From: "David S. Miller" <davem@redhat.com>
To: alan@lxorguk.ukuu.org.uk
Cc: lm@bitmover.com, tom@rhadamanthys.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] TCP Zero Copy for mmapped files
Date: Thu, 02 Jan 2003 15:16:00 -0800 (PST) [thread overview]
Message-ID: <20030102.151600.129375771.davem@redhat.com> (raw)
In-Reply-To: <1041549644.24829.66.camel@irongate.swansea.linux.org.uk>
From: Alan Cox <alan@lxorguk.ukuu.org.uk>
Date: 02 Jan 2003 23:20:44 +0000
On Thu, 2003-01-02 at 22:28, Larry McVoy wrote:
> The VM cost hurts. Badly. Imagine that the network costs ZERO. Then
> the map/unmap/vm ops become the dominating term. That's why it is a
> fruitless approach, it still has a practical limit which is too low.
It depends how predictable your content is. With a 64bit box and a porn
server its probably quite tidy
Let's say you have infinite VM (which is what 64-bit almost is :) then
the cost is setting up all of these useless VMAs for each and every
file (which is a 1 time cost, ok), and also the VMA lookup each
write() call.
With sendfile() all of this goes straight to the page cache directly
without a VMA lookup.
next prev parent reply other threads:[~2003-01-02 23:15 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-12-30 1:09 [PATCH] TCP Zero Copy for mmapped files Thomas Ogrisegg
2002-12-30 1:29 ` Larry McVoy
2003-01-02 6:37 ` David S. Miller
2003-01-02 22:12 ` Thomas Ogrisegg
2003-01-02 22:28 ` Larry McVoy
2003-01-02 23:20 ` Alan Cox
2003-01-02 23:16 ` David S. Miller [this message]
2003-01-03 0:56 ` Alan Cox
2003-01-03 2:40 ` David S. Miller
2003-01-03 2:41 ` Linus Torvalds
2003-01-02 23:13 ` David S. Miller
2003-01-03 0:45 ` Thomas Ogrisegg
2003-01-03 1:01 ` Larry McVoy
2003-01-03 1:59 ` Alan Cox
2003-01-06 14:36 ` Gianni Tedesco
2003-01-06 23:29 ` David S. Miller
2003-01-03 1:56 ` Alan Cox
2003-01-03 1:27 ` Larry McVoy
2003-01-03 2:42 ` David S. Miller
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=20030102.151600.129375771.davem@redhat.com \
--to=davem@redhat.com \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=linux-kernel@vger.kernel.org \
--cc=lm@bitmover.com \
--cc=tom@rhadamanthys.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.