<div dir="ltr">Please post your spec files and the commands used to benchmark<br><br>avati<br><br><div class="gmail_quote">2008/9/20 Graeme <span dir="ltr"><<a href="mailto:graeme@sudo.ca">graeme@sudo.ca</a>></span><br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div class="Ih2E3d">Anand Avati wrote:<br>
> Sorry for the wiki not being clear. While it is true the performance<br>
> translators can be loaded on either client or server, the<br>
> effectiveness is not the same. write-behind is more effective on the<br>
> client side.<br>
<br>
</div>Alright, just finished a new batch of benchmarking on 1.4pre5, with<br>
somewhat surprising results:<br>
<br>
1.3.10: write=20.8MB/sec, read=36.1MB/sec, rewrite=12.5MB/sec<br>
1.4pre5 (with read-ahead, write-behind on client side):<br>
write=13.8MB/sec, read=62.9MB/sec, rewrite=10.3MB/sec<br>
<br>
So, the read performance enhancement is very obvious with 1.4, but for<br>
some reason my write performance is greatly reduced. I'm not sure how to<br>
interpret this, given everyone saying writes should be much faster with<br>
1.4 and with write-behind on the client side.<br>
<br>
Can someone explain this behaviour, and perhaps hint how to get my write<br>
performance back to 1.3 levels without losing the gains in read performance?<br>
<font color="#888888"><br>
G<br>
<br>
</font></blockquote></div><br><br clear="all"><br>-- <br>If I traveled to the end of the rainbow<br>As Dame Fortune did intend,<br>Murphy would be there to tell me<br>The pot's at the other end.<br>
</div>