From owner-freebsd-hackers Thu Feb 1 00:45:02 1996 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.7.3/8.7.3) id AAA07126 for hackers-outgoing; Thu, 1 Feb 1996 00:45:02 -0800 (PST) Received: from irz301.inf.tu-dresden.de (irz301.inf.tu-dresden.de [141.76.1.11]) by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id AAA07110 for ; Thu, 1 Feb 1996 00:44:55 -0800 (PST) Received: from sax.sax.de by irz301.inf.tu-dresden.de (8.6.12/8.6.12-s1) with ESMTP id JAA29365; Thu, 1 Feb 1996 09:43:09 +0100 Received: by sax.sax.de (8.6.11/8.6.12-s1) with UUCP id JAA27604; Thu, 1 Feb 1996 09:43:08 +0100 Received: (from j@localhost) by uriah.heep.sax.de (8.7.3/8.6.9) id JAA26219; Thu, 1 Feb 1996 09:35:48 +0100 (MET) From: J Wunsch Message-Id: <199602010835.JAA26219@uriah.heep.sax.de> Subject: Re: Swapping (was Re: Good news -- pipe stuff) To: freebsd-hackers@freebsd.org (FreeBSD hackers) Date: Thu, 1 Feb 1996 09:35:48 +0100 (MET) Cc: jehamby@lightside.com Reply-To: joerg_wunsch@uriah.heep.sax.de (Joerg Wunsch) In-Reply-To: <199601312213.PAA17374@rocky.sri.MT.net> from "Nate Williams" at Jan 31, 96 03:13:07 pm X-Phone: +49-351-2012 669 X-Mailer: ELM [version 2.4 PL23] MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit Sender: owner-hackers@freebsd.org Precedence: bulk As Nate Williams wrote: > > Another thing to look into, although I don't have a benchmark on this, but > > FreeBSD has a nasty tendency to "bind" during heavy VM/disk activity. I > > don't know if this is because the IDE driver is CPU intensive, or if this > > affects people (to a lesser extent) with SCSI drives. > > This is an IDE thing. Basically, the system must uses lots more CPU and > is much less effecient than using the SCSI drivers. Just to add one more point here: I can burn a CD-R while running full multi-user under FreeBSD. Of course, this is a SCSI-only machine, and it's got 32 MB RAM, but then this allows me to run full X11 *and* burn a CD-R simultaneously. Since the CD-R's are _very_ picky when it comes to a low but steady data-flow, this basically proves that the system does not ``freeze'' for more than ~ 1 second or so, otherwise the CD-R would stop accepting data. People usually yell at us when we declare IDE to `crap' somewhere in Usenet... :) -- cheers, J"org joerg_wunsch@uriah.heep.sax.de -- http://www.sax.de/~joerg/ -- NIC: JW11-RIPE Never trust an operating system you don't have sources for. ;-)