BAM guys get about 30000 events/ sec on their new tests. Please talk to
them and compare

On Sat, Sep 29, 2012 at 10:52 AM, Reka Thirunavukkarasu <[email protected]>wrote:

> Hi
>
> I'll talk with BAM team in order to make it more accuracy.
>
>>
>> On Fri, Sep 28, 2012 at 6:25 PM, Afkham Azeez <[email protected]> wrote:
>>
>>> What I was expecting was a test where you send a service request, and
>>> the service sends back an echo or something, take note of the latency, then
>>> make that same log a request with that new appender enabled, and record the
>>> latency and compare.  This has to be done for about 50k messages for each
>>> round.
>>
>>
> Sure. I will include this into the testing.
>
> Thanks,
> Reka
>
> On Fri, Sep 28, 2012 at 4:59 PM, Reka Thirunavukkarasu <[email protected]>wrote:
>>
>>> Hi all,
>>>
>>> The following are the results which i have got when doing performance
>>> test with new logging vs sys-log. Each request got printed with 100 logs.
>>> So the logs count is all together RequestsCount * 100. I couldn't make it
>>> to test with much high load since i did the testing on my local machine. I
>>> have done this testing for ST at the moment.
>>>
>>> New Logging
>>> ==========
>>>
>>> Requests Count        Throughput(/sec)-Sys-log        Latency(time taken
>>> to writte logs in BAM after sys-log written down)
>>>
>>> 500                          40.2
>>> 67s
>>> 1000                        34.8
>>> 147s
>>> 2000                        32.1
>>> 287s
>>>
>>> Sys-Log only
>>> =========
>>>
>>> 500                         47.6
>>> 1000                       46.4
>>> 2000                       44.4
>>>
>>> I have attached here with the profile and memory usage of sys-log and
>>> new logging framework.
>>>
>>> FYI:
>>> For sys-Log, i haven't noticed much different in memory usage and
>>> profile different while concurrent request count varies. But with New
>>> logging memory usage seems to be getting bit high with request count
>>> increases. The profiles for new logging with all three request attached
>>> here with.
>>>
>>> I'll update the thread while i'm doing the test for tenant as well as
>>> for high loads. Also, please suggest if i need to include any other steps..
>>>
>>> Thanks,
>>> Reka
>>>
>>
>>
>>
>> --
>> *Afkham Azeez*
>> Director of Architecture; WSO2, Inc.; http://wso2.com
>> Member; Apache Software Foundation; http://www.apache.org/
>> * <http://www.apache.org/>**
>> email: **[email protected]* <[email protected]>* cell: +94 77 3320919
>> blog: **http://blog.afkham.org* <http://blog.afkham.org>*
>> twitter: **http://twitter.com/afkham_azeez*<http://twitter.com/afkham_azeez>
>> *
>> linked-in: **http://lk.linkedin.com/in/afkhamazeez*
>> *
>> *
>> *Lean . Enterprise . Middleware*
>>
>>
>


-- 
============================
Srinath Perera, Ph.D.
  Senior Software Architect, WSO2 Inc.
  Visiting Faculty, University of Moratuwa
  Member, Apache Software Foundation
  Research Scientist, Lanka Software Foundation
  Blog: http://srinathsview.blogspot.com/
  Photos: http://www.flickr.com/photos/hemapani/
 Phone: 0772360902
_______________________________________________
Dev mailing list
[email protected]
http://wso2.org/cgi-bin/mailman/listinfo/dev

Reply via email to