More data on 7.2-RELEASE "hangs"

[Marc G. Fournier]

On Wed, 13 May 2009, Steven Hartland wrote:

> We've seen things similar to this when an process uncommon process does 
> a query which locks the a table for a large amount of time on mysql.

Sooooo many reasons why I hate MySQL :(

One thing that we are trying right now is actually along these lines ... 
we've been working with MySQL 5.1 + NDBD for clustering ... after the last 
hang, we disabled both the NDBD startup, and mysql, to see if that is the 
cause, so nice to have some validation on this one ...

> In our example this turned out to be an admin query in vbulletin. When
> it happened it turned a machine which was purring along quite nicely
> into a totally unresponsive machine in a matter of a few seconds as
> apache spawned more process that also then instantly stalled...

Let me check that the next time around ... compare the specific # of http 
processes between monitor runs and see if there is a 'sudden jump' ...

We'll see hwo the next 'test period' works out, with that MySQL stuff 
offline ... the other thing I've been working on is moving jails off of 
that server, one at a time, to see if I can narrow down which one is 
causing the spike ... I will focus on the mysql backend ones going 
forward, to eliminate those ...

Thx ...

  ----
Marc G. Fournier           Hub.Org Networking Services (http://www.hub.org)
Email . scrappy at hub.org                              MSN . scrappy at hub.org
Yahoo . yscrappy               Skype: hub.org        ICQ . 7615664