This is an attempt to add some simple monitoring so if the Pagure task
queue starts backing up, we know about it.
---
commit f207778a0e5aceba6c18885be7478317aaeab4b0
Author: Ricky Elrod <codeblock@fedoraproject.org>
Date: Fri May 26 23:09:02 2017 +0000
add simple monitoring for pagure's celery redis queue
Signed-off-by: Ricky Elrod <codeblock@fedoraproject.org>
diff --git a/roles/nagios_client/files/scripts/check_redis_queue.sh
b/roles/nagios_client/files/scripts/check_redis_queue.sh
new file mode 100644
index 0000000..ca1f186
--- /dev/null
+++ b/roles/nagios_client/files/scripts/check_redis_queue.sh
@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+
+. /usr/lib64/nagios/plugins/utils.sh
+
+if [[ "$#" -ne 3 ]]; then
+ echo "Arguments: key warn crit"
+ exit $STATE_UNKNOWN
+fi
+
+tasks="$(redis-cli llen "$1" | awk '{print $1}')"
+
+check_range $tasks $2:$3
+status=$?
+
+if [[ "$status" == "$STATE_OK" ]]; then
+ echo "OK: $1 queue has $tasks tasks"
+elif [[ "$status" == "$STATE_WARNING" ]]; then
+ echo "WARNING: $1 queue has $tasks tasks"
+elif [[ "$status" == "$STATE_CRITICAL" ]]; then
+ echo "CRITICAL: $1 queue has $tasks tasks"
+fi
+
+exit $status
diff --git a/roles/nagios_client/tasks/main.yml
b/roles/nagios_client/tasks/main.yml
index 714be36..22ddd4f 100644
--- a/roles/nagios_client/tasks/main.yml
+++ b/roles/nagios_client/tasks/main.yml
@@ -73,6 +73,7 @@
- check_osbs_builds.py
- check_osbs_api.py
- check_ipa_replication
+ - check_redis_queue.sh
when: not inventory_hostname.startswith('noc')
tags:
- nagios_client
@@ -146,6 +147,7 @@
- check_koschei_watcher_proc.cfg
- check_testcloud.cfg
- check_mirrorlist_docker_proxy.cfg
+ - check_celery_redis_queue.cfg
notify:
- restart nrpe
tags:
diff --git a/roles/nagios_client/templates/check_celery_redis_ queue.cfg.j2
b/roles/nagios_client/templates/check_celery_redis_ queue.cfg.j2
new file mode 100644
index 0000000..56279f3
--- /dev/null
+++ b/roles/nagios_client/templates/check_celery_redis_ queue.cfg.j2
@@ -0,0 +1 @@
+command[check_celery_redis_queue]=/usr/lib64/nagios/ plugins/check_redis_queue.sh
celery 5 10
diff --git a/roles/nagios_server/files/nagios/services/pagure_redis. cfg
b/roles/nagios_server/files/nagios/services/pagure_redis. cfg
new file mode 100644
index 0000000..d5387d0
--- /dev/null
+++ b/roles/nagios_server/files/nagios/services/pagure_redis. cfg
@@ -0,0 +1,6 @@
+define service {
+ host_name pagure01.fedoraproject.org
+ service_description Redis/celery queue
+ check_command check_by_nrpe!check_celery_redis_queue
+ use defaulttemplate
+}
_______________________________________________
infrastructure mailing list -- infrastructure@lists.fedoraproject.org
To unsubscribe send an email to infrastructure-leave@lists.fedoraproject.org