400 Commits (master)
 

Author SHA1 Message Date
B.E. Droge 0824028ea5 Escape percentage symbol in cron file 2 years ago
Egon Rijpkema dcfd54fdea Ignore 'All the cvmfs' 2 years ago
B.E. Droge 4d9e2e1108 split long line 2 years ago
B.E. Droge ace8727b76 fix quotes 2 years ago
B.E. Droge 303fe58d6d Add inefficient jobs detector 2 years ago
Egon Rijpkema 0e57aa26b0 Added load alert for OSS 2 years ago
Egon Rijpkema 5c0253db9a Better formatting 2 years ago
Egon Rijpkema 8c44d4d262 Added mds load warning. 2 years ago
Egon Rijpkema df885a618d Initial version of runaway jobs detector. 2 years ago
B.E. Droge ea270a3292 Change gpu qos thresholds 2 years ago
Egon Rijpkema bdaa77b85a Be a little more gracefull. 2 years ago
Egon Rijpkema 1f5b7ed924 New channel. 2 years ago
Egon Rijpkema 412d3f550c kill-hogs has its own channel now. 2 years ago
Egon Rijpkema f294efeff1 Some nodeis report node_filesystem_free_bytes 2 years ago
Egon Rijpkema 355bf714ca Merge branch 'feature/gpu-detector' 2 years ago
Egon Rijpkema edcfebde04 initial commit of gpu_detector 2 years ago
Egon Rijpkema 08963ce123 Add support for jobs using multiple GPUs. 2 years ago
Egon Rijpkema 6f6a1d55cd initial commit, work in progress 2 years ago
Egon Rijpkema fb2d12f334 Added more appropriate message 3 years ago
B.E. Droge a762b7eb54 Added monk feature to some vulture nodes 3 years ago
B.E. Droge a8a12f344e Modified URL to wiki 3 years ago
B.E. Droge dd4ccd8722 Changed redmine url to new wiki url 3 years ago
B.E. Droge 502e059c74 Changed URL to scientific output in the SLURM epilog 3 years ago
Egon Rijpkema 588c925cbd When is say 10 seconds it should be 10 seconds. 3 years ago
Egon Rijpkema 2622037ea0 Added check against nodes_todo 3 years ago
Egon Rijpkema c9ae3b04d9 Tool to remount /apps on all nodes. 3 years ago
Egon Rijpkema 3dd59b289d Added labels for slurm and sql. 3 years ago
root dec81a6d9a Merge branch 'master' of ssh://git.webhosting.rug.nl:222/HPC/pg-playbooks 3 years ago
root ca668e1ab5 update 3 years ago
root 61d44f1447 update 3 years ago
Egon Rijpkema 6cf4532c64 This is peregrine, not gearshift. 3 years ago
Egon Rijpkema 646b34ee46 Added alert for drained nodes. 3 years ago
B.E. Droge cd3894038f Increase max time for lab partition to 24h 3 years ago
Egon Rijpkema b08c397c1d removed timeout 3 years ago
B.E. Droge 6204ec6483 Merge branch 'feature/undockerize_slurm' of HPC/pg-playbooks into master 3 years ago
B.E. Droge 789f0fba59 Changed copy into template for ssmtp.conf 3 years ago
B.E. Droge 24fd01a7f5 Time limit of short partition should be 30 (minutes), not 30*60 3 years ago
Egon Rijpkema 073d4bf4f9 find needs more time. 3 years ago
root 604b0cdf76 deleted 3 years ago
root 979a04ee03 update 3 years ago
root 67b255ba63 update 3 years ago
root 151f76d3e4 update 3 years ago
root ac4e5f5eb0 update 3 years ago
root a96fd96300 update 3 years ago
root 43fc47f94b update 3 years ago
root 2fa32acb22 update 3 years ago
root 45bbdb3990 update 3 years ago
root 4e6943cf30 update 3 years ago
B.E. Droge 359e0d523f Added full name for SLURM account 3 years ago
B.E. Droge 1e87ac291b Fix file permissions of logrotate config 3 years ago