Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add ansible example playbook for deployment #14

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
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
19 changes: 19 additions & 0 deletions ansible/ansible.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
---
- hosts:
roles:

# Fastapi that collects stats about Pulsar nodes

- role: pdg.tpv_metascheduler_api

# Condor monitoring scripts to be ran using telegraf (can be set up on Pulsar nodes)

- role: hxr.monitor-cluster

# Telegraf

- role: dj-wasabi.telegraf




78 changes: 78 additions & 0 deletions ansible/monitoring.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,78 @@
# Monitoring
# TODO: add example outputs here
telegraf_plugins_extra:

monitor_galaxy_tool_times:
plugin: "exec"
config:
- commands = ["/usr/bin/monitor-galaxy-tool-times"]
- timeout = "10m"
- data_format = "influx"
- interval = "10m"

monitor_galaxy_queue:
plugin: "exec"
config:
- commands = [
"{{ custom_telegraf_env}} {{ gxadmin_bin_dir }}/gxadmin iquery queue-overview --short-tool-id"
]
- timeout = "15s"
- data_format = "influx"
- interval = "15s"

monitor_galaxy_queue_state:
plugin: "exec"
config:
- commands = [
"{{ custom_telegraf_env}} {{ gxadmin_bin_dir }}/gxadmin iquery queue --by destination"
]
- timeout = "1m"
- data_format = "influx"
- interval = "1m"

monitor_condor_queue:
plugin: "exec"
config:
- commands = ["sudo /usr/bin/monitor-condor-queue"]
- timeout = "2m"
- data_format = "influx"
- interval = "2m"

monitor_condor_queue_jobs:
plugin: "exec"
config:
- commands = ["sudo /usr/bin/monitor-condor-queue-jobs"]
- timeout = "2m"
- data_format = "influx"
- interval = "2m"

monitor_condor_util:
plugin: "exec"
config:
- commands = ["sudo /usr/bin/monitor-condor-utilisation"]
- timeout = "5m"
- data_format = "influx"
- interval = "10m"

# Some custom galaxy monitoring stuff
galaxy_jobs_queued:
plugin: "exec"
config:
- commands = ["{{ custom_telegraf_env }} /usr/bin/gxadmin iquery jobs-queued"]
- timeout = "15s"
- data_format = "influx"
- interval = "1m"
galaxy_jobs_queued_internal:
plugin: "exec"
config:
- commands = ["{{ custom_telegraf_env }} /usr/bin/gxadmin iquery jobs-queued-internal-by-handler"]
- timeout = "15s"
- data_format = "influx"
- interval = "1m"
galaxy_jobs_queue_overview:
plugin: "exec"
config:
- commands = ["{{ custom_telegraf_env }} /usr/bin/gxadmin iquery queue-overview --short-tool-id"]
- timeout = "30s"
- data_format = "influx"
- interval = "1m"
2 changes: 2 additions & 0 deletions ansible/requirements.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
roles:
- name: dj-wasabi.telegraf
Loading