From:	Martin Str|mberg <ams AT ludd DOT luth DOT se>
Message-Id:	<200009251929.VAA06410@father.ludd.luth.se>
Subject:	Re: bnu2951b.zip's ar is slow
In-Reply-To:	<5567-Mon25Sep2000221100+0300-eliz@is.elta.co.il> from Eli Zaretskii at "Sep 25, 2000 10:11:01 pm"
To:	eliz AT is DOT elta DOT co DOT il (Eli Zaretskii)
Date:	Mon, 25 Sep 2000 21:29:40 +0200 (MET DST)
Cc:	djgpp-workers AT delorie DOT com (DJGPP-WORKERS)
X-Mailer:	ELM [version 2.4ME+ PL54 (25)]
MIME-Version:	1.0
Reply-To:	djgpp-workers AT delorie DOT com
Errors-To:	nobody AT delorie DOT com
X-Mailing-List:	djgpp-workers AT delorie DOT com
X-Unsubscribes-To:	listserv AT delorie DOT com

According to Eli Zaretskii:
> > From: Martin Str|mberg <ams AT ludd DOT luth DOT se>
> > What's up with ar from bnu2951b.zip? On my 386, ar-ing libc with ar
> > from bnu281b.zip takes 246 s and ar from bnu2951b.zip takes 16406
> > s. And that's not a typo.
> 
> How much memory does that 386 screamer have?  Is it possible that the
> large performance hit is due to paging because of the larger memory
> required by bnu2951b, rather than to actually slower code?

4 MiB.

I know that paging can make performance go out the window, but this is
a little extreme; if it only was three or four times as slow or even
ten, but ~65 times?!

I haven't been sitting beside the computer the whole time while it's
been aring, but I've passed it occasionally and it's not been swapping
like mad. Rather the impression is that it hardly touches the disk...


Right,

						MartinS

- Raw text -