On Thu, Sep 20, 2012 at 04:33:09AM +0000, Markus Stockhausen wrote:
> > Fundamentally, you are doing it all wrong. High throughput, low
> > latency NFS servers write dirty data to disk fast, not leave it
> > memory until you run out of clean memory because that causes
> > everything to block waiting for writeback IO completion to be ale to
> > free memory...
>
> Maybe I did not make it clear enough.
Plenty clear enough. Maybe I did not make it clear enough:
Nobody has the time to try to diagnose a problem on a configuration
that is obviously broken and pessimal for writeback behaviour. The
first step is to report your actual problem, not an artificial
behaviour you *think* demonstrates the same problem....
> The above setup is only
> for demonstration purposes. To expose the problem better. In
> real life we can see stalls tat thange from 0.5-1 seconds. Even
> with all caches active, small dirty writeback settings and unlimited
> bandwidth.
So describe the application, etc that you see this problem. Start
with:
http://xfs.org/index.php/XFS_FAQ#Q:_What_information_should_I_include_when_reporting_a_problem.3F
and we can go from there.
> In between I found others complaining about the same problem:
>
> http://lwn.net/Articles/486313/
> http://oss.sgi.com/archives/xfs/2011-09/msg00189.html
How do you know they are the same problem?
Indeed, they aren't even writeback problems - they are application
IO latency issues caused by the introduction of stable pages during
writeback.
> So just one last question: Can I savely revert the the mentioned
> commit d76ee18a8551e33ad7dbd55cac38bc7b094f3abb if I only
> write data to a battery backed up hardware raid controller on a
> server that is attached to an UPS?
NFS servers don't use mmap, so that patch is not causing your
writeback problems.
Cheers,
Dave.
--
Dave Chinner
david@xxxxxxxxxxxxx
|