Kuro5hin.org: technology and culture, from the trenches
create account | help/FAQ | contact | links | search | IRC | site news
[ Everything | Diaries | Technology | Science | Culture | Politics | Media | News | Internet | Op-Ed | Fiction | Meta | MLP ]
We need your support: buy an ad | premium membership

[P]
The Next Big Thing(tm) in storage devices

By maphew in News
Tue May 16, 2000 at 03:01:05 AM EST
Tags: Technology (all tags)
Technology

Ever wonder what the NextBigThing(tm) in digital storage technology might be?
Well, I don't have the answer, but for likely candidates, check out the growing attraction of nonmagnetic storage by Franco Vitaliano. It's the most well rounded article I've seen on the subject, covering molecular array read/write engines, atomic force microscopy, holographics, multilayer volumetrics, and DNA storage research.


The 'sound'-byte most likely to make you salivate: "... also touting a new solid-state 3-D technology that they claim could put 2,300 GB on a credit-card-sized device costing no more than $50. ... can apparently be implemented with conventional storage hardware ... possible that products using this new 3-D storage technology will be on the market by the end of 2001."

First seen on VXM Network an interesting high signal-to-noise site (once you break the frames anyway).

Sponsors

Voxel dot net
o Managed Hosting
o VoxCAST Content Delivery
o Raw Infrastructure

Login

Related Links
o the growing attraction of nonmagnetic storage
o VXM Network
o Also by maphew


Display: Sort:
The Next Big Thing(tm) in storage devices | 14 comments (14 topical, editorial, 0 hidden)
I've heard so many 'NextBigThing' s... (3.00 / 1) (#8)
by ZamZ on Mon May 15, 2000 at 08:19:17 PM EST

ZamZ voted 1 on this story.

I've heard so many 'NextBigThing' stories as far as storage goes, but I read this article earlier and as maphew says, its a well written piece and worth the read.

On 'The Other Site' they have one o... (2.00 / 1) (#5)
by Marcin on Mon May 15, 2000 at 08:42:13 PM EST

Marcin voted -1 on this story.

On 'The Other Site' they have one of these about once a month.

I'll believe these things when I see 'em :)
M.

If we ever get that solid-state sto... (2.50 / 2) (#4)
by RobotSlave on Mon May 15, 2000 at 08:50:38 PM EST

RobotSlave voted 1 on this story.

If we ever get that solid-state storage, Oracle is going to be in for a world of hurt.

For those that haven't dabbled in database admin:

To meet data integrity constraints, any RDBMS worthy of the name must write every INSERT to permanent storage (disk, today) before returning a success state for the insert. This is an enormous performance bottleneck, and Oracle (and other RDBMS vendors) have comitted crazy development energy to developing what amount to file systems and memory managers optimised for the RDBMS. If the bottleneck goes away, there won't be any noticable performance difference between Oracle and PostgreSQL-- in fact, Oracle, optimised for rotating magnetic disks, might be slower. Free of performance constraints, developers could then devote all of their time to adding features (like replication). PostgrSQL would match Oracle feature for feature very quickly. Oracle would have a hard time keeping up-- just imagine what it might be like for their developers to work around the hairballs in the codebase that optimise for rotating disks...

Re: If we ever get that solid-state sto... (3.50 / 2) (#9)
by ZamZ on Tue May 16, 2000 at 04:19:05 AM EST

I'm not so sure on this one. Oracle copes real well with an EMC config. The unit I'm working on at the moment has an 8G read/write cache with a fibre connection to the box. Thats enough to keep writes pretty happy.

Solid state might be a different matter. At the point where the memory is on the main board then I'd agree, buffer maintenance just isn't necessary. But at that point you'd probably switch to an OS mode that would store all state information in memory. You would thus be more likely to ignore the whole 'disk' concept and rely on keeping everything in memory, maintaining a kind of permanent buffer. Depends on the transfer rate to it I spose :>)

ZamZ

[ Parent ]
Cool beans. Need something I can p... (none / 0) (#3)
by warpeightbot on Mon May 15, 2000 at 08:54:24 PM EST

warpeightbot voted 1 on this story.

Cool beans. Need something I can put on top of the monitor without fear anyway. If it holds several gig, or maybe terabytes, so much the better.

next time add more commentary or ju... (none / 0) (#1)
by davidu on Mon May 15, 2000 at 10:01:59 PM EST

davidu voted 1 on this story.

next time add more commentary or jump start some discussion...

Re: next time add more commentary or ju... (none / 0) (#11)
by maphew on Tue May 16, 2000 at 12:07:25 PM EST

You're right. I was hoping to see more commentary on the {un}likelihood of the technology approaches. Obviously I picked the wrong lead-in. Normally I too gloss over the NBT type stories. I liked this one because of it's greater than usual depth. Guess I have a few things to learn about submitting stories. :)

-matt

[ Parent ]
If I see it in my lifetime, I'll be... (none / 0) (#6)
by deimos on Mon May 15, 2000 at 10:06:03 PM EST

deimos voted 0 on this story.

If I see it in my lifetime, I'll be impressed.
irc.kuro5hin.org: Good Monkeys, Great Typewriters.

More vaporware. Sigh.... (none / 0) (#2)
by Pseudonymous Coward on Mon May 15, 2000 at 11:54:33 PM EST

Pseudonymous Coward voted 0 on this story.

More vaporware. Sigh.

I really don't care.... (1.00 / 2) (#7)
by guppie on Tue May 16, 2000 at 02:20:49 AM EST

guppie voted 0 on this story.

I really don't care.

What? The land of the free? Whoever told you that is your enemy.
-Zack de la Rocha

Vapor (3.00 / 1) (#10)
by duxup on Tue May 16, 2000 at 06:08:41 AM EST

Data storage media always seems to have a bit more vapor-hardware hit the news than anything else. Each claim more extravagant than the next. It's disappointing. I'm still basically using the same manner of storage that I have since I worked with PCs originally. The only exception to data storage changes on my PC seems to be IBM's announcements of larger disk drives. At least they wait until it can be sold sometime relatively soon before getting anyone's hopes up.

comments about the article itself? (2.50 / 2) (#12)
by maphew on Tue May 16, 2000 at 12:51:22 PM EST

Hi *,

Hey, I realize we've all heard about the NBT before, and granted most of the time it's primary purpose is to drum up mindshare and maybe venture capital. This article is different, it's not about a single company or a single technology, but rather a survey of promising research areas, which do include some company names. Although I deliberately left out the company name in the sound-byte, the byte itself was badly chosen, more appropiate 'to the other site' as some have noted. I hear and respond.

The way the lead-in as it should have been written might look like this:

Exponential or geometric increases in digital data storage is almost a given. Also a given is that movable heads and spinning magnetic platters have physical limitations which will be reached soon, if we haven't already. What is not known yet is what the new storage container (or containers) will look like. Will they be molecular arrays or DNA polymer strands? The much ballyhoo'd hologram or 3D fluorescent scanning microscopy? or...? You may not have to wait long to find out. Some new technologies are slated to be in production in the second and third quarters of this year. Others are waiting for the end of 2001 or 2005.

Which technology do you think will win out? Or perhaps you have ideas about a research avenue which the article didn't address? Or heck, maybe you don't give a hoot what's under the hood and want to talk about how on earth are we going to manage and use and filter all that data? ('cause, you know, data always expands to fill the available room...)

cheers,

-matt

What if things go wrong? (1.00 / 1) (#13)
by zeda on Tue May 16, 2000 at 05:15:03 PM EST

I read somewhere that the government likes to grind up old HD's that have classified data and that with the current bit density you can still have a decent amount of info on a 1/16" square piece of HD. As we get smaller and smaller are we going to have more problems disposing of data.

It also makes you wonder about data recovery. Does anyone try to fix bad CDROM's these days, what about DVD-ROMS's. I know I have had a bad cd burn that I wish I could have recovered. It would suck having a tera-byte disk go bad.

Re: What if things go wrong? (none / 0) (#14)
by jovlinger on Wed May 17, 2000 at 02:03:23 PM EST

Incineration should suffice for a long time. Alternately, do it by software, and rewrite the medium many times. Mind you; the memory effect you're alluding to is pretty specific to electro-magnetic devices. If we start storing information in the configuration of atoms, it should be easy enough to completely wipe the medium. Johan

[ Parent ]
The Next Big Thing(tm) in storage devices | 14 comments (14 topical, 0 editorial, 0 hidden)
Display: Sort:

kuro5hin.org

[XML]
All trademarks and copyrights on this page are owned by their respective companies. The Rest 2000 - Present Kuro5hin.org Inc.
See our legalese page for copyright policies. Please also read our Privacy Policy.
Kuro5hin.org is powered by Free Software, including Apache, Perl, and Linux, The Scoop Engine that runs this site is freely available, under the terms of the GPL.
Need some help? Email help@kuro5hin.org.
My heart's the long stairs.

Powered by Scoop create account | help/FAQ | mission | links | search | IRC | YOU choose the stories!