Riak - low throughput
richard at basho.com
Sat Feb 23 03:38:53 EST 2013
If not done so already, It would be useful to run basho bench on the
cluster to see what the raw back end performance is
On Thu, Feb 21, 2013 at 2:37 PM, Christian Dahlqvist <christian at basho.com>wrote:
> Does this mean that you are using a single connection to each node in your
> test? If this is the case I would recommend increasing the number of
> threads as Dmitri Zagidulin recommended in his response in order to get
> better throughput.
> Also, what is the size of the objects you are writing?
> Best regards,
> On 21 Feb 2013, at 13:40, catchme <lhariharan at hotmail.com> wrote:
> > * What type of hardware are these three nodes?
> > Using Redhat UNIX servers
> > 4 vCPU - Intel(R) Xeon(R) CPU;31GB memory
> > * Can you provide a gist of the script?
> > Using Jmeter to send the requests. Have 4 threads sending requests to
> > nodes continously
> > * What client library are you using?
> > Java protocol-buffer client
> > --
> > View this message in context:
> > Sent from the Riak Users mailing list archive at Nabble.com.
> > _______________________________________________
> > riak-users mailing list
> > riak-users at lists.basho.com
> > http://lists.basho.com/mailman/listinfo/riak-users_lists.basho.com
> riak-users mailing list
> riak-users at lists.basho.com
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the riak-users