Re: VM patches in 2.6.4-rc1-mm2

From: Nick Piggin (piggin_at_cyberone.com.au)
Date: 03/10/04

  • Next message: markstone_at_tom.com: "unknown" 
    Date:	Wed, 10 Mar 2004 19:36:24 +1100
To: Mike Fedyk <mfedyk@matchmail.com>

    Mike Fedyk wrote:

    > Andrew Morton wrote:
    >
    >> Mike Fedyk <mfedyk@matchmail.com> wrote:
    >>
    >>> Most of the previous 2.6 kernels I was running on these servers
    >>> would be lightly hitting swap by now. This definitely looks better
    >>> to me.
    >>
    >>
    >>
    >> It sounds worse to me. "Lightly hitting swap" is good. It gets rid
    >> of stuff,
    >> freeing up physical memory.
    >
    >
    > Andrew, it looks like you're right. This[1] server doesn't seem to be
    > hitting swap enough. But my other[2] file server is doing great with
    > it on the other hand (though, it hasn't swapped at all).
    >

    Just curious, what makes you say [1] isn't hitting swap enough and [2]
    is OK? The graphs are better now, by the way. Thank you.

    > Maybe a little tuning is in order?
    >
    > Any patches I should try?
    >

    Mainline doesn't put enough pressure on slab with highmem systems. This
    creates a lot more ZONE_NORMAL pressure and that causes swapping.

    Now with the 2.6 VM, you don't do any mapped memory scaning at all
    while you only have a small amount of memory pressure. This means that
    truely inactive mapped pages never get reclaimed.

    The patches you are using do not address this. My split active list
    patches should do so. Alternatively you can increase
    /proc/sys/vm/swappiness, but that isn't a complete solution, and might
    make things too swappy. It is a difficult beast to control.

    -
    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: markstone_at_tom.com: "unknown"

    Relevant Pages

    • Re: Ingo Molnar and Con Kolivas 2.6 scheduler patches
      ... you say we're persuing perfection. ... Do you say these sort of things to the virtual memory people? ... strive to give it more information, and and Con's patches make much better ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [Lhms-devel] [PATCH 0/7] Fragmentation Avoidance V19
      ... value on ppc64. ... My system has 6GB of memory and I would 'load ... Without these patches, it was almost impossible ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: VM patches in 2.6.4-rc1-mm2
      ... > sure it should be hitting swap more. ... >> Mainline doesn't put enough pressure on slab with highmem systems. ... VM patches can get merged into -linus. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: 2.6.3-mm4-rcu_ll SMP memory leak ?
      ... > I'm running said kernel, and after 5 days I've noticed that all my ... > is there some way to see how much memory the kernel uses for its ... Is it vanilla 2.6.3-mm4 or it has some other patches in it? ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: VM patches in 2.6.4-rc1-mm2
      ... > Mike Fedyk wrote: ... >> Any patches I should try? ... > Mainline doesn't put enough pressure on slab with highmem systems. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    Loading