OpenVZ Forum


Home » Mailing lists » Users » Crazy IO utilization in VE running on Debian Squeeze host
Re: Crazy IO utilization in VE running on Debian Squeeze host [message #42151 is a reply to message #42149] Wed, 09 March 2011 19:58 Go to previous messageGo to previous message
Pavel Shevaev is currently offline  Pavel Shevaev
Messages: 4
Registered: February 2011
Junior Member
> I have been using OpenVZ 2.6.32 kernel in production for around 1 year
> on several machines at home and at work and I do not have this issue.
> Although I am using gentoo and the git kernel
>
> http://git.openvz.org/?p=linux-2.6.32-openvz;a=summary

Thanks for reply, however it seems I'm not the only one -
http://openvz.org/pipermail/users/2010-September/003822.html

BTW, some more details about my IO hardware: the server uses hardware
RAID-10 with BBU. Initially Percona was running using O_DIRECT for
InnoDB flushing but then I switched to the default flushing mode and
IO numbers became somewhat better... However after this I got several
data corruptions and simply stopped any further experiments.

--
Best regards, Pavel

Report message to a moderator

[Message index]
 
Read Message
Read Message
Read Message
Read Message
Previous Topic: Strange hiccups for new socket connections in Debian Lenny using 2.6.26-2-openvz-amd64
Next Topic: OpenSVC driver for OpenVZ merged
Goto Forum:
  

[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Fri Apr 10 07:54:31 GMT 2026

Total time taken to generate the page: 0.55175 seconds
Powered by FUDforum Powered by Virtuozzo Containers