More data on 7.2-RELEASE "hangs"

Steven Hartland killing at multiplay.co.uk
Wed May 13 18:22:47 UTC 2009


----- Original Message ----- 
From: "Marc G. Fournier" <scrappy at hub.org>

> Right now, IO is running ~775 processes ... at the time of the vmstat I 
> provided earlier, it was up to 1400 processes ... since there is only 5 
> minutes between script runs, something is causing it to go from zero swap 
> -> high swap within a very short period of time, but since things get 
> badly locked up when it happens, I can't isolate where ...

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.

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...

So its likely the overloaded diagnosis could well be correct, but as
you say it hard to diagnose with the machine in such an unusable state.

Reducing max handlers etc on apache will help with this prevent the
machine becoming unusable and hence give you time and resources to
determine what the real issue is.

    Regards
    Steve

================================================
This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. 

In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337
or return the E.mail to postmaster at multiplay.co.uk.



More information about the freebsd-stable mailing list