slurm.yml

slurm_cgroup_config:
  CgroupMountpoint: "/sys/fs/cgroup"
  CgroupAutomount: yes
  ConstrainCores: yes
  TaskAffinity: no
  ConstrainRAMSpace: no
  ConstrainSwapSpace: no
  ConstrainDevices: no
  AllowedRamSpace: 99.5
  AllowedSwapSpace: 0
  MaxRAMPercent: 99.5
  MaxSwapPercent: 100
  MinRAMSpace: 30
slurm_config:
  ClusterName: usegalaxy
  SchedulerType: sched/backfill
  TaskPlugin: task/cgroup #,task/affinity
  #TaskPluginParam: Sched
  SelectType: select/cons_res
  ProctrackType: proctrack/cgroup
  JobAcctGatherType: jobacct_gather/cgroup
  AccountingStorageType: accounting_storage/slurmdbd
  AccountingStorageHost: "{{ galaxy_host }}"
  ReturnToService: 1
  SelectTypeParameters: CR_Core_Memory
  ControlMachine: "{{ galaxy_host }}"
  SlurmctldLogFile: /var/log/slurm/slurmctld.log
  SlurmdLogFile: /var/log/slurm/slurmd.log
  SlurmdDebug: 3
  DefMemPerCPU: 1000
  SrunPortRange: "{{ slurm_SrunPortRange }}"
slurmdbd_config:
  AuthType: auth/munge
  DbdAddr: "{{ galaxy_host }}"
  DbdHost: "{{ galaxy_host }}"
  SlurmUser: slurm
  LogFile: /var/log/slurm/slurmdbd.log
  PidFile: /var/run/slurmdbd.pid
  StorageType: accounting_storage/mysql
  StorageHost: " {{ db_host }}"
  StoragePort: 3306
  StoragePass: "{{ mysql_slurm_password }}"
  StorageUser: "{{ mysql_slurm_username }}"
  StorageLoc: slurm_acct_db

slurm_nodes_old:
  - name: "{{ slurm_host }}"
    CoresPerSocket: "{{ hostvars[slurm_host].ansible_processor_cores }}"
    Sockets: "{{ hostvars[slurm_host].ansible_processor_count }}"
    ThreadsPerCore: "{{ hostvars[slurm_host].ansible_processor_threads_per_core }}"
    CPUs: "{{ hostvars[slurm_host].ansible_processor_vcpus }}"
    RealMemory: "{{ hostvars[slurm_host].ansible_memtotal_mb }}"

slurm_partitions:
  - name: "usegalaxy_{{ env }}"
    Default: YES
    MaxTime: UNLIMITED
    Nodes: "{{ groups[ 'slurm' ] | join(',') }}"

slurm_munge_key: files/munge/munge.key

slurm_node_ips: "{{ groups['slurm'] | map('extract', hostvars, ['ansible_eth0', 'ipv4', 'address']) | join(',') }}"

# Needs to be /data/part0 as it is not possible to share a drive with a mounted drive in it
# Will need to extend this when/if new drives come online
nfs_exports:
  - path: "/srv/galaxy"
#    export: "{{ slurm_node_ips }}(rw,async,no_root_squash)"
    export: "{{ groups['slurm'] | map('extract', hostvars, ['ansible_eth0', 'ipv4', 'address']) | join('(rw,async,no_root_squash) ')}}(rw,async,no_root_squash)"
  - path: "/data/part0"
#    export: "{{ slurm_node_ips }}(rw,sync,no_root_squash)"
    export: "{{ groups['slurm'] | map('extract', hostvars, ['ansible_eth0', 'ipv4', 'address']) | join('(rw,sync,no_root_squash) ')}}(rw,sync,no_root_squash)"
  - path: "/cvmfs/data.galaxyproject.org"
    export: "*(ro,sync,no_root_squash,no_subtree_check,fsid=101)"
  - path: "/cvmfs/data.usegalaxy.no"
    export: "*(ro,sync,no_root_squash,no_subtree_check,fsid=102)"

nfs_client_imports:
  - local: "/srv/galaxy"
    remote: "/srv/galaxy"
    server_host: "{{ galaxy_host }}"
  - local: "/data/part0"
    remote: "/data/part0"
    server_host: "{{ galaxy_host }}"
#  - local: "/cvmfs/data.galaxyproject.org"
#   remote: "/cvmfs/data.galaxyproject.org"
#   server_host: "{{ galaxy_host }}"
#  - local: "/cvmfs/data.usegalaxy.no"
#   remote: "/cvmfs/data.usegalaxy.no"
#   server_host: "{{ galaxy_host }}"

cvmfs_role: client
galaxy_cvmfs_repos_enabled: config-repo

cvmfs_server_urls:
  - domain: galaxyproject.org
    use_geoapi: yes
    #key_dir: "/cvmfs/cvmfs-config.galaxyproject.org/etc/cvmfs/keys/galaxyproject.org/"
    urls:
      #- "http://invivo.hpc.uio.no/cvmfs/@fqrn@"
      - "http://cvmfs1-ufr0.galaxyproject.eu/cvmfs/@fqrn@"
      - "http://cvmfs1-psu0.galaxyproject.org/cvmfs/@fqrn@"
      - "http://cvmfs1-iu0.galaxyproject.org/cvmfs/@fqrn@"
      - "http://cvmfs1-tacc0.galaxyproject.org/cvmfs/@fqrn@"
      #- "http://cvmfs1-mel0.gvl.org.au/cvmfs/@fqrn@"
  - domain: "{{ galaxy_host }}"
    use_geoapi: no
    urls:
      - "http://{{ cvmfs0_host }}/cvmfs/@fqrn@"

telegraf_plugins_extra:
  services:
    plugin: "exec"
    config:
      - commands = ["/usr/local/bin/systemd_status.py -t fail2ban slurmd autofs"]
      - timeout = "15s"
      - data_format = "influx"
      - interval = "1m"