From owner-freebsd-hackers Wed Jan 28 21:51:38 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id VAA02426 for hackers-outgoing; Wed, 28 Jan 1998 21:51:38 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from labinfo.iet.unipi.it (labinfo.iet.unipi.it [131.114.9.5]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id VAA02413 for ; Wed, 28 Jan 1998 21:51:30 -0800 (PST) (envelope-from luigi@labinfo.iet.unipi.it) Received: from localhost (luigi@localhost) by labinfo.iet.unipi.it (8.6.5/8.6.5) id FAA05338; Thu, 29 Jan 1998 05:20:25 +0100 From: Luigi Rizzo Message-Id: <199801290420.FAA05338@labinfo.iet.unipi.it> Subject: Re: Busmastering code for IDE drives in 2.2.6? To: bac@sympatico.ca (Brian Campbell) Date: Thu, 29 Jan 1998 05:20:25 +0100 (MET) Cc: freebsd-hackers@FreeBSD.ORG In-Reply-To: <19980128185953.56562@pobox.com> from "Brian Campbell" at Jan 28, 98 06:59:34 pm X-Mailer: ELM [version 2.4 PL23] Content-Type: text Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG X-To-Unsubscribe: mail to majordomo@FreeBSD.org "unsubscribe hackers" > > > with the big code merges into 2.2.5-STABLE over the last weeks, I wonder ... > That's the easy answer. > > It requires two files (/sys/pci/ide_pci.c and /sys/ide_pcireg.h) to be added, > two files (/sys/i386/isa/wd.c /sys/i386/isa/wdreg.h) to be replaced, and > a line to be changed in /sys/i386/conf/files.i386. > > I've been running with it in 2.2-x since it was announced and it > works just fine. Hardly a dramatic change. However, I've asked > the same question before and met with the same disapproving glare. perhaps you can put together a small .tgz which goes into some "experimental" or "unsupported" directory so that people can try it even if it's not into the source tree. I did the same with PnP and snd driver and I think it was useful to several people. Talk to Jordan about this. NOTES: 1) I don't believe that there is any risk of the "unsupported" dir becoming a kitchen sink, especially if we restrict to features/kernel modules which are considered of some interest or already are in -current and have little impact on the rest of the system (i.e. I would not expect a smp.tgz package, but I _would like_ to see there the various splashkits or the cbq package which was posted some time ago, or possibly an IPV6 implementation...) 2) about the IDE busmastering code, I still would like to see some good benchmark result showing when/how it improves performance. The only comment I have seen (from the author ?) is that it improves throughput by a few percent under moderate load, but no data on how it behaves say with concurrent activity on the IDE bus, or with heavily loaded systems. Cheers Luigi -----------------------------+-------------------------------------- Luigi Rizzo | Dip. di Ingegneria dell'Informazione email: luigi@iet.unipi.it | Universita' di Pisa tel: +39-50-568533 | via Diotisalvi 2, 56126 PISA (Italy) fax: +39-50-568522 | http://www.iet.unipi.it/~luigi/ _____________________________|______________________________________