From owner-freebsd-hackers Sat Sep 2 16:15:54 1995 Return-Path: hackers-owner Received: (from majordom@localhost) by freefall.FreeBSD.org (8.6.11/8.6.6) id QAA10567 for hackers-outgoing; Sat, 2 Sep 1995 16:15:54 -0700 Received: from etinc.com (etinc-gw.new-york.net [165.254.13.209]) by freefall.FreeBSD.org (8.6.11/8.6.6) with ESMTP id QAA10561 for ; Sat, 2 Sep 1995 16:15:52 -0700 Received: from websurfer.etinc.com (websurfer.etinc.com [204.141.95.5]) by etinc.com (8.6.11/8.6.9) with SMTP id TAA00201 for ; Sat, 2 Sep 1995 19:15:57 -0400 Date: Sat, 2 Sep 1995 19:15:57 -0400 Message-Id: <199509022315.TAA00201@etinc.com> X-Sender: dennis@etinc.com X-Mailer: Windows Eudora Version 2.0.3 Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" To: hackers@freebsd.org From: dennis@etinc.com (dennis) Subject: Re: novell ne2000 cards with FreeBSD...opinions? Sender: hackers-owner@freebsd.org Precedence: bulk >>Date: Sun, 3 Sep 1995 07:36:08 +1000 >>From: Bruce Evans >>To: bde@zeta.org.au, davidg@Root.COM >>Subject: Re: novell ne2000 cards with FreeBSD...opinions? >>Cc: hackers@freebsd.org >>Sender: hackers-owner@freebsd.org >>Precedence: bulk >> >>>>Shared memory on my NE2000/WD8013EBT card is 50% faster, but that isn't >>>>saying much. The driver spends half its time bcopying to the shared >>>>memory instead of more that half its time doing explicit i/o instructions. >>>>The speeds are something like: >>>> >>>> i/o instructions: 2MB/sec >>>> bcopy: 3MB/sec >>>> IDE disk controllers: 3.3MB/sec PIO mode 0 (or 1?) spec >>>> 8MHz ISA bus max: 4MB/sec >> >>> Your bus is slow. The 8013 usually has memory speeds of 4MB/sec. >> >>Isn't a slow bus the usual case? On one of my systems, the (AMI) BIOS >>has options for 1-5 bus wait states but not 0. I use 1. There are >>options to use a faster bus speed but I don't use them. On another of >>my systems, the (AMI) BIOS doesn't have any bus options. It apparently >>defaults to 2 bus wait states. >> All machines are different. Or more accurately all motherboards are different, even if they use the same chip sets. The tuning parameters that are available are sometimes quite deceptive and certainly not equal between two different MBs. The term "wait-state" is really not correct in this context. A wait state implies an additional bus cycle, but does not necessarily tell you what the cycle was like before adding 1. Some MBs have long address setup cycles, some have extra cycles between certain types of access cycles, and some have longer standard cycles than others. I've had motherboards that I couldn't get 20Mbs at 12Mhz and 0 wait states, and others that I've gotten over 50Mbs. Some MBs are "safe"...they work with all cards but they're pigs. Every motherboard is a new experience. Dennis