geronimo-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Jeff Genender <jgenen...@apache.org>
Subject Re: Geronimo peak performance
Date Fri, 14 Apr 2006 20:25:08 GMT
Rainer,

Would you have a perl script similar to this?:

http://blogs.sun.com/roller/page/travi?entry=ultrasparc_t1_utilization_explained

The guy describes, it but doesn't offer it.

Thanks,

Jeff

Rainer Jung wrote:
> When preparing for the test, have a look at the very interesting
> cpustat/cputrack. Without this you won't really be able to judge on the
> cpu usage. Classical tools like sar/vmstat/prstat easily lead to wrong
> results (the amount of work a single strand [hardware thread] is able to
> do is not fixed. It really shares the core with the other strands. If
> they stall, it will execute on every cycle, if all 4 strands are busy
> each one will only execute on every 4th cycle. So the cpu power
> available to a strand is dynamic, but tools like prstat are not able to
> show that.
> 
> For memory bus usage busstat is the way to go.
> 
> If you need more info, you could start an off topic thread or mail me
> directly.
> 
> Rainer
> 
> Jeff Genender wrote:
>> Yep...each core will handle 4 hardware threads.  It was built for
>> multiple threads and a JVM (multithreaded of course) is made for this
>> box.  For an appserver under load, I think the numbers should be
>> impressive on this box.
>>
>> The cool thing about this machine is, each core is viewed as 4 cpus.
>> That means this box looks like it has 16 CPUs running (4 cores x 4
>> hardware threads)!
>>
>> I can't wait to pound on this and see what it can do.  I am going to
>> have T2000->T2000 trials going on to maximize the throughput for CPU.
>> They come with 4 1 Ghz Ethernet ports each, so I am going to pipe these
>> up and hopefully there will be zero bottleneck on IO.

Mime
View raw message