xfs
[Top] [All Lists]

TAKE 964647 - file corruption seen when DMF recalls files with buffered

To: sgi.bugs.xfs@xxxxxxxxxxxx
Subject: TAKE 964647 - file corruption seen when DMF recalls files with buffered i/o
From: dgc@xxxxxxx (David Chinner)
Date: Tue, 5 Jun 2007 17:52:12 +1000 (EST)
Cc: xfs@xxxxxxxxxxx
Sender: xfs-bounce@xxxxxxxxxxx
Map unwritten extents correctly for I/o completion processing

If we have multiple unwritten extents within a single page, we fail
to tell the I/o completion construction handlers we need a new handle
for the second and subsequent blocks in teh page. While we still issue
the I/O correctly, we do not have the correct ranges recorded in the
ioend structures and hence when we go to convert the unwritten extents
we screw it up.

Make sure we start a new ioend every time the mapping changes
so that we convert the correct ranges on I/O completion.

Date:  Tue Jun  5 17:51:26 AEST 2007
Workarea:  chook.melbourne.sgi.com:/build/dgc/isms/2.6.x-xfs
Inspected by:  hch@xxxxxxxxxxxxx

The following file(s) were checked into:
  longdrop.melbourne.sgi.com:/isms/linux/2.6.x-xfs-melb


Modid:  xfs-linux-melb:xfs-kern:28797a
fs/xfs/linux-2.6/xfs_aops.c - 1.146 - changed
http://oss.sgi.com/cgi-bin/cvsweb.cgi/xfs-linux/linux-2.6/xfs_aops.c.diff?r1=text&tr1=1.146&r2=text&tr2=1.145&f=h
        - If the mapping changes between blocks in xfs_page_state_convert, make
          sure that we also start a new ioend for the new mapping.



<Prev in Thread] Current Thread [Next in Thread>
  • TAKE 964647 - file corruption seen when DMF recalls files with buffered i/o, David Chinner <=