<div dir="ltr"><div>Very nice, looking forward to the Lucene bench results.<br><br></div><div>I hope you'll run it with a distributed cache as well!<br><br></div></div><div class="gmail_extra"><br><br><div class="gmail_quote">
On Tue, Jan 29, 2013 at 3:30 PM, Sanne Grinovero <span dir="ltr"><<a href="mailto:sanne@infinispan.org" target="_blank">sanne@infinispan.org</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
No I'm not comparing with Lucene 3.6 now with this configuration. It<br>
is well known that Lucene 4 is significantly faster than Lucene 3, so<br>
that would be unfair.<br>
<br>
What is interesting is that when comparing our implementations vs. the<br>
Apache stock ones while using Lucene 3 we where "very close", often a<br>
bit faster but not too exciting.<br>
Now comparing with the stock ones using Lucene 4 it seems we're<br>
getting into a better position... and I didn't even profile it, this<br>
is the first run after finishing coding the functional requirements.<br>
<br>
Still these figures are produced by a stress test whose primary<br>
purpose is to verify consistency and no-corruptions under stress.. I<br>
happened to add some metrics for fun, but to provide realistic figures<br>
one should run Lucene's own bench suite.. I'll do that next week.<br>
<br>
@Manik yes I'm not using a CacheStore, I would presume the same. This<br>
is why I've created the Lucene-specific CacheLoader, maybe I should<br>
complete the job and make it a CacheStore.<br>
<span class="HOEnZb"><font color="#888888"><br>
Sanne<br>
</font></span><div class="HOEnZb"><div class="h5"><br>
On 29 January 2013 13:14, Tristan Tarrant <<a href="mailto:ttarrant@redhat.com">ttarrant@redhat.com</a>> wrote:<br>
> Have you got numbers comparing against Lucene 3.6 ?<br>
><br>
> Tristan<br>
><br>
> On 01/29/2013 12:53 AM, Sanne Grinovero wrote:<br>
>> These are preliminary results of our stressor; looks quite promising<br>
>> as I haven't yet looked into profiling / tuning:<br>
>><br>
>> Stock Lucene RAMDirectory<br>
>> Searches: 14.799.852<br>
>> Writes: 195.935<br>
>><br>
>> Stock Lucene FSDirectory (Memory mapping on SSD)<br>
>> Searches: 9.628.593<br>
>> Writes: 105.930<br>
>><br>
>> Our custom Infinispan Directory (LOCAL)<br>
>> Searches: 17.815.874<br>
>> Writes: 184.140<br>
>><br>
>> Figures represent operations performed in 15 minutes on a relatively<br>
>> small index.<br>
>><br>
>> Cheers,<br>
>> Sanne<br>
>> _______________________________________________<br>
>> infinispan-dev mailing list<br>
>> <a href="mailto:infinispan-dev@lists.jboss.org">infinispan-dev@lists.jboss.org</a><br>
>> <a href="https://lists.jboss.org/mailman/listinfo/infinispan-dev" target="_blank">https://lists.jboss.org/mailman/listinfo/infinispan-dev</a><br>
>><br>
><br>
> _______________________________________________<br>
> infinispan-dev mailing list<br>
> <a href="mailto:infinispan-dev@lists.jboss.org">infinispan-dev@lists.jboss.org</a><br>
> <a href="https://lists.jboss.org/mailman/listinfo/infinispan-dev" target="_blank">https://lists.jboss.org/mailman/listinfo/infinispan-dev</a><br>
_______________________________________________<br>
infinispan-dev mailing list<br>
<a href="mailto:infinispan-dev@lists.jboss.org">infinispan-dev@lists.jboss.org</a><br>
<a href="https://lists.jboss.org/mailman/listinfo/infinispan-dev" target="_blank">https://lists.jboss.org/mailman/listinfo/infinispan-dev</a><br>
</div></div></blockquote></div><br></div>