Skip to content
This repository was archived by the owner on Jul 8, 2026. It is now read-only.
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions config.schema.json
Original file line number Diff line number Diff line change
Expand Up @@ -1077,6 +1077,10 @@
"description": "Whether to create placement groups (SLURM only). Defaults to true",
"type": "boolean"
},
"warmup": {
"description": "Always keep 1 node running. Defaults to false",
"type": "boolean"
},
"idle_timeout": {
"description": "Idle time (seconds) before shutting down VMs. Choose lower than autoscale.idle_timeout",
"type": "integer"
Expand Down
20 changes: 20 additions & 0 deletions playbooks/scheduler.yml
Original file line number Diff line number Diff line change
Expand Up @@ -54,3 +54,23 @@
name: '*'
state: latest
# exclude: kernel*,kmod*,amlfs*

- name: copy queue warmup script
template:
src: 'queue-warmup.sh'
dest: '/usr/local/sbin/queue-warmup.sh'
mode: '0733'
when: ( queue_manager is defined and queue_manager == "slurm" )
tags: scheduler-warmup
- name: set up cronjob for queue warmup
cron:
name: "queue-warmup"
job: "/usr/local/sbin/queue-warmup.sh {{ warmup_queues | map(attribute='name') | join(' ') }}"
minute: "*/5"
weekday: 1-5
user: "root"
state: "present"
vars:
warmup_queues: "{{ queues | selectattr('warmup', 'defined') | selectattr('warmup', 'equalto', true) }}"
when: ( queue_manager is defined and queue_manager == "slurm" )
tags: scheduler-warmup
31 changes: 31 additions & 0 deletions playbooks/templates/queue-warmup.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
#!/bin/bash
# Usage: ./warmup-queues.sh viz hb2la
set -e

# SLURM node states & state flags on AZ-HOP

# idle VM allocated and idling
# idle~ VM not allocated from Azure
# idle# VM being allocated from Azure
# idle% VM being powered down
# mix Some CPUs allocated but not all

for queue in "$@"; do
available=`sinfo -p $queue --states=mix,idle --noheader | grep -v idle~ | grep -v idle# | grep -v idle% | wc -l`
allocating=`sinfo -p $queue --states=idle --noheader | grep idle# | wc -l`

if [[ $available == 0 && $allocating == 0 ]]; then
echo "Allocating 1 node on queue $queue"
srun --partition $queue bash > /dev/null 2>&1 &
PID=$!
sleep 2
set +e
kill $PID
set -e
elif [[ $available -gt 0 ]]; then
# "touch" one available node so that it won't be deallocated by slurm after timeout
set +e
srun --partition $queue "exit" > /dev/null 2>&1 &
set -e
fi
done