Date: Sat, 30 Oct 1999 21:24:21 +0000 (GMT) From: Terry Lambert <tlambert@primenet.com> To: nate@mt.sri.com Cc: tlambert@primenet.com, rjesup@wgate.com, imp@village.org, arch@freebsd.org Subject: Re: Racing interrupts Message-ID: <199910302124.OAA00920@usr06.primenet.com> In-Reply-To: <199910291851.MAA05434@mt.sri.com> from "Nate Williams" at Oct 29, 99 12:51:41 pm
next in thread | previous in thread | raw e-mail | index | archive | help
> > I don't believe in impossible > > OK, I want to fly w/out use of external devices. > > Oh, you mean with software? > > I want my computer to run 100X faster than it does now, w/out changing > any of the hardware! There is a difference between violation of physical laws, and a race window that is a result of a lack of code correctness. You have not demonstrated that the race window to which you refer is in fact an artifact of the hardware design, and not an artifact of the software design. You have practically admitted that this is the case, when you performed your analysis of the race in a PCMCIA/PCCARD utilyzing fast interrupts (answer: don't use fast interrupts, or make them an option for ejectable cards, which is defaulted to disabled). > > and I don't care about overhead if something is worth doing. > > Cool. I want you to start using my new compressed FS, which allows you > to store 3X as much data on your hard disk. Unfortunately, the overhead > of compressing/decompressing slows access to 1K/sec max., but it's worth > doing, so the overhead is irrelevant. > > In other words, do you realize how silly you sound? Not as silly as you sound, claiming that something which bounds your I/O to 1k/sec max is "worth doing". 8-). Note: to thwart your taking the I/O rate bounding strawman as a reson why PCMCIA/PCCARD devices should be allowed to use fast interrupts by default, I will quote Ed Lane: "I can make it go as fast as you want, so long as it doesn't have to work." Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-arch" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199910302124.OAA00920>