We have also come across the situation where we needed to make a move
from file systems. We ended up going with Veritas file system which we
saw the greatest increase in performance from simply changing the main
file system. It was a big win when we realized the file system actually
didn't cost anything.<br><br><div><span class="gmail_quote">On 10/5/07, <b class="gmail_sendername">Robert Banz</b> <<a href="mailto:banz@umbc.edu">banz@umbc.edu</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br><br><br><br>On Oct 5, 2007, at 10:01, John Madden wrote:<br><br>>> I think that this is partly because ext3 does more aggressive read<br>>> ahead<br>>> (which would be a mixed blessing under heavy load), partly because
<br>>> reiserfs suffers from fragmentation. I imagine that there is<br>>> probably a<br>>> tipping point under the sort of very heavy load that Fastmail see.<br>><br>> I second that - reiserfs seems to be truly horrible in write-heavy
<br>> situations. Worse, a backup of our remaining reiserfs partition takes<br>> *days* to complete -- 165GB at ~500k/s. And this is a 32-disk<br>> stripe of<br>> fibre channel.<br><br>I think what truly scares me about reiser is those rather regular
<br>posts to various mailing lists I'm on saying "my reiser fs went poof<br>and lost all my data, what should I do?"<br><br>-rob<br><br>----<br>Cyrus Home Page: <a href="http://cyrusimap.web.cmu.edu/">http://cyrusimap.web.cmu.edu/
</a><br>Cyrus Wiki/FAQ: <a href="http://cyrusimap.web.cmu.edu/twiki">http://cyrusimap.web.cmu.edu/twiki</a><br>List Archives/Info: <a href="http://asg.web.cmu.edu/cyrus/mailing-list.html">http://asg.web.cmu.edu/cyrus/mailing-list.html
</a><br></blockquote></div><br>