Hello, in the varnish_ munin plugin included with official munin package and hosted at <a href="http://munin-monitoring.org/browser/munin/plugins/node.d/varnish_.in">http://munin-monitoring.org/browser/munin/plugins/node.d/varnish_.in</a> it says the official way to send patches is this list. <div>
<br></div><div>We have been using a modified varnish_ plugin for some time and I finally I have taken the code in sync with current plugin in order to send upstream our modifications.<div><br></div><div>Attached is a patch that does add a few values to some graphs:</div>
<div>* Add client_drop to request_rate graph.</div><div>* Add s_pass s_pipe to hit_rate graph (now they are closer to sum 100% as we have ~3% of s_pass which weren't shown previously).</div><div>* Add backend_toolate & backend_retry to backend_traffic graph.</div>
<div>* Add n_wrk_lqueue & n_wrk_queued to threads graph.</div><div>* Add Transient memory to memory_usage graph.</div><div><br></div><div>In our old plugin we also have a graph that I'm not sure how to do now and I think it's useful. It shows the average object size measured as:</div>
<div><div> 'rpn' => [ 'SMF_s0_g_bytes', 'SMA_s0_g_bytes', '+', 'n_object', '/' ]</div><div><br></div><div>We sum the values of the two storages because at one time we switched from the file storage to the malloc storage and we lost the graphs. Usually one will be zero and the other will be the current memory in use. I know that it's not the exact average object size as there are more things stored, but at least for our cache contents seems to be a valuable metric, we are in the range 15-20k.</div>
<div><br></div><div>But in the current version I'm not sure how to replicate this graph.</div><div><br></div><div>Regards.</div><div><br></div>-- <br>Jorge Nerín<br><<a href="mailto:jnerin@gmail.com">jnerin@gmail.com</a>>
</div></div>