james@bigtex.uucp (James Van Artsdalen) (08/14/88)
In article <18.23040D6B@rubbs1.FIDONET.ORG>, Mark.Medici@rubbs1.FIDONET.ORG (Mark Medici) wrote: > My understanding is that you won't need a modem with ISDN, that it > will accept digital signals. I also beleive that there will be an > interface to allow non-ISDN data equipment to be used on ISDN lines, > but you might need a similar setup at both ends. I would tend to suspect that high speed modems like the Trailblazer+ wouldn't easily survive the analog->digital->analog transition. Even if they did, you still have to have a black box for your PC: Mess-DOS rolls over dead at the thought of 9600bps (interrupt latency on extended memory on slow machines), much less 8Kbytes/sec! I rather expect the problem is worse on OS/2 (for different reasons). Even using an NS16550A serial chip with the 16 byte FIFO isn't going to cut the interrupt rate enough, not that the Mess-DOS file system is currently good for sustained 8K/sec anyway. -- James R. Van Artsdalen ...!uunet!utastro!bigtex!james "Live Free or Die" Home: 512-346-2444 Work: 328-0282; 110 Wild Basin Rd. Ste #230, Austin TX 78746
Ralf.Brown@B.GP.CS.CMU.EDU (08/14/88)
In article <6108@bigtex.uucp>, james@bigtex.uucp (James Van Artsdalen) writes: }[...] Mess-DOS }rolls over dead at the thought of 9600bps (interrupt latency on }extended memory on slow machines), much less 8Kbytes/sec! I rather Better not tell that to all the 4.77 MHz IBM PC's running USRobotics HSTs at 9600 or even 19200.... }[...] Even }using an NS16550A serial chip with the 16 byte FIFO isn't going to cut 6400 / 16 = 400 interrupts per second. Sounds quite manageable to me, even on a 4.77 MHz 8088 box. When I still had my Eagle PC (4.77 8088), I used to run a print spooler that sped up the clock tick interrupt to 2330 times per second! (in order to pump >1000 bytes/sec of graphics data to the printer) The PC could even have handled 4660/second, as the spooler consumed about 30% of CPU cycles. If a serial port handler can't hack 1/12 the interrupt rate, something is wrong.... }[...] not that the Mess-DOS file system is }currently good for sustained 8K/sec anyway. Even if DOS is quite sloppy and needs two rotations to write a track on a floppy disk, it can write two tracks (9K) in 0.8 seconds, which sure looks like more than 8K/sec to me.... It's only when the floppy disk gets quite fragmented that DOS might have trouble getting 8K/sec onto the floppy disk--but that's caused by the floppy and not by DOS. -- UUCP: {ucbvax,harvard}!cs.cmu.edu!ralf -=-=-=- Voice: (412) 268-3053 (school) ARPA: ralf@cs.cmu.edu BIT: ralf%cs.cmu.edu@CMUCCVMA FIDO: Ralf Brown 1:129/31 Disclaimer? I |Ducharm's Axiom: If you view your problem closely enough claimed something?| you will recognize yourself as part of the problem.
mark@intek01.UUCP (Mark McWiggins) (08/15/88)
Mark.Medici@rubbs1.FIDONET.ORG (Mark Medici) wrote: > My understanding is that you won't need a modem with ISDN, that it > will accept digital signals. I also beleive that there will be an > interface to allow non-ISDN data equipment to be used on ISDN lines, > but you might need a similar setup at both ends. You won't need a modem, but you will need another sort of board to handle the ISDN protocol. Actually, I believe that Hayes has a prototype board they're using in an ISDN trial in their corporate offices around Atlanta. I read that ISDN chipsets exist, so I don't think there's any obstacle to cheap ISDN if enough of them were sold. Some information-services entrpreneur needs to build a $400 ISDN-capable PC about four years hence and bundle with it a classified ad/news/computer game/traffic report/anything else you could think of system. Could be the real "information appliance" that the MacIntosh was supposed to be. Could destroy the residential real estate industry. Oh boy! -- Mark McWiggins UUCP: uunet!intek01!mark DISCLAIMER: I could be wrong. INTERNET: intek01!mark@uunet.uu.net (206) 455-9935
johnson@c10sd1.StPaul.NCR.COM (Wayne D. T. Johnson) (08/16/88)
In article <6108@bigtex.uucp> james@bigtex.UUCP (James Van Artsdalen) writes: >if they did, you still have to have a black box for your PC: Mess-DOS >rolls over dead at the thought of 9600bps (interrupt latency on >extended memory on slow machines), much less 8Kbytes/sec! I rather If you were counting on the PC to do all the work, yes 8K/sec would be messy. However, if you connected this in through a DMA channel or used the AT string commands (which are faster than DMA for smaller blocks, ask DOS) you could get some pretty good rates. I just finished a product that could handle 2 19.2 lines at once, recording this data to disk as well as the screen and also scans that data for specific strings. Our biggest problem was getting the special comm adapter to go as fast as we could. And just thing of what you could do with ISDN and LAN tech.... makes one want to drool. -- Wayne Johnson (Voice) 612-638-7665 NCR Comten, Inc. (E-MAIL) W.Johnson@StPaul.NCR.COM or Roseville MN 55113 johnson@c10sd1.StPaul.NCR.COM These opinions (or spelling) do not necessarily reflect those of NCR Comten.
james@bigtex.uucp (James Van Artsdalen) (09/01/88)
In article <23056a96@ralf>, Ralf.Brown@B.GP.CS.CMU.EDU writes: > In article <6108@bigtex.uucp>, I wrote: | [...] Mess-DOS | rolls over dead at the thought of 9600bps (interrupt latency on | extended memory on slow machines), much less 8Kbytes/sec! I rather > Better not tell that to all the 4.77 MHz IBM PC's running USRobotics > HSTs at 9600 or even 19200.... Hmm... It's entirely possible that the problem is strictly related to extended memory. Extended memory on ATs leaves interrupts turned off for a very long period of time, and this is factor if you're using a disk cache, as most people seem to these days. | [...] Even using an NS16550A serial chip with the 16 byte FIFO | isn't going to cut > 6400 / 16 = 400 interrupts per second. Sounds quite manageable to me, > even on a 4.77 MHz 8088 box. When I still had my Eagle PC (4.77 > 8088), I used to run of CPU cycles. [...] If a serial port handler can't > hack 1/12 the interrupt rate, something is wrong.... The problem isn't the serial port, or even the interrupt rate, but MS-DOS and the design of extended memory systems. | [...] not that the Mess-DOS file system is | currently good for sustained 8K/sec anyway. > Even if DOS is quite sloppy and needs two rotations to write a track on a > floppy disk, it can write two tracks (9K) in 0.8 seconds, which sure looks > like more than 8K/sec to me.... It might write that if you did a write() with a 9K buffer, but not if you did 18 writes of 512 bytes, as is the norm for most programs (standard I/O package influence). There is a lot of overhead between a program and the routines that actually write a sector to the disk. I would not be surprised if 8K/sec were near the limits of what a hard disk could sustain (assuming substantial interrupt overhead merely getting the 8K/sec into RAM). -- James R. Van Artsdalen ...!uunet!utastro!bigtex!james "Live Free or Die" Home: 512-346-2444 Work: 328-0282; 110 Wild Basin Rd. Ste #230, Austin TX 78746