Re: numbers don't lie ...

On Tue, 19 Sep 2006, Kris Kennaway wrote:

KK> > OF> Because buildworld is I/O-bound on systems with sufficiently
KK> > OF> fast processors.
KK> > OF>
KK> > OF> Try putting the contents of /usr/src into a RAM disk and
KK> > OF> repeat the benchmark. The numbers might look a little
KK> > OF> different then. Of course, you should have sufficient RAM
KK> > OF> in the machines -- If they're going to swap to the disks,
KK> > OF> your benchmark won't be happy.
KK> > OF>
KK> > OF> I think putting /usr/obj onto a RAM disk is _not_ necessary
KK> > OF> because of soft-updates, so the processes shouldn't block
KK> > OF> on writes.
KK> >
KK> > My experiments show that if you have enough memory to host radmdrive for
KK> > /usr/src you'd better leave it for caching - there were no statistically
KK> > meaningful performance difference, at least on machines with 1G+ RAM.
KK>
KK> Really? My measurements show the opposite (on a system with 16GB of
KK> RAM).

My last test on amd64/dualcore with 4G of RAM and -j4 shows
(buildworld+buildkernel):

==> /tmp/buildlog <==
1996.45 real 3032.94 user 624.83 sys
Script done on Tue Sep 19 14:44:54 2006

==> /tmp/buildlog.md <==
1957.45 real 3033.93 user 585.78 sys
Script done on Tue Sep 19 15:20:42 2006

Second one was with 512M/4k/512 swap-backed md, the former with /usr/src on the
gmirror'ed pair of SATAs.



Sincerely,
D.Marck [DM5020, MCK-RIPE, DM3-RIPN]
------------------------------------------------------------------------
*** Dmitry Morozovsky --- D.Marck --- Wild Woozle --- marck@xxxxxxxx ***
------------------------------------------------------------------------
_______________________________________________
freebsd-hackers@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: sieve.rb sample
    ... timex ruby sieve1.rb ... sys 0.00 ... that the first run of my Benchmark seemed to be noticably quicker than ... Somehow calling #sieve2 is slowing down subsequent calls to #sieve1. ...
    (comp.lang.ruby)
  • Re: file of exact size
    ... The benchmark to beat is eight minutes. ... given todays average harware performance, 1 minute seems a good goal ... sys 0m8.674s ... if (towrite> file_size) ...
    (comp.lang.c)
  • Re: HP-UX 11.11 performance with Ingres 2.6
    ... Not really having a benchmark of how long it would take to process the data I started doing some tests. ... The linux box is a Compaq P4 desktop with RH FC3 and r3/109 installed using express_install, ... At first I thought the script bombed out in some places, but looking at the script logs all the data was processed properly. ... I can post any relevant config info, but at this point I'm not sure what is relevant. ...
    (comp.lang.perl.misc)
  • Re: How to get non-unique elements from an array?
    ... These are WAY off of benchmark tests, which shows Lyndon's script just killing all others.... ... What I'd like to see is if Perl is faster than Ruby at this job... ... inefficient array processing on my part. ...
    (comp.lang.ruby)
  • Re: Compress::Zlib vs. external gzip call
    ... > I'm writing a script that needs to run in as fast a time as possible. ... > sub compress_zlib ... I'm afraid the benchmark is useless. ... so you're not catching the interesting ...
    (comp.lang.perl.misc)