Re: [Qemu-devel] barriers: block layer preparations

[Christoph Hellwig]

On Tue, May 05, 2009 at 04:51:39PM +0300, Avi Kivity wrote:
> >+                                    qcow_aio_write_cb, acb, 2);
> >  
> 
> 2?

Typo.

> An alternative approach is to add a new op, bdrv_aio_barrier(), 
> submitted immediately after the write.  It's probably more complicated 
> overall.

Yeah, it sounds more complicated to implement to me.

> A barrier for read can be meaningful if the guest wishes to read a 
> known-to-be-stable write.  I don't think any guest can make use of this 
> though.

I don't know of any storage standard having anything like this or any
OS taking advantage of it.  I'd be happy to review anything like that,
though.