On Fri, 2011-04-15 at 17:34 +0200, Christoph Hellwig wrote: > On Fri, Apr 15, 2011 at 04:26:41PM +0100, Stefan Hajnoczi wrote: > > On Fri, Apr 15, 2011 at 4:05 PM, Christoph Hellwig <h...@lst.de> wrote: > > > NAK. ?Just wait for the bloody NFS client fix to get in instead of > > > adding crap like that. > > > > That's totally fine if NFS client will be fixed in the near future but > > this doesn't seem likely: > > > > http://www.spinics.net/lists/linux-nfs/msg20462.html > > The code to use preadv/pwritev has been in qemu for over 2 years, > and it took people to notice the NFS slowdown until now, so don't > expect it to be fixed three days layer.
True. That brings up a different question - whether we are doing enough testing on mainline QEMU :( > I can't event see you in the relevent threads arguing for getting it > fixed, so don't complain. I asked Stefan to work on a QEMU patch - since my QEMU skills are limited and Stefan is more appropriate person to deal with QEMU :) As mentioned earlier, we don't see performance with any temporary solutions suggested so far (RPC table slot + ASYNC) comes anywhere close to readv/writev support patch or linearized QEMU. Thanks, Badari
