Alex,
Is it a good step to increase number of virtual
interfaces/robots to 1000/machine and keep the request
rate/robot to 0.4/sec. Will this help to achive
400requests/sec/machine without experiencing "virtual
memory exceeded in new" problem and help not generate
a best-effort workload.
Thank you
Mohan
--- Alex Rousskov <rousskov@measurement-factory.com>
wrote:
> On Tue, 28 Nov 2000, mohan kanumuru wrote:
>
> > Using attached workload file, I am able to
> simulate
> > without problem upto 250 requests/sec using 100
> robots
> > per machine. I tried 400 request/sec using 100
> robots,
> > but application is stopping after printing out a
> > message "virtual memory exceeded in new".
>
> That is because you have limited each robot to have
> up to 4 open
> connections at a time (open_conn_lmt = 4). With that
> limit, you cannot
> get 400 req/sec with 100 robots. Moreover, even
> doing 250 req/sec with
> 100 robots is very risky -- make sure your
> transaction queues (plotted
> on the autogenerated report) do not grow long, or
> you will end up with
> a best-effort workload!
>
> BTW, mailing list archive contains a few messages
> explaining the
> "virtual memory exceeded in new" error.
>
> Alex.
>
__________________________________________________
Do You Yahoo!?
Yahoo! Shopping - Thousands of Stores. Millions of Products.
http://shopping.yahoo.com/
This archive was generated by hypermail 2b29 : Tue Jul 10 2001 - 12:00:16 MDT