From: Tim Bird <tim.bird@am.sony.com>
To: Robert Schwebel <r.schwebel@pengutronix.de>
Cc: Bill Gatliff <bgat@billgatliff.com>,
David VomLehn <dvomlehn@cisco.com>,
linux-embedded@vger.kernel.org,
Juergen Beisert <jbe@pengutronix.de>,
Sascha Hauer <sha@pengutronix.de>,
Wolfram Sang <wsa@pengutronix.de>
Subject: Re: flicker free booting
Date: Fri, 31 Jul 2009 18:26:54 -0700 [thread overview]
Message-ID: <4A7399DE.3000904@am.sony.com> (raw)
In-Reply-To: <20090731200555.GF29245@pengutronix.de>
Robert Schwebel wrote:
> On Fri, Jul 31, 2009 at 12:48:37PM -0700, Tim Bird wrote:
>>> Those fractions-of-seconds boot times are beyond the reach of the
>>> 200 MHz-class ARM9 processors and similar, where it takes two or
>>> three seconds just to load and uncompress the kernel from NOR or
>>> NAND flash.
>> While I don't disagree from a practical standpoint - at Sony using XIP
>> we have been able to finish kernel boot on a 192 MHZ ARM9 in 186
>> milliseconds. In the lab, anyway?
>
> Wow, that's pretty fast; if that would be possible for standard
> scenarios, it would indeed be better to do everything on the kernel
> side.
>
> Can you elaborate about the details of that experiment? Was that normal
> XIP from NOR? What size has this kernel been?
This was done quite some time ago, and it looks like my memory was
not too good. According to slides I did at the time, it was
actually 110 milliseconds. I'm sure this was a 2.4 kernel (likely
2.4.20). I couldn't find the size of the kernel used in the test, but
I think it was about 800k, uncompressed. (I'm not positive, though.)
It was normal XIP from NOR flash.
See slides 21 and 22 in the following:
http://elinux.org/images/7/78/ReducingStartupTime_v0.8.pdf
Here is some salient data:
With Compression W/ O Compression XIP
Copy 56 msec 120 msec 0 msec
Decompression 545 msec 0 msec 0 msec
Kernel execution 88 msec 88 msec 110 msec
Total: 689 msec 208 msec 110 msec
Note that copy time went up when going from a compressed to an
uncompressed kernel. Decompression time went down (to 0, no
surpise). When XIP was used, both copy time and decompression
time were eliminated, but kernel execution time for the boot
went from 88 msec to 110 msec. So XIP did incur a pretty
hefty runtime penalty.
Aaahhh, 2.4. The kernel was simpler in those days... :-)
-- Tim
=============================
Tim Bird
Architecture Group Chair, CE Linux Forum
Senior Staff Engineer, Sony Corporation of America
=============================
next prev parent reply other threads:[~2009-08-01 1:26 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-02 15:22 Representing Embedded Architectures at the Kernel Summit James Bottomley
2009-06-02 17:29 ` Josh Boyer
2009-06-02 17:42 ` James Bottomley
2009-06-02 17:52 ` David VomLehn
2009-06-02 18:25 ` James Bottomley
2009-06-02 18:51 ` Josh Boyer
2009-06-02 19:30 ` Tim Bird
2009-06-02 20:37 ` [Ksummit-2009-discuss] " James Bottomley
2009-06-02 20:44 ` Bill Gatliff
2009-06-02 21:34 ` Robert Schwebel
2009-06-03 3:35 ` Greg KH
[not found] ` <20090731152617.GW29245@pengutronix.de>
2009-07-31 15:53 ` flicker free booting Robert Schwebel
2009-07-31 18:03 ` David VomLehn
2009-07-31 18:09 ` Robert Schwebel
2009-07-31 18:42 ` Bill Gatliff
2009-08-03 8:19 ` Sascha Hauer
2009-08-03 8:37 ` Geert Uytterhoeven
2009-07-31 18:46 ` Bill Gatliff
2009-07-31 19:48 ` Tim Bird
2009-07-31 19:51 ` Bill Gatliff
2009-07-31 20:05 ` Robert Schwebel
2009-08-01 1:26 ` Tim Bird [this message]
2009-07-31 19:25 ` Bill Gatliff
2009-08-01 14:25 ` Jamie Lokier
2009-06-03 0:03 ` [Ksummit-2009-discuss] Representing Embedded Architectures at the Kernel Summit David VomLehn
2009-06-03 0:52 ` Eric W. Biederman
2009-06-03 1:42 ` Steven Rostedt
2009-06-02 22:21 ` Jean-Christophe PLAGNIOL-VILLARD
2009-06-03 6:24 ` [Ksummit-2009-discuss] " Ralf Baechle
2009-06-10 23:13 ` Kumar Gala
2009-06-14 3:48 ` Grant Likely
2009-06-10 23:08 ` Kumar Gala
2009-06-02 17:29 ` Grant Likely
2009-06-02 17:45 ` David VomLehn
2009-06-02 18:46 ` Grant Likely
2009-06-02 17:48 ` James Bottomley
2009-06-03 12:17 ` Mark Brown
2009-06-04 18:18 ` Grant Likely
2009-06-02 21:10 ` Russell King
2009-06-02 21:16 ` Bill Gatliff
2009-06-02 21:16 ` Bill Gatliff
2009-06-02 21:16 ` Bill Gatliff
2009-06-04 20:15 ` Grant Likely
2009-06-02 21:18 ` Geert Uytterhoeven
2009-06-02 21:18 ` Geert Uytterhoeven
2009-06-02 21:18 ` Geert Uytterhoeven
2009-06-03 7:07 ` [Ksummit-2009-discuss] " Ralf Baechle
2009-06-02 21:40 ` Robert Schwebel
2009-06-02 21:40 ` Robert Schwebel
2009-06-02 21:40 ` Robert Schwebel
2009-06-02 21:48 ` Russell King
2009-06-04 20:08 ` Grant Likely
2009-06-04 20:08 ` Grant Likely
2009-06-04 20:08 ` Grant Likely
[not found] ` <3340601010994331832@unknownmsgid>
2009-06-04 20:24 ` Grant Likely
2009-06-03 6:53 ` [Ksummit-2009-discuss] " Ralf Baechle
2009-06-03 13:04 ` Catalin Marinas
2009-06-03 13:18 ` Josh Boyer
2009-06-03 13:45 ` Catalin Marinas
2009-06-03 14:11 ` Josh Boyer
2009-06-03 14:06 ` Jean-Christophe PLAGNIOL-VILLARD
2009-06-03 16:19 ` James Bottomley
2009-06-03 17:09 ` Russell King
2009-06-03 18:43 ` Andrew Morton
2009-06-03 19:01 ` James Bottomley
2009-06-04 3:11 ` David VomLehn (dvomlehn)
2009-06-04 3:24 ` Mike Frysinger
2009-06-04 3:24 ` Mike Frysinger
2009-06-04 9:23 ` Mel Gorman
2009-06-03 19:08 ` Catalin Marinas
2009-06-10 9:42 ` Thomas Petazzoni
2009-06-16 6:42 ` Mike Rapoport
2009-06-16 8:06 ` Mike Frysinger
2009-06-16 8:06 ` Mike Frysinger
2009-06-16 12:19 ` [Ksummit-2009-discuss] " Ralf Baechle
2009-06-17 4:26 ` H. Peter Anvin
2009-06-17 15:04 ` Ralf Baechle
2009-06-17 17:14 ` H. Peter Anvin
2009-06-16 16:06 ` Grant Likely
2009-06-16 18:18 ` Jamie Lokier
2009-06-16 19:28 ` Grant Likely
2009-06-16 20:07 ` Jamie Lokier
2009-06-16 20:10 ` Marcel Holtmann
2009-06-16 21:04 ` Grant Likely
2009-06-18 3:05 ` Paul Mundt
2009-06-17 14:31 ` Kumar Gala
2009-06-18 2:51 ` Paul Mundt
2009-06-19 2:59 ` Kumar Gala
2009-06-19 3:00 ` Paul Mundt
2009-06-19 7:53 ` Kumar Gala
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=4A7399DE.3000904@am.sony.com \
--to=tim.bird@am.sony.com \
--cc=bgat@billgatliff.com \
--cc=dvomlehn@cisco.com \
--cc=jbe@pengutronix.de \
--cc=linux-embedded@vger.kernel.org \
--cc=r.schwebel@pengutronix.de \
--cc=sha@pengutronix.de \
--cc=wsa@pengutronix.de \
/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.