fix(client): add label for container and cancel by label (#1172)

client/starwhale/core/eval/executor.py

@@ -200,6 +200,8 @@ def _gen_run_container_cmd(self, typ: str, step: str, task_index: int) -> str:
             f"{self._version}-{step}-{task_index}",
             "-e",
             "DEBUG=1",
+            "-l",
+            f"version={self._version}",
         ]
 
         cmd += [

client/starwhale/core/eval/model.py

@@ -3,6 +3,7 @@
 import os
 import json
 import typing as t
+import subprocess
 from abc import ABCMeta, abstractmethod
 from http import HTTPStatus
 from collections import defaultdict
@@ -14,7 +15,7 @@
 from starwhale.base.uri import URI
 from starwhale.utils.fs import move_dir
 from starwhale.api._impl import wrapper
-from starwhale.base.type import EvalTaskType, InstanceType, JobOperationType
+from starwhale.base.type import InstanceType, JobOperationType
 from starwhale.base.cloud import CloudRequestMixed
 from starwhale.consts.env import SWEnv
 from starwhale.utils.http import ignore_error
@@ -283,8 +284,13 @@ def _do_container_action(
         elif action == JobOperationType.RESUME:
             cmd += ["unpause"]
 
-        # TODO: search container first
-        cmd += [f"{self.name}-{EvalTaskType.ALL}", f"{self.name}-{EvalTaskType.SINGLE}"]
+        # search container first
+        out = subprocess.check_output(
+            ["docker", "ps", "-f", f"label=version={self.store.id}", "-q"]
+        )
+        _container = out.decode().strip()
+
+        cmd += [_container]
         try:
             check_call(cmd)
         except Exception as e:

client/tests/core/test_eval.py

@@ -116,8 +116,9 @@ def test_stanalone_remove(self):
             / self.job_name
         ).exists()
 
+    @patch("starwhale.core.eval.model.subprocess.check_output")
     @patch("starwhale.core.eval.model.check_call")
-    def test_stanalone_actions(self, m_call: MagicMock):
+    def test_stanalone_actions(self, m_call: MagicMock, m_call_output: MagicMock):
         uri = URI(f"local/project/self/{URIType.EVALUATION}/{self.job_name}")
         job = StandaloneEvaluationJob(uri)
 

client/tests/core/test_executor.py

@@ -117,7 +117,7 @@ def test_run(self, m_scheduler: MagicMock, m_call: MagicMock) -> None:
 
         assert ppl_cmd == " ".join(
             [
-                f"docker run --net=host --rm --name {build_version}--0 -e DEBUG=1",
+                f"docker run --net=host --rm --name {build_version}--0 -e DEBUG=1 -l version={build_version}",
                 f"-v {job_dir}:/opt/starwhale",
                 f"-v {sw.rootdir}:/root/.starwhale",
                 f"-v {sw.object_store_dir}:{sw.object_store_dir}",