DESCRIPTION

pcap: use a decent trace for parser benchmarking

Change-Id: I45900d5a25160d37ceb4dc6a06175d6a6b74f475
Signed-off-by: Itzel Singleton xxx@xxx.xxx


COMMENTS

author: Itzel Singleton
date: 2014-07-24 23:00:55.000000000

Uploaded patch set 1.

-------------------------------------
author: Brenden Conley
date: 2014-07-24 23:48:52.000000000

Patch Set 1:

Build Started https://hudson.eclipse.org/linuxtools/job/linuxtools-gerrit/7947/

-------------------------------------
author: Brenden Conley
date: 2014-07-25 00:27:09.000000000

Patch Set 1: Verified-1

Build Failed 

https://hudson.eclipse.org/linuxtools/job/linuxtools-gerrit/7947/ : FAILURE

-------------------------------------
author: Ivy Mitchell
date: 2014-07-25 01:23:55.000000000

Patch Set 1:

what made the other trace indecent?

-------------------------------------
author: Itzel Singleton
date: 2014-07-25 06:55:38.000000000

Patch Set 1:

It contained only 640 events, so the parser finished parsing the whole file in a couple of microseconds. Thus, the variation of the results was a large percentage of the total CPU time, which is bad.

This new trace contains 100k events (and is totally annonymized), so the benchmark gives more precise results. This allows to really see the influence of future commits on the parsing speed.

-------------------------------------
author: Brenden Conley
date: 2014-07-25 14:42:03.000000000

Patch Set 1: -Verified

Build Started https://hudson.eclipse.org/linuxtools/job/linuxtools-gerrit/7951/

-------------------------------------
author: Brenden Conley
date: 2014-07-25 15:23:18.000000000

Patch Set 1: Verified+1

Build Successful 

https://hudson.eclipse.org/linuxtools/job/linuxtools-gerrit/7951/ : SUCCESS

-------------------------------------
author: Kaeden Tapia
date: 2014-07-25 18:43:45.000000000

Patch Set 1: Code-Review+2 Verified+1

-------------------------------------
