- 14 Apr, 2016 4 commits
-
-
Morris Jette authored
select/cray - Initiate step node health check at start of step termination rather than after application completely ends so that NHC can capture information about hung (non-killable) processes. bug 2192
-
Danny Auble authored
-
Danny Auble authored
the message. This was needed for sbcast or srun --bcast since the tree width is different than the default. Bug 2512
-
Danny Auble authored
-
- 13 Apr, 2016 16 commits
-
-
Tim Wickberg authored
Make default compression vary based on library availability.
-
Morris Jette authored
A node's CPULoad was getting reset to NoVal on reconfiguration. This change preserves the old value, which can fix a possible race condition with respect to test4.13
-
Tim Wickberg authored
Calling functions all moved to src/bcast/
-
Morris Jette authored
power/cray - Fix bug introduced in 15.08.10 preventin operation in many cases. bug 2628
-
Morris Jette authored
-
Morris Jette authored
Was printing integer using %u format
-
Morris Jette authored
burst_buffer/cray - Fix for script creating or deleting persistent buffer would fail "paths" operation and hold the job. bug 2624
-
Danny Auble authored
and it doesn't meet basic requirements.
-
Tim Wickberg authored
-
Morris Jette authored
Test previously failed with heterogeous nodes (i.e. different core counts on different nodes). bug 2597
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
We know it is in 1.7.1 but not in 1.3.0
-
Danny Auble authored
-
Danny Auble authored
tree_msg_to_stepds() which does the same thing.
-
Danny Auble authored
nodes not able to contact.
-
- 12 Apr, 2016 2 commits
-
-
Brian Christiansen authored
Bug 2431
-
Morris Jette authored
-
- 11 Apr, 2016 18 commits
-
-
Danny Auble authored
This reverts commit 2243bf33.
-
Marlys Konhke authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Alejandro Sanchez authored
-
Tim Wickberg authored
-
Morris Jette authored
-
Morris Jette authored
Conflicts: src/plugins/burst_buffer/cray/burst_buffer_cray.c src/plugins/select/cons_res/select_cons_res.c
-
Morris Jette authored
The gprof tool is showing most time is being consumed by the bit_test() function as called from the select plugin, which in turn was called by the backfill scheduler. These changes replace the for loop end-points. Previous logic tested for all possible nodes. The new logic identifes the first and last bit set in the node bitmap and uses those end-points instead. Node the logic to find the first and last bits set starts off with a word-based search (testing for a 64-bit zero value rather than testing each individual bit). The net result is a small performance improvement. bug 2588
-
Tim Wickberg authored
Bug 2622.
-
Tim Wickberg authored
Bug 2622.
-
Tim Wickberg authored
-
Morris Jette authored
burst_buffer/cray - Decrement job's prolog_running counter if pre_run fails. bug 2621
-
Morris Jette authored
If a job is no longer in configuring state, then clear the prolog_running counter on slurmctld restart or reconfigure. bug 2621
-