Re: + cgroup-memory-controller-document-huge-memory-cache-overhead-in-kconfig.patch added to -mm tree

[Balbir Singh]

On Sat, Feb 23, 2008 at 1:02 PM,  <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
>
>  The patch titled
>      cgroup memory controller: document huge memory/cache overhead in Kconfig
>  has been added to the -mm tree.  Its filename is
>      cgroup-memory-controller-document-huge-memory-cache-overhead-in-kconfig.patch
>
>  Before you just go and hit "reply", please:
>    a) Consider who else should be cc'ed
>    b) Prefer to cc a suitable mailing list as well
>    c) Ideally: find the original patch on the mailing list and do a
>       reply-to-all to that, adding suitable additional cc's
>
>  *** Remember to use Documentation/SubmitChecklist when testing your code ***
>
>  See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
>  out what to do about this
>
>  The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
>
>  ------------------------------------------------------
>  Subject: cgroup memory controller: document huge memory/cache overhead in Kconfig
>  From: Andi Kleen <andi@xxxxxxxxxxxxxx>
>
>  Document huge memory/cache overhead of memory controller in Kconfig
>
>  I was a little surprised that 2.6.25-rc* increased struct page for the
>  memory controller.  At least on many x86-64 machines it will not fit into a
>  single cache line now anymore and also costs considerable amounts of RAM.
>  At earlier review I remembered asking for a external data structure for
>  this.
>
>  It's also quite unobvious that a innocent looking Kconfig option with a
>  single line Kconfig description has such a negative effect.
>
>  This patch attempts to document these disadvantages at least so that users
>  configuring their kernel can make a informed decision.
>
>  Signed-off-by: Andi Kleen <ak@xxxxxxx>
>  Cc: Balbir Singh <balbir@xxxxxxxxxx>
>  Acked-by: Paul Menage <menage@xxxxxxxxxx>
>  Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
>  ---
>
>   init/Kconfig |    8 ++++++++
>   1 file changed, 8 insertions(+)
>
>  diff -puN init/Kconfig~cgroup-memory-controller-document-huge-memory-cache-overhead-in-kconfig init/Kconfig
>  --- a/init/Kconfig~cgroup-memory-controller-document-huge-memory-cache-overhead-in-kconfig
>  +++ a/init/Kconfig
>  @@ -394,6 +394,14 @@ config CGROUP_MEM_CONT
>           Provides a memory controller that manages both page cache and
>           RSS memory.
>
>  +         Note that setting this option increases fixed memory overhead
>  +         associated with each page of memory in the system by 4/8 bytes
>  +         and also increases cache misses because struct page on many 64bit
>  +         systems will not fit into a single cache line anymore.
>  +
>  +         Only enable when you're ok with these trade offs and really
>  +         sure you need the memory controller.
>  +

Andrew,

I asked Andi what architectures have a cacheline size such that 56
bytes would fit in the cache, but 64 bytes would not. I have not heard
back. I would like Andi's approval to change the text to

         Note that setting this option increases fixed memory overhead
         associated with each page of memory in the system by 4/8 bytes
         Only enable when you're ok with these trade offs and really
         sure you need the memory controller.

Andi, please confirm at the earliest.

Balbir
--
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/