From owner-freebsd-isdn Sat Oct 10 09:49:42 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id JAA27828 for freebsd-isdn-outgoing; Sat, 10 Oct 1998 09:49:42 -0700 (PDT) (envelope-from owner-freebsd-isdn@FreeBSD.ORG) Received: from uranus.factum-data.de (uranus.factum-data.de [195.238.147.34]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id JAA27823 for ; Sat, 10 Oct 1998 09:49:39 -0700 (PDT) (envelope-from p@znet.de) Received: from pascal by uranus.factum-data.de with local (Exim 1.82 #2) id 0zS2Cq-0004m3-00; Sat, 10 Oct 1998 18:49:24 +0200 Message-ID: <19981010184901.45843@uranus.factum-data.de> Date: Sat, 10 Oct 1998 18:49:01 +0200 From: Pascal Gienger To: Christoph Weber-Fahr Subject: Re: what's wrong with a1 and irq 2 ? References: <199810091511.RAA10239@helena.otelo-call.de> <199810092100.XAA10590@helena.otelo-call.de> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit X-Mailer: Mutt 0.88 In-Reply-To: <199810092100.XAA10590@helena.otelo-call.de>; from Christoph Weber-Fahr on Fri, Oct 09, 1998 at 11:00:54PM +0200 Sender: owner-freebsd-isdn@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org '`date`' ergab 'Fri Oct 09 11:00:54 MET DST 1998', als Christoph Weber-Fahr schrieb: > This effect is still there. I would conclude that it is not related > to the use of IRQ 2/9 and probably caused by the high interrupt load. Hmm... Here with my 486 DX 33 there are approx 270-300 Interrupts per second. Not a very tough job for the CPU... > Is Syscons particularily affected by high interrupt load ? I am experiencing something similar: When doing fast screen switches or scrolling operations with syscons, the isic-driver looses packets, resulting in rerequesting TCP-Packets. But I never got a slugghish or "slow" screen update due to isic0. Perhaps priorities are somehow reversed in my setup? Funny enough: With the old BISDN, excessive work with syscons did not lead to loss of packets of the tel-driver of BISDN. The loss of packets is only reproduced using syscons. Neither with the VT-Emulation (pcvt) nor with graphical things like X11. > I don't think this interrupt stuff is 'normal'. This is eating 10% of the > computing power of a 486/50 with only one B channel used. > On the other hand I can put the same card into a lousy 386sx/16 and > blast 2 simultaneous IDTrans sesssions with full speed over both B > channels under good plain old DOS. (I've done that!). There > must be some problem in the driver somewhere, which AVM's own > DOS CAPI driver doesn't have. Hmm i can dial up 2 providers and do a full 7,5kbyte/sec-ftp with each provider simultaneously without a very big noticeable machine load as far as no "CTRL-ALT-F"-Key is pressed to switch to syscons... ;-) Pascal -- _ _ | Pascal Gienger |_> <_\ |_||_ - magazin für konstanz pg@paul-magazin.de (Redaktion) | p@znet.de (privat) http://www.paul-magazin.de/ Tel. 07531/52709 Fax 07531/52739 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-isdn" in the body of the message