- 23 Mar, 2017 20 commits
-
-
Brian Christiansen authored
when the job is being purged due a the origin job being "cleaned" (e.g slurmctld -c).
-
Brian Christiansen authored
-
Brian Christiansen authored
instead of just all of the viables. I need to be able send the viable list to only a specific sibling. For example if reconciliation finds that a sibling doesn't have a job that the origin thinks it could.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
The connection's memory wasn't getting free'd which caused issues when the connection needed to be restablished.
-
Brian Christiansen authored
-
Brian Christiansen authored
data_size is used when sending buffer messages (e.g. RESPONSE_JOB_INFO).
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
This protects the fed_mgr_fed_rec. Reverted 315cff15. This is a cleaner patch.
-
Brian Christiansen authored
This reverts commit 315cff15.
-
Brian Christiansen authored
This reverts commit e5f2c720.
-
Brian Christiansen authored
Continuation of 315cff15
-
Morris Jette authored
-
Morris Jette authored
-
Brian Christiansen authored
-
Morris Jette authored
Explicitly test WIFEXITED() rather than assume an exit code if WIFSIGNALED is false. bug 3562
-
- 22 Mar, 2017 9 commits
-
-
Morris Jette authored
This will avoid filling the slurmctld logs with communication error messages when a cluster in the federation is down.
-
Morris Jette authored
-
Morris Jette authored
bug 3610
-
Morris Jette authored
No change to logic
-
Morris Jette authored
-
Morris Jette authored
Fix some recently introduced memory leaks related to lists of RPCs.
-
Morris Jette authored
Correct spelling of persistent in various comments and log messages. No changed to logic.
-
Morris Jette authored
Log the RPCs queued for processing by the federation agent which remain unprocessed at slurmctld shutdown
-
Morris Jette authored
The broadcast was temporarily removed for testing purposes
-
- 21 Mar, 2017 11 commits
-
-
Danny Auble authored
# Conflicts: # src/slurmctld/proc_req.c
-
Danny Auble authored
Bug 3097
-
Danny Auble authored
-
Tim Shaw authored
-
Brian Christiansen authored
Value stored to 'rc' is never read.
-
Michael Meier authored
-
Michael Meier authored
-
Morris Jette authored
Add message type strings and job IDs where possible
-
Morris Jette authored
Failed RPCs get requeued and retried with exponential backup. Repeatedly failing RPCs get logged (need to improve that).
-
Thomas Opfer authored
Fix correct macro this time, Tim Wickberg's fault for prior failed patch. Bug 3605.
-
Thomas Opfer authored
This reverts commit 53523c54.
-