Subject: Re: Extension of fsync_range() to permit forcing disk cache flushing
To: Jason Thorpe <>
From: Bill Studenmund <>
List: tech-kern
Date: 12/16/2004 16:58:16
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Thu, Dec 16, 2004 at 01:48:25PM -0800, Jason Thorpe wrote:
> On Dec 16, 2004, at 12:16 PM, Bill Studenmund wrote:
> >The current implementation just flushes the whole disk cache. Future
> >implementations may be selective and issue finer-grained cache flushes.
> >
> >Thoughts?
> Looks fine, except that the DIOCCACHESYNC ioctl is being invoked=20
> incorrectly.  The argument is actually an "int", not a "long". =20
> Non-zero tells the driver to issue the command even if it does not=20
> consider any blocks to be dirty (the sd driver keeps track of this so=20
> it can know if it needs to issue the command on close, etc.)

Here's a revised diff.

Take care,


Content-Type: application/pgp-signature
Content-Disposition: inline

Version: GnuPG v1.2.3 (NetBSD)