AW: [ejabberd] ejabberd vs Jabber XCP

Mickael Remond mickael.remond at process-one.net
Fri May 5 16:24:23 MSD 2006


* Pieter Rautenbach <Pieter.Rautenbach at clockspeed.co.za> [2006-05-05 13:21:04 +0200]:

> It's indeed a 64-bit server. I understand the reasoning, but I disagree: not all
> ejabberd data in memory could be strings! Thus, the memory usage cannot be
> entirely attributed to the use of strings. Here are similar figures for a single
> CPU server, having 14,065 users online:
> USER     PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
> ejabberd 16   0 4778m 3.7g 1692 R 23.3 95.8 63:00.41  beam

I confirm however, that data in memory are largely strings.

You can compare the memory consumption on 32-bit and 64-bit
architecture. It almost doubles.

We have planed to change the data structure used during the summer to
reduce the memory consumption. Impact of the reduced memory consumption
will be higher on 64bit server.

-- 
Mickaël Rémond
 http://www.process-one.net/


More information about the ejabberd mailing list