[rabbitmq-discuss] memory usage

Alexis Richardson alexis.richardson at cohesiveft.com
Tue Feb 10 08:12:20 GMT 2009


Got it.  Thanks.

Are you able to replicate the failure on local machines?  I would
understand if you do not have a local harness, but even so, that
strikes me as the next step.  (Unless we all replicate your EC2 set-up
which might be non-trivial)

alexis



On Tue, Feb 10, 2009 at 7:59 AM, Valentino Volonghi <dialtone at gmail.com> wrote:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
>
> On Feb 9, 2009, at 11:27 PM, Alexis Richardson wrote:
>
>> One question (not very helpful..)
>>
>> Is this in your local system?  I recall you mentioned EC2 and would
>> like to ask whether it is on there.
>
> Yes, it's on a couple of EC2 c1.medium instances running Ubuntu 8.04.
>
> When I manage to complete the test I can get pretty good numbers
> of about 4000 users connected at the same time (short requests) with
> about 2500 req/sec handled on those relatively poor machines, but
> the test only runs for about 15 minutes and if I keep the rate for some
> more time I'm pretty sure i can get the system to reliably crash.
>
> The problem here, before erlang crashing because addressable space
> is finished is erlang crashing for timeouts while kswapd is running :).
>
> - --
> Valentino Volonghi aka Dialtone
> Now running MacOS X 10.5
> Home Page: http://www.twisted.it
> http://www.adroll.com
>
> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v1.4.9 (Darwin)
>
> iEYEARECAAYFAkmRM+YACgkQ9Llz28widGXO8gCgmfdbxqtanJShafA2mJ4AshOa
> 6acAoL9c9Ra4eIERecUxSqVqZEqGp9mD
> =Jkm5
> -----END PGP SIGNATURE-----
>




More information about the rabbitmq-discuss mailing list