Interleaved memory performance - a query

[mckay at burdvax.UUCP]

We here at burdvax are about to install an  interleaved memory system
on a VAX 11/780 running Berkeley 4.2 and have had a  couple of lively
discussions about the  performance value  of interleaved  memory.  We
have a somewhat largish configuration:  a) 1 Unibus  with 2 CDC9766's
off  of  an  Emulex  SC21V controller,  an 8  line DZ  connected to a
Rascal-Vadic modem rack, 64 tty ports on  an Emulex  CS21 emulating 4
DH's, an Interlan 10MB Ethernet controller, 2 Versatecs, a Printronix
interfaced thru an LP11 and a Cipher 800/1600bpi tape drive  off of a
TU11 controller; b) an RM03 disk on a Massbus; c) 4  CDC9766's off of
an Emulex SC780 (a second Massbus).  

I was wondering whether  there is  any experimental  data or rational
consensus out in netland  about this  performance issue.   Also, does
anyone run 4.2 without interleaved memory?   Finally, do  some of the
Berkeley Unix subsystems, eg "Fast file system", expect to be running
on systems with interleaved memory?   What I  am thinking  of here is
the disk block sizes,  eg 8K  blocks (1/2  track) vs  4KB blocks (1/4
track),  seem  fairly  large  for  a  system  with  a  single  memory
controller.  


Any info, including references on this topic would be appreciated.
Please begin discussion by mailing to me and I will summarize.


Thanks in advance.

Don McKay
...sdcrdcf!burdvax!mckay
...psuvax1!burdvax!mckay

Research & Development		System Development Corporation
				Paoli, PA