From bbc14842530ff1ff2d80bb7134acc9bc180cd6f3 Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Sun, 13 Oct 2019 22:39:52 -0700 Subject: [PATCH] check-rabbitmq-queue: Adjust threshholds for paging. Ultimately, this isn't an effective way to monitor this queue; we want time-based monitoring, not count-based monitoring. Doing that properly will likely involve modifying the queue processor to write something about its status. But until we add the monitoring we want, it makes sense to leave this active with low limits. --- scripts/nagios/check-rabbitmq-queue | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/nagios/check-rabbitmq-queue b/scripts/nagios/check-rabbitmq-queue index 064e9d7138..768e0b16a2 100755 --- a/scripts/nagios/check-rabbitmq-queue +++ b/scripts/nagios/check-rabbitmq-queue @@ -14,14 +14,14 @@ WARN_THRESHOLD = { # The user_activity worker has high throughput and uses a # LoopQueueProcessingWorker, so it's normal to have a moderate # backlog. - 'user_activity': 100, + 'user_activity': 1000, } CRIT_THRESHOLD_DEFAULT = 50 CRIT_THRESHOLD = { 'missedmessage_emails': CRIT_THRESHOLD_DEFAULT, # A backlog of hundreds of events for user_activity likely # indicates an outage of the processor. - 'user_activity': 500, + 'user_activity': 5000, } states = {