danny@itm.UUCP (Danny) (09/09/87)
Distribution:
While this may come under the headings of "Wishful Thinking" and
"Pipe Dream", let me desribe the computer that I'm waiting for.
This is at once, both a step forwards, and a step back.
How about a computer with say, 300 Meg of RAM. There is, also,
a hard disk of 300 Meg or so (coinsidence? nope). That's right,
your memory *is* your file system. I also envision hardware support
(surely software could carry the burden at first) so that every write
to RAM that would affect a file would be queued to also be written
onto the disk. The disk could either be backed up by conventional
means, or removable for off-site storage.
Talk about fast! Whoa Nelly (sorry Nelly)!
The step forwards is obvious, the step back is that this scheme
smacks of the flavor of Multics. Now, I've heard a lot about Multics,
but I ain't never seen one. But, as I remember, to access a "file"
one asked the system to map it into your address space. Hmm.
The technology to do this exists today. Unix would fit nicely
onto this hardware, perhaps even removing some sections of the kernel.
df(1) and du(1) would instantly have archaic names (disk? what disk?),
and sync([12]) would still be alive and kicking.
Nevertheless, whatever else may be happening, a scoo-bah of memory
has mucho apeal. Comments?
Danny
--
Daniel S. Cox
({seismo!gatech|ihnp4!akgua}!itm!danny)hunt@spar.SPAR.SLB.COM (Neil Hunt) (09/10/87)
In article <1184@itm.UUCP> danny@itm.UUCP (Danny) writes: > [...] > How about a computer with say, 300 Meg of RAM. There is, also, > [...] > Nevertheless, whatever else may be happening, a scoo-bah of memory >has mucho apeal. Comments? > Better make sure that it has full error correction ! On a Sun 3, I believe that you can put 28 Mbytes of mem, at which time you should expect a parity error to be detected about once a month, with current technology. Thus 300 Megabytes will get a soft error every three days or so (bit of a pain !). I understand that Sun 4s will have error *correction* hardware so that they can correct single bit (?) errors, and thus go to larger memories without crashing too often. Does anyone know about soft failure modes of DRAMs ? How likely is it to find double bit errors ? With denser and denser memory chips, one might expect that one day soon, background alpha particles will be able to flip several adjacent bits. By the way, my dream machine would have much more than 300 M ! Some people here have swap discs in the 100s of M on their lispms, and still could use more ! Also I don't know why you would have a conventional disc to back up your DRAM. I would trust my (EC) memory more than a disc, but do conventional type backups on an Optical WORM disc now and then. Neil/.
gore@nucsrl.UUCP (09/12/87)
/ nucsrl:comp.unix.wizards / danny@itm.UUCP (Danny) / 7:36 am Sep 9, 1987 / > > How about a computer with say, 300 Meg of RAM. There is, also, >a hard disk of 300 Meg or so (coinsidence? nope). That's right, >your memory *is* your file system. I also envision hardware support >(surely software could carry the burden at first) so that every write >to RAM that would affect a file would be queued to also be written >onto the disk. The disk could either be backed up by conventional >means, or removable for off-site storage. Why do you need hard disk then? All you need is a reliable constant power source for your memory. Then you can do backups from memory, rather then shadowing it with a hard disk and backing up the disk. Jacob Gore gore@EECS.NWU.Edu Northwestern Univ., EECS Dept. {gargoyle,ihnp4,chinet}!nucsrl!gore