Linux Container Development
 help / color / mirror / Atom feed
From: Balbir Singh <balbir-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
To: KAMEZAWA Hiroyuki
	<kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
Cc: "containers-qjLDD68F18O7TbgM5vRIOg@public.gmane.org"
	<containers-qjLDD68F18O7TbgM5vRIOg@public.gmane.org>,
	"linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org"
	<linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>,
	"yamamoto-jCdQPDEk3idL9jVzuh4AOg@public.gmane.org"
	<yamamoto-jCdQPDEk3idL9jVzuh4AOg@public.gmane.org>,
	hugh-DTz5qymZ9yRBDgjK7y7TUQ@public.gmane.org
Subject: Re: [RFC][ for -mm] memory controller enhancements for NUMA [0/10] introduction
Date: Thu, 15 Nov 2007 11:55:50 +0530	[thread overview]
Message-ID: <473BE66E.2000707@linux.vnet.ibm.com> (raw)
In-Reply-To: <20071114173950.92857eaa.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>

KAMEZAWA Hiroyuki wrote:
> Hi,
> 
> This is a patch-set for memory controlelr on NUMA. 
> patches are
> 
> 1. record nid/zid on page_cgroup struct
> 2. record per-zone active/inactive
> 3-9 Patches for isolate global-lru reclaiming and memory controller reclaming
> 10. implements per-zone LRU on memory controller.
> 
> now this is just RFC.
> 
> Tested on 
>   2.6.24-rc2-mm1 + x86_64/fake-NUMA( # of nodes = 3)
> 
> I did test with numactl under memory limitation.
>  % numactl -i 0,1,2 dd if=.....
> 
> It seems per-zone-lru works well.
> 
> I'd like to do test on ia64/real-NUMA when I have a chance.
> 
> Any comments are welcome.
> 

Hi, KAMEZAWA-San,

Thanks for the patchset, I'll review it and get back. I'd
also try and get some testing done on it.

> Thanks,
>  -kame
> 

-- 
	Warm Regards,
	Balbir Singh
	Linux Technology Center
	IBM, ISTL

  parent reply	other threads:[~2007-11-15  6:25 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-11-14  8:39 [RFC][ for -mm] memory controller enhancements for NUMA [0/10] introduction KAMEZAWA Hiroyuki
     [not found] ` <20071114173950.92857eaa.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2007-11-14  8:41   ` [RFC][ for -mm] memory controller enhancements for NUMA [1/10] record nid/zid on page_cgroup KAMEZAWA Hiroyuki
     [not found]     ` <20071114174131.cf7c4aa6.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2007-11-14  8:59       ` KAMEZAWA Hiroyuki
2007-11-14  9:22       ` YAMAMOTO Takashi
     [not found]     ` <20071114092243.9331F1CD66B-Pcsii4f/SVk@public.gmane.org>
2007-11-14 10:31       ` kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A
2007-11-14  8:42   ` [RFC][ for -mm] memory controller enhancements for NUMA [2/10] account active inactive KAMEZAWA Hiroyuki
2007-11-14  8:43   ` [RFC][ for -mm] memory controller enhancements for NUMA [3/10] define macro for global lru scan KAMEZAWA Hiroyuki
2007-11-14  8:45   ` [RFC][ for -mm] memory controller enhancements for NUMA [4/10] calc mapped_ratio in cgroup KAMEZAWA Hiroyuki
2007-11-14  8:48   ` [RFC][ for -mm] memory controller enhancements for NUMA [5/10] calc active/inactive impabance KAMEZAWA Hiroyuki
2007-11-14  8:50   ` [RFC][ for -mm] memory controller enhancements for NUMA [6/10] record reclaim priority KAMEZAWA Hiroyuki
2007-11-14  8:51   ` [RFC][ for -mm] memory controller enhancements for NUMA [7/10] calc scan numbers per zone KAMEZAWA Hiroyuki
2007-11-14  8:53   ` [RFC][ for -mm] memory controller enhancements for NUMA [8/10] move reclaim_mapped calc routine (cleanup for later patch) KAMEZAWA Hiroyuki
2007-11-14  8:55   ` [RFC][ for -mm] memory controller enhancements for NUMA [9/10] zone reclaim vs. cgroup reclaim isolation KAMEZAWA Hiroyuki
2007-11-14  8:57   ` [RFC][ for -mm] memory controller enhancements for NUMA [10/10] per-zone-lru KAMEZAWA Hiroyuki
     [not found]     ` <20071114091138.30BA11CD65F-Pcsii4f/SVk@public.gmane.org>
2007-11-14 10:29       ` kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A
     [not found]     ` <20071114175737.d5066644.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2007-11-14  9:11       ` YAMAMOTO Takashi
2007-11-15 11:36       ` KAMEZAWA Hiroyuki
2007-11-15  6:25   ` Balbir Singh [this message]
     [not found]     ` <473BE66E.2000707-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2007-11-15  6:39       ` [RFC][ for -mm] memory controller enhancements for NUMA [0/10] introduction KAMEZAWA Hiroyuki

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=473BE66E.2000707@linux.vnet.ibm.com \
    --to=balbir-23vcf4htsmix0ybbhkvfkdbpr1lh4cv8@public.gmane.org \
    --cc=containers-qjLDD68F18O7TbgM5vRIOg@public.gmane.org \
    --cc=hugh-DTz5qymZ9yRBDgjK7y7TUQ@public.gmane.org \
    --cc=kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org \
    --cc=linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org \
    --cc=yamamoto-jCdQPDEk3idL9jVzuh4AOg@public.gmane.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox