collection name

Author: zhiqiang-hhhh

vectordb_bench/backend/clients/doris/doris.py

@@ -18,6 +18,7 @@ def __init__(
             dim: int,
             db_config: dict,
             db_case_config: DorisCaseConfig,
+            collection_name: str | None = None,
             drop_old: bool = False,
             **kwargs,
     ):
@@ -26,8 +27,9 @@ def __init__(
         self.case_config = db_case_config
         self.dim = dim
         self.search_fn = db_case_config.search_param()["metric_fn"]
+        # Prefer provided collection_name; otherwise fallback to a simple default
         # e.g. l2_distance128, inner_product128
-        self.table_name = self.search_fn + str(dim)
+        self.table_name = collection_name if collection_name else (self.search_fn + str(dim))
 
         # Store connection configuration for lazy initialization
         self.auth_options = AuthOptions(

vectordb_bench/backend/task_runner.py

@@ -97,13 +97,33 @@ def normalize(self) -> bool:
 
     def init_db(self, drop_old: bool = True) -> None:
         db_cls = self.config.db.init_cls
+        # Compose a compact, case-unique collection/table name for Doris to avoid cross-case interference
+        collection_name = None
+        try:
+            from .clients import DB
+            if self.config.db == DB.Doris:
+                import re, hashlib
+                # Primary identifier = case-type enum name from CLI (e.g., Performance768D10M)
+                case_type_name = self.config.case_config.case_id.name
+                base = f"vdb_{case_type_name.lower()}"
+                # Sanitize to [a-z0-9_]
+                base = re.sub(r"[^a-z0-9_]+", "_", base).strip("_")
+                # Cap to 63 chars; add short hash if truncated
+                if len(base) > 63:
+                    h = hashlib.md5(base.encode()).hexdigest()[:6]
+                    base = f"{base[:(63-7)]}_{h}"
+                collection_name = base
+        except Exception:
+            # If anything goes wrong, fall back silently; Doris will use its default name logic
+            collection_name = None
 
         self.db = db_cls(
             dim=self.ca.dataset.data.dim,
             db_config=self.config.db_config.to_dict(),
             db_case_config=self.config.db_case_config,
             drop_old=drop_old,
             with_scalar_labels=self.ca.with_scalar_labels,
+            **({"collection_name": collection_name} if collection_name else {}),
         )
 
     def _pre_run(self, drop_old: bool = True):