Subject: Re: letting userland issue FUA writes
To:, Bill Studenmund <>
From: =?ISO-8859-1?Q?Joachim_K=F6nig-Baltes?= <>
List: tech-kern
Date: 03/17/2006 09:43:04
Bill Studenmund wrote:

 > The problem is it's not the exact semantics for what I want. I want
 > FUA down to the array. Among other things, you can have an array that
 > has a Battery-Backed-up-Unit and will write FUA'd writes to the BBU
 > and just pass non-FUA through to the disks. Waiting for after the call
 > can't change that behavior.  :-(

Yes, understood.

and Thor Lancelot Simon wrote:
> On Wed, Mar 15, 2006 at 07:53:24PM -0500, Christos Zoulas wrote:
>>I don't know. It seems to me something similar to writev might work, where
>>there is a flags field in iov. The problem I see is that there is no such
>>interface/api in POSIX and other people haven't had the need for this before.
> I think we should add an argument to pwritev -- or add another pwritev like
> call.

and later, Bill Studenmund wrote:
 > That was my thought. Or actually some write_with_flag and
 > writev_with_flag syscalls. One flag could fold in pwrite vs normal
 > write, and another flag could fold in FUA.

Or add a "const void *buf" argument to fsync_range, not as general as
with pwritev or adding syscalls, but perhaps less intrusive on the