On Mon, 2006-12-11 at 17:03 +0100, Jens Axboe wrote:
> On Mon, Dec 11 2006, Ming Zhang wrote:
> > On Mon, 2006-12-11 at 15:50 +0100, Jens Axboe wrote:
> > > > > > > Linux doesn't guarantee any request ordering for O_DIRECT io.
> > > > > > 
> > > > > > so this means it can be inserted front and back. and no fixed
> > > order?
> > > > > 
> > > > > It'll be sort inserted like any other request. That might be
> > > front, it
> > > > > might be back, or it migth be somewhere in the middle.
> > > > 
> > > > ic, so no special treatment here.
> > > 
> > > Nope. In fact the block layer and io scheduler do not know that this
> > > is
> > > an O_DIRECT request, the bio originates from the same path as any
> > > other
> > > regular fs request. 
> > 
> > one more question. since our point to have this block io is to by pass
> > OS and send to high performance storage target. so if I use NOOP
> > scheduler here, which simply add request to the tail of queue, then
> > block io later will preserve the order. will this be ok? even device can
> > do out of order, but device should do it in a safe way i think...
> 
> noop won't reorder requests through insertion sort, but it could
> potentially still do so for merges.

oops, forgot merge. :P

> 
> Putting any sort of faith in what a device will or will not do outside
> of what is mandated by the spec, is not a good plan imho :-)
> 

make sense.

thanks again for all explanations. we have a much clearer pictures now.


-
To unsubscribe from this list: send the line "unsubscribe linux-btrace" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to