<html>
<head>
<meta content="text/html; charset=windows-1252"
http-equiv="Content-Type">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<div class="moz-cite-prefix">Just out of curiosity, I've reverted
latest changes in ISPN so that the HEAD was dc6708f (- Pedro
Ruivo, 10 days ago : ISPN-3117 (Non)TxAsyncBackupTest.testReplace
fails randomly) and re-ran the tests for 1kB entries for HotRod,
Memcached, REST.<br>
<br>
Results:<br>
<br>
HotRod<br>
entry size -> overhead per entry<br>
1kB -> 159<br>
<br>
REST<br>
1kB -> 199<br>
<br>
Memcached<br>
1kB -> 212<br>
<br>
<br>
Martin<br>
<br>
<br>
<br>
Dne 24.5.2013 14:50, Martin Gencur napsal(a):<br>
</div>
<blockquote cite="mid:519F6231.7070604@redhat.com" type="cite">
<meta http-equiv="Context-Type" content="text/html;
charset=windows-1252">
<div class="moz-cite-prefix">Hi,<br>
so I gave it another try with latest Infinispan and
Infinispan-server snapshots (HEAD: a901168, resp. bc432fa) . In
short, the results are still the same for inVM mode but worse
for client-server mode. Of course, I haven't changed anything in
the test since last time.<br>
<br>
This time, I left out the results for 1MB entries because
there's high distortion due to the low number of entries stored
in a cache (storing 100MB of data). Previously, the results
looked better for HotRod compared to the first round of tests I
did for ISPN 5.2. Now the results for HotRod are worst of the
three measurements, inVM mode remains the same:<br>
<br>
HotRod (ISPN 5.2):<br>
entry size -> overhead per entry<br>
512B -> 174B<br>
1kB -> 178B<br>
10kB -> 176B<br>
<br>
HotRod (ISPN 5.3-SNAPSHOT, a few weeks ago)<br>
512B -> 159 (~ -9%)<br>
1kB -> 159 (~ -11%)<br>
10kB -> 154 (this is perhaps affected by the low number of
entries stored in mem.)<br>
<br>
HotRod (ISPN 5.3-SNAPSHOT, now)<br>
512B -> 191<br>
1kB -> 191 (measured twice)<br>
10kB -> 186 (looks a bit distorted already)<br>
<br>
------------------------<br>
<br>
Memcached (ISPN 5.2)
<div> 512B -> 184</div>
<div> 1kB -> 181</div>
<div> 10kB -> 182<br>
<br>
Memcached (ISPN 5.3-SNAPSHOT)</div>
512 -> 228<br>
1kB -> 227<br>
10kB -> 235<br>
<br>
--------------------------------<br>
<br>
REST (ISPN 5.2)<br>
<div> 512B -> 208</div>
<div> 1kB -> 205</div>
<div> 10kB -> 206<br>
<br>
REST (ISPN 5.3-SNAPSHOT)<br>
512 -> 247<br>
1kB -> 247<br>
10kB -> 251<br>
<br>
------------------------------------<br>
<br>
inVM (ISPN 5.2)<br>
<div> 512B -> 151</div>
<div> 1kB -> 151</div>
<div> 10kB -> 155</div>
<br>
inVM (ISPN 5.3-SNAPSHOT)</div>
512 -> 150<br>
1kB -> 150<br>
10kB -> 150<br>
<br>
<br>
Martin<br>
<br>
<br>
Dne 23.5.2013 18:13, Mircea Markus napsal(a):<br>
</div>
<blockquote
cite="mid:5F34959B-134F-4B5A-AB0A-B557808F8221@redhat.com"
type="cite">
<pre wrap="">Hi Martin,
Galder has finalised the remaining bits of ISPN-2281. Is it possible for you to re-run the test to see where we are with the memory consumption?
On 13 May 2013, at 10:44, Galder Zamarreño <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:galder@redhat.com"><galder@redhat.com></a> wrote:
</pre>
<blockquote type="cite">
<blockquote type="cite">
<pre wrap="">On May 7, 2013, at 4:55 PM, Manik Surtani <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:msurtani@redhat.com"><msurtani@redhat.com></a> wrote:
</pre>
<blockquote type="cite">
<pre wrap="">On 7 May 2013, at 15:39, Martin Gencur <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:mgencur@redhat.com"><mgencur@redhat.com></a> wrote:
</pre>
<blockquote type="cite">
<pre wrap="">I can make a blog post once we have this for Memcached and REST. I guess it is not ready yet.
</pre>
</blockquote>
<pre wrap="">Yes please. Nice work. :)
</pre>
</blockquote>
</blockquote>
</blockquote>
<pre wrap="">Cheers,
</pre>
</blockquote>
<br>
</blockquote>
<br>
</body>
</html>