Files
milvus/scripts/segcore_error_boundary_baseline.txt
zhagnluandluzhang 48faae3b3a enhance: parallelize json stats build (#52120)
issue: #53765

JSON stats build benchmark — 500K rows per segment
Concurrent segments || Non-parallel || 8 workers || Speedup
1 || 6.810 s || 1.641 s || 4.15× faster
4 || 7.140 s || 4.806 s || 1.49× faster
8 || 10.878 s || 9.658 s || 1.13× faster
Setup: Release build, 12 CPUs, local filesystem, one warm-up followed by
five measured runs; median values are reported. Data generation is
excluded from the timing.
Note: “Non-parallel” means each segment is built serially internally.
Multiple segment builds are still launched concurrently in 8-segment
cases.

Signed-off-by: luzhang <[email protected]>
Co-authored-by: luzhang <[email protected]>
2026-09-24 19:07:34 +08:00

210 lines
12 KiB
Plaintext

knowhere internal/core/src/clustering/KmeansClustering.cpp
knowhere internal/core/src/clustering/KmeansClustering.h
knowhere internal/core/src/common/binary_set_c.cpp
knowhere internal/core/src/common/BitsetView.h
knowhere internal/core/src/common/Chunk.h
knowhere internal/core/src/common/ChunkWriter.cpp
knowhere internal/core/src/common/Consts.h
knowhere internal/core/src/common/FieldData.cpp
knowhere internal/core/src/common/FieldData.h
knowhere internal/core/src/common/FieldMeta.h
knowhere internal/core/src/common/IndexMeta.h
knowhere internal/core/src/common/QueryInfo.h
knowhere internal/core/src/common/QueryResult.h
knowhere internal/core/src/common/Schema.h
knowhere internal/core/src/common/Types.h
knowhere internal/core/src/common/TypeTraits.h
knowhere internal/core/src/common/Utils.h
knowhere internal/core/src/config/ConfigKnowhere.cpp
knowhere internal/core/src/exec/expression/ExprTestBase.h
knowhere internal/core/src/exec/operator/IterativeElementFilterNode.cpp
knowhere internal/core/src/exec/operator/IterativeFilterNode.cpp
knowhere internal/core/src/exec/operator/RescoresNode.cpp
knowhere internal/core/src/exec/operator/search-groupby/StrictGroupFilteredSearch.cpp
knowhere internal/core/src/exec/operator/Utils.h
knowhere internal/core/src/exec/QueryContext.h
knowhere internal/core/src/indexbuilder/index_c.cpp
knowhere internal/core/src/indexbuilder/VecIndexCreator.cpp
knowhere internal/core/src/index/IndexFactory.cpp
knowhere internal/core/src/index/Utils.cpp
knowhere internal/core/src/index/Utils.h
knowhere internal/core/src/index/VectorDiskIndex.cpp
knowhere internal/core/src/index/VectorDiskIndex.h
knowhere internal/core/src/index/VectorIndex.h
knowhere internal/core/src/index/VectorIndexValidDataUtils.h
knowhere internal/core/src/index/VectorMemIndex.cpp
knowhere internal/core/src/index/VectorMemIndex.h
knowhere internal/core/src/mmap/ChunkData.h
knowhere internal/core/src/query/CachedSearchIterator.cpp
knowhere internal/core/src/query/CachedSearchIterator.h
knowhere internal/core/src/query/helper.h
knowhere internal/core/src/query/Plan.cpp
knowhere internal/core/src/query/PlanImpl.h
knowhere internal/core/src/query/PlanProto.cpp
knowhere internal/core/src/query/SearchBruteForce.cpp
knowhere internal/core/src/query/SearchBruteForce.h
knowhere internal/core/src/query/SearchOnGrowing.cpp
knowhere internal/core/src/query/SearchOnIndex.cpp
knowhere internal/core/src/query/SearchOnSealed.cpp
knowhere internal/core/src/query/SubSearchResult.h
knowhere internal/core/src/query/Utils.h
knowhere internal/core/src/segcore/check_vec_index_c.cpp
knowhere internal/core/src/segcore/ChunkedSegmentSealedImpl.cpp
knowhere internal/core/src/segcore/ChunkedSegmentSealedImpl.h
knowhere internal/core/src/segcore/ConcurrentVector.h
knowhere internal/core/src/segcore/FieldIndexing.cpp
knowhere internal/core/src/segcore/FieldIndexing.h
knowhere internal/core/src/segcore/IndexConfigGenerator.cpp
knowhere internal/core/src/segcore/IndexConfigGenerator.h
knowhere internal/core/src/segcore/InsertRecord.h
knowhere internal/core/src/segcore/load_index_c.cpp
knowhere internal/core/src/segcore/metrics_c.cpp
knowhere internal/core/src/segcore/reduce/Reduce.cpp
knowhere internal/core/src/segcore/SegcoreConfig.h
knowhere internal/core/src/segcore/segcore_init_c.cpp
knowhere internal/core/src/segcore/segment_c.cpp
knowhere internal/core/src/segcore/SegmentGrowingImpl.cpp
knowhere internal/core/src/segcore/SegmentInterface.h
knowhere internal/core/src/segcore/storagev1translator/InterimSealedIndexTranslator.cpp
knowhere internal/core/src/segcore/storagev1translator/InterimSealedIndexTranslator.h
knowhere internal/core/src/segcore/storagev1translator/SealedIndexTranslator.cpp
knowhere internal/core/src/segcore/storagev1translator/SealedIndexTranslator.h
knowhere internal/core/src/segcore/Utils.cpp
knowhere internal/core/src/segcore/vector_index_c.cpp
knowhere internal/core/src/storage/DiskFileManagerImpl.cpp
knowhere internal/core/src/storage/Event.cpp
arrow internal/core/src/common/ArrowDataWrapper.h
arrow internal/core/src/common/ChunkWriter.cpp
arrow internal/core/src/common/ChunkWriter.h
arrow internal/core/src/common/ColumnarArrayChunkBuilder.cpp
arrow internal/core/src/common/FieldData.cpp
arrow internal/core/src/common/FieldData.h
arrow internal/core/src/common/FieldDataInterface.h
arrow internal/core/src/common/init_c.cpp
arrow internal/core/src/common/Schema.cpp
arrow internal/core/src/common/Schema.h
arrow internal/core/src/common/Types.h
arrow internal/core/src/index/json_stats/JsonKeyStats.cpp
arrow internal/core/src/index/json_stats/JsonKeyStats.h
arrow internal/core/src/index/json_stats/parquet_writer.cpp
arrow internal/core/src/index/json_stats/parquet_writer.h
arrow internal/core/src/index/json_stats/utils.cpp
arrow internal/core/src/index/json_stats/utils.h
arrow internal/core/src/index/skipindex_stats/SkipIndexStats.cpp
arrow internal/core/src/index/skipindex_stats/SkipIndexStats.h
arrow internal/core/src/segcore/arrow_field_utils.cpp
arrow internal/core/src/segcore/arrow_field_utils.h
arrow internal/core/src/segcore/boost_score.cpp
arrow internal/core/src/segcore/ChunkedSegmentSealedImpl.cpp
arrow internal/core/src/segcore/ChunkedSegmentSealedImpl.h
arrow internal/core/src/segcore/external_utils_c.cpp
arrow internal/core/src/segcore/memory_planner.cpp
arrow internal/core/src/segcore/memory_planner.h
arrow internal/core/src/segcore/packed_reader_c.cpp
arrow internal/core/src/segcore/packed_writer_c.cpp
arrow internal/core/src/segcore/retrieve_result_export_c.cpp
arrow internal/core/src/segcore/retrieve_result_export_c.h
arrow internal/core/src/segcore/search_result_export_c.cpp
arrow internal/core/src/segcore/segment_c.cpp
arrow internal/core/src/segcore/SegmentGrowingImpl.cpp
arrow internal/core/src/segcore/storagev1translator/ChunkTranslator.cpp
arrow internal/core/src/segcore/storagev1translator/DefaultValueChunkTranslator.cpp
arrow internal/core/src/segcore/storagev2translator/AsyncLoadPipeline.cpp
arrow internal/core/src/segcore/storagev2translator/GroupChunkTranslator.cpp
arrow internal/core/src/segcore/storagev2translator/GroupChunkTranslator.h
arrow internal/core/src/segcore/storagev2translator/ManifestGroupTranslator.cpp
arrow internal/core/src/segcore/storagev2translator/ManifestGroupTranslator.h
arrow internal/core/src/segcore/TextColumnCache.cpp
arrow internal/core/src/segcore/TextColumnCache.h
arrow internal/core/src/storage/ArrowFileSystemChunkManager.cpp
arrow internal/core/src/storage/loon_ffi/ffi_reader_c.cpp
arrow internal/core/src/storage/loon_ffi/util.cpp
arrow internal/core/src/storage/PayloadReader.cpp
arrow internal/core/src/storage/PayloadReader.h
arrow internal/core/src/storage/PayloadStream.cpp
arrow internal/core/src/storage/PayloadStream.h
arrow internal/core/src/storage/PayloadWriter.cpp
arrow internal/core/src/storage/PayloadWriter.h
arrow internal/core/src/storage/RecordBatchSize.h
arrow internal/core/src/storage/RemoteInputStream.cpp
arrow internal/core/src/storage/RemoteInputStream.h
arrow internal/core/src/storage/RemoteOutputStream.cpp
arrow internal/core/src/storage/RemoteOutputStream.h
arrow internal/core/src/storage/StatusToErrorCode.h
arrow internal/core/src/storage/Util.cpp
arrow internal/core/src/storage/Util.h
milvus_storage internal/core/src/common/Schema.cpp
milvus_storage internal/core/src/index/json_stats/JsonKeyStats.cpp
milvus_storage internal/core/src/index/json_stats/parquet_writer.cpp
milvus_storage internal/core/src/index/json_stats/parquet_writer.h
milvus_storage internal/core/src/index/json_stats/utils.cpp
milvus_storage internal/core/src/segcore/arrow_fs_c.cpp
milvus_storage internal/core/src/segcore/ChunkedSegmentSealedImpl.cpp
milvus_storage internal/core/src/segcore/ChunkedSegmentSealedImpl.h
milvus_storage internal/core/src/segcore/default_fs.cpp
milvus_storage internal/core/src/segcore/default_fs.h
milvus_storage internal/core/src/segcore/external_utils_c.cpp
milvus_storage internal/core/src/segcore/memory_planner.cpp
milvus_storage internal/core/src/segcore/memory_planner.h
milvus_storage internal/core/src/segcore/packed_reader_c.cpp
milvus_storage internal/core/src/segcore/packed_writer_c.cpp
milvus_storage internal/core/src/segcore/segment_c.cpp
milvus_storage internal/core/src/segcore/SegmentGrowingImpl.cpp
milvus_storage internal/core/src/segcore/SegmentGrowingImpl.h
milvus_storage internal/core/src/segcore/SegmentLoadInfo.cpp
milvus_storage internal/core/src/segcore/SegmentLoadInfo.h
milvus_storage internal/core/src/segcore/storagev2translator/AsyncChunkReader.cpp
milvus_storage internal/core/src/segcore/storagev2translator/AsyncChunkReader.h
milvus_storage internal/core/src/segcore/storagev2translator/AsyncLoadPipeline.cpp
milvus_storage internal/core/src/segcore/storagev2translator/AsyncLoadPipeline.h
milvus_storage internal/core/src/segcore/storagev2translator/GroupChunkTranslator.cpp
milvus_storage internal/core/src/segcore/storagev2translator/GroupChunkTranslator.h
milvus_storage internal/core/src/segcore/storagev2translator/JsonStatsTranslator.cpp
milvus_storage internal/core/src/segcore/storagev2translator/JsonStatsTranslator.h
milvus_storage internal/core/src/segcore/storagev2translator/ManifestGroupTranslator.cpp
milvus_storage internal/core/src/segcore/storagev2translator/ManifestGroupTranslator.h
milvus_storage internal/core/src/segcore/TextColumnCache.cpp
milvus_storage internal/core/src/segcore/TextColumnCache.h
milvus_storage internal/core/src/storage/ArrowFileSystemChunkManager.cpp
milvus_storage internal/core/src/storage/ArrowFileSystemChunkManager.h
milvus_storage internal/core/src/storage/FileManager.h
milvus_storage internal/core/src/storage/IndexEntryEncryptedLocalWriter.cpp
milvus_storage internal/core/src/storage/IndexEntryEncryptedLocalWriter.h
milvus_storage internal/core/src/storage/minio/MinioChunkManager.cpp
milvus_storage internal/core/src/storage/loon_ffi/ffi_reader_c.cpp
milvus_storage internal/core/src/storage/loon_ffi/loon_error_code.h
milvus_storage internal/core/src/storage/loon_ffi/milvus_table_c.cpp
milvus_storage internal/core/src/storage/loon_ffi/property_singleton.h
milvus_storage internal/core/src/storage/loon_ffi/util.cpp
milvus_storage internal/core/src/storage/loon_ffi/util.h
milvus_storage internal/core/src/storage/minio/MinioChunkManager.cpp
milvus_storage internal/core/src/storage/RemoteInputStream.cpp
milvus_storage internal/core/src/storage/StatusToErrorCode.h
milvus_storage internal/core/src/storage/storage_c.cpp
milvus_storage internal/core/src/storage/StorageV2FSCache.cpp
milvus_storage internal/core/src/storage/StorageV2FSCache.h
milvus_storage internal/core/src/storage/Util.cpp
milvus_storage internal/core/src/storage/Util.h
tantivy internal/core/src/common/Common.cpp
tantivy internal/core/src/indexbuilder/index_c.cpp
tantivy internal/core/src/indexbuilder/ScalarIndexCreator.cpp
tantivy internal/core/src/index/HybridScalarIndex.cpp
tantivy internal/core/src/index/HybridScalarIndex.h
tantivy internal/core/src/index/IndexFactory.cpp
tantivy internal/core/src/index/IndexFactory.h
tantivy internal/core/src/index/IndexInfo.h
tantivy internal/core/src/index/InvertedIndexTantivy.cpp
tantivy internal/core/src/index/InvertedIndexTantivy.h
tantivy internal/core/src/index/JsonFlatIndex.h
tantivy internal/core/src/index/JsonHybridScalarIndex.h
tantivy internal/core/src/index/json_stats/bson_inverted.cpp
tantivy internal/core/src/index/json_stats/bson_inverted.h
tantivy internal/core/src/index/json_stats/JsonKeyStats.cpp
tantivy internal/core/src/index/json_stats/JsonKeyStats.h
tantivy internal/core/src/index/Meta.h
tantivy internal/core/src/index/NgramInvertedIndex.cpp
tantivy internal/core/src/index/TextMatchIndex.cpp
tantivy internal/core/src/index/TextMatchIndex.h
tantivy internal/core/src/pb/index_cgo_msg.pb.h
tantivy internal/core/src/segcore/Utils.cpp