From owner-freebsd-hackers Thu Aug 31 20:01:59 1995 Return-Path: hackers-owner Received: (from majordom@localhost) by freefall.FreeBSD.org (8.6.11/8.6.6) id UAA07373 for hackers-outgoing; Thu, 31 Aug 1995 20:01:59 -0700 Received: from localhost (localhost [127.0.0.1]) by freefall.FreeBSD.org (8.6.11/8.6.6) with SMTP id UAA07365 ; Thu, 31 Aug 1995 20:01:56 -0700 Message-Id: <199509010301.UAA07365@freefall.FreeBSD.org> X-Authentication-Warning: freefall.FreeBSD.org: Host localhost didn't use HELO protocol To: "Rodney W. Grimes" cc: FreeBSD-hackers@freebsd.org Subject: Re: 4GB Drives In-reply-to: Your message of "Thu, 31 Aug 95 18:58:38 PDT." <199509010158.SAA13422@gndrsh.aac.dev.com> Date: Thu, 31 Aug 1995 20:01:55 -0700 From: "Justin T. Gibbs" Sender: hackers-owner@freebsd.org Precedence: bulk >> >> Hmm. Are you sure that the drive will not disconnect even for a short ti >me >> >> after receiving its command? >> > >> >Darn sure, I effectivly disabled disconnect/reconnect by tweaking the >> >buffer full/empty ratios and a few other parameters in mode page 2. >> >> Why not just turn off disconnections in SCSI-Select? :) > >Because I can't do that on an NCR 53C825 :-). Ahh. Can't help you there. There was a time when the aic7xxx driver had slightly slower per transaction times than the NCR cards, but then I realized that I was still bzeroing SCB structures for each command. Although when the driver first started, an SCB entry was only 32 bytes big, now the SCB holds almost 2k of data (each SCB has an array of 255 SG segments as well as other book-keeping info) and the bzero was totally unnecessary. Needless to say, after I realized my mistake, the transaction times fell through the floor. I'll think you'll be plesantly surprised with the performance of the aic7xxx driver especially for your particular application. >> You will need to pause the sequencer in order to change the status >> of the led anyway if you do it from the kernel, so the edges should >> be distinguishable between kernel blinks and sequencer blinks. > >I well be blinking the controller LED from the sequencer, not the kernel, >I have lots of blinking signals from the kernel, I have 8 x 16 bits worth >of them if I so desire :-). :) > >-- >Rod Grimes rgrimes@gndrsh.aac.dev.com >Accurate Automation Company Reliable computers for FreeBSD -- Justin T. Gibbs =========================================== Software Developer - Walnut Creek CDROM FreeBSD: Turning PCs into workstations ===========================================