Merge pull request #1522 from typhoonzero/k8s_cluster_rerun

Fix k8s cluster job rerunable
8 years ago · fe018da27a
parent 9827a5c665 9059eea4f4
commit fe018da27a
1 changed files with 2 additions and 1 deletions
--- a/doc/howto/usage/k8s/src/k8s_train/start_paddle.py
+++ b/doc/howto/usage/k8s/src/k8s_train/start_paddle.py
@ -132,7 +132,8 @@ def startPaddle(idMap={}, train_args_dict=None):
    logDir = JOB_PATH_OUTPUT + "/node_" + str(trainerId)
    if not os.path.exists(JOB_PATH_OUTPUT):
        os.makedirs(JOB_PATH_OUTPUT)
-    os.mkdir(logDir)
+    if not os.path.exists(logDir):
+        os.mkdir(logDir)
    copyCommand = 'cp -rf ' + JOB_PATH + \
        "/" + str(trainerId) + "/data/*" + " ./data/"
    os.system(copyCommand)