Repository: hadoop
Updated Branches:
refs/heads/trunk e37458447 -> c16c49b8c
YARN-8587. Added retries for fetching docker exit code.
Contributed by Charo Zhang
Project: http://git-wip-us.apache.org/repos/asf/hadoop/repo
Commit: http://git-wip-us.apache.org/repos/asf/hadoop/commit/c16c49b8
Tree: http://git-wip-us.apache.org/repos/asf/hadoop/tree/c16c49b8
Diff: http://git-wip-us.apache.org/repos/asf/hadoop/diff/c16c49b8
Branch: refs/heads/trunk
Commit: c16c49b8c3b8e2e42c00e79a50e7ae029ebe98e2
Parents: e374584
Author: Eric Yang <[email protected]>
Authored: Wed Oct 24 17:28:23 2018 -0400
Committer: Eric Yang <[email protected]>
Committed: Wed Oct 24 17:29:46 2018 -0400
----------------------------------------------------------------------
.../impl/container-executor.c | 30 +++++++++++---------
1 file changed, 16 insertions(+), 14 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hadoop/blob/c16c49b8/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/native/container-executor/impl/container-executor.c
----------------------------------------------------------------------
diff --git
a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/native/container-executor/impl/container-executor.c
b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/native/container-executor/impl/container-executor.c
index 6704177..1ca94fe 100644
---
a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/native/container-executor/impl/container-executor.c
+++
b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/native/container-executor/impl/container-executor.c
@@ -2006,20 +2006,22 @@ int launch_docker_container_as_user(const char * user,
const char *app_id,
docker_binary, container_id);
fprintf(LOGFILE, "Obtaining the exit code...\n");
fprintf(LOGFILE, "Docker inspect command: %s\n",
docker_inspect_exitcode_command);
- FILE* inspect_exitcode_docker = popen(docker_inspect_exitcode_command, "r");
- if(inspect_exitcode_docker == NULL) {
- fprintf(ERRORFILE, "Done with inspect_exitcode, inspect_exitcode_docker is
null\n");
- fflush(ERRORFILE);
- exit_code = -1;
- goto cleanup;
- }
- res = fscanf (inspect_exitcode_docker, "%d", &exit_code);
- if (pclose (inspect_exitcode_docker) != 0 || res <= 0) {
- fprintf (ERRORFILE,
- "Could not inspect docker to get exitcode: %s.\n",
docker_inspect_exitcode_command);
- fflush(ERRORFILE);
- exit_code = -1;
- goto cleanup;
+ int count = 0;
+ int max_retries = get_max_retries(&CFG);
+ while (count < max_retries) {
+ FILE* inspect_exitcode_docker = popen(docker_inspect_exitcode_command,
"r");
+ res = fscanf (inspect_exitcode_docker, "%d", &exit_code);
+ if (pclose (inspect_exitcode_docker) != 0 || res <= 0) {
+ fprintf (ERRORFILE, "Could not inspect docker to get Exit code %s.\n",
docker_inspect_exitcode_command);
+ fflush(ERRORFILE);
+ exit_code = -1;
+ } else {
+ if (exit_code != 0) {
+ break;
+ }
+ }
+ sleep(3);
+ count++;
}
fprintf(LOGFILE, "Exit code from docker inspect: %d\n", exit_code);
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
