Re: [Lhms-devel] [PATCH 0/7] Fragmentation Avoidance V19

From: Mike Kravetz (kravetz_at_us.ibm.com)
Date: 10/31/05

  • Next message: Zwane Mwaikambo: "Re: [patch 1/5] i386 generic cmpxchg" 
    Date:	Sun, 30 Oct 2005 21:57:25 -0800
To: Mel Gorman <mel@csn.ul.ie>

    On Sun, Oct 30, 2005 at 06:33:55PM +0000, Mel Gorman wrote:
    > Here are a few brief reasons why this set of patches is useful;
    >
    > o Reduced fragmentation improves the chance a large order allocation succeeds
    > o General-purpose memory hotplug needs the page/memory groupings provided
    > o Reduces the number of badly-placed pages that page migration mechanism must
    > deal with. This also applies to any active page defragmentation mechanism.

    I can say that this patch set makes hotplug memory remove be of
    value on ppc64. My system has 6GB of memory and I would 'load
    it up' to the point where it would just start to swap and let it
    run for an hour. Without these patches, it was almost impossible
    to find a section that could be offlined. With the patches, I
    can consistently reduce memory to somewhere between 512MB and 1GB.
    Of course, results will vary based on workload. Also, this is
    most advantageous for memory hotlug on ppc64 due to relatively
    small section size (16MB) as compared to the page grouping size
    (8MB). A more general purpose solution is needed for memory hotplug
    support on architectures with larger section sizes.

    Just another data point, 

    -- 
Mike
-
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: Zwane Mwaikambo: "Re: [patch 1/5] i386 generic cmpxchg"

    Relevant Pages

    • RE: [PATCHv5 3/3] vhost_net: a kernel-level virtio server
      ... I have collected your 3 patches in kernel side and 4 patches in queue side. ... structures can be moved around in memory at any time ... Userspace hypervisors are supported as well as kvm. ... In this version I only support raw socket as a backend, ...
      (Linux-Kernel)
    • 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: [Fastboot] Re: [PATCH] Fix for broken kexec on panic
      ... be able to drop all of the crashdump-* patches. ... using either the legacy interrupt controller or IOAPICs. ... In addition there is nothing non-portable about the architecture, ... The biggest theoretical gotcha are systems with hot plug memory. ...
      (Linux-Kernel)
    • [PATCH 0/36] drivers edac new features drivers and fixes
      ... This series of patches enhances the feature set of EDAC, ... adds some new memory drivers. ... 2- Altered the file 'edac_mc.c' to be for memory controller code only. ...
      (Linux-Kernel)
    • Re: [Lhms-devel] [PATCH 0/7] Fragmentation Avoidance V19 - Summary
      ... Another reason for avoiding memory fragmentation, ... > that, with more work built upon these patches, we can grant large pages ... > the easy reclaim zone, alloc your pages and away we go". ... >> there aren't actually a lot of higher order allocations in the kernel. ...
      (Linux-Kernel)
    Loading