[prev in list] [next in list] [prev in thread] [next in thread] 

List:       fuse-devel
Subject:    Re: [fuse-devel] stat performance on multicore systems: measurements
From:       Stefan Westerfeld <stefan () space ! twc ! de>
Date:       2012-07-31 13:26:28
Message-ID: 20120731132628.GA7224 () space ! twc ! de
[Download RAW message or body]

   Hi!

On Mon, Jul 30, 2012 at 05:21:49PM +0200, Miklos Szeredi wrote:
> Stefan Westerfeld <stefan@space.twc.de> writes:
> 
> > The way I think it should work is that the FUSE fs will have different worker
> > threads which are bound to one cpu per thread. If two processes running on cpu
> > 1 and 3 access the filesystem, FUSE should use a worker thread bound to cpu 1
> > to process requests from the userspace process running on cpu 1 and another
> > worker thread bound to cpu 3 to process requests from the userspace process
> > running on cpu 3.
> 
> Does the following patch help?
> 
> The wake_up_sync() call should prefer scheduling the woken up task on
> the same CPU as the waker.

No, the performance stays the same, and the filesystem thread(s) and the
userspace client still get executed on different cpus most of the time.


Btw, I wrote my own patch, which is a bit different from yours: I added the cpu
the fuse kernel code was running on to the fuse_in_header struct. Then I made
the libfuse library set the cpu affinity to the value from the header it
received. The result wasn't good: with my patch, the filesystem would move to
the cpu the userland process had, which in turn made the userland process move
to some other cpu. And so on... So this didn't work out the way I thought it
would (and performance was even worse than before).

   Cu... Stefan
-- 
Stefan Westerfeld, Hamburg/Germany, http://space.twc.de/~stefan

------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and 
threat landscape has changed and how IT managers can respond. Discussions 
will include endpoint security, mobile security and the latest in malware 
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
fuse-devel mailing list
fuse-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/fuse-devel
[prev in list] [next in list] [prev in thread] [next in thread]