- 06 Jul, 2018 3 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Broderick Gardner authored
bug 5337
-
- 05 Jul, 2018 3 commits
-
-
Danny Auble authored
the database. Bug 5247
-
Morris Jette authored
Previous logic could trigger KNL node reboot when job did not request any KNL MCDRAM or NUMA modes as features. For example: srun -N3 -C "[foo*1&bar*2]" hostname would trigger reboot of all KNL nodes even though no KNL-specific features were requested. This bug only exists in v18.08 and was introduced when expanding KNL node feature specification capabilities.
-
Morris Jette authored
Invoke select_g_job_test() one time with all valid node rather than multiple times when adding higher weight nodes. This results in the job allocation always accumulating nodes from lower to higher weights rather than possibly using mostly higher weight nodes. It also streamlines the resource allocation process for most configurations by eliminating some repeated logic as groups of nodes are added for consideration by the select plugin.
-
- 04 Jul, 2018 4 commits
-
-
Felip Moll authored
Cleaned up code that could've caused performance issues when reading config and there was nodes with features defined. bug4980
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
- 03 Jul, 2018 7 commits
-
-
Morris Jette authored
fix for commit 4a0a6a94 bug 4821
-
Morris Jette authored
bug 4821
-
Morris Jette authored
Add 64-bit sched_weight (scheduling weight) to node_set struct Populate it with the node's weight (possibly reboot weight) plus high-order bits for FLEX-reservation and rebooting. No longer are node weights of INFINITE or (INFINITE-1) used to flag FLEX or reboot requirements so we don't need to worry about overlapping node weight values. It also will cleanly allow the cons_tres plugin to be passed ALL usable nodes at one time to accumulate resources from the lowest weight first and only use individual higher weight nodes as needed (rather than possibly using mostly higher weight nodes). bug 4821
-
Felip Moll authored
breaks out node sets by in/out flex reservation and need to reboot bug 4821
-
Morris Jette authored
The node weight of a node requiring reboot is not a fixed value in v18.08, but configurable bug 4821
-
Morris Jette authored
bug 5337
-
Broderick Gardner authored
bug 5337
-
- 02 Jul, 2018 9 commits
-
-
Broderick Gardner authored
bug 5337
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
This test change addresses gres api changes introduced in commit 6e0469b5
-
Morris Jette authored
-
Morris Jette authored
Implicitly set node count, task count, ntasks_per_* as appropriate
-
Morris Jette authored
Prior logic lacked a line-feed and ran lines together
-
- 29 Jun, 2018 5 commits
-
-
Morris Jette authored
-
Morris Jette authored
Previous logic was implicitly starting 2 tasks due to the combination of --gpus and --gpus-per-node
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
- 27 Jun, 2018 1 commit
-
-
Morris Jette authored
Original logic was testing against number of available CPUs on a node, not the number actually being allocated. This can easily result in a valid job not being possible to run. Note that setting the max_cpus parameter requires the "scontrol update jobid=# numcpus=#-#" command be explicitly executed as the option is not available at job submit time, so it isn't something likely to happen on a production system. Also note this bug exists in the cons_res plugin and was just copied to cons_tres.
-
- 26 Jun, 2018 6 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Felip Moll authored
-
Felip Moll authored
When one asks for an inactive feature and also specifies the node with -w flag, the node will be rebooted despite it may contain running jobs. bug4821
-
Morris Jette authored
Return resource array structure rather than just CPU count
-
Tim Wickberg authored
and avoid race condition calling task before proctrack can introduce. Bug 5319
-
- 25 Jun, 2018 2 commits
-
-
Morris Jette authored
to work correctly. Bug 5155 Bug 4516
-
Morris Jette authored
delayed until the first job completes execution and it's burst buffer stage-out is completed. Bug 4675
-