linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: "John Stoffel" <john@stoffel.org>
Cc: Jeff Garzik <jeff@garzik.org>,
	Roman Zippel <zippel@linux-m68k.org>,
	ext2-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org,
	cmm@us.ibm.com, linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH 2/9] sector_t format string
Date: Thu, 10 Aug 2006 09:54:13 -0700	[thread overview]
Message-ID: <20060810095413.3797b4a2.akpm@osdl.org> (raw)
In-Reply-To: <17627.23974.848640.278643@stoffel.org>

On Thu, 10 Aug 2006 12:24:06 -0400
"John Stoffel" <john@stoffel.org> wrote:

> >>>>> "Roman" == Roman Zippel <zippel@linux-m68k.org> writes:
> 
> Roman> If you force everyone to use 64bit sector numbers, I don't
> Roman> understand how you can claim "still working just fine on
> Roman> 32bit"?  At some point ext4 is probably going to be the de
> Roman> facto standard, which very many people want to use, because it
> Roman> has all the new features, which won't be ported to ext2/3. So I
> Roman> still don't understand, what's so wrong about a little tuning
> Roman> in both directions?
> 
> The problem as I see it, is that you want extents, but you don't want
> the RAM/DISK/ROM penalty of 64bit blocks, since embedded devices won't
> ever go past the existing ext3 sizes, right?

For ext3 on x86:

CONFIG_LBD=y:

box:/usr/src/25> size fs/jbd/jbd.o fs/ext3/ext3.o
   text    data     bss     dec     hex filename
  51076       8      32   51116    c7ac fs/jbd/jbd.o
  87466    1020       4   88490   159aa fs/ext3/ext3.o

CONFIG_LBD=n:

box:/usr/src/25> size fs/jbd/jbd.o fs/ext3/ext3.o
   text    data     bss     dec     hex filename
  51133       8      32   51173    c7e5 fs/jbd/jbd.o
  87679    1020       4   88703   15a7f fs/ext3/ext3.o

That's a grand total of 270 bytes of text saved.  aka 0.19%.

We'll save four bytes in the inode (unlikely to save anything due to slab
packing).

We'll save 12 bytes against open-for-writing files due to
ext3_block_alloc_info shrinkage (unlikely to save anything due to kmalloc
size roundup).

IOW, unless I've missed something major, we're looking at a total saving of
around a 16th of a page.  We can save more than that any day of the week by
going around and deleting some crap from somewhere.  We can surely save
more than this by taming ext4's inlining frenzy.

I'd expect any runtime savings to be similarly modest.

-------------------------------------------------------------------------
Using Tomcat but need to do more? Need to support web services, security?
Get stuff done quickly with pre-integrated technology to make your job easier
Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642

  parent reply	other threads:[~2006-08-10 16:54 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-08-10  1:20 [PATCH 2/9] sector_t format string Mingming Cao
2006-08-10  6:40 ` Andrew Morton
2006-08-10 11:05   ` Roman Zippel
2006-08-10 12:02     ` Jeff Garzik
2006-08-10 12:24       ` Roman Zippel
2006-08-10 12:25         ` Jeff Garzik
2006-08-10 12:30           ` Roman Zippel
2006-08-10 12:33             ` Jeff Garzik
2006-08-10 13:08               ` Roman Zippel
2006-08-10 13:14                 ` Jeff Garzik
2006-08-10 13:27                   ` Roman Zippel
2006-08-10 13:30                     ` Jeff Garzik
2006-08-10 13:52                       ` Roman Zippel
2006-08-10 14:04                         ` [Ext2-devel] " Eric Sandeen
2006-08-10 14:19                           ` Roman Zippel
2006-08-10 14:21                             ` Jeff Garzik
2006-08-10 14:35                               ` Roman Zippel
2006-08-10 14:06                         ` Jeff Garzik
2006-08-10 14:24                           ` Roman Zippel
2006-08-10 14:26                             ` Jeff Garzik
2006-08-10 14:41                               ` Roman Zippel
2006-08-10 16:24                     ` John Stoffel
2006-08-10 16:43                       ` Roman Zippel
2006-08-10 16:54                       ` Andrew Morton [this message]
2006-08-10 17:24                         ` Roman Zippel
2006-08-10 15:31   ` [Ext2-devel] " Theodore Tso
2006-08-10 16:37     ` Roman Zippel
2006-08-10 21:59       ` [Ext2-devel] " Mingming Cao
2006-08-10 19:17   ` Joel Becker
2006-08-10 19:44     ` Alexey Dobriyan
2006-08-10 19:57       ` Andrew Morton
2006-08-10 20:41         ` Alexey Dobriyan
2006-08-10 20:17       ` Jeff Mahoney
2006-08-11  5:57         ` Jan Engelhardt
2006-08-11  8:31           ` Bernd Petrovitsch
2006-08-11  9:07             ` Jan Engelhardt
2006-08-11 14:48           ` Jeff Mahoney
2006-08-11  0:59   ` Mingming Cao
2006-08-11  2:11     ` Eric Sandeen
2006-08-11 22:06     ` Mingming Cao

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=20060810095413.3797b4a2.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=cmm@us.ibm.com \
    --cc=ext2-devel@lists.sourceforge.net \
    --cc=jeff@garzik.org \
    --cc=john@stoffel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=zippel@linux-m68k.org \
    /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).