Re: [PATCH 2/3] relay: Fix race condition which occurs when reading across CPUs.

[Mathieu Desnoyers <compudj@krystal.dyndns.org>]

* Eduard - Gabriel Munteanu (eduard.munteanu@linux360.ro) wrote:
> On Mon, 16 Jun 2008 20:28:44 +0200
> Jens Axboe <jens.axboe@oracle.com> wrote:
>  
> > Hmm dunno, that is what blktrace also did but primarily for
> > performance reasons. It's tricky - Tom stated that he is working on a
> > lib to abstract this from applications. While that is handy for
> > telling you what to do, it also an annoyance that you HAVE to do it
> > that way (it's supposed to just be a "normal" fs, not with funky
> > restrictions).
> > 
> > So perhaps provide both versions in-kernel and let the kernel user
> > device. For blktrace, we have one app and we know we can use the
> > faster variant since readers are affine. For more debug style exports
> > or where you don't know your consumer, use the safer variant (which
> > should be the default action).
> 
> This sounds good. Though short debug info can be exported through
> debugfs alone, there is another use to this patch: global channels,
> which currently require kernel users to write their own locking
> mechanism.
> 
> So, are you fine with me patching relay _and blktrace_ code to use
> faster variants named relay_write_affine() and __relay_write_affine()?
> This implies having relay_write() and __relay_write() be the slower,
> safer paths. Do you agree with this names, provided the functions are
> documented correctly?
> 
> kmemtrace will use the affine versions and set CPU affinity anyway, but
> it would be nice to have a consistent behavior from relay's part.
> 

How about not changing the code, not providing a safe version of
relay_write, but document its use and what kind of locking the in-kernel
user must provide ?

Mathieu

> 
> 	Cheers,
> 	Eduard
> 

-- 
Mathieu Desnoyers
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68