...
| Code Block |
|---|
service MilvusService {
rpc Import(ImportRequest) returns (ImportResponse) {}
rpc GetImportState(GetImportStateRequest) returns (GetImportStateResponse) {}
}
message ImportRequest {
string collection_name = 1; // target collection
string partition_name = 2; // target partition
bool row_based = 3; // the file is row-based or column-based
repeated string files = 4; // file paths to be imported
repeated common.KeyValuePair options = 5; // import options, bucket, etc.
}
message ImportResponse {
common.Status status = 1;
repeated int64 tasks = 2; // id array of import tasks
}
message GetImportStateRequest {
int64 task = 1; // id of an import task
}
enum ImportState {
ImportPending = 0;
ImportFailed = 1;
ImportDownloaded = 2;
ImportParsed = 3;
ImportPersisted = 4;
ImportCompleted = 5;
}
message GetImportStateResponse {
common.Status status = 1;
ImportState state = 2; // is this import task finished or not
int64 row_count = 3; // if the task is finished, this value is how many rows are imported. if the task is not finished, this value is how many rows are parsed. return 0 if failed.
repeated int64 id_list = 4; // auto generated ids if the primary key is autoid
repeated common.KeyValuePair infos = 5; // more informations about the task, progress percent, file path, failed reason, etc.
} |
The call chain of import worflow:
3. Rootcoord RPC interfaces
...
| Code Block |
|---|
service RootCoord {
rpc Import(milvus.ImportRequest) returns (milvus.ImportResponse) {}
rpc GetImportState(milvus.GetImportStateRequest) returns (milvus.GetImportStateResponse) {}
rpc ReportImport(ImportResult) returns (common.Status) {}
}
message ImportResult {
common.Status status = 1;
int64 task_id = 2; // id of the task
common.ImportState state = 3; // state of the task
repeated int64 segments = 4; // id array of new sealed segments
repeated int64 auto_ids = 5; // auto-generated ids for auto-id primary key
int64 row_count = 6; // how many rows are imported by this task
repeated common.KeyValuePair infos = 7; // more informations about the task, file path, failed reason, etc.
} |
The call chain of import worflow:
4. Datacoord RPC interfaces
...
| Code Block |
|---|
service DataCoord {
rpc Import(ImportTask) returns (ImportTaskResponse) {}
}
message ImportTask {
common.Status status = 1;
string collection_name = 2; // target collection
string partition_name = 3; // target partition
bool row_based = 4; // the file is row-based or column-based
int64 task_id = 5; // id of the task
repeated string files = 6; // file paths to be imported
repeated common.KeyValuePair infos = 7; // more informations about the task, bucket, etc.
}
message ImportTaskResponse {
common.Status status = 1;
int64 datanode_id = 2; // which datanode takes this task
} |
The relationship between ImportRequest and ImportTask:
For row-based request, the RootCoord splits the request into multiple ImportTask, each json file is a ImportTask.
For column-based request, all files will be regarded as one ImportTask.
5. Datanode interfaces
The declaration of import API in datanode RPC:
...
To achieve this property, the segments shall be marked as "LoadingImporting" state and be invisible before the whole loading procedure completes.
...