Re: freebsd vs linux: performance problem


--- Erich Dollansky <oceanare@xxxxxxxxxxxxxx> wrote:

Hi,

Shantanu Ghosh wrote:
--- Erich Dollansky <oceanare@xxxxxxxxxxxxxx> wrote:

Don't you call memcpy?

Well, I first did - then I wrote a function to do the same, just to
make sure that the code executed is exactly the same in both the
cases.
The difference was there both when using memcpy, and when using the
replacement function.

Do you have Linux compatibility installed on the FreeBSD machine?

You should then be able to run the Linux binary to see what happens
then.

I have had once the problem of a task moving from CPU to CPU and s
performing badly on FreeBSD.

I am not informed how this is handled currently.

This could be something I am facing. I noticed that when I run vmstat
while running this code, on linux, there's hardly any perceptible
difference in the number of context switches, but on freebsd, the
number of context switches in the system seems to go up a bit. However,
this is not very reliable.

Do you know how I can check this migration?


I also assume that this example is a single-threaded program which
should perform just fine on single CPU machine.

One other thing, can you just boot up with one CPU and one core to
see
what happens then?

While I have not tried it on this machine, on a single cpu machine, the
non-SMP build of freebsd seems to perform as well as linux for this
kind of test.

Thanks a lot for your help.

Erich
_______________________________________________
freebsd-performance@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to
"freebsd-performance-unsubscribe@xxxxxxxxxxx"


--
Shantanu.



____________________________________________________________________________________
Be a better friend, newshound, and
know-it-all with Yahoo! Mobile. Try it now. http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ

_______________________________________________
freebsd-performance@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "freebsd-performance-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: FreeBSD 4.x Opteron Question
    ... the FreeBSD developers told everyone that 5.3 was da ... initially over linux not because there's a bunch of good guys on the ... My tests measure kernel performance; ... > a networking device is a key performance indicator. ...
    (freebsd-questions)
  • Re: Newbie Experience
    ... I've only been around since FreeBSD 5.4 ... FreeBSD kernel too. ... always sunshine and linux is farts. ... in the hey day of AT&T Unix I'm ...
    (freebsd-questions)
  • Re: Review of FreeBSD 5.4
    ... but not less problems compared to FreeBSD. ... If you like to have a bleeding edge system using debian --- just go ... > the linux kernel suffers. ... When the kernel suffers, everyone who uses ...
    (comp.unix.bsd.freebsd.misc)
  • Re: FreeBSD & Linux distro
    ... as a FreeBSD advocacy the tone of the article should be neutral and all ... do not like Linux and more over I have never used it in my life but I ... Statement of the type BSD appears more stable than Linux is ... fewer FreeBSD advocates make claims like that, however, is part of the ...
    (freebsd-questions)
  • Re: Compare Linux and Freebsd Redux
    ... >> Perhaps the most unsettling 'misinformation' about the FreeBSD vs. ... >> Linux situation was the spin that Linux was somehow more 'open', ... >> the official Linux tree... ... your own distribution is that the FreeBSD distribution is/was already ...
    (comp.unix.bsd.freebsd.misc)