Mailing-List: contact users-help@activemq.apache.org; run by ezmlm
Precedence: bulk
Reply-To: users@activemq.apache.org
Received-SPF: pass (nike.apache.org: domain of chubrilo@gmail.com designates
 209.85.215.172 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:sender:in-reply-to:references:date
         :x-google-sender-auth:message-id:subject:from:to:content-type
         :content-transfer-encoding;
        b=VLuJSAVBd8YjL0s+en5VUNA0ivAB3YsZ+p/Eed/nJWIJKezXBm4JHmsmrXbbTOgg5o
         14mwBCWh8rYI0YZU3bOm/T+1SnCqb31WcqOMI0FNGKpzKcsDt9795hMIrwD/vQwp0HoS
         WGC+ihfGc9MIeD7nFOo/ZX6OqnicPg4/Cz+3s=
MIME-Version: 1.0
Sender: chubrilo@gmail.com
In-Reply-To: <AANLkTinV3cT8euTRpcGC9nbTGQYA0boxuQEkrGSC1gGU@mail.gmail.com>
References: <AANLkTinV3cT8euTRpcGC9nbTGQYA0boxuQEkrGSC1gGU@mail.gmail.com>
Date: Wed, 15 Dec 2010 16:49:09 +0100
Message-ID: <AANLkTimnc8bAXX9gKNdyHH1B+2RFpcOxfM0j9kpbS7Gh@mail.gmail.com>
Subject: Re: ActiveMQ consumer performance and scalability
From: Dejan Bosanac <dejan@nighttale.net>
To: users@activemq.apache.org
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

Hi,

you can find some additional tips for performance tuning here:

http://activemq.apache.org/performance-tuning.html

and

http://fusesource.com/wiki/display/ProdInfo/FUSE%20Message%20Broker%20Perfo=
rmance%20Tuning%20Guide

Cheers
--
Dejan Bosanac
-----------------
FuseSource - The experts in open source integration and messaging.
Email: dejanb@fusesource.com
Web: http://fusesource.com
Twitter: =A0http://twitter.com/dejanb
ActiveMQ in Action - http://www.manning.com/snyder/
Blog - http://www.nighttale.net


On Wed, Dec 15, 2010 at 3:41 PM, Stanislaw Kogut <skogut@sistyma.net> wrote=
:
> Hello.
>
> I'm currently evaluating ActiveMQ as a message broker for our service. We
> need scalable, transacted, low-latency message broker, but ActiveMQ shows
> not very good results to me.
>
> Config: ActiveMQ 5.4.2 with nio:// transport, KahaDB persistence adapter =
and
> data directory on tmpfs filesystem (to get rid of disk performance impact=
).
>
> In details: With persistence enabled and commiting every message sent to
> broker we have about 2k messages/s on producer side, and similar consumin=
g
> speed with one producing thread.
> It also has good latency - about 5 milliseconds to deliver message, but 2=
k
> msg/s can be slow in future, so I'm trying to commit messages after some
> count of them sent, for example after every 100 messages. This shows bett=
er
> throughput, about 10k messages/s, but now consumer side looks slow. Also,
> latency is increased because time to fill this "100 messages" cap.
>
> Also, consumer side is not able to consume all these messages on this rat=
e
> and queue length grows.
>
> It is very possible also, I will have more than one producer for one queu=
e
> because of application design. I also test this scenario and producers ar=
e
> relatively fast, but consumer become very slow, receiving 1-2 messages pe=
r
> second. With enabled producer flow-control broker can stop producers and
> serve consumer better, but it has very bad impact on latency as producer
> should wait for broker to acknowledge messages, preventing new data from
> being sent.
>
>
> Is there is a way to consume messages from queue faster? I'm tried both
> implementing MessageListener and MessageConsumer.receive(), but both show
> same result. Usage of vmCursor or prefetching in broker makes no changes =
to
> situation.
>
> Also, is there any topology for distirbuting one ActiveMQ queue to more t=
han
> one machine without big latency impact to increase it's throughput?
>
> --
> Regards,
> Stanislaw Kogut
> Sistyma LLC
>