[net.arch] I/O concensus?

jss@sjuvax.UUCP (Jonathan Shapiro) (11/30/84)

[Aren't you hungry...?]
	Is there any general concensus about the best way to handle IO to slow
devices?  I have been thinking about building a board whose disk interface
has a sort of staging area of 4K or so and then tells the processor its
there and come get it... This would allow, for example, hard disk backup
which happened in bursts at memory to memory speed rather than memory to
disk speed.

	My plan is to put a separate processor and bus on the disk interfac
and connect these to the main bus through an IO port.  Any 
thoughts/suggestions?

jc@sdcsvax.UUCP (John Cornelius) (12/01/84)

Xyplex makes a terminal subsystem for VAX that moves the character processing
out onto a coax cable network. Boxes on the network perform all driver
functions associated with characters. Data is transferred from the net to the
VAX in records (usually one line) except when in cbreak mode. Drivers exist for
VMS and UNIX. Records are transferred to the terminal in whatever size they are
presented to the driver via DMA. The system has the additional feature that it
allows up to 256 VAXen or terminal clusters to be connected on the same
network. Terminals on any cluster can access any VAX if desired. Each cluster
has an equivalent of L.sys and ttys so such things can be restricted of need
be.