Skip to content
Snippets Groups Projects
Select Git revision
  • 20180923
  • 20181019
  • 20181022
  • 201902
  • 24june
  • 34-nvme-disk-not-mounted
  • AddKaraageCommitVersion
  • CRAMSdev
  • FixCvlSssdConfig
  • FixSlurmConfigBackup
  • Oct2018
  • Sep2019
  • a16s
  • add-pmiX-functionality-to-slurm01
  • add_slurmstats
  • add_strigger_clusterbuild
  • admin_packages
  • allow_private_network_input
  • ansible_include_errors
  • autoupdate_update
20 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.011Aug87131Jul131110519Jun26May18151121Apr7630Mar272421201023Feb7131Jan6543221Dec201513128528Nov25242322161110325Oct2421720Sep15137616Aug1112115432129Jul25222120136424Jun222120191614137231May30272625181243228Apr2726222018151454130Mar242322211714109312129Feb23191511109422Jan151217Dec158742126Nov2524201918171110543230Oct28272620161514830Sep292524232221181716141311109874131Aug292827262521201914131210754331Jul302423finally corrected the cuda collectd scriptUpdate cuda_collectd.py.j2Merge branch 'gpu_util' into 'master' Remove unused fan_speed monitoring, add monitoring of memory and gpu utilizationforgot to include the buddyinfo script for collectdMerge branch 'cuda_collectd' into 'master' more meaningful comments in name: task,ansible_include…ansible_include_errorsPlaced comment after include, as newer ansible version will include a file but no execute it without such a linetemplated the outgoing and ingoing ports on the NAT which runs on the DTN nodenat_rolenat_roletemplate out device names for iptables. Use ip route <IP> to determine device names.change the way a script is called to determine number of GPUsslurm_gres_probeslurm_gres_probeMerge branch 'gluster' into 'master' Added "set quorum ratio" commandchanged a role to run on "+ delegate_to: "{{ gluster_servers[0] }}"" so it is consistent within playbookcollectd monitoring changes ... monitor additional things in proc, don't monitor slabinfo as its noisy, monitor gpusMerge branch 'master' of gitlab.erc.monash.edu.au:hpc-team/ansible_cluster_in_a_box into improve_nat_rolechanged a role to run on "+ delegate_to: "{{ gluster_servers[0] }}"" so it is consistent within playbookAdded "set quorum ratio" commandPlaced comment after include, as newer ansible version will include a file but no execute it without such a linemore meaningful comments in name: task,template out device names for iptables. Use ip route <IP> to determine device names.templated the outgoing and ingoing ports on the NAT which runs on the DTN nodechange the way a script is called to determine number of GPUswe found that kernel packages reinstalled default centos repos. We need to remove them at this point (again)Merge branch 'nagios_slurmctld' into 'master' nagios script for slurmctldMerge branch 'prolog' into 'master' Update main.ymlRemove adding cluster on slurmRemoved the /tmp clean-up until the script is sortedRemoved the /tmp clean-up until the script is sortedDropping cache on epilog & prologMerge branch 'update_kernel' into 'master' Update the mofed versionMerge branch 'collectd' into 'master' add a collectd role that can be deploed to compute and login nodesMerge branch 'fix_hpcsystems' into 'master' Merge branch 'fix_gluster' into 'master' update the hpcsystems role to include the naggy_quota cronjob and update the tools via pipfix the volcreate to be more sane