Re: [Qemu-devel] [PATCH 1/2] linux aio: support flush operation

[Stefan Hajnoczi]

On Thu, Jul 28, 2011 at 1:15 PM, Christoph Hellwig <address@hidden> wrote:
> On Thu, Jul 28, 2011 at 09:47:05AM +0200, Kevin Wolf wrote:
>> > Indeed.  This has come up a few times, and actually is a mostly trivial
>> > task.  Maybe we should give up waiting for -blockdev and separate cache
>> > mode settings and allow a nocache-writethrough or similar mode now?  It's
>> > going to be around 10 lines of code + documentation.
>>
>> I understand that there may be reasons for using O_DIRECT | O_DSYNC, but
>> what is the explanation for O_DSYNC improving performance?
>
> There isn't any, at least for modern Linux.  O_DSYNC at this point is
> equivalent to a range fdatasync for each write call, and given that we're
> doing O_DIRECT the ranges flush doesn't matter.  If you do have a modern
> host and an old guest it might end up beeing faster because the barrier
> implementation in Linux used to suck so badly, but that's not inhrent
> to the I/O model.  If you guest however doesn't support cache flushes
> at all O_DIRECT | O_DSYNC is the only sane model to use for local filesystems
> and block devices.

I can rebase this cache=directsync patch and send it:
http://repo.or.cz/w/qemu/stefanha.git/commitdiff/6756719a46ac9876ac6d0460a33ad98e96a3a923

The other weird caching-related option I was playing with is -drive
...,readahead=on|off.  It lets you disable the host kernel readahead
on buffered modes (cache=writeback|writethrough):
http://repo.or.cz/w/qemu/stefanha.git/commitdiff/f2fc2b297a2b2dd0cccd1dc2f7c519f3b0374e0d

Stefan