LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: David Rientjes <rientjes@google.com>
To: Andi Kleen <ak@suse.de>
Cc: Andrew Morton <akpm@osdl.org>, Rohit Seth <rohitseth@google.com>,
	linux-kernel@vger.kernel.org
Subject: Re: [patch -mm 3/5] x86_64: fixed-size remaining fake nodes
Date: Mon, 29 Jan 2007 10:38:45 -0800 (PST)	[thread overview]
Message-ID: <Pine.LNX.4.56.0701291032160.26116@hadoop0.corp.google.com> (raw)
In-Reply-To: <200701291436.59930.ak@suse.de>

On Mon, 29 Jan 2007, Andi Kleen wrote:

> On Thursday 25 January 2007 22:37, David Rientjes wrote:
> > Any leftover memory is allocated
> > to a final node unless the command-line ends with a comma.
> 
> That sounds like syntactical vinegar and a nasty trap. Remember 
> that venus probe that got lost because of a wrong comma.
> Can you find some nicer syntax for that please? 
> 

The only other appropriate syntax that comes to mind is perhaps a 
command-line that ends with a 0.  For example, numa=fake=2*512,0 would 
allocate two 512M nodes and nothing for the remaining RAM.

> Also it's pretty complex. Are there use cases for all of this? 
> 

There are.  Configurable node sizes (i.e. 'numa=fake=512,4*128', etc) are 
the major concept and help to avoid the overhead associated with something 
like 64 nodes of 64M each on a 4G machine.  We've seen some inefficiencies 
with scanning through so many zone lists on page_alloc when we encounter a 
full node.  Additional support such as 'numa=fake=2*512,*128' are used 
more for machines where you're unsure of their total system RAM in the 
first place but want to make sure you have the node sizes you need.

		David

  reply	other threads:[~2007-01-29 18:39 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-01-25 21:37 [patch -mm 1/5] x86_64: configurable fake numa node sizes David Rientjes
2007-01-25 21:37 ` [patch -mm 2/5] x86_64: split remaining fake nodes equally David Rientjes
2007-01-25 21:37   ` [patch -mm 3/5] x86_64: fixed-size remaining fake nodes David Rientjes
2007-01-25 21:37     ` [patch -mm 4/5] x86_64: fake numa function annotations David Rientjes
2007-01-25 21:37       ` [patch -mm 5/5] x86_64: fake numa for cpusets document David Rientjes
2007-01-29 13:36     ` [patch -mm 3/5] x86_64: fixed-size remaining fake nodes Andi Kleen
2007-01-29 18:38       ` David Rientjes [this message]
2007-01-30  1:19         ` David Rientjes

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=Pine.LNX.4.56.0701291032160.26116@hadoop0.corp.google.com \
    --to=rientjes@google.com \
    --cc=ak@suse.de \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rohitseth@google.com \
    --subject='Re: [patch -mm 3/5] x86_64: fixed-size remaining fake nodes' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).