public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Pavel Machek <pavel@ucw.cz>
To: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Nigel Cunningham <ncunningham@linuxmail.org>,
	suspend2-devel@lists.suspend2.net,
	Olivier Galibert <galibert@pobox.com>,
	grundig <grundig@teleline.es>, Avuton Olrich <avuton@gmail.com>,
	jan@rychter.com, linux-kernel@vger.kernel.org
Subject: Re: uswsusp history lesson [was Re: [Suspend2-devel] Re: swsusp / suspend2 reliability]
Date: Sat, 8 Jul 2006 23:10:03 +0200	[thread overview]
Message-ID: <20060708211003.GC2546@elf.ucw.cz> (raw)
In-Reply-To: <200607082052.02557.rjw@sisk.pl>

Hi!

> > We have kswapd frozen, hooks to stop other processes trying to free memory 
> > (yes, I'm going to switch to your method of taking the pages off the lists), 
> > and userspace processes are frozen or their pages are excluded from the list.
> > 
> > > However, if we are sure that we can use LRU pages as additional storage in
> > > b), they just can be included in the memory image without copying
> > > and we only need some extra room for the other data and code.
> > > If LRU pages take 50% of memory, this would allow us to create
> > > a signle snapshot image as big as 75% of RAM (on x86_64).  IMO the
> > > remaining 25% are not worth the increased complexity of suspend2,
> > > especially that on 1 GB machine 75% of RAM is too much to save
> > > for performance reasons (ie. the extra time you save by making the
> > > system more responsive after resume is lost for saving and restoring
> > > the image, even if compression is used).
> > 
> > It's only too slow on swsusp. With Suspend2, I regularly suspend 1GB images on 
> > both my desktop and laptop machines. I agree that it might be
> > slower on a 

uswsusp is as fast as suspend2. It does same LZF compression.

> > > Furthermore, I tried to measure how much time would actually be saved if
> > > the images were greater than 50% of RAM (current swsusp's limit) and it
> > > turned out to be 10% at the very last, with compression (on a 256MB box
> > > with PII).
> > 
> > I think you'll find that this depends very much on the kind of workload you 
> > have, and how you try to compare apples with apples. If you're running lots 
> > of memory intensive apps (say VMware with a couple of hundred meg allocated, 
> > Open Office writer, Kmail, a couple of terminals and so on - I'm just 
> > describing what I normally run), you'll miss that extra memory more.

Do you think you could get some repeatable benchmark for Rafael? He
worked quite hard on feature only to find out it makes little difference...

									Pavel
-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

  reply	other threads:[~2006-07-08 21:10 UTC|newest]

Thread overview: 135+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-06-26 15:47 Suspend2 - Request for review & inclusion in -mm Nigel Cunningham
2006-06-27 13:33 ` Pavel Machek
2006-06-27 15:22   ` [Suspend2-devel] " Brad Campbell
2006-06-27 15:41     ` Andreas Mohr
2006-06-27 16:01       ` Avuton Olrich
2006-06-27 22:23         ` Pavel Machek
2006-06-27 22:22       ` swsusp / suspend2 reliability (was Re: [Suspend2-devel] Re: Suspend2 - Request for review & inclusion in -mm) Pavel Machek
2006-06-27 22:38         ` Sebastian Kügler
2006-06-27 22:51           ` Pavel Machek
2006-06-27 23:18             ` Sebastian Kügler
2006-06-28 19:53               ` Pavel Machek
2006-06-28 22:19                 ` Sebastian Kügler
2006-06-28 22:24                   ` Pavel Machek
2006-06-28 22:37                     ` Sebastian Kügler
2006-06-28 22:46                       ` Pavel Machek
2006-06-28 23:06                         ` Sebastian Kügler
2006-06-28 22:52                   ` Rafael J. Wysocki
2006-06-28 23:09                     ` Sebastian Kügler
2006-06-28  8:56         ` Andreas Jellinghaus
2006-06-28 19:58           ` Pavel Machek
2006-07-06 19:15         ` swsusp / suspend2 reliability Jan Rychter
2006-07-07 13:50           ` Pavel Machek
2006-07-07 14:05             ` [Suspend2-devel] " Rohan Dhruva
2006-07-07 18:21               ` David Fox
2006-07-07 21:42                 ` Pavel Machek
2006-07-07 15:03             ` dirk husemann
2006-07-07 23:19               ` Pavel Machek
2006-07-07 18:03             ` Olivier Galibert
2006-07-07 23:18               ` Pavel Machek
2006-07-07 15:19           ` Avuton Olrich
2006-07-07 16:09             ` grundig
2006-07-07 17:44               ` Olivier Galibert
2006-07-07 21:39                 ` Pavel Machek
2006-07-07 21:56                   ` Olivier Galibert
2006-07-07 23:25                     ` Pavel Machek
2006-07-07 23:33                       ` [Suspend2-devel] " Nigel Cunningham
2006-07-08  0:04                         ` Pavel Machek
2006-07-08  0:28                         ` uswsusp history lesson [was Re: [Suspend2-devel] Re: swsusp / suspend2 reliability] Pavel Machek
2006-07-08  3:42                           ` Nigel Cunningham
2006-07-08 10:38                             ` Rafael J. Wysocki
2006-07-08 11:13                               ` Bojan Smojver
2006-07-08 18:34                                 ` Rafael J. Wysocki
2006-07-08 22:35                                   ` Bojan Smojver
2006-07-08 11:31                               ` Nigel Cunningham
2006-07-08 11:42                                 ` Bojan Smojver
2006-07-08 12:52                                 ` Pavel Machek
2006-07-08 13:26                                   ` Nigel Cunningham
2006-07-08 21:04                                     ` Pavel Machek
2006-07-08 22:25                                       ` Nigel Cunningham
2006-07-08 18:52                                 ` Rafael J. Wysocki
2006-07-08 21:10                                   ` Pavel Machek [this message]
2006-07-08 22:28                                     ` Nigel Cunningham
2006-07-08 23:54                                       ` Pavel Machek
2006-07-09  0:02                                         ` Nigel Cunningham
2006-07-09  0:09                                           ` Pavel Machek
2006-07-09 10:03                                           ` Rafael J. Wysocki
2006-07-11 12:45                                   ` Nigel Cunningham
2006-07-11 21:54                                     ` Rafael J. Wysocki
2006-07-11 22:01                                       ` Nigel Cunningham
2006-07-11 22:34                                         ` Rafael J. Wysocki
2006-07-11 23:00                                           ` Nigel Cunningham
2006-07-12 10:09                                             ` Rafael J. Wysocki
2006-07-12 10:16                                               ` Nigel Cunningham
2006-07-08 11:22                             ` Pavel Machek
2006-07-08  4:33                           ` Avuton Olrich
2006-07-08 11:12                             ` Pavel Machek
2006-07-08 11:21                               ` Nigel Cunningham
2006-07-08  4:58                           ` Bojan Smojver
2006-07-08  9:11                           ` uswsusp history lesson Jan Rychter
2006-07-08 10:14                             ` [Suspend2-devel] " Bojan Smojver
2006-07-08 10:41                               ` Arjan van de Ven
2006-07-08 11:11                                 ` Bojan Smojver
2006-07-08 11:13                                   ` Pavel Machek
2006-07-08 11:16                                     ` Bojan Smojver
2006-07-08 11:20                                     ` Nigel Cunningham
2006-07-08 13:19                                   ` Arjan van de Ven
2006-07-08 22:32                                     ` Bojan Smojver
2006-07-08 16:43                                 ` Olivier Galibert
2006-07-08 16:47                                   ` Arjan van de Ven
2006-07-08 17:01                                     ` Alon Bar-Lev
2006-07-08 19:36                                       ` grundig
2006-07-08 17:49                                     ` Olivier Galibert
2006-07-08 18:03                                       ` Arjan van de Ven
2006-07-08 21:46                                       ` Alan Cox
2006-07-09  0:19                                         ` Olivier Galibert
2006-07-08 17:39                                   ` Alan Cox
2006-07-08 23:57                                     ` Pavel Machek
2006-07-09  0:03                                       ` Nigel Cunningham
     [not found]                                 ` <ce9ef0d90607080942w685a6b60q7611278856c78ac0@mail.gmail.com>
2006-07-08 16:50                                   ` Arjan van de Ven
2006-07-08 19:25                                     ` Rafael J. Wysocki
2006-07-08 19:39                                       ` Arjan van de Ven
2006-07-08 20:22                                         ` Pavel Machek
2006-07-10  9:11                                         ` dirk husemann
2006-07-10  9:18                                           ` Arjan van de Ven
2006-07-10 10:02                                             ` Pavel Machek
2006-07-10 21:49                                               ` Nigel Cunningham
2006-07-10 23:22                                                 ` Pavel Machek
2006-07-10 23:37                                                   ` Nigel Cunningham
2006-07-10 12:45                                             ` Thomas Tuttle
2006-07-10 13:05                                               ` Arjan van de Ven
     [not found]                                       ` <ce9ef0d90607081248n1f2fc79fw199b493f3ca6313@mail.gmail.com>
2006-07-08 19:58                                         ` Rafael J. Wysocki
2006-07-08 20:13                                           ` Alon Bar-Lev
2006-07-08 20:23                                             ` Rafael J. Wysocki
2006-07-08 22:20                                         ` Nigel Cunningham
2006-07-08 23:46                                       ` Bojan Smojver
2006-07-08 23:53                                         ` Pavel Machek
2006-07-09  0:18                                           ` Bojan Smojver
2006-07-09  0:32                                             ` Pavel Machek
2006-07-09  1:05                                               ` Bojan Smojver
2006-07-09 13:51                                                 ` Rafael J. Wysocki
2006-07-09 21:06                                                   ` Nigel Cunningham
2006-07-09 21:36                                                     ` Rafael J. Wysocki
2006-07-09 21:46                                                       ` Nigel Cunningham
2006-07-09 22:30                                                         ` Rafael J. Wysocki
2006-07-10  3:57                                                     ` Jason Lunz
2006-07-10  6:20                                                       ` Nigel Cunningham
2006-07-11 14:47                                                         ` Jason Lunz
2006-07-11 20:13                                                           ` Bojan Smojver
2006-07-10  0:28                                                   ` Bojan Smojver
2006-07-09 12:15                                       ` Matthew Garrett
2006-07-09 21:04                                         ` Nigel Cunningham
2006-07-10  9:10                                       ` dirk husemann
2006-07-08  0:28                       ` [Suspend2-devel] Re: swsusp / suspend2 reliability Bojan Smojver
2006-07-07 19:27           ` Hua Zhong
2006-07-07 21:10             ` Alon Bar-Lev
2006-07-07 23:48               ` Christian Trefzer
2006-06-27 16:50     ` [Suspend2-devel] Re: Suspend2 - Request for review & inclusion in -mm dirk husemann
2006-06-27 19:03     ` Pavel Machek
2006-06-27 19:19       ` Dave Jones
2006-06-27 21:47         ` Pavel Machek
2006-06-28  6:00       ` Brad Campbell
2006-06-28 20:03         ` Pavel Machek
2006-06-28  6:09       ` Markus Gaugusch
     [not found]     ` <200606271940.23934.jaroslav@aster.pl>
     [not found]       ` <1e1a7e1b0606280228y6c4a0d19p12f8112d216d1aba@mail.gmail.com>
2006-06-28 11:31         ` [Suspend2-devel] " Tim Dijkstra
2006-06-27 23:37   ` Nigel Cunningham

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=20060708211003.GC2546@elf.ucw.cz \
    --to=pavel@ucw.cz \
    --cc=avuton@gmail.com \
    --cc=galibert@pobox.com \
    --cc=grundig@teleline.es \
    --cc=jan@rychter.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ncunningham@linuxmail.org \
    --cc=rjw@sisk.pl \
    --cc=suspend2-devel@lists.suspend2.net \
    /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