Re: Problem Report: Question about FETCH_PROBABILITY behavior.

SourceForge Headquarters 225 Broadway Suite 1600 San Diego, CA 92101 +1 (858) 422-6466

Hi Robert,

Thanks for your quick response.  Per your suggestion, I slightly
modified './conf-examples/fetch-probability.conf' as follows:
=-=-=-=
  ########### GENERAL SECTION ################################

  BATCH_NAME= fetch-prob
  CLIENTS_NUM_MAX=5
  INTERFACE   =eth0
  NETMASK=255.255.240.0
  IP_ADDR_MIN= 10.56.1.1
  IP_ADDR_MAX= 10.56.15.254
  CYCLES_NUM= 100
  URLS_NUM= 2

  ########### URL SECTION ####################################

  URL=http://localhost:8080/index.html
  URL_SHORT_NAME="local"
  REQUEST_TYPE=GET
  TIMER_URL_COMPLETION = 0
  TIMER_AFTER_URL_SLEEP = 1000
  FETCH_PROBABILITY = 70

  URL=http://localhost:8080/one.html
  URL_SHORT_NAME="ACE"
  REQUEST_TYPE=GET
  TIMER_URL_COMPLETION = 0
  TIMER_AFTER_URL_SLEEP = 1000
  FETCH_PROBABILITY = 30
=-=-=-=

With five clients and 100 cycles, I would expect that out of a potential
500 requests for each URL that the actual requests made during a curl-
loader run would be something like this:

   URL:local ~350 total requests ( (5 clients * 100 cycles) * 0.7)
   URL:ACE   ~150 total requests ( (5 clients * 100 cycles) * 0.3)

Here are the results from three different runs:

1)
Test total duration was 62 seconds and CAPS average 2:
H/F   Req:309,1xx:0,2xx:309,3xx:0,4xx:0,5xx:0,Err:0,T-
Err:0,D:1ms,D-2xx:1ms,Ti:1362B/s,To:627B/s
H/F/S Req:0,1xx:0,2xx:0,3xx:0,4xx:0,5xx:0,Err:0,T-
Err:0,D:0ms,D-2xx:0ms,Ti:0B/s,To:0B/s
 Operations:     Success       Failed     Timed out
URL0:local      6      132    0      0    0      0
URL1:ACE        8      177    0      0    0      0

2) 
Test total duration was 69 seconds and CAPS average 1:
H/F   Req:343,1xx:0,2xx:343,3xx:0,4xx:0,5xx:0,Err:0,T-
Err:0,D:1ms,D-2xx:1ms,Ti:1360B/s,To:625B/s
H/F/S Req:0,1xx:0,2xx:0,3xx:0,4xx:0,5xx:0,Err:0,T-
Err:0,D:0ms,D-2xx:0ms,Ti:0B/s,To:0B/s
 Operations:     Success       Failed     Timed out
URL0:local      0      134    0      0    0      0
URL1:ACE        3      209    0      0    0      0

3)
Test total duration was 77 seconds and CAPS average 2:
H/F   Req:382,1xx:0,2xx:382,3xx:0,4xx:0,5xx:0,Err:0,T-
Err:0,D:1ms,D-2xx:1ms,Ti:1356B/s,To:624B/s
H/F/S Req:0,1xx:0,2xx:0,3xx:0,4xx:0,5xx:0,Err:0,T-
Err:0,D:0ms,D-2xx:0ms,Ti:0B/s,To:0B/s
 Operations:     Success       Failed     Timed out
URL0:local      5      168    0      0    0      0
URL1:ACE        7      214    0      0    0      0

As you can see, the outcomes are significantly different from what I
expected.

Can you help shed some light on what is going on? Is the error in my
expectations, the configuration, or curl-loader?

Thanks,

  //david

On Sun, 2009-01-25 at 19:17 +0200, Robert Iakobashvili wrote:
> Hi David,
> 
> On Fri, Jan 23, 2009 at 8:24 PM, David Hotchkiss <dhotchkiss@iso-
> ne.com> wrote:
>         CURL-LOADER VERSION: 0.47, December 2, 2008
>         
>         
>         
>         ########### URL SECTION ####################################
>         
>         URL=http://localhost:8080/one.html
>         URL_SHORT_NAME="one"
>         REQUEST_TYPE=GET
>         TIMER_AFTER_URL_SLEEP=200
>         
>         URL=http://localhost:8080/two.html
>         URL_SHORT_NAME="two"
>         REQUEST_TYPE=GET
>         TIMER_AFTER_URL_SLEEP=200
>         
>         URL=http://localhost:8080/three.html
>         URL_SHORT_NAME="three"
>         REQUEST_TYPE=GET
>         TIMER_AFTER_URL_SLEEP=200
>         
>         =-=-=-=-= Configuration without FETCH_PROBABILITY:  END  =-=-
>         =-=-=-=
>         
>         =-=-=-=-= Configuration with FETCH_PROBABILITY: BEGIN =-=-=-=-
>         =-=
>         
>         ########### GENERAL SECTION ################################
>         BATCH_NAME= test
>         CLIENTS_NUM_MAX=1
>         CLIENTS_NUM_START=1
>         INTERFACE=eth0
>         NETMASK=255.255.240.0
>         IP_ADDR_MIN= 10.56.1.1
>         IP_ADDR_MAX= 10.56.15.254
>         CYCLES_NUM=10
>         URLS_NUM=3
>         
>         ########### URL SECTION ####################################
>         
>         URL=http://localhost:8080/one.html
>         URL_SHORT_NAME="one"
>         REQUEST_TYPE=GET
>         TIMER_AFTER_URL_SLEEP=200
>         
>         URL=http://localhost:8080/two.html
>         URL_SHORT_NAME="two"
>         REQUEST_TYPE=GET
>         TIMER_AFTER_URL_SLEEP=200
>         FETCH_PROBABILITY=10
>         
>         URL=http://localhost:8080/three.html
>         URL_SHORT_NAME="three"
>         REQUEST_TYPE=GET
>         TIMER_AFTER_URL_SLEEP=200
>         
>         
>         
>         QUESTION/ SUGGESTION/ PATCH:
>         Is the observed behavior the intended outcome? or should the
>         expected
>         request frequencies be something like this:
>         
>          URL0: 10 requests
>          URL1: ~1 request(s)
>          URL2: 10 requests
>         
>         for the second configuration?
> 
> Thank you for the PRF form filled in due course.
> 
> Your understanding of the intended behavior is correct.
> Our documentation does not describe the feature clear enough.
> 
> What user is supposed to do is to specify several URLs each with 
> FETCH_PROBABILITY, so that the sum of all the probabilities will be
> 100.
> 
> For the outcome, that you are expecting, it might be something like:
> 
> URL1:
> FETCH_PROBABILITY 45
> 
> URL2:
> FETCH_PROBABILITY 5
> 
> URL3:
> FETCH_PROBABILITY 45
> 
> I would measure them using more cycles, at least 100.
> 
> You might see some usage examples in directory conf-examples 
> 
> -- 
> Truly,
> Robert Iakobashvili, Ph.D.
> ......................................................................
> www.ghotit.com
> Assistive technology that understands you
> ......................................................................
> 