linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Martin J. Bligh" <mbligh@mbligh.org>
To: "David S. Miller" <davem@davemloft.net>,
	Nick Piggin <nickpiggin@yahoo.com.au>
Cc: jschopp@austin.ibm.com, mel@csn.ul.ie, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, akpm@osdl.org
Subject: Re: Avoiding external fragmentation with a placement policy Version 12
Date: Thu, 02 Jun 2005 22:34:42 -0700	[thread overview]
Message-ID: <357240000.1117776882@[10.10.2.4]> (raw)
In-Reply-To: <20050602.214927.59657656.davem@davemloft.net>

>> It would really help your cause in the short term if you can
>> demonstrate improvements for say order-3 allocations (eg. use
>> gige networking, TSO, jumbo frames, etc).
> 
> TSO chops up the user data into PAGE_SIZE chunks, it doesn't
> make use of non-zero page orders.
> 
> AF_UNIX sockets, however, will happily use higher order
> pages.  But even this is limited to SKB_MAX_ORDER which
> is currently defined to 2.
> 
> So the only way to get order 3 or larger allocations with
> the networking is to use jumbo frames but without TSO enabled.

One of the calls I got the other day was for loopback interface. 
Default MTU is 16K, which seems to screw everything up and do higher 
order allocs. Turning it down to under 4K seemed to fix things. I'm 
fairly sure loopback doesn't really need phys contig memory, but it 
seems to use it at the moment ;-)

> Actually, even with TSO enabled, you'll get large order
> allocations, but for receive packets, and these allocations
> happen in software interrupt context.

Sounds like we still need to cope then ... ?

M.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart@kvack.org"> aart@kvack.org </a>

  reply	other threads:[~2005-06-03  5:34 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-05-31 11:20 Mel Gorman
2005-06-01 20:55 ` Joel Schopp
2005-06-01 23:09   ` Nick Piggin
2005-06-01 23:23     ` David S. Miller, Nick Piggin
2005-06-01 23:28     ` Martin J. Bligh
2005-06-01 23:43       ` Nick Piggin
2005-06-02  0:02         ` Martin J. Bligh
2005-06-02  0:20           ` Nick Piggin
2005-06-02 13:55             ` Mel Gorman
2005-06-02 15:52             ` Joel Schopp
2005-06-02 19:50               ` Ray Bryant
2005-06-02 20:10                 ` Joel Schopp
2005-06-04 16:09                   ` Marcelo Tosatti
2005-06-03  3:48               ` Nick Piggin
2005-06-03  4:49                 ` David S. Miller, Nick Piggin
2005-06-03  5:34                   ` Martin J. Bligh [this message]
2005-06-03  5:37                     ` David S. Miller, Martin J. Bligh
2005-06-03  5:42                       ` Martin J. Bligh
2005-06-03  5:51                         ` David S. Miller, Martin J. Bligh
2005-06-03 13:13                         ` Mel Gorman
2005-06-03  6:43                     ` Nick Piggin
2005-06-03 13:57                       ` Martin J. Bligh
2005-06-03 16:43                         ` Dave Hansen
2005-06-03 18:43                           ` David S. Miller, Dave Hansen
2005-06-04  1:44                       ` Herbert Xu
2005-06-04  2:15                         ` Nick Piggin
2005-06-05 19:52                           ` David S. Miller, Nick Piggin
2005-06-03 13:05                 ` Mel Gorman
2005-06-03 14:00                   ` Martin J. Bligh
2005-06-08 17:03                     ` Mel Gorman
2005-06-08 17:18                       ` Martin J. Bligh
2005-06-10 16:20                         ` Christoph Lameter
2005-06-10 17:53                           ` Steve Lord
2005-06-02 18:28           ` Andi Kleen
2005-06-02 18:42             ` Martin J. Bligh
2005-06-02 13:15       ` Mel Gorman
2005-06-02 14:01         ` Martin J. Bligh
     [not found]       ` <20050603174706.GA25663@localhost.localdomain>
2005-06-03 17:56         ` Martin J. Bligh
2005-06-01 23:47     ` Mike Kravetz
2005-06-01 23:56       ` Nick Piggin
2005-06-02  0:07         ` Mike Kravetz
2005-06-02  9:49   ` Mel Gorman

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='357240000.1117776882@[10.10.2.4]' \
    --to=mbligh@mbligh.org \
    --cc=akpm@osdl.org \
    --cc=davem@davemloft.net \
    --cc=jschopp@austin.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    --cc=nickpiggin@yahoo.com.au \
    /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