tech-kern archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: Proposal: B_ARRIER (addresses wapbl performance?)



On Tue, Dec 09, 2008 at 12:56:27PM -0800, Jason Thorpe wrote:
> 
> On Dec 9, 2008, at 12:23 PM, Manuel Bouyer wrote:
> 
> >Sure. And you don't care much about command completion either, as
> >long as the write to disk happen in order.
> 
> And the only way to ensure that is using FUA (or explicit cache  
> flushing).

Err, no. The ensure that is using FUA for all write (which is the same
as turning off write cache, and which should be done for tagged-queuing
devices) *and* wait for a write to complete before queuing another one.
If you don't wait for command completion, or allow FUA/non FUA commands to
be sent to device, the device is allowed to reorder FUA commands, or
non-FUA commands around FUA commands. ordered task is what prevent
write reordering.

-- 
Manuel Bouyer <bouyer%antioche.eu.org@localhost>
     NetBSD: 26 ans d'experience feront toujours la difference
--


Home | Main Index | Thread Index | Old Index