g r o t t o 1 1

Peeve Farm
Breeding peeves for show, not just to keep as pets
  Blog \Blôg\, n. [Jrg, fr. Jrg. "Web-log".
     See {Blogger, BlogSpot, LiveJournal}.]
     A stream-of-consciousness Web journal, containing
     links, commentary, and pointless drivel.


On My Blog Menu:

InstaPundit
USS Clueless
James Lileks
Little Green Footballs
As the Apple Turns
Entropicana
Cold Fury
Capitalist Lion
Red Letter Day
Eric S. Raymond
Tal G in Jerusalem
Secular Islam
Aziz Poonawalla
Corsair the Rational Pirate
.clue

« ? Blogging Brians # »





Book Plug:

Buy it and I get
money. I think.
BSD Mall




 10/6/2003 -  10/8/2003
 9/29/2003 -  10/5/2003
 9/22/2003 -  9/28/2003
 9/15/2003 -  9/21/2003
  9/8/2003 -  9/14/2003
  9/1/2003 -   9/7/2003
 8/25/2003 -  8/31/2003
 8/18/2003 -  8/24/2003
 8/11/2003 -  8/17/2003
  8/4/2003 -  8/10/2003
 7/28/2003 -   8/3/2003
 7/21/2003 -  7/27/2003
 7/14/2003 -  7/20/2003
  7/7/2003 -  7/13/2003
 6/30/2003 -   7/6/2003
 6/23/2003 -  6/29/2003
 6/16/2003 -  6/22/2003
  6/9/2003 -  6/15/2003
  6/2/2003 -   6/8/2003
 5/26/2003 -   6/1/2003
 5/19/2003 -  5/25/2003
 5/12/2003 -  5/18/2003
  5/5/2003 -  5/11/2003
 4/28/2003 -   5/4/2003
 4/21/2003 -  4/27/2003
 4/14/2003 -  4/20/2003
  4/7/2003 -  4/13/2003
 3/31/2003 -   4/6/2003
 3/24/2003 -  3/30/2003
 3/17/2003 -  3/23/2003
 3/10/2003 -  3/16/2003
  3/3/2003 -   3/9/2003
 2/24/2003 -   3/2/2003
 2/17/2003 -  2/23/2003
 2/10/2003 -  2/16/2003
  2/3/2003 -   2/9/2003
 1/27/2003 -   2/2/2003
 1/20/2003 -  1/26/2003
 1/13/2003 -  1/19/2003
  1/6/2003 -  1/12/2003
12/30/2002 -   1/5/2003
12/23/2002 - 12/29/2002
12/16/2002 - 12/22/2002
 12/9/2002 - 12/15/2002
 12/2/2002 -  12/8/2002
11/25/2002 -  12/1/2002
11/18/2002 - 11/24/2002
11/11/2002 - 11/17/2002
 11/4/2002 - 11/10/2002
10/28/2002 -  11/3/2002
10/21/2002 - 10/27/2002
10/14/2002 - 10/20/2002
 10/7/2002 - 10/13/2002
 9/30/2002 -  10/6/2002
 9/23/2002 -  9/29/2002
 9/16/2002 -  9/22/2002
  9/9/2002 -  9/15/2002
  9/2/2002 -   9/8/2002
 8/26/2002 -   9/1/2002
 8/19/2002 -  8/25/2002
 8/12/2002 -  8/18/2002
  8/5/2002 -  8/11/2002
 7/29/2002 -   8/4/2002
 7/22/2002 -  7/28/2002
 7/15/2002 -  7/21/2002
  7/8/2002 -  7/14/2002
  7/1/2002 -   7/7/2002
 6/24/2002 -  6/30/2002
 6/17/2002 -  6/23/2002
 6/10/2002 -  6/16/2002
  6/3/2002 -   6/9/2002
 5/27/2002 -   6/2/2002
 5/20/2002 -  5/26/2002
 5/13/2002 -  5/19/2002
  5/6/2002 -  5/12/2002
 4/29/2002 -   5/5/2002
 4/22/2002 -  4/28/2002
 4/15/2002 -  4/21/2002
  4/8/2002 -  4/14/2002
  4/1/2002 -   4/7/2002
 3/25/2002 -  3/31/2002
 3/18/2002 -  3/24/2002
 3/11/2002 -  3/17/2002
  3/4/2002 -  3/10/2002
 2/25/2002 -   3/3/2002
 2/18/2002 -  2/24/2002
 2/11/2002 -  2/17/2002
  2/4/2002 -  2/10/2002
 1/28/2002 -   2/3/2002
 1/21/2002 -  1/27/2002
 1/14/2002 -  1/20/2002
  1/7/2002 -  1/13/2002
12/31/2001 -   1/6/2002
12/24/2001 - 12/30/2001
12/17/2001 - 12/23/2001
Sunday, April 14, 2002
16:41 - NVRAM Breakthrough
http://www.chron.com/cs/CDA/story.hts/tech/news/1363062

(top) link
Man, do we ever take some things for granted in the computer world.

Like, for example, the inherent difference between RAM and hard-disk storage.

When you think about it, it seems a ridiculous couple of things to have to coexist in modern computers. And yet so many of the functions in computing-- in fact, almost all of them-- are dedicated to dealing with moving data from one to the other and back again.

Oddly enough, hard drive space and RAM size have not wildly diverged. Rather, they've stayed separated only by about one or two powers of ten. When 386-based PCs were all the rage, an 80MB hard drive and 2MB of RAM was quite a serviceable arrangement. A couple of years ago, 128MB of RAM and a 10GB hard drive were fairly normal. Today, you can expect to get a fairly high-end machine with 1GB of RAM and 80GB of disk space.

If you'd asked me in 1991 what our computers' respective storage sizes would be in 2002, I'd probably have said we would have 1GB RAM/512MB hard drives, or maybe 100GB hard drives powering machines with 16MB of RAM. I wouldn't have known which way it would go-- but I would never have guessed that the ratio of sizes would remain roughly the same.

With this in mind, doesn't it seem weird that our mass storage media are still so much fundamentally slower than our powered run-time memory?

Why do we have to educate new computer users about such concepts as:
  • The computer has to "boot" each time you turn it on, so that it can copy the operating system from the disk into memory.
  • When you run programs, the computer has to copy the programs from the disk into memory before they can do anything. When you quit programs, they are deleted from RAM, but remain on the disk.
  • When you work on documents in applications, the data exists only in RAM, until you explicitly "save" it-- tell the program to copy it from RAM onto the disk.
  • Each time you turn the computer off, everything in the RAM is deleted-- any data in documents you haven't saved, any programs that are running, the whole active copy of the operating system. This means that when you turn it back on, you have to wait while the computer boots, copying it all back into memory again.

Is it just me, or does this seem a little bit ridiculous?

We expect people who are brand-new to computers to accept these machinations as "just the way it is". We have to have training courses which spend their first couple of weeks explaining the difference between hard drives and RAM and why the two exist. Yet we have Palm devices that we can "turn off" and turn back on-- only to have exactly the same data on the screen as was there when we turned it off; and we have Macs that can "sleep", use almost no power, and come back up to exactly where they were before. (Although Macs will still lose all their RAM contents if you unplug them-- and Wintel PCs have "sleep" too, but it isn't anywhere near as efficient or fast.) So why can't computers just... be like Palms?

Well, if this new NVRAM development is for real and viable, we may have just that in our future.

Imagine-- you boot your computer once, and that's the last time you'll do it unless the computer crashes or you have to upgrade the OS. Regular shutdowns, like at the end of the day, are like turning off a Palm or putting a Mac to sleep-- just touch a button and the screen goes dark and the fans spin down, but everything in memory is still right where you left it. Touch the same button again, and pop! There's all your data again, unharmed.

And booting the computer would take only ten seconds or so, because you don't have to copy anything from disk to memory. The operating system just runs from where it is-- the compiled bytecode exists on disk in a format that can be directly executed. The only thing the computer has to do during boot is to fire up the I/O systems and test the devices. Then it's ready to rock.

Want to run a program? No need to "load" it into memory anymore-- if it's stored on the computer, it's both permanently stored and ready to execute. Just open it and it's running.

Want to create a document, or edit some existing data? Just open the file-- it's right there in memory already. Make changes, and they're all instantly and permanently stored. No "saving" necessary.

Of course, this means that many applications' "Revert to Saved" functions would now have to be reworked-- right now, the function represents a cheap hack that simply discards whatever's in RAM and reloads the file from the disk. But if there's no discrepancy anymore between the file on disk and the file in memory-- there's only the one copy now-- the apps would have to consciously keep a copy of the file, in the form that it was in when you opened it, in a temporary memory location-- and "Revert" would throw out your current file and read in this backup copy. But then, this also opens up the door to any application having an arbitrary number of "undo" levels, rather than the binary nature of "what's on disk" and "what's in RAM".

Reportedly, this new NVRAM is both high-capacity and fast. It must be slower than existing RAM (there's more for it to do), but then it's definitely going to be faster than doing everything off disk (run an OS completely in swap space and you'll know how painful that can be). So that's two out of three: fast and spacious. If they can nail the third key factor-- cheap-- then we'll have a revolution on our hands that rivals the transistor.

Back to Top


© Brian Tiemann