netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesse Barnes <jesse.barnes@intel.com>
To: hadi@cyberus.ca
Cc: Arthur Kepner <akepner@sgi.com>,
	Lennert Buytenhek <buytenh@wantstofly.org>,
	netdev@oss.sgi.com, gnb@sgi.com
Subject: Re: [PATCH] use mmiowb in tg3_poll
Date: Tue, 31 May 2005 09:45:36 -0700	[thread overview]
Message-ID: <200505310945.36903.jesse.barnes@intel.com> (raw)
In-Reply-To: <1117544022.6134.54.camel@localhost.localdomain>

On Tuesday, May 31, 2005 5:53 am, jamal wrote:
> Did i read correctly that your reads are about 2x more expensive than
> the writes?

The test above just measures the difference between using a full PIO 
read to ensure write ordering vs. the lighter weight mmiowb call.  As 
for your question though, non-relaxed reads are very expensive on the 
Altix platform due to its highly distributed NUMA I/O architecture.  
The _relaxed variants can be quite fast however, and can be used 
anytime a PIO read doesn't imply anything about previous DMA 
transactions.

Jesse

      reply	other threads:[~2005-05-31 16:45 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <200410211613.19601.jbarnes@engr.sgi.com>
2004-10-21 23:28 ` [PATCH] use mmiowb in tg3.c Jesse Barnes
2004-10-21 23:40   ` David S. Miller
2004-10-22  1:16     ` Benjamin Herrenschmidt
2004-10-22  1:33       ` akepner
2004-10-22  2:07         ` Benjamin Herrenschmidt
2004-10-22  3:01     ` Jesse Barnes
2004-10-22  4:00       ` Paul Mackerras
2004-10-22 20:51   ` [PATCH] use mmiowb in tg3_poll akepner
2005-05-28 23:12     ` Lennert Buytenhek
2005-05-30 16:30       ` Arthur Kepner
2005-05-31 12:53         ` jamal
2005-05-31 16:45           ` Jesse Barnes [this message]

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=200505310945.36903.jesse.barnes@intel.com \
    --to=jesse.barnes@intel.com \
    --cc=akepner@sgi.com \
    --cc=buytenh@wantstofly.org \
    --cc=gnb@sgi.com \
    --cc=hadi@cyberus.ca \
    --cc=netdev@oss.sgi.com \
    /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;
as well as URLs for NNTP newsgroup(s).