Date: Thu, 3 Oct 2002 15:56:26 -0700 (PDT) From: Nate Lawson <nate@root.org> To: attila! <attila@hun.org> Cc: "FreeBSD 5.0-CURRENT" <current@freebsd.org> Subject: RE: aic7890/91 controller Message-ID: <Pine.BSF.4.21.0210031550140.92684-100000@root.org> In-Reply-To: <20021003165514.9dv685621@hun.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, 3 Oct 2002, attila! wrote: > Sent: Thu, 3 Oct 2002 05:20:08 +0200 by marius@alchemy.franken.de > + Sent: Wed, 2 Oct 2002 19:53:27 -0700 by Scott Long > + * On Thu, 3 Oct 2002, attila! wrote: > + * > Adaptec's > + * > documentation expliciely states that the bus speed is the > + * > rate of the _slowest_ device on the channel. > + * > + * No it does not. > + > + Well, the whole bus will switch to SE-speed if a SE-device > + is connected, guess that's what he meant. > > Well, I won't argue with the man from Adaptec, but if I > use a 68 to 50 pin adaptor, the channel will not operate > at 160 MB/sec (80 x 16 bits wide) since the differential > lines are hosed. It may not have been Adaptec > documentation specific to the aic7899, but I have seen > more than one reference to the ills of mixing > high-speed differential and 50 pin SE devices. The > reasons are blatantly obvious. Scott was right, you are right (after clarifying your point). If you have two differential devices (or 2 SE), the bus will not be "the rate of the slowest device" as you originally said. However, if you mix differential with SE, the max speed of the bus will be SE (as you later said). Please don't confuse device speed with bus speed. You can have a tape drive on a differential U320 bus that can only read at 1 MB/sec at the same time a set of 10k RPM drives on the same bus read at 55 MB/sec each. -Nate To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.21.0210031550140.92684-100000>