2.4.28 - kswapd excessive cpu usage under heavy IO

From: Per Jessen (per_at_computer.org)
Date: 12/06/04

  • Next message: Martin Zwickel: "Re: nVidea Graphics card not recognised by lspci"
    To: linux-kernel@vger.kernel.org
    Date:	Mon, 6 Dec 2004 12:14:48 +0100
    
    

    (apologies if this is sent more than once)
    I've found similar incidences in the archives, but none that indicates that a
    solution was found.
    I'm seeing excessive cpu usage by kswapd on a 4way 500MHZ Xeon with 2GB RAM.  A
    find in a directory containing perhaps 6-700,000 files makes the box almost
    grind to a halt.  In 12days uptime, kswap has used 590:43.82, and during the
    find-exercise usually runs with 90-100% util.
    The file-system is 150GB with JFS117 on a software-RAID5 - not exactly optimal,
    I agree, but reasonably workable.

    I've read that 2.6 has significant improvements in this area, but upgrading is
    not currently an option.  

    All hints & suggestions much appreciated.

    -- 
    Per Jessen, Zurich
    http://www.spamcek.com - let your spam stop here.
    -
    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: Martin Zwickel: "Re: nVidea Graphics card not recognised by lspci"

    Relevant Pages

    • Re: [RFC] [PATCH] driver core: allow userspace to unbind drivers from devices.
      ... >> Care to resend it? ... I can't find it in my archives. ... Apologies for sending it as an attachment ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: Fwd: 2.4.28 - kswapd excessive cpu usage under heavy IO
      ... > I've found similar incidences in the archives, but none that indicates that a ... send the line "unsubscribe linux-kernel" in ... Please read the FAQ at http://www.tux.org/lkml/ ...
      (Linux-Kernel)
    • page allocation failure
      ... only thing I can do is switch between virtual consoles (until I hit the ... Then the same for lots of other processes (pdflush, syslogd, klogd, ... (but I'll keep an eye on the archives). ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: suspend-to-RAM [was Re: Totally broken PCI PM calls]
      ... Just insert infinite ... > Well, my apologies, the behavior changed recently: ... > button to resume doesn't shutdown the machine anymore: ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [OT] Re: ATTACK TO MY SYSTEM
      ... Wakko Warner wrote: ... >>First, apologies to all since this is technically offtopic, but there ... When the virus stops, i ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)