mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Nitin Gupta" <nitingupta910@gmail.com>
To: "Daniel Hazelton" <dhazelton@enter.net>
Cc: "Bret Towe" <magnade@gmail.com>,
	lkml <linux-kernel@vger.kernel.org>,
	linux-mm-cc@laptop.org,
	linuxcompressed-devel@lists.sourceforge.net,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Richard Purdie" <richard@openedhand.com>,
	"Satyam Sharma" <satyam.sharma@gmail.com>
Subject: Re: [RFC] LZO de/compression support - take 6
Date: Wed, 30 May 2007 10:49:45 +0530	[thread overview]
Message-ID: <4cefeab80705292219x31956353r308b0ed0a052071@mail.gmail.com> (raw)
In-Reply-To: <200705291932.04255.dhazelton@enter.net>

On 5/30/07, Daniel Hazelton <dhazelton@enter.net> wrote:
> I just noticed a bug in my testbed/benchmarking code. It's fixed, but I
> decided to compare version 6 of the code against the *unsafe* decompressor
> again. The results of the three runs I've put it through after changing it to
> compare against the unsafe decompressor were startling. `Tiny's` compressor
> is still faster - I've seen it be rated up to 3% faster. The decompressor,
> OTOH, when compared to the unsafe version (which is the comparison that
> started me on this binge of hacking), is more than 7% worse. About 11% slower
> on the original test against a C source file, and about 6% slower for random
> data.

Unsafe vs safe is within 10%. Its okay.

> However, looking at the numbers involved, I can't see a reason to keep
> the unsafe version around - the percentages look worse than they are - from 1
> to 3 microseconds.

Not just numbers. Most of applications cannot afford to use unsafe
versions anyway (like fs people).

(well, the compressed-cache people might want those extra
> usecs - but the difference will never be noticeable anywhere outside the
> kernel)
>
> DRH
>

compressed cache people require every single percent of that
performance. For now, ccaching is not ready for mainline (many things
need to be done). So, till then I will keep off the unsafe version. If
ever compressed caching is on its way to mainline _then_ I will try
and add back the unsafe version. But I see no other project that
really cares about unsafe version so it's okay to keep it off.


- Nitin

  reply	other threads:[~2007-05-30  5:20 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-05-28 14:34 Nitin Gupta
2007-05-28 14:40 ` Nitin Gupta
2007-05-28 14:49   ` Daniel Hazelton
2007-05-28 15:06     ` Nitin Gupta
2007-05-28 15:43       ` Adrian Bunk
2007-05-28 16:03         ` Nitin Gupta
2007-05-28 17:11           ` Adrian Bunk
2007-05-28 19:59             ` Daniel Hazelton
2007-05-28 20:18             ` Daniel Hazelton
2007-05-28 20:52               ` Daniel Hazelton
2007-05-29  5:55             ` Nitin Gupta
2007-05-29  8:08             ` Michael-Luke Jones
2007-05-29 11:40               ` Adrian Bunk
2007-05-29 12:03                 ` Nitin Gupta
2007-05-29 13:13                   ` Daniel Hazelton
2007-05-29 21:10             ` Jan Engelhardt
2007-05-29 21:26               ` Adrian Bunk
2007-05-30  5:31                 ` Nitin Gupta
2007-05-30 13:56                   ` Johannes Stezenbach
2007-05-30 14:24                     ` Satyam Sharma
2007-05-28 15:30   ` Adrian Bunk
2007-05-28 15:47     ` Nitin Gupta
2007-05-28 15:55       ` Daniel Hazelton
2007-05-28 17:01         ` Adrian Bunk
2007-05-28 19:51           ` Daniel Hazelton
2007-05-28 15:49     ` Daniel Hazelton
2007-05-28 22:57   ` Bret Towe
2007-05-29  5:48     ` Nitin Gupta
2007-05-29 13:09       ` Daniel Hazelton
2007-05-28 22:53 ` Bret Towe
2007-05-28 22:58   ` Bret Towe
2007-05-29  5:58   ` Nitin Gupta
2007-05-29 20:14     ` Daniel Hazelton
2007-05-29 20:33       ` Daniel Hazelton
2007-05-29 21:48         ` Daniel Hazelton
2007-05-29 23:32     ` Daniel Hazelton
2007-05-30  5:19       ` Nitin Gupta [this message]
2007-05-29  8:17 ` Makefile question (was [RFC] LZO de/compression support - take 6) Michael-Luke Jones
2007-05-29 10:41   ` Satyam Sharma
2007-05-29 10:51     ` Michael-Luke Jones
2007-05-29 11:27       ` Satyam Sharma
2007-05-29 13:33         ` JFFS2 using 'private' zlib header " Michael-Luke Jones
2007-05-29 13:43           ` Daniel Hazelton
2007-05-29 15:15             ` Satyam Sharma
2007-05-29 16:20               ` Daniel Hazelton
2007-05-30  5:31               ` Mark Adler
2007-05-30 13:05                 ` Daniel Hazelton
2007-05-30 13:30                 ` Satyam Sharma
2007-05-30 23:02                   ` Mark Adler
2007-05-30 23:26                     ` Daniel Hazelton
2007-06-01  3:06                     ` Daniel Hazelton
2007-06-01 17:24                       ` Satyam Sharma
2007-05-30 13:41               ` Artem Bityutskiy
2007-05-30 15:46                 ` Artem Bityutskiy
2007-05-30 16:12                   ` Satyam Sharma
2007-05-30 16:43                     ` Artem Bityutskiy
2007-05-29 20:48 ` [RFC] LZO de/compression support - take 6 Jan Engelhardt
2007-05-30  5:54   ` Nitin Gupta
2007-05-30  8:31     ` Jan Engelhardt
2007-05-30 10:47       ` Nitin Gupta
2007-05-31 12:34 ` Nitin Gupta
2007-05-31 18:21   ` Satyam Sharma

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=4cefeab80705292219x31956353r308b0ed0a052071@mail.gmail.com \
    --to=nitingupta910@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=dhazelton@enter.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm-cc@laptop.org \
    --cc=linuxcompressed-devel@lists.sourceforge.net \
    --cc=magnade@gmail.com \
    --cc=richard@openedhand.com \
    --cc=satyam.sharma@gmail.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®