<br><br><div class="gmail_quote">On Thu, Feb 25, 2010 at 1:38 PM, Daniel Maher <span dir="ltr"><<a href="mailto:dma%2Bgluster@witbe.net">dma+gluster@witbe.net</a>></span> wrote:<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="im">Raghavendra G wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Hi Daniel,<br>
<br>
Can you decrease the cache size in io-cache (say to 128MB)? If the files being served are bigger than this size, you can as well remove io-cache from configuration. Do let us know if this solves your issue.<br>
</blockquote>
<br></div>
Some of the files that are generated during the test are under 128M, and some are much larger - effectively, the test deals with larger and larger sets of data as it runs its course.<br>
<br>
At your suggestion, i changed the io-cache size from the default setting (as generated by the configurator) to 128M, and re-ran the test. The results are now much more consistent with what would be expected :<br>
<br>
real 21m31.019s<br>
real 21m30.932s<br>
real 21m28.965s<br>
real 21m26.095s<br>
real 21m26.388s<br>
real 21m29.377s<br>
real 21m32.180s<br>
real 21m26.600s<br>
real 21m28.354s<br>
(cut for brevity)<br>
<br>
However, at two points during the multi-day test run, something strange happened. The time to completion dropped _dramatically_, and stayed there for numerous iterations, before jumping back up again :<br></blockquote><div>
<br>Mostly reads are being served from io-cache?<br> <br></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
real 21m27.806s<br>
real 21m45.434s<br>
real 14m41.468s<br>
real 12m41.172s<br>
real 12m39.779s<br>
real 12m34.595s<br>
real 12m42.223s<br>
real 12m41.111s<br>
(repeat 30 iterations)<br>
real 12m40.185s<br>
real 12m40.517s<br>
real 13m25.394s<br>
real 21m26.375s<br>
real 21m28.476s<br>
<br>
I am forced to assume that something else on either the client or the server nodes caused this behaviour, but i cannot imagine what. The nodes, frankly, aren't doing anything else. Very strange.<br>
<br>
I am going to remove the io-cache entirely and see what, if any, effect that has.<div><div></div><div class="h5"><br>
<br>
-- <br>
Daniel Maher <dma+gluster AT witbe DOT net><br>
<br>
<br>
_______________________________________________<br>
Gluster-devel mailing list<br>
<a href="mailto:Gluster-devel@nongnu.org" target="_blank">Gluster-devel@nongnu.org</a><br>
<a href="http://lists.nongnu.org/mailman/listinfo/gluster-devel" target="_blank">http://lists.nongnu.org/mailman/listinfo/gluster-devel</a><br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br>Raghavendra G<br><br>