From mboxrd@z Thu Jan  1 00:00:00 1970
From: wolfgang.rostek@gmx.de (Wolfgang Rostek)
Date: Fri, 3 Apr 2015 17:34:44 +0200
Subject: [lttng-dev] major variations in perfomance figures
In-Reply-To: <CA+jJMxuOT-zRW4k74C-gD3n4XP3mWO4HGYCLu=LT+EnMuRncAQ@mail.gmail.com>
References: <trinity-1e9921b3-666b-4656-bcb8-a2125944698f-1427831168919@3capp-gmx-bs39>
 <CA+jJMxuEdC4aaAZci3rwWM3sGJbyqchBeuVG2iTM5Ag11zKPwg@mail.gmail.com>
 <trinity-44577199-4bb4-4bf1-8595-785637f25968-1428072450572@3capp-gmx-bs60>,
 <CA+jJMxuOT-zRW4k74C-gD3n4XP3mWO4HGYCLu=LT+EnMuRncAQ@mail.gmail.com>
Message-ID: <trinity-a202c764-638a-4c9a-b09f-c588cfe2cdb8-1428075284708@3capp-gmx-bs13>

...
> > Frequence scaling I can't imagine on my dektop machine.
> > It is a jump between 350ns and 800ns. In the loop below
> > all the events of one test run are of equal time distance,
> > either slow or fast.
> 
> Frequency scaling can still definitely play a role, even on a desktop machine.
> Also, Core i5 chips support Turbo Boost which should be disabled to
> perform benchmarks.
> 
> I'm guessing you get your time measurements from the timestamps in the
> trace?
Yes

I'm not hunting for a detailed benchmark. Only such a large variance makes
me thoughtful. For such a test I did expect some 10-30% but not this more 
than 200%.

Wolfgang R.