Question

I have a Apache + Haproxy + Mongrel Cluster setup. I want to receive alerts whenever my Mongrel queue length gets too high.

How to I get the current Mongrel Queue length and make it available for alerting tools such as Monit and Nagios?

I know that Haproxy has the information about Mongrel queue as it intelligently sends requests to least busy Mongrel in the cluster. I wonder how it finds out? I need a similar mechanism to generate alerts and/or restart mongrels when such a condition arrives.

Answer 1

Add this to your haproxy config

        stats uri /haproxy/hastats 

Then use lynx to get the stats like this: (assuming haproxy runs on port 10000 – adjust to suit)

 lynx --dump http://my-server:10000/haproxy/hastats 

Each there will be a line for each of your server entries in the haproxy config file, telling you whether it’s up or down, how long it’s queue is, like this:

            Server                 Queue             Sessions                    Errors   Name    Weight Status Act. Bck. Curr. Max. Curr. Max. Limit  Cumul.   Conn. Resp. Sec. Check Down primary     1      UP    Y    -      0    0    68  386     - 134385861   207   699    0  7028  150 secondary    1      UP    Y    -      0    0    71  248     - 134464984   216   551    0  7129   98 

Now all you need is a script to get the current queue (column 6) and feed it into nagios, and you’re away!