4BSD/ULE numbers...

From: Emanuel Strobl (Emanuel.strobl_at_gmx.net)
Date: 09/26/05

  • Next message: Kris Kennaway: "Re: 4BSD/ULE numbers..." 
    To: freebsd-current@freebsd.org
Date: Mon, 26 Sep 2005 18:47:27 +0200

    Hello,

    I tried ULE with BETA5 and for me it felt a bit sluggish when making ports.
    So I did some "realworld" simulation and compared 4BSD/ULE to see what
    numbers tell me. And the prooved my feeling right.
    It seems that ULE is priorizing nice a little higher, but in general the
    output of the 4 BSD machine is higher and finishing the tests took not so
    long as with ULE, especially the "make configure" differs horribly.

    What I did is to start "flops" with (standard) nice, start bonnie++
    simultaniously (without nice) and run "make configure"
    in /usr/ports/net/samba3.

    I did the same with flops unniced... But same result, 4BSD gives better
    benchmarks results in shorter time...

    Unfortunately I don't know a good way to format these results in a nice
    way, so here's a example of the script I ran and attached the resulting
    text files:

    #!/bin/csh
    cd /usr/ports/net/samba3
    make clean
    make extract
    /usr/bin/time -h -o /tmp/flops.ule.nonice.time flops >
    /tmp/flops.ule.nonice.result &
    /usr/bin/time -h -o /tmp/bonnie++.ule.nonice.time bonnie++ -d /usr -u 0 -r
    256 > /tmp/bonnie++.ule.nonice.result &
    /usr/bin/time -h -o /tmp/samba.configure.ule.nonice.time make configure

    For anyone who can imagine what goes wrong in ULE, I can't ;)

    -Harry

  • Next message: Kris Kennaway: "Re: 4BSD/ULE numbers..."