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.

Results:

HotRod
entry size -> overhead per entry
1kB -> 159

REST
1kB -> 199

Memcached
1kB -> 212


Martin



Dne 24.5.2013 14:50, Martin Gencur napsal(a):
Hi,
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.

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:

HotRod (ISPN 5.2):
entry size -> overhead per entry
512B  -> 174B
1kB   -> 178B
10kB  -> 176B

HotRod (ISPN 5.3-SNAPSHOT, a few weeks ago)
512B  -> 159 (~ -9%)
1kB   -> 159 (~ -11%)
10kB  -> 154 (this is perhaps affected by the low number of entries stored in mem.)

HotRod (ISPN 5.3-SNAPSHOT, now)
512B  -> 191
1kB   -> 191 (measured twice)
10kB  -> 186 (looks a bit distorted already)

------------------------

Memcached (ISPN 5.2)
512B  -> 184
1kB   -> 181
10kB  -> 182

Memcached (ISPN 5.3-SNAPSHOT)
512   -> 228
1kB   -> 227
10kB  -> 235

--------------------------------

REST (ISPN 5.2)
512B  -> 208
1kB   -> 205
10kB  -> 206

REST (ISPN 5.3-SNAPSHOT)
512   -> 247
1kB   -> 247
10kB  -> 251

------------------------------------

inVM (ISPN 5.2)
512B  -> 151
1kB   -> 151
10kB  -> 155

inVM (ISPN 5.3-SNAPSHOT)
512   -> 150
1kB   -> 150
10kB  -> 150


Martin


Dne 23.5.2013 18:13, Mircea Markus napsal(a):
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 <galder@redhat.com> wrote:


On May 7, 2013, at 4:55 PM, Manik Surtani <msurtani@redhat.com> wrote:


On 7 May 2013, at 15:39, Martin Gencur <mgencur@redhat.com> wrote:


I can make a blog post once we have this for Memcached and REST. I guess it is not ready yet.

Yes please.  Nice work.  :)

Cheers,