Re: top hogs CPU in 2.6: kallsyms_lookup is very slow

From: Paulo Marques (pmarques_at_grupopie.com)
Date: 09/17/04

  • Next message: Paul Jackson: "Re: [RFC, 2.6] a simple FIFO implementation"
    Date:	Fri, 17 Sep 2004 12:27:16 +0100
    To: Denis Vlasenko <vda@port.imtp.ilyichevsk.odessa.ua>
    
    

    Denis Vlasenko wrote:
    > On Thursday 16 September 2004 15:17, William Lee Irwin III wrote:
    >>Did the kallsyms patches reduce the cpu overhead from get_wchan()?
    >
    >
    > Yes. top does not hog CPU anymore. It takes even a liitle bit *less*
    > CPU than in 2.4 now.

    Great!

    I was the one who wrote those patches, so I'm glad to know that they
    actually made a difference in real world workloads (like using "top").

    Reading /proc/kallsyms should be a lot faster too, although there is no
    comparison with 2.4 kernel, because there where no kallsyms there. It
    can be compared with previous 2.6 kernels, though.

    -- 
    Paulo Marques - www.grupopie.com
    To err is human, but to really foul things up requires a computer.
    Farmers' Almanac, 1978
    -
    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: Paul Jackson: "Re: [RFC, 2.6] a simple FIFO implementation"

    Relevant Pages

    • Re: OOPS: Something about kswapd
      ... > CPU: AMD Athlon XP ... > OOPS during ROCK linux compilation, ... > entry unable to handle kernel NULL pointer dereference at virtual ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • USB mouse hiccups (was RFD: Kernel release numbering)
      ... and the 2.6.11 is a Mandrake-ised kernel + Linus patches - at least I ... I planted them carrots right here!! ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: sendfile() with 100 simultaneous 100MB files
      ... There is no reason to allocate more ram and waste more cpu cycles to make a second copy of the data before passing it to the network layer. ... The mmap and madvice though, is a good idea, and I imagine it is causing the kernel to perform large block readahead. ... I last looked at the kernel implementation of sendfile about 6 years ago, but I remember it not looking very good. ... To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ ...
      (Linux-Kernel)
    • Re: Issues with INET sockets through loopback (lo)
      ... >> I have tried more regular communication patterns but this gives full CPU ... but my point is that kernel goes into the idle state even ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: 2.6.0-test6 crash while reading files in /proc/fs/reiserfs/sda1
      ... The kernel is 2.6.0-test6 from kernel.org. ... No other patches. ... I did cat file> /dev/null on each one. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)