public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: ebiederm@xmission.com (Eric W. Biederman)
To: Simon Kirby <sim@netnation.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: O_NONBLOCK on files
Date: 19 Sep 2001 01:05:06 -0600	[thread overview]
Message-ID: <m1r8t3fyot.fsf@frodo.biederman.org> (raw)
In-Reply-To: <20010918234648.A21010@netnation.com>
In-Reply-To: <20010918234648.A21010@netnation.com>

Simon Kirby <sim@netnation.com> writes:

> I've always wondered why it's not possible to do this:
> 
> fd = open("an_actual_file",O_RDONLY);
> fcntl(fd,F_SETFL,O_NONBLOCK);
> r = read(fd,buf,4096);
> 
> And actually have read return -1 and errno == EWOULDBLOCK/EAGAIN if the
> block requested is not already cached.
> 
> Wouldn't this be the ideal interface for daemons of all types that want
> to stay single-threaded and still offer useful performance when the
> working set doesn't fit in cache?  It works with sockets, so why not
> with files?

Besides the SUS or the POSIX specs...
What would cause the data to be read in if read just checks the caches?
With sockets the other side is clearing pushing or pulling the data.  With
files there is no other side...

This is resolveable just not currently implemented.

Eric


  reply	other threads:[~2001-09-19  7:13 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-09-19  6:46 O_NONBLOCK on files Simon Kirby
2001-09-19  7:05 ` Eric W. Biederman [this message]
2001-09-19  7:24   ` Simon Kirby
2001-09-24 20:47     ` Matti Aarnio
2001-09-24 21:05       ` Simon Kirby
2001-09-24 21:30         ` Benjamin LaHaise
2001-09-19  8:52   ` Erik Andersen

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=m1r8t3fyot.fsf@frodo.biederman.org \
    --to=ebiederm@xmission.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sim@netnation.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