[Job Debugging] If user command's exitcode is none zero, container wi…

…ll be reserved. (#2225)
microsoft · Feb 28, 2019 · 7410b3d · 7410b3d
1 parent 590b4da
commit 7410b3d
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 0 deletions.
diff --git a/src/rest-server/src/models/job.js b/src/rest-server/src/models/job.js
@@ -444,6 +444,7 @@ class Job {
           'azRDMA': azureEnv.azRDMA === 'false' ? false : true,
           'paiMachineList': paiConfig.machineList,
           'reqAzRDMA': data.jobEnvs && data.jobEnvs.paiAzRDMA === true ? true : false,
+          'isDebug': data.jobEnvs && data.jobEnvs.isDebug === true ? true : false,
         });
     return dockerContainerScript;
   }

diff --git a/src/rest-server/src/templates/dockerContainerScript.mustache b/src/rest-server/src/templates/dockerContainerScript.mustache
@@ -202,6 +202,15 @@ else
   wait $user_command_pid
   user_command_exitcode=$?
   echo "job has finished with exit code $user_command_exitcode"
+{{# isDebug }}
+  if [[ $user_command_exitcode -ne 0 ]]; then
+    echo "============================================================================="
+    echo "======   The job container failed, so it will be reserved for 1 week   ======"
+    echo "======          After debugging, please stop the job manually.         ======"
+    echo "============================================================================="
+    sleep 604800
+  fi
+{{/ isDebug }}
   exit $user_command_exitcode
 fi