Re: 2.6.11-mm2

From: J.A. Magallon (jamagallon_at_able.es)
Date: 03/09/05

  • Next message: Dominik Brodowski: "Re: PCMCIA product id strings -> hashes generation at compilation time? [Was: Re: [patch 14/38] pcmcia: id_table for wavelan_cs]"
    Date:	Tue, 08 Mar 2005 23:36:58 +0000
    To: Robert Love <rml@tech9.net>
    
    

    HI all...

    On 03.08, Andrew Morton wrote:
    >
    > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.11/2.6.11-mm2/
    >

    (replied to this because this is the kernel I am testing on :) )

    Can cpu affinity really be changed for a running process ?
    Does it need something like io or yielding to take effect ?

    I am playin with Robert Love's taskset (symlinked to runon, it is easier
    to type and I'm more used to it), because I want to play with hyperthreading
    and wanted a method to force two threads on the same physical package.
    It works fine to bound a new process to a cpu set, but I does not change
    anything for a running process.

    I try runon -c -p 0 <pid> for my numbercruncher and it does nothing, top
    shows it is in the same cpus where it started:

    werewolf:~# runon -c -p 0 8277
    pid 8277's current affinity list: 0-3
    pid 8277's new affinity list: 0
    werewolf:~# runon -c -p 8277
    pid 8277's current affinity list: 0

    The program uses posix threads, 2 in this case. The two threads change from
    cpu sometimes (not too often), but do not go into the same processor
    immediately as when I start the program directly with runon/taskset.

    Any idea ?

    TIA

    --
    J.A. Magallon <jamagallon()able!es>     \               Software is like sex:
    werewolf!able!es                         \         It's better when it's free
    Mandrakelinux release 10.2 (Cooker) for i586
    Linux 2.6.11-jam3 (gcc 3.4.3 (Mandrakelinux 10.2 3.4.3-3mdk)) #1
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at  http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at  http://www.tux.org/lkml/
    

  • Next message: Dominik Brodowski: "Re: PCMCIA product id strings -> hashes generation at compilation time? [Was: Re: [patch 14/38] pcmcia: id_table for wavelan_cs]"

    Relevant Pages