What kind of logic there could be?<div><br></div><div>I notice that in old version, if page has no buffer in writepage, then xfs will create a empty buffer and attach to page. This logic there at least untill 2.6.33. But now xfs need this never happens (assert) when coming to writepage. But I guess, when use mmap, there is no buffer attach to page because it operates on page directly on kernel. xfs should create buffer before submit bio. There must be sth I don't know. Maybe sbd can help me out.</div>
<div><br></div><div>Thanks very much,</div><div>Mike</div><div><br><br><div class="gmail_quote">On Mon, Aug 30, 2010 at 7:30 PM, Dave Chinner <span dir="ltr"><<a href="mailto:david@fromorbit.com">david@fromorbit.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div class="im">On Mon, Aug 30, 2010 at 05:56:07PM -0500, Mike Gao wrote:<br>
</div><div class="im">> Thanks very much for help. The kernel is pretty old, 2.6.19 but the xfs is<br>
> pretty new.<br>
> the block size is 512 and use mmap for test with write and read compare.<br>
> (xfstest 074).<br>
<br>
</div><div><div></div><div class="h5">Can you reproduce it on a more recent kernel? The buffer flags are<br>
modified by code outside XFS which could be significantly different in<br>
2.6.19 comapred to 2.6.34/35, so it may not be aproblem with the<br>
XFS code as such....<br>
<br>
Cheers,<br>
<br>
Dave.<br>
--<br>
Dave Chinner<br>
<a href="mailto:david@fromorbit.com">david@fromorbit.com</a><br>
</div></div></blockquote></div><br></div>