From a38651483c035a65f8e799d92e695a742190d5b6 Mon Sep 17 00:00:00 2001 From: Ralph Castain Date: Fri, 16 Feb 2024 07:39:40 -0700 Subject: [PATCH] Only trigger job failed to start once Trigger the "job failed to start" state only when the first process to do so reports. This avoids a "bounce" effect that causes the job object to be multiply released. Signed-off-by: Ralph Castain --- src/mca/errmgr/dvm/errmgr_dvm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/mca/errmgr/dvm/errmgr_dvm.c b/src/mca/errmgr/dvm/errmgr_dvm.c index f0fce5afdc..8c8cea4712 100644 --- a/src/mca/errmgr/dvm/errmgr_dvm.c +++ b/src/mca/errmgr/dvm/errmgr_dvm.c @@ -486,6 +486,7 @@ static void proc_errors(int fd, short args, void *cbdata) PRTE_FLAG_SET(jdata, PRTE_JOB_FLAG_ABORTED); /* kill the job */ _terminate_job(jdata->nspace); + PRTE_ACTIVATE_JOB_STATE(jdata, PRTE_JOB_STATE_FAILED_TO_START); } /* if this was a daemon, report it */ if (PMIX_CHECK_NSPACE(jdata->nspace, PRTE_PROC_MY_NAME->nspace)) { @@ -493,7 +494,6 @@ static void proc_errors(int fd, short args, void *cbdata) pmix_show_help("help-errmgr-base.txt", "failed-daemon-launch", true, prte_tool_basename); } - PRTE_ACTIVATE_JOB_STATE(jdata, PRTE_JOB_STATE_FAILED_TO_START); break; case PRTE_PROC_STATE_CALLED_ABORT: