From xemacs-m  Fri Jan 10 16:22:13 1997
Received: from altair.xemacs.org (steve@xemacs.miranova.com [206.190.83.19])
          by xemacs.org (8.8.4/8.8.4) with ESMTP
	  id QAA25349 for <xemacs-beta@xemacs.org>; Fri, 10 Jan 1997 16:22:11 -0600 (CST)
Received: (from steve@localhost)
          by altair.xemacs.org (8.8.4/8.8.4)
	  id OAA15556; Fri, 10 Jan 1997 14:32:13 -0800
Sender: steve@xemacs.org
To: xemacs-beta@xemacs.org
Subject: Re: Inserting into a buffer.
References: <Pine.SGI.3.95.961219034733.22578D-100000@shellx.best.com> <rvn2v965c3.fsf@sdnp5.ucsd.edu> <m24thhawcp.fsf@altair.xemacs.org> <rvvi96m11p.fsf@sdnp5.ucsd.edu> <kigohexpnqc.fsf@jagor.srce.hr>
X-Url: http://www.miranova.com/%7Esteve/
Mail-Copies-To: never
X-Face: #!T9!#9s-3o8)*uHlX{Ug[xW7E7Wr!*L46-OxqMu\xz23v|R9q}lH?cRS{rCNe^'[`^sr5"
 f8*@r4ipO6Jl!:Ccq<xoV[Qz2u8<8-+Vwf2gzJ44lf_/y9OaQ`@#Q65{U4/TC)i2`~/M&QI$X>p:9I
 OSS'2{-)-4wBnVeg0S\O4Al@)uC[pD|+
X-Attribution: sb
From: Steven L Baur <steve@miranova.com>
In-Reply-To: Hrvoje Niksic's message of 10 Jan 1997 16:13:31 +0100
Mime-Version: 1.0 (generated by tm-edit 7.100)
Content-Type: text/plain; charset=US-ASCII
Date: 10 Jan 1997 14:32:11 -0800
Message-ID: <m23ew9xitw.fsf@altair.xemacs.org>
Lines: 38
X-Mailer: Red Gnus v0.80/XEmacs 20.0

Hrvoje Niksic writes:

> David Moore (dmoore@ucsd.edu) wrote:
>> Steven L Baur <steve@miranova.com> writes:
>> > That must be coming from the relocating allocator.  Try running the
>> > same test with it disabled from configure.

> Speaking of which, does Emacs have something like the relocating
> alocator?

Yes.  Guess who told rms about it? :-)

>> Results on Hrvoje's benchmark are improved under solaris if the
>> relocating allocator is turned off.  (180sec->150sec with -O4 on 19.15b7
>> for sparcserver5 with 64M).  I may look into the code, because I don't
>> see why mmap should be costing that much more.

> It's probably not mmap syscall that is costing, but the fact that
> *anything* is called, as opposed to the no-relocation case.

This is probably system dependent.  I've watched how much effort Linus
has spent optimizing it, and I wonder how much work Sun did with
Solaris.

>> The patch below speeds up inserts and other operaations on
>> buffers with no extents in them.  On Hrvoje's benchmark: 180sec->120sec.

> It's a great speedup (33%) -- thanks!  I believe this could influence
> many other benchmarks, the speed of which might have in fact depended
> on the speed of inserting into the buffer.

Yup.  It would be a good idea to spend some time benchmarking with
tomorrow's betas.  David's patch is in both 19.15 and 20.0.
-- 
steve@miranova.com baur
Unsolicited commercial e-mail will be billed at $250/message.
"That Bill Clinton.  He probably doesn't know how to log on to the
Internet."  -- Rush Limbaugh, noted Computer Expert

