package writebuffer import ( "fmt" "math/rand" "testing" "time" "github.com/samber/lo" "github.com/stretchr/testify/mock" "github.com/stretchr/testify/suite" "github.com/milvus-io/milvus-proto/go-api/v2/commonpb" "github.com/milvus-io/milvus-proto/go-api/v2/msgpb" "github.com/milvus-io/milvus-proto/go-api/v2/schemapb" "github.com/milvus-io/milvus/internal/allocator" "github.com/milvus-io/milvus/internal/flushcommon/metacache" "github.com/milvus-io/milvus/internal/flushcommon/metacache/pkoracle" "github.com/milvus-io/milvus/internal/flushcommon/syncmgr" "github.com/milvus-io/milvus/internal/proto/datapb" "github.com/milvus-io/milvus/internal/storage" "github.com/milvus-io/milvus/pkg/common" "github.com/milvus-io/milvus/pkg/metrics" "github.com/milvus-io/milvus/pkg/mq/msgstream" "github.com/milvus-io/milvus/pkg/util/paramtable" "github.com/milvus-io/milvus/pkg/util/testutils" "github.com/milvus-io/milvus/pkg/util/tsoutil" ) type L0WriteBufferSuite struct { testutils.PromMetricsSuite channelName string collID int64 collSchema *schemapb.CollectionSchema syncMgr *syncmgr.MockSyncManager metacache *metacache.MockMetaCache allocator *allocator.MockGIDAllocator } func (s *L0WriteBufferSuite) SetupSuite() { paramtable.Get().Init(paramtable.NewBaseTable()) s.collID = 100 s.collSchema = &schemapb.CollectionSchema{ Name: "test_collection", Fields: []*schemapb.FieldSchema{ { FieldID: common.RowIDField, Name: common.RowIDFieldName, DataType: schemapb.DataType_Int64, }, { FieldID: common.TimeStampField, Name: common.TimeStampFieldName, DataType: schemapb.DataType_Int64, }, { FieldID: 100, Name: "pk", DataType: schemapb.DataType_Int64, IsPrimaryKey: true, }, { FieldID: 101, Name: "vector", DataType: schemapb.DataType_FloatVector, TypeParams: []*commonpb.KeyValuePair{ {Key: common.DimKey, Value: "128"}, }, }, }, } s.channelName = "by-dev-rootcoord-dml_0v0" } func (s *L0WriteBufferSuite) composeInsertMsg(segmentID int64, rowCount int, dim int, pkType schemapb.DataType) ([]int64, *msgstream.InsertMsg) { tss := lo.RepeatBy(rowCount, func(idx int) int64 { return int64(tsoutil.ComposeTSByTime(time.Now(), int64(idx))) }) vectors := lo.RepeatBy(rowCount, func(_ int) []float32 { return lo.RepeatBy(dim, func(_ int) float32 { return rand.Float32() }) }) flatten := lo.Flatten(vectors) var pkField *schemapb.FieldData switch pkType { case schemapb.DataType_Int64: pkField = &schemapb.FieldData{ FieldId: common.StartOfUserFieldID, FieldName: "pk", Type: schemapb.DataType_Int64, Field: &schemapb.FieldData_Scalars{ Scalars: &schemapb.ScalarField{ Data: &schemapb.ScalarField_LongData{ LongData: &schemapb.LongArray{ Data: tss, }, }, }, }, } case schemapb.DataType_VarChar: pkField = &schemapb.FieldData{ FieldId: common.StartOfUserFieldID, FieldName: "pk", Type: schemapb.DataType_VarChar, Field: &schemapb.FieldData_Scalars{ Scalars: &schemapb.ScalarField{ Data: &schemapb.ScalarField_StringData{ StringData: &schemapb.StringArray{ Data: lo.Map(tss, func(v int64, _ int) string { return fmt.Sprintf("%v", v) }), }, }, }, }, } } return tss, &msgstream.InsertMsg{ InsertRequest: &msgpb.InsertRequest{ SegmentID: segmentID, Version: msgpb.InsertDataVersion_ColumnBased, RowIDs: tss, Timestamps: lo.Map(tss, func(id int64, _ int) uint64 { return uint64(id) }), FieldsData: []*schemapb.FieldData{ { FieldId: common.RowIDField, FieldName: common.RowIDFieldName, Type: schemapb.DataType_Int64, Field: &schemapb.FieldData_Scalars{ Scalars: &schemapb.ScalarField{ Data: &schemapb.ScalarField_LongData{ LongData: &schemapb.LongArray{ Data: tss, }, }, }, }, }, { FieldId: common.TimeStampField, FieldName: common.TimeStampFieldName, Type: schemapb.DataType_Int64, Field: &schemapb.FieldData_Scalars{ Scalars: &schemapb.ScalarField{ Data: &schemapb.ScalarField_LongData{ LongData: &schemapb.LongArray{ Data: tss, }, }, }, }, }, pkField, { FieldId: common.StartOfUserFieldID + 1, FieldName: "vector", Type: schemapb.DataType_FloatVector, Field: &schemapb.FieldData_Vectors{ Vectors: &schemapb.VectorField{ Dim: int64(dim), Data: &schemapb.VectorField_FloatVector{ FloatVector: &schemapb.FloatArray{ Data: flatten, }, }, }, }, }, }, }, } } func (s *L0WriteBufferSuite) composeDeleteMsg(pks []storage.PrimaryKey) *msgstream.DeleteMsg { delMsg := &msgstream.DeleteMsg{ DeleteRequest: &msgpb.DeleteRequest{ PrimaryKeys: storage.ParsePrimaryKeys2IDs(pks), Timestamps: lo.RepeatBy(len(pks), func(idx int) uint64 { return tsoutil.ComposeTSByTime(time.Now(), int64(idx)+1) }), }, } return delMsg } func (s *L0WriteBufferSuite) SetupTest() { s.syncMgr = syncmgr.NewMockSyncManager(s.T()) s.metacache = metacache.NewMockMetaCache(s.T()) s.metacache.EXPECT().Schema().Return(s.collSchema).Maybe() s.metacache.EXPECT().Collection().Return(s.collID).Maybe() s.allocator = allocator.NewMockGIDAllocator() s.allocator.AllocOneF = func() (int64, error) { return int64(tsoutil.ComposeTSByTime(time.Now(), 0)), nil } } func (s *L0WriteBufferSuite) TestBufferData() { s.Run("normal_run", func() { wb, err := NewL0WriteBuffer(s.channelName, s.metacache, s.syncMgr, &writeBufferOption{ idAllocator: s.allocator, }) s.NoError(err) pks, msg := s.composeInsertMsg(1000, 10, 128, schemapb.DataType_Int64) delMsg := s.composeDeleteMsg(lo.Map(pks, func(id int64, _ int) storage.PrimaryKey { return storage.NewInt64PrimaryKey(id) })) seg := metacache.NewSegmentInfo(&datapb.SegmentInfo{ID: 1000}, pkoracle.NewBloomFilterSet()) s.metacache.EXPECT().GetSegmentsBy(mock.Anything, mock.Anything).Return([]*metacache.SegmentInfo{seg}) s.metacache.EXPECT().GetSegmentByID(int64(1000)).Return(nil, false).Once() s.metacache.EXPECT().AddSegment(mock.Anything, mock.Anything, mock.Anything).Return() s.metacache.EXPECT().UpdateSegments(mock.Anything, mock.Anything).Return() metrics.DataNodeFlowGraphBufferDataSize.Reset() err = wb.BufferData([]*msgstream.InsertMsg{msg}, []*msgstream.DeleteMsg{delMsg}, &msgpb.MsgPosition{Timestamp: 100}, &msgpb.MsgPosition{Timestamp: 200}) s.NoError(err) value, err := metrics.DataNodeFlowGraphBufferDataSize.GetMetricWithLabelValues(fmt.Sprint(paramtable.GetNodeID()), fmt.Sprint(s.metacache.Collection())) s.NoError(err) s.MetricsEqual(value, 5607) delMsg = s.composeDeleteMsg(lo.Map(pks, func(id int64, _ int) storage.PrimaryKey { return storage.NewInt64PrimaryKey(id) })) err = wb.BufferData([]*msgstream.InsertMsg{}, []*msgstream.DeleteMsg{delMsg}, &msgpb.MsgPosition{Timestamp: 100}, &msgpb.MsgPosition{Timestamp: 200}) s.NoError(err) s.MetricsEqual(value, 5847) }) s.Run("pk_type_not_match", func() { wb, err := NewL0WriteBuffer(s.channelName, s.metacache, s.syncMgr, &writeBufferOption{ idAllocator: s.allocator, }) s.NoError(err) pks, msg := s.composeInsertMsg(1000, 10, 128, schemapb.DataType_VarChar) delMsg := s.composeDeleteMsg(lo.Map(pks, func(id int64, _ int) storage.PrimaryKey { return storage.NewInt64PrimaryKey(id) })) seg := metacache.NewSegmentInfo(&datapb.SegmentInfo{ID: 1000}, pkoracle.NewBloomFilterSet()) s.metacache.EXPECT().GetSegmentsBy(mock.Anything, mock.Anything).Return([]*metacache.SegmentInfo{seg}) s.metacache.EXPECT().AddSegment(mock.Anything, mock.Anything, mock.Anything).Return() s.metacache.EXPECT().UpdateSegments(mock.Anything, mock.Anything).Return() metrics.DataNodeFlowGraphBufferDataSize.Reset() err = wb.BufferData([]*msgstream.InsertMsg{msg}, []*msgstream.DeleteMsg{delMsg}, &msgpb.MsgPosition{Timestamp: 100}, &msgpb.MsgPosition{Timestamp: 200}) s.Error(err) }) } func (s *L0WriteBufferSuite) TestCreateFailure() { metacache := metacache.NewMockMetaCache(s.T()) metacache.EXPECT().Collection().Return(s.collID) metacache.EXPECT().Schema().Return(&schemapb.CollectionSchema{}) _, err := NewL0WriteBuffer(s.channelName, metacache, s.syncMgr, &writeBufferOption{ idAllocator: s.allocator, }) s.Error(err) } func TestL0WriteBuffer(t *testing.T) { suite.Run(t, new(L0WriteBufferSuite)) }