|
|
assert.Equal(t, []int64{101}, meta.GetInputFieldIDs())
|
|
})
|
|
|
|
t.Run("struct array sub field input is unsupported", func(t *testing.T) {
|
|
structSchema := newFunctionChainStructTestSchema()
|
|
chainPB := l2FunctionChain(mapOp("score1", "expr", columnArg("struct_scalar_array")))
|
|
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{chainPB}, structSchema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "unsupported field type")
|
|
assert.Contains(t, err.Error(), "Array")
|
|
})
|
|
|
|
t.Run("nil schema", func(t *testing.T) {
|
|
_, _, err := getFunctionChainInputField(nil, "ts")
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "neither a previous output nor a collection field")
|
|
})
|
|
|
|
t.Run("duplicate stage", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
l2FunctionChain(mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName))),
|
|
l2FunctionChain(mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName))),
|
|
}, schema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "appears more than once")
|
|
})
|
|
|
|
t.Run("non l2 stage", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
{
|
|
Stage: schemapb.FunctionChainStage_FunctionChainStageL1Rerank,
|
|
Ops: []*schemapb.FunctionChainOp{mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName))},
|
|
},
|
|
}, schema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "is not supported in search request")
|
|
})
|
|
|
|
t.Run("empty l2 chain", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
l2FunctionChain(),
|
|
}, schema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "function chain[0] must contain at least one op")
|
|
})
|
|
|
|
t.Run("unknown field", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
l2FunctionChain(mapOp("score1", "decay", columnArg("unknown"))),
|
|
}, schema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "unknown")
|
|
assert.Contains(t, err.Error(), "neither a previous output nor a collection field")
|
|
})
|
|
|
|
t.Run("unsupported system input", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
l2FunctionChain(mapOp("score1", "expr", columnArg("$timestamp"))),
|
|
}, schema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "system input \"$timestamp\" is not supported")
|
|
})
|
|
|
|
t.Run("unsupported system output", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
l2FunctionChain(mapOp(types.IDFieldName, "expr", columnArg(types.ScoreFieldName), columnArg("ts"))),
|
|
}, schema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "system output \"$id\" is not writable")
|
|
})
|
|
|
|
t.Run("reserved temporary system output", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
l2FunctionChain(mapOp("$tmp_score", "expr", columnArg(types.ScoreFieldName), columnArg("ts"))),
|
|
}, schema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "system output \"$tmp_score\" is not writable")
|
|
})
|
|
|
|
t.Run("score system output is writable", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
l2FunctionChain(mapOp(types.ScoreFieldName, "expr", columnArg(types.ScoreFieldName), columnArg("ts"))),
|
|
}, schema)
|
|
require.NoError(t, err)
|
|
})
|
|
|
|
t.Run("unsupported field type", func(t *testing.T) {
|
|
_, err := newFunctionChainRerankMeta([]*schemapb.FunctionChain{
|
|
l2FunctionChain(mapOp("score1", "expr", columnArg("vec"))),
|
|
}, schema)
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "unsupported field type")
|
|
assert.Contains(t, err.Error(), "FloatVector")
|
|
})
|
|
}
|
|
|
|
func newFunctionChainTestSchema() *schemaInfo {
|
|
return mustNewSchemaInfo(&schemapb.CollectionSchema{
|
|
Fields: []*schemapb.FieldSchema{
|
|
{FieldID: 100, Name: "pk", DataType: schemapb.DataType_Int64, IsPrimaryKey: true},
|
|
{FieldID: 101, Name: "ts", DataType: schemapb.DataType_Int64},
|
|
{FieldID: 102, Name: "tag", DataType: schemapb.DataType_VarChar},
|
|
{FieldID: 103, Name: "vec", DataType: schemapb.DataType_FloatVector, TypeParams: []*commonpb.KeyValuePair{{Key: "dim", Value: "4"}}},
|
|
{FieldID: 104, Name: "flag", DataType: schemapb.DataType_Bool},
|
|
{FieldID: 105, Name: "price", DataType: schemapb.DataType_Double},
|
|
},
|
|
})
|
|
}
|
|
|
|
func newFunctionChainStructTestSchema() *schemaInfo {
|
|
return mustNewSchemaInfo(&schemapb.CollectionSchema{
|
|
Fields: []*schemapb.FieldSchema{
|
|
{FieldID: 100, Name: "pk", DataType: schemapb.DataType_Int64, IsPrimaryKey: true},
|
|
},
|
|
StructArrayFields: []*schemapb.StructArrayFieldSchema{
|
|
{
|
|
Name: "structArray",
|
|
Fields: []*schemapb.FieldSchema{
|
|
{FieldID: 201, Name: "struct_scalar_array", DataType: schemapb.DataType_Array, ElementType: schemapb.DataType_Int32},
|
|
},
|
|
},
|
|
},
|
|
})
|
|
}
|
|
|
|
func l2FunctionChain(ops ...*schemapb.FunctionChainOp) *schemapb.FunctionChain {
|
|
return &schemapb.FunctionChain{
|
|
Stage: schemapb.FunctionChainStage_FunctionChainStageL2Rerank,
|
|
Ops: ops,
|
|
}
|
|
}
|
|
|
|
func l0FunctionChain(ops ...*schemapb.FunctionChainOp) *schemapb.FunctionChain {
|
|
return &schemapb.FunctionChain{
|
|
Stage: schemapb.FunctionChainStage_FunctionChainStageL0Rerank,
|
|
Ops: ops,
|
|
}
|
|
}
|
|
|
|
func l2LimitFunctionChain(limit int64) *schemapb.FunctionChain {
|
|
return l2FunctionChain(&schemapb.FunctionChainOp{
|
|
Op: types.OpTypeLimit,
|
|
Params: map[string]*schemapb.FunctionParamValue{
|
|
"limit": {Value: &schemapb.FunctionParamValue_Int64Value{Int64Value: limit}},
|
|
},
|
|
})
|
|
}
|
|
|
|
func mapOp(output string, exprName string, args ...*schemapb.FunctionChainExprArg) *schemapb.FunctionChainOp {
|
|
return &schemapb.FunctionChainOp{
|
|
Op: types.OpTypeMap,
|
|
Outputs: []string{output},
|
|
Expr: &schemapb.FunctionChainExpr{
|
|
Name: exprName,
|
|
Args: args,
|
|
Params: map[string]*schemapb.FunctionParamValue{},
|
|
},
|
|
}
|
|
}
|
|
|
|
func columnArg(name string) *schemapb.FunctionChainExprArg {
|
|
return &schemapb.FunctionChainExprArg{Arg: &schemapb.FunctionChainExprArg_Column{Column: &schemapb.FunctionChainColumnArg{Name: name}}}
|
|
}
|