mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Diego Calleja <diegocg@gmail.com>
To: Lee Revell <rlrevell@joe-job.com>
Cc: prakashp@arcor.de, paolo.ciarrocchi@gmail.com, gregkh@suse.de,
	pmcfarland@downeast.net,
	linux-hotplug-devel@lists.sourceforge.net,
	linux-kernel@vger.kernel.org
Subject: Re: [ANNOUNCE] hotplug-ng 001 release
Date: Tue, 15 Feb 2005 00:43:29 +0100	[thread overview]
Message-ID: <20050215004329.5b96b5a1.diegocg@gmail.com> (raw)
In-Reply-To: <1108422240.28902.11.camel@krustophenia.net>

El Mon, 14 Feb 2005 18:04:00 -0500,
Lee Revell <rlrevell@joe-job.com> escribió:

> Last I heard Gentoo does not even do it by default.
> 
> I don't see why so much effort goes into improving boot time on the
> kernel side when the most obvious user space problem is ignored.


There's stuff that it could be done in the kernel to help improving those numbers,
IMHO.

xp logs all the io done the first two minutes after booting. The next time it boots
it tries to read all those files at once so the programs will find stuff in memory
instead of having to do lots of small seeks. Some people in the linux field have
got a list of the files used at startup and they've thrown it at a "readhead" script,
which seems to help but IMHO it's somewhat "hacky" compared with the 
xp's trick. xp also does that when you start a program, it saves a log of all the
io done and it preloads it efficiently at startup - it improves "cold-cache" loading
times a _lot_. I haven't seen any alternative for that in the linux world, and
being able to keep track of al the io done by a given process would fix that (some
people has put used printk's for that, but i think it can be done better)

Also, it analyzes all those io "logs" and defragments (in background every 3 days,
and with low load without the user noticing it) the disk according to the _use_ of the
systems. Linux kernel can keep a file unfragmented, but currently there's no way
linux can do decisions like "this system starts openoffice, so I'm going to move the
binaries to another place of the disk where they'll load faster" or "when X program
uses /lib/libfoo.so it also uses /lib/libbar.so, so I'm going to put those two together
in the disk because that will avoid seeks". Kernel only can keep a single file
unfragmented, but it doesn't know about how several files must be (un)fragmented
between them. Being able to defragment things seems to be the one fix that (even
mac os x does it)

Userspace is where the problem is, but it's not going to be fixed. Ever. If
something, it's going to be worse - it's how software works. And even if you make
openoffice "fast", you still could _improve_ things with the tricks described
above. Disks are too slow, and things like demand-loading executables generate
too many small seeks, and programs can't control demand-loading so I don't
think userspace is the only with work to do.

  parent reply	other threads:[~2005-02-14 23:43 UTC|newest]

Thread overview: 76+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-02-11  0:40 Greg KH
2005-02-11  0:52 ` Greg KH
2005-02-11  1:30   ` Kasper Sandberg
2005-02-11  6:41     ` Greg KH
2005-02-11 11:47       ` Kasper Sandberg
2005-02-11 17:06         ` Greg KH
2005-02-12  0:02           ` Kasper Sandberg
2005-02-11  1:07 ` Patrick McFarland
2005-02-11  1:16   ` Greg KH
2005-02-11 20:40     ` Vojtech Pavlik
2005-02-14  4:06     ` Lee Revell
2005-02-14  8:32       ` Paolo Ciarrocchi
2005-02-14  8:51         ` Prakash Punnoor
2005-02-14 23:04           ` Lee Revell
2005-02-14 23:16             ` Greg KH
2005-02-14 23:28               ` Lee Revell
2005-02-15 15:15                 ` Stefan Seyfried
2005-02-15 20:12                   ` kernel
2005-02-14 23:21             ` Roland Dreier
2005-02-14 23:45               ` [OT] speeding boot process (was Re: [ANNOUNCE] hotplug-ng 001 release) Lee Revell
2005-02-15  0:16                 ` Tim Bird
2005-02-15  1:17                   ` Lee Revell
2005-02-15  1:45                     ` Kyle Moffett
2005-02-15  7:32                       ` Gábor Lénárt
2005-02-15  8:34                         ` Paolo Ciarrocchi
2005-02-15  9:27                           ` [OT] speeding boot process Bernd Petrovitsch
2005-02-15  8:55                       ` [OT] speeding boot process (was Re: [ANNOUNCE] hotplug-ng 001 release) Helge Hafting
2005-02-15  9:33                         ` Bernd Petrovitsch
2005-02-15 13:20                           ` Helge Hafting
2005-02-15 13:28                             ` Paulo Marques
2005-02-15 13:50                             ` Bernd Petrovitsch
2005-02-16  1:54                             ` Miquel van Smoorenburg
2005-02-15  3:38                     ` Jim Crilly
2005-02-15  5:52                       ` Nigel Cunningham
2005-02-15  6:15                         ` Jim Crilly
2005-02-15  6:39                           ` Nigel Cunningham
2005-02-15 19:32                           ` Lee Revell
2005-02-17 18:37                     ` jlnance
2005-02-17 19:18                       ` Chris Larson
2005-02-19  5:53                         ` Jim Crilly
2005-02-17 20:00                       ` Helge Hafting
2005-02-19  5:56                         ` Jim Crilly
2005-02-19 22:47                           ` Helge Hafting
2005-02-20  2:09                             ` Jim Crilly
2005-02-15  8:33                 ` Paolo Ciarrocchi
2005-02-14 23:43             ` Diego Calleja [this message]
2005-02-15 19:51               ` [ANNOUNCE] hotplug-ng 001 release Lee Revell
2005-02-15 21:02                 ` Diego Calleja
2005-02-15 21:32                   ` Chris Friesen
2005-02-15 21:09                 ` Valdis.Kletnieks
2005-02-15 19:56               ` Optimizing disk-I/O [was Re: [ANNOUNCE] hotplug-ng 001 release] Linas Vepstas
2005-02-15 20:46                 ` Adam Goode
2005-02-15 21:11                   ` Diego Calleja
2005-02-15 21:21                 ` Valdis.Kletnieks
2005-02-11  3:18 ` [ANNOUNCE] hotplug-ng 001 release Bill Nottingham
2005-02-11  6:46   ` Greg KH
2005-02-11 16:19     ` Christian Bornträger
2005-02-11 17:01       ` Greg KH
2005-02-11 19:01         ` Erik Andersen
2005-02-11 19:23           ` Greg KH
2005-02-11 21:37             ` Erik van Konijnenburg
2005-02-11 21:49               ` Greg KH
2005-02-11 22:06                 ` Erik van Konijnenburg
2005-02-11 22:13                   ` Greg KH
2005-02-12  0:48                     ` Ingo Oeser
2005-02-14 22:43                       ` Greg KH
2005-02-11  9:52 ` Olivier Galibert
2005-02-11 17:08   ` Greg KH
2005-02-11 20:06 ` Harald Dunkel
2005-02-11 21:01   ` Greg KH
2005-02-12  8:30     ` Harald Dunkel
2005-02-14 22:36       ` Greg KH
2005-02-15  5:39         ` Harald Dunkel
2005-02-15  7:14           ` Greg KH
2005-02-14 10:29 Michal Rokos
     [not found] <20050211211028.GB21512@suse.de>
2005-02-17  6:46 ` Michael Tokarev

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=20050215004329.5b96b5a1.diegocg@gmail.com \
    --to=diegocg@gmail.com \
    --cc=gregkh@suse.de \
    --cc=linux-hotplug-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paolo.ciarrocchi@gmail.com \
    --cc=pmcfarland@downeast.net \
    --cc=prakashp@arcor.de \
    --cc=rlrevell@joe-job.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

all inboxes | Powered by JetHome®