- 05 Oct, 2016 13 commits
-
-
Morris Jette authored
-
Morris Jette authored
node_features/knl_cray plugin: drain any node not reported by "capmc node_status" on startup or reconfig. Also re-tests on failed node restart for job.
-
Morris Jette authored
node_features/knl_cray plugin: Remove any KNL MCDRAM or NUMA features from node's configuration if capmc does NOT report the node as being KNL. For example, we don't want a non-KNL node with features="quad,cache".
-
Morris Jette authored
Add new knl.conf configuration parameter CapmcRetries Modify capmc_suspend and capmc_resume to retry operations when Cray State Manager is down. Add retry logic to node_features/knl_cray to handle Cray State manager being down. bug 3100
-
Danny Auble authored
from commit ee4a9776.
-
Danny Auble authored
-
Danny Auble authored
reset by list_count. Also remove a nested if for cleaner code.
-
Danny Auble authored
-
Tim Wickberg authored
Logs go to both locations when running in non-daemonized mode. Don't refer to this as "debug" mode, while useful for debugging it's not directly related. Bug 3146.
-
Morris Jette authored
node_features/knl_cray plugin: Substantially streamline and speed up logic to load current node state on reconfigure failure or unexpected node boot. Completely eliminate capmc calls and just use cnselect to load current node mode information.
-
Morris Jette authored
node_features/knl_cray plugin: drain any node not reported by "capmc node_status" on startup or reconfig. Also re-tests on failed node restart for job.
-
Morris Jette authored
node_features/knl_cray plugin: Remove any KNL MCDRAM or NUMA features from node's configuration if capmc does NOT report the node as being KNL. For example, we don't want a non-KNL node with features="quad,cache".
-
Brian Christiansen authored
Found by clang. Continuation of 76d62ae4
-
- 04 Oct, 2016 9 commits
-
-
Brian Christiansen authored
-
Morris Jette authored
Missed a flag that needed to move on Cray systems too
-
Morris Jette authored
Add new knl.conf configuration parameter CapmcRetries Modify capmc_suspend and capmc_resume to retry operations when Cray State Manager is down. Add retry logic to node_features/knl_cray to handle Cray State manager being down. bug 3100
-
Danny Auble authored
from commit ee4a9776.
-
Danny Auble authored
-
Danny Auble authored
reset by list_count. Also remove a nested if for cleaner code.
-
Danny Auble authored
-
Tim Wickberg authored
Logs go to both locations when running in non-daemonized mode. Don't refer to this as "debug" mode, while useful for debugging it's not directly related. Bug 3146.
-
Morris Jette authored
-
- 03 Oct, 2016 2 commits
-
-
Dominik Bartkiewicz authored
-
Tim Wickberg authored
Removing the bl_bgq Makefile from configure.ac was a mistake. Add back and run autogen.sh to fix build.
-
- 30 Sep, 2016 16 commits
-
-
Alejandro Sanchez authored
Otherwise they'll truncate when packed into the RPC and end up as some bizarre value at the controller. Bug 3098.
-
Tim Wickberg authored
CID 44797.
-
Tim Wickberg authored
Coverity doesn't like the odd structure that was left behind. No functional difference. CID 44793.
-
Dominik Bartkiewicz authored
Set completed time for pending/running runaway jobs to the max of (start, eligible, submit) times. Bug 3075
-
Morris Jette authored
-
Morris Jette authored
Change "sched_params" to "power_params" because that's what it contains.
-
Morris Jette authored
Added new SchedulerParameters options step_retry_count and step_retry_time to control scheduling behaviour of job steps waiting for resources. bug 3121
-
Gennaro Oliva authored
-
Morris Jette authored
Previous logic would always retry in 60 to 69 secs (based upon srun PID). New logic will wait up to SlurmctldTimeout + 9 secs (minimum value 60 seconds, maximum 309 seconds).
-
Morris Jette authored
This change can reduce RPCs sent by srun up to 50%.
-
Artem Polyakov authored
Avoid using slurm_forward_data because it causes thread spawn that introduces unwanted delays. Bug 3102.
-
Tim Wickberg authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Counter became invalid due to re-use of a variable within a loop.
-
Morris Jette authored
THis can happen due to signal/retry logic and the result is vestigial srun ports that are no longer valid and slurmctld sending messages to invalid ports to notify them about available resources as other steps complete
-