[Gluster-devel] Problem with TLA ver > 887

[Geoff Kassel]

Hi,
   I'd like to second this report of something awry with the latest TLA. I've 
seen weird load issues (seemingly I/O related, not CPU) from the latest TLA 
as well - seemingly affecting primarily Apache, PHP-CGI and Suexec by causing 
these processes to become zombies waiting for I/O. Thanks to these zombie 
processes, load would creep up to ridiculous figures like 100+.

   Reverting to TLA 849 seemed to resolve the issue.

   This is using TCP with AFR/Unify, also with no performance translators.

   (Sorry for any duplication of this message - it seems the first one didn't 
get through.)

Kind regards,

Geoff Kassel.

On Thu, 5 Feb 2009, Mickey Mazarick wrote:
> I haven't done any full regression testing to see where the problem is
> but the later TLA versions are causeing out storage servers to spike to
> 100% cpu usage and the clients never see any files. Our initial tests
> are with ibverbs/HA but no performance translators.
>
> Thanks!
> -Mickey Mazarick