Comments on: Query Response time histogram – new feature in Percona Server

By: Baron Schwartz

Baron Schwartz — Sun, 23 Jan 2011 21:32:47 +0000

There are now graphs for this in the Cacti templates I maintain:

http://code.google.com/p/mysql-cacti-templates/wiki/MySQLTemplates

Scroll down to these graphs:

# MySQL Query Response Time (Microseconds)
# MySQL Query Time Histogram (Count)

By: Vadim

Vadim — Tue, 17 Aug 2010 01:23:55 +0000

Sean,

It should come in next two weeks.

By: Sean

Sean — Mon, 16 Aug 2010 22:43:04 +0000

Vadim, is there an eta date on the next release (5.1-12.0)?

By: Dimitri

Dimitri — Mon, 12 Jul 2010 18:41:24 +0000

Great stuff!! – specially when monitoring live the difference between periods you may point exactly to the moment when the deviation is happening!..

Will add it to dim_STAT too

Rgds,
-Dimitri

By: peter

peter — Mon, 12 Jul 2010 16:19:51 +0000

Rob,

This feature acts as a “fingerprint” for a lot of systems – there are going to be some slow queries and some short two, while distribution will stay more or less the same.
Not all the systems have this property of course some may have cron jobs etc which cause significant behavior variance.

For systems with stable workload we can monitory such histogram every 5 minutes or so and track for significant variances.

Periodic spikes in response time is a frequent problem which is often noticed too late – after it significantly impacts production. Though most of such problems start with more subtle changes.

By: Farid

Farid — Mon, 12 Jul 2010 08:54:28 +0000

Great stuff !

Wondering if there is any overhead with this function enabled ?

By: Shlomi Noach

Shlomi Noach — Mon, 12 Jul 2010 06:24:39 +0000

Very good stuff! Keep up the good work!

By: matt

matt — Mon, 12 Jul 2010 03:51:27 +0000

thanks, it’s very useful!

By: Mark Callaghan

Mark Callaghan — Mon, 12 Jul 2010 03:36:34 +0000

Excellent. It is great to see our tools and processes get better.

By: Vadim

Vadim — Mon, 12 Jul 2010 03:06:47 +0000

Rob,

I agree, tagging of queries would give even more sense for query monitoring.
I think we will add it eventually.