linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jamie Lokier <jamie@shareable.org>
To: "linux-os (Dick Johnson)" <linux-os@analogic.com>
Cc: Diego Calleja <diegocg@gmail.com>,
	Ram Gupta <ram.gupta5@gmail.com>,
	mloftis@wgops.com, barryn@pobox.com, a1426z@gawab.com,
	linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: Re: [RFC] VM: I have a dream...
Date: Mon, 23 Jan 2006 16:50:02 +0000	[thread overview]
Message-ID: <20060123165002.GA6140@mail.shareable.org> (raw)
In-Reply-To: <Pine.LNX.4.61.0601231058200.11299@chaos.analogic.com>

linux-os (Dick Johnson) wrote:
> On Mon, 23 Jan 2006, Diego Calleja wrote:
> > However, I doubt the approach is really useful. If you need that much
> > swap space, you're going well beyond the capabilities of the machine.
> > In fact, I bet that most of the cases of machines needing too much
> > memory will be because of bugs in the programs and OOM'ing would be
> > a better solution.
> 
> You have roughly 2 GB of dynamic address-space avaliable to each
> task (stuff that's not the kernel and not the runtime libraries).
> You can easily have 500 tasks, even RedHat out-of-the-box creates
> about 60 tasks. That's 1,000 GB of potential swap-space required
> to support this.

And how many machines is it useful to use that much swap-space on?

> This is not beyond the capabilites of a 32-bit
> machine with a fast front-side bus and fast I/O (like wide SCSI).

Anything but the most expensively RAM-equipped machine would be stuck
in a useless swap-storm, if it's got 1000GB of GB of active swap space
and only a relatively tiny amount of physical RAM (e.g. 16GB).  The
same is true if only, say, 10% of the swap space is in active use.

Wide SCSI isn't fast enough to make that useful.

I think that was the point Diego was making: you can use that much
swap space, but by the time you do, whatever task you hoped to
accomplish won't get anywhere due to the swap-storm.

> Some persons tend to forget that 32-bit address space is available
> to every user, some is shared, some is not. A reasonable rule-of-
> thumb is to provide enough swap-space to duplicate the address-
> space of every potential task.

I think that's a ridiculous rule of thumb.  Not least because (a) even
the biggest drive available (e.g. 1TB) doesn't provide that much
swap-space, and (b) if you're actively using only a tiny fraction of
that, your machine has already become uselessly slow - even root
logins and command prompts don't work under those conditions.

-- Jamie

  reply	other threads:[~2006-01-23 16:50 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-01-21 18:08 [RFC] VM: I have a dream Al Boldi
2006-01-21 18:42 ` Jamie Lokier
2006-01-21 18:46 ` Avi Kivity
2006-01-23 19:52   ` Bryan Henderson
2006-01-25 22:04     ` Al Boldi
2006-01-26 19:18       ` Bryan Henderson
2006-01-27 16:12         ` Al Boldi
2006-01-27 19:17           ` Bryan Henderson
2006-01-30 13:21             ` Al Boldi
2006-01-30 13:35               ` Kyle Moffett
2006-01-31 15:56                 ` Al Boldi
2006-01-31 16:34                   ` Kyle Moffett
2006-01-31 23:14                     ` Bryan Henderson
2006-01-31 16:34                   ` Lennart Sorensen
2006-01-31 19:23                   ` Jamie Lokier
2006-02-01  4:06                   ` Barry K. Nathan
2006-02-02 15:11                   ` Alan Cox
2006-02-02 18:59                     ` Al Boldi
2006-02-02 22:33                       ` Bryan Henderson
2006-02-03 14:46                       ` Alan Cox
2006-01-30 16:49               ` Bryan Henderson
2006-01-26  0:03     ` Jon Smirl
2006-01-26 19:48       ` Bryan Henderson
2006-01-22  8:16 ` Pavel Machek
2006-01-22 12:33 ` Robin Holt
2006-01-23 18:03   ` Al Boldi
2006-01-23 18:40     ` Valdis.Kletnieks
2006-01-23 19:26       ` Benjamin LaHaise
2006-01-23 19:40         ` Valdis.Kletnieks
2006-01-23 22:26     ` Pavel Machek
2006-01-22 19:55 ` Barry K. Nathan
2006-01-23  5:23   ` Michael Loftis
2006-01-23  5:46     ` Chase Venters
2006-01-23  8:20       ` Barry K. Nathan
2006-01-23 13:17       ` Jamie Lokier
2006-01-23 20:21         ` Peter Chubb
2006-01-23 15:05     ` Ram Gupta
2006-01-23 15:26       ` Diego Calleja
2006-01-23 16:11         ` linux-os (Dick Johnson)
2006-01-23 16:50           ` Jamie Lokier [this message]
2006-01-24  2:08           ` Horst von Brand
2006-01-25  6:13             ` Jamie Lokier
2006-01-25  9:23             ` Bernd Petrovitsch
2006-01-25  9:42               ` Lee Revell
2006-01-25 15:02                 ` Jamie Lokier
2006-01-25 23:24                   ` Lee Revell
2006-01-25 15:05               ` Jamie Lokier
2006-01-25 15:47                 ` Bernd Petrovitsch
2006-01-25 16:09                 ` Diego Calleja
2006-01-25 17:26                   ` Jamie Lokier
2006-01-26 19:13                     ` Bryan Henderson
2006-01-25 23:28                 ` Lee Revell
2006-01-26  1:29                   ` Diego Calleja
2006-01-26  5:01                   ` Jamie Lokier
2006-01-26  5:11                     ` Lee Revell
2006-01-26 14:46                       ` Dave Kleikamp
2006-01-24  2:10           ` Horst von Brand
2006-01-25 22:27         ` Nix
2006-01-26 15:13           ` Denis Vlasenko
2006-01-26 16:23             ` Nix
2006-01-23 20:43       ` Michael Loftis
2006-01-23 22:42         ` Nikita Danilov
2006-01-24 14:36           ` Ram Gupta
2006-01-24 15:04             ` Diego Calleja
2006-01-24 20:59               ` Bryan Henderson
2006-01-24 15:11             ` Nikita Danilov
2006-01-23 22:57         ` Ram Gupta
  -- strict thread matches above, loose matches on Subject: below --
2006-02-01 13:58 Al Boldi
2006-02-01 14:38 ` Jamie Lokier
2006-02-02 12:26   ` Al Boldi

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=20060123165002.GA6140@mail.shareable.org \
    --to=jamie@shareable.org \
    --cc=a1426z@gawab.com \
    --cc=barryn@pobox.com \
    --cc=diegocg@gmail.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-os@analogic.com \
    --cc=mloftis@wgops.com \
    --cc=ram.gupta5@gmail.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).