All of lore.kernel.org
 help / color / mirror / Atom feed
From: Greg Ungerer <gerg@snapgear.com>
To: Jamie Lokier <jamie@shareable.org>
Cc: "Jared Hulbert" <jaredeh@gmail.com>,
	Linux-kernel@vger.kernel.org, linux-embedded@vger.kernel.org,
	linux-mtd <linux-mtd@lists.infradead.org>,
	"Jörn Engel" <joern@logfs.org>,
	tim.bird@AM.SONY.COM, cotte@de.ibm.com, nickpiggin@yahoo.com.au
Subject: Re: [PATCH 00/10] AXFS: Advanced XIP filesystem
Date: Fri, 22 Aug 2008 09:46:45 +1000	[thread overview]
Message-ID: <48ADFE65.1050007@snapgear.com> (raw)
In-Reply-To: <20080821110749.GA1926@shareable.org>


Jamie Lokier wrote:
> Jared Hulbert wrote:
>> The biggest improvement is in the way AXFS allows for each page to be XIP or
>> not.  First, a user collects information about which pages are accessed on a
>> compressed image for each mmap()ed region from /proc/axfs/volume0.  That
>> 'profile' is used as an input to the image builder.  The resulting image has
>> only the relevant pages uncompressed and XIP.  The result is smaller memory
>> sizes and faster launches.
> 
> Sounds great, really nice idea.
> 
> How does it fare with no MMU?  Can the profiler and image builder lay
> out the XIP pages in such a way that no-MMU mmaps can map those regions?

The key for XIP on noMMU would be the ability to store a
file as one complete contiguous chunk. Can AXFS do this?

Regards
Greg



------------------------------------------------------------------------
Greg Ungerer  --  Chief Software Dude       EMAIL:     gerg@snapgear.com
Secure Computing Corporation                PHONE:       +61 7 3435 2888
825 Stanley St,                             FAX:         +61 7 3891 3630
Woolloongabba, QLD, 4102, Australia         WEB: http://www.SnapGear.com

WARNING: multiple messages have this Message-ID (diff)
From: Greg Ungerer <gerg@snapgear.com>
To: Jamie Lokier <jamie@shareable.org>
Cc: cotte@de.ibm.com, linux-embedded@vger.kernel.org,
	nickpiggin@yahoo.com.au, "Jörn Engel" <joern@logfs.org>,
	Linux-kernel@vger.kernel.org,
	linux-mtd <linux-mtd@lists.infradead.org>,
	tim.bird@AM.SONY.COM
Subject: Re: [PATCH 00/10] AXFS: Advanced XIP filesystem
Date: Fri, 22 Aug 2008 09:46:45 +1000	[thread overview]
Message-ID: <48ADFE65.1050007@snapgear.com> (raw)
In-Reply-To: <20080821110749.GA1926@shareable.org>


Jamie Lokier wrote:
> Jared Hulbert wrote:
>> The biggest improvement is in the way AXFS allows for each page to be XIP or
>> not.  First, a user collects information about which pages are accessed on a
>> compressed image for each mmap()ed region from /proc/axfs/volume0.  That
>> 'profile' is used as an input to the image builder.  The resulting image has
>> only the relevant pages uncompressed and XIP.  The result is smaller memory
>> sizes and faster launches.
> 
> Sounds great, really nice idea.
> 
> How does it fare with no MMU?  Can the profiler and image builder lay
> out the XIP pages in such a way that no-MMU mmaps can map those regions?

The key for XIP on noMMU would be the ability to store a
file as one complete contiguous chunk. Can AXFS do this?

Regards
Greg



------------------------------------------------------------------------
Greg Ungerer  --  Chief Software Dude       EMAIL:     gerg@snapgear.com
Secure Computing Corporation                PHONE:       +61 7 3435 2888
825 Stanley St,                             FAX:         +61 7 3891 3630
Woolloongabba, QLD, 4102, Australia         WEB: http://www.SnapGear.com

  parent reply	other threads:[~2008-08-21 23:46 UTC|newest]

Thread overview: 107+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-08-21  5:44 [PATCH 00/10] AXFS: Advanced XIP filesystem Jared Hulbert
2008-08-21  5:44 ` Jared Hulbert
2008-08-21  6:32 ` Frans Meulenbroeks
2008-08-21  6:32   ` Frans Meulenbroeks
2008-08-21 19:32   ` Jared Hulbert
2008-08-21 19:32     ` Jared Hulbert
2008-08-22  2:04     ` Nick Piggin
2008-08-22  2:04       ` Nick Piggin
2008-08-21  8:39 ` Dave Chinner
2008-08-21  8:39   ` Dave Chinner
2008-08-21 14:19   ` Jared Hulbert
2008-08-21 14:19     ` Jared Hulbert
2008-08-21 14:31     ` Leon Woestenberg
2008-08-21 14:31       ` Leon Woestenberg
2008-08-21 14:42       ` Jared Hulbert
2008-08-21 14:42         ` Jared Hulbert
2008-08-21 14:49       ` Geert Uytterhoeven
2008-08-21 14:49         ` Geert Uytterhoeven
2008-08-21 10:25 ` Carsten Otte
2008-08-21 10:25   ` Carsten Otte
2008-08-21 10:43   ` Nick Piggin
2008-08-21 10:43     ` Nick Piggin
2008-08-21 12:53     ` Arnd Bergmann
2008-08-21 12:53       ` Arnd Bergmann
2008-08-21 14:12       ` Jared Hulbert
2008-08-21 14:12         ` Jared Hulbert
2008-08-21 14:14         ` Arnd Bergmann
2008-08-21 14:14           ` Arnd Bergmann
2008-08-21 14:13     ` Jared Hulbert
2008-08-21 14:13       ` Jared Hulbert
2008-08-22  2:32       ` Nick Piggin
2008-08-22  2:32         ` Nick Piggin
2008-08-21 14:30   ` Jared Hulbert
2008-08-21 14:30     ` Jared Hulbert
2008-08-21 11:07 ` Jamie Lokier
2008-08-21 11:07   ` Jamie Lokier
2008-08-21 14:11   ` Jared Hulbert
2008-08-21 14:11     ` Jared Hulbert
2008-08-22  0:12     ` Greg Ungerer
2008-08-22  0:12       ` Greg Ungerer
2008-08-22  2:48       ` Jared Hulbert
2008-08-22  2:48         ` Jared Hulbert
2008-08-25  6:35         ` Greg Ungerer
2008-08-25  6:35           ` Greg Ungerer
2008-08-25 11:43           ` Jamie Lokier
2008-08-25 11:43             ` Jamie Lokier
2008-08-25 14:02             ` Greg Ungerer
2008-08-25 14:02               ` Greg Ungerer
2008-08-22 18:13       ` Jamie Lokier
2008-08-22 18:13         ` Jamie Lokier
2008-08-22 18:16         ` Jared Hulbert
2008-08-22 18:16           ` Jared Hulbert
2008-08-22 18:37           ` Jamie Lokier
2008-08-22 18:37             ` Jamie Lokier
2008-08-22 18:43             ` Jamie Lokier
2008-08-22 18:43               ` Jamie Lokier
2008-09-12 21:52               ` Jared Hulbert
2008-09-12 21:52                 ` Jared Hulbert
2008-09-15 16:34                 ` Jamie Lokier
2008-09-15 16:34                   ` Jamie Lokier
2008-09-15 19:43                   ` Jared Hulbert
2008-09-15 19:43                     ` Jared Hulbert
2008-09-19 19:20                     ` Trent Piepho
2008-09-19 19:20                       ` Trent Piepho
2008-09-16  6:57                   ` Ricard Wanderlof
2008-09-16  6:57                     ` Ricard Wanderlof
2008-09-16  6:57                     ` Ricard Wanderlof
2008-09-16 15:30                     ` Jared Hulbert
2008-09-16 15:30                       ` Jared Hulbert
2008-09-12 20:17             ` Jared Hulbert
2008-09-12 20:17               ` Jared Hulbert
2008-09-15 16:40               ` Jamie Lokier
2008-09-15 16:40                 ` Jamie Lokier
2008-08-21 23:46   ` Greg Ungerer [this message]
2008-08-21 23:46     ` Greg Ungerer
2008-08-22 18:10     ` Jamie Lokier
2008-08-22 18:10       ` Jamie Lokier
2008-08-22 14:54 ` Geert Uytterhoeven
2008-08-22 14:54   ` Geert Uytterhoeven
2008-08-22 15:19   ` Arnd Bergmann
2008-08-22 15:19     ` Arnd Bergmann
2008-08-22 16:51   ` Jared Hulbert
2008-08-22 16:51     ` Jared Hulbert
2008-08-25  9:37     ` Geert Uytterhoeven
2008-08-25  9:37       ` Geert Uytterhoeven
2008-08-25  9:37       ` Geert Uytterhoeven
2008-08-25 10:52       ` Carsten Otte
2008-08-25 10:52         ` Carsten Otte
2008-08-25 12:16     ` David Woodhouse
2008-08-25 12:16       ` David Woodhouse
2008-08-28 15:40     ` Geert Uytterhoeven
2008-08-28 15:40       ` Geert Uytterhoeven
2008-09-02 15:37       ` Geert Uytterhoeven
2008-09-02 15:37         ` Geert Uytterhoeven
2008-09-02 16:44         ` Jared Hulbert
2008-09-02 16:44           ` Jared Hulbert
2008-09-02 17:15           ` Jörn Engel
2008-09-02 17:15             ` Jörn Engel
2008-09-02 17:15             ` Jörn Engel
2008-09-02 17:47             ` Jared Hulbert
2008-09-02 17:47               ` Jared Hulbert
2008-09-02 18:33           ` Geert Uytterhoeven
2008-09-02 18:33             ` Geert Uytterhoeven
2008-08-22 22:09   ` Will Marone
2008-08-22 22:09     ` Will Marone
2008-08-25  7:23     ` Geert Uytterhoeven
2008-08-25  7:23       ` Geert Uytterhoeven

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=48ADFE65.1050007@snapgear.com \
    --to=gerg@snapgear.com \
    --cc=Linux-kernel@vger.kernel.org \
    --cc=cotte@de.ibm.com \
    --cc=jamie@shareable.org \
    --cc=jaredeh@gmail.com \
    --cc=joern@logfs.org \
    --cc=linux-embedded@vger.kernel.org \
    --cc=linux-mtd@lists.infradead.org \
    --cc=nickpiggin@yahoo.com.au \
    --cc=tim.bird@AM.SONY.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 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.