Really, redundant file servers

[mangler at cit-vax.UUCP]

In article <12959 at sun.uucp> dss at sun.UUCP (Daniel Steinberg) writes:
>In many ways it is simpler to have a physical disk shadow than a
>filesystem shadow...

Another variation is two servers for a set of dual-ported disks.
In this case there's no duplication of effort, and you're not
buying twice as many disks.  Eagles are so reliable that you'll
see more downtime from power outages than from broken drives.
This would be an attractive mode for us, because we've got the
hardware for it.

The hard part is getting two machines to share dual-ported disks
read-write.  The problem is caching; dual-port kits have no way
to let the other CPU know that something was written and that
something in the in-core cache should be invalidated.  Some other
way has to be provided to communicate this (Ethernet?).  The SI
SIMACS controller is supposed to be able to do this - I don't
understand how.  (Maybe they just don't cache anything?  But
that's too horrible to contemplate...).

Don Speck   speck at vlsi.caltech.edu  {seismo,rutgers,ames}!cit-vax!speck