Message-ID: <018a01c3fa21$dae5bda0$9002a8c0@consensys.com>
From: "Alex Wun" <alexwun@consensys.com>
To: <linux-xfs@oss.sgi.com>
References: <E1AmMZz-0006cB-00@maine.americas.sgi.com>
Subject: XFS Writes: IOLOCK_EXCL
Date: Mon, 23 Feb 2004 10:29:40 -0500
MIME-Version: 1.0
Content-Disposition: inline
Content-Type: text/plain
Content-Transfer-Encoding: 7bit
Content-length: 1377
Sender: linux-xfs-bounce@oss.sgi.com
Errors-to: linux-xfs-bounce@oss.sgi.com
Precedence: bulk

Hi.

What I've been trying to do is squeeze some more write performance out of my system.
(Dual Pentium Xeon processors, 1GB ram, software RAID, 2.4.20 kernel patched with XFS 1.3.1)

I've ended up fiddling with some XFS code and have found that write performance can improve significantly in certain applications (i.e. exporting the filesystem over a network).  I've left the system running (and writing) over the weekend and it seems to be stable.  Although things look good for now, I'd like to be certain that I haven't broken anything.

Essentially, this is what I've done:

In the function xfs_fsync():

Instead of:

            VOP_FLUSH_PAGES(...);

I essentially have:
                  VOP_COMMIT_PAGES(...);
                  xfs_iunlock(ip, XFS_IOLOCK_EXCL);
                  VOP_CLEANUP_PAGES(...);
                  xfs_ilock(ip, XFS_IOLOCK_EXCL);


Where VOP_COMMIT_PAGES() + VOP_CLEANUP_PAGES() does the same thing as VOP_FLUSH_PAGES() but in two parts, first the writing of the pages then the cleanup.  So I've basically released the XFS_IOLOCK_EXCL during page cleanup.

This may not work for everyone but it seems to give me better writing (maybe strict operating conditions will apply?). But I'd just like to ask, from a conceptual stand-point, whether this is a legitimate thing to do.

Thanks for your time,
Alex Wun


[[HTML alternate version deleted]]