mirror of
https://gitee.com/milvus-io/milvus.git
synced 2026-01-07 19:31:51 +08:00
ee216877bb
Add support for DataNode compaction using file resources in ref mode. SortCompation and StatsJobs will build text indexes, which may use file resources. relate: https://github.com/milvus-io/milvus/issues/43687 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> - Core invariant: file resources (analyzer binaries/metadata) are only fetched, downloaded and used when the node is configured in Ref mode (fileresource.IsRefMode via CommonCfg.QNFileResourceMode / DNFileResourceMode); Sync now carries a version and managers track per-resource versions/resource IDs so newer resource sets win and older entries are pruned (RefManager/SynchManager resource maps). - Logic removed / simplified: component-specific FileResourceMode flags and an indirection through a long-lived BinlogIO wrapper were consolidated — file-resource mode moved to CommonCfg, Sync/Download APIs became version- and context-aware, and compaction/index tasks accept a ChunkManager directly (binlog IO wrapper creation inlined). This eliminates duplicated config checks and wrapper indirection while preserving the same chunk/IO semantics. - Why no data loss or behavior regression: all file-resource code paths are gated by the configured mode (default remains "sync"); when not in ref-mode or when no resources exist, compaction and stats flows follow existing code paths unchanged. Versioned Sync + resourceID maps ensure newly synced sets replace older ones and RefManager prunes stale files; GetFileResources returns an error if requested IDs are missing (prevents silent use of wrong resources). Analyzer naming/parameter changes add analyzer_extra_info but default-callers pass "" so existing analyzers and index contents remain unchanged. - New capability: DataNode compaction and StatsJobs can now build text indexes using external file resources in Ref mode — DataCoord exposes GetFileResources and populates CompactionPlan.file_resources; SortCompaction/StatsTask download resources via fileresource.Manager, produce an analyzer_extra_info JSON (storage + resource->id map) via analyzer.BuildExtraResourceInfo, and propagate analyzer_extra_info into BuildIndexInfo so the tantivy bindings can load custom analyzers during text index creation. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
140 lines
3.4 KiB
Protocol Buffer
140 lines
3.4 KiB
Protocol Buffer
syntax = "proto3";
|
|
|
|
package milvus.proto.indexcgo;
|
|
option go_package="github.com/milvus-io/milvus/pkg/v2/proto/indexcgopb";
|
|
|
|
import "common.proto";
|
|
import "schema.proto";
|
|
|
|
message TypeParams {
|
|
repeated common.KeyValuePair params = 1;
|
|
}
|
|
|
|
message IndexParams {
|
|
repeated common.KeyValuePair params = 1;
|
|
}
|
|
|
|
// TypeParams & IndexParams will be replaced by MapParams later
|
|
message MapParams {
|
|
repeated common.KeyValuePair params = 1;
|
|
}
|
|
|
|
message MapParamsV2 {
|
|
map<string, string> params = 1;
|
|
}
|
|
|
|
message Binary {
|
|
string key = 1;
|
|
bytes value = 2;
|
|
}
|
|
|
|
message BinarySet {
|
|
repeated Binary datas = 1;
|
|
}
|
|
|
|
message FieldInsertFiles {
|
|
repeated string file_paths = 1;
|
|
}
|
|
|
|
// segment insert files include all field insert files
|
|
message SegmentInsertFiles {
|
|
repeated FieldInsertFiles field_insert_files = 1;
|
|
}
|
|
|
|
// Synchronously modify StorageConfig in index_coord.proto file
|
|
message StorageConfig {
|
|
string address = 1;
|
|
string access_keyID = 2;
|
|
string secret_access_key = 3;
|
|
bool useSSL = 4;
|
|
string bucket_name = 5;
|
|
string root_path = 6;
|
|
bool useIAM = 7;
|
|
string IAMEndpoint = 8;
|
|
string storage_type = 9;
|
|
bool use_virtual_host = 10;
|
|
string region = 11;
|
|
string cloud_provider = 12;
|
|
int64 request_timeout_ms = 13;
|
|
string sslCACert = 14;
|
|
string GcpCredentialJSON = 15;
|
|
uint32 max_connections = 16;
|
|
}
|
|
|
|
// Synchronously modify OptionalFieldInfo in index_coord.proto file
|
|
message OptionalFieldInfo {
|
|
int64 fieldID = 1;
|
|
string field_name = 2;
|
|
int32 field_type = 3;
|
|
repeated string data_paths = 4;
|
|
int32 element_type = 5;
|
|
}
|
|
|
|
message BuildIndexInfo {
|
|
string clusterID = 1;
|
|
int64 buildID = 2;
|
|
int64 collectionID = 3;
|
|
int64 partitionID = 4;
|
|
int64 segmentID = 5;
|
|
int64 index_version = 6;
|
|
int32 current_index_version = 7;
|
|
int64 num_rows = 8;
|
|
int64 dim = 9;
|
|
string index_file_prefix = 10;
|
|
repeated string insert_files = 11;
|
|
// repeated int64 data_ids = 12;
|
|
schema.FieldSchema field_schema = 12;
|
|
StorageConfig storage_config = 13;
|
|
repeated common.KeyValuePair index_params = 14;
|
|
repeated common.KeyValuePair type_params = 15;
|
|
string store_path = 16;
|
|
int64 store_version = 17;
|
|
string index_store_path = 18;
|
|
repeated OptionalFieldInfo opt_fields = 19;
|
|
bool partition_key_isolation = 20;
|
|
int32 current_scalar_index_version = 21;
|
|
int64 json_key_stats_tantivy_memory = 22;
|
|
int64 lack_binlog_rows = 23;
|
|
int64 storage_version = 24;
|
|
SegmentInsertFiles segment_insert_files = 25;
|
|
StoragePluginContext storage_plugin_context = 26;
|
|
int64 json_stats_max_shredding_columns = 27;
|
|
double json_stats_shredding_ratio_threshold = 28;
|
|
int64 json_stats_write_batch_size = 29;
|
|
string manifest = 30;
|
|
string analyzer_extra_info = 31;
|
|
}
|
|
|
|
message StoragePluginContext {
|
|
int64 encryption_zone_id = 1;
|
|
int64 collection_id = 2;
|
|
string encryption_key = 3;
|
|
}
|
|
|
|
message LoadTextIndexInfo {
|
|
int64 FieldID = 1;
|
|
int64 version = 2;
|
|
int64 buildID = 3;
|
|
repeated string files = 4;
|
|
schema.FieldSchema schema = 5;
|
|
int64 collectionID = 6;
|
|
int64 partitionID = 7;
|
|
common.LoadPriority load_priority = 8;
|
|
bool enable_mmap = 9;
|
|
int64 index_size = 10;
|
|
}
|
|
|
|
message LoadJsonKeyIndexInfo {
|
|
int64 FieldID = 1;
|
|
int64 version = 2;
|
|
int64 buildID = 3;
|
|
repeated string files = 4;
|
|
schema.FieldSchema schema = 5;
|
|
int64 collectionID = 6;
|
|
int64 partitionID = 7;
|
|
common.LoadPriority load_priority = 8;
|
|
bool enable_mmap = 9;
|
|
string mmap_dir_path = 10;
|
|
int64 stats_size = 11;
|
|
}
|