On Tue, Dec 10, 2002 at 07:18:58AM -0800, Jason R Thorpe wrote:
> On Tue, Dec 10, 2002 at 10:06:40AM -0500, Thor Lancelot Simon wrote:
> 
>  > I can't quote you chapter and verse right now, but I've had it quoted at
>  > me a number of times on this very subject.  If WCE is not set, command
>  > completion is required to mean the data's on the platter -- no SYNCHRONIZE
>  > CACHE required.
> 
> Yes, that I understand -- I was talking about the TQ + WCE case.

My contention is that if you use TQ effectively, there's no reason to turn
on WCE, which is dangerous and inconvenient (e.g. you have to figure out
_when_ to send SYNCHRONIZE CACHE, which is nontrivial in a filesystem that
is not designed around the concept of explicit barriers) anyway.

-- 
 Thor Lancelot Simon	                                      tls@rek.tjls.com
   But as he knew no bad language, he had called him all the names of common
 objects that he could think of, and had screamed: "You lamp!  You towel!  You
 plate!" and so on.              --Sigmund Freud