To what solid state drive technology are you referring that would make good use as a heap? I wouldn't think that NAND flash would be suitable due to the write/erase constraints.

NAND flash is going away. Right now it loses half it's write endurance, and it's eraseblocks double in size, every shrink. Eraseblocks are already at 4MB and write endurance is below a 1000 writes, pretty soon additional shrinks will bring no value. This happens because of fundamental physical limits, and no-one believes they can be overcome -- even the biggest proponents are talking about delaying the inevitable for a few years instead of avoiding it.

Right now, there is a hundred-billion-dollar stampede going on for finding out it's successor. Players include:

MRAM (Toshiba, Hitachi, Hynix, IBM, Everspin(Freescale spinoff), Samsung, NEC)

FeRAM (Ramtron, IBM, TI, Fujitsu, Samsung, Matsushita, Oki, Toshiba, Infineon, Hynix, Symetrix)

ReRAM (HP, ITRI, IMEC, Panasonic, Rambus)

CBRAM (NEC, Sony, Axon, Micron)

PRAM (Intel, IBM, ST Micro, Samsung, Numoxys)

I might have missed a few backers. Also, all names after a technology are not working together, especially in FeRAM there are multiple competing approaches.

An interesting commonality about these technologies is that they all aim to be universal memories. That is, they intend to eventually replace both DRAM and Flash, and some are even aiming for the last cache levels in cpus. This will probably lead to some changes in system design. Although I think the people who are calling for the death of filesystems are going about it all wrong -- I expect the role of filesystems to expand, not shrink. All they need is new block layers.

Note that while everyone says memristors (ReRAM), they aren't even the most likely candidate (if I'd have to pick, I'd say PRAM), HP just has the best marketing.

IMFT got NAND down to 20nm with 3K - 5K write endurance. Hynix has plans to produce 15nm soon(unclear on endurance). Many thought getting NAND to it's current level would be impossible, the same could be said about hard drives.

Write amplification isn't much of an issue with smart firmware.

The new memory techs aren't market viable as we speak and it's questionable if first generation commercial devices featuring them will even be available within a few years and at what cost? Many of them also have drawbacks which hamper their viability or parallel the drawbacks of NAND.

I still think a real replacement for NAND is probably a decade out at least.

Leon Chua also considers PRAM to be a memristor technology [1].

  All 2-terminal non-volatile memory devices based on
  resistance switching are memristors, regardless of the
  device material and physical operating mechanisms.

[1] http://www.springerlink.com/content/f41r8m054x550430/

MRAM maybe? (http://en.wikipedia.org/wiki/Magnetoresistive_random-access_...)

Was thinking of this article earlier this week: http://lwn.net/Articles/498289/ (which I'm presuming is some MRAM thing)

1.) If capacity increases, for a given workload, overwriting updates save less capacity. So even without new technology, there's a trend towards less overwrites of a given block for a fixed workload.

2.) Memristor Memory

Memristors?

Multics already implemented "single-level storage" in the 1960s. Effectively, the disk was all swap space for a huge RAM disk.

https://en.wikipedia.org/wiki/Multics#Novel_ideas

The research group I was part of worked on single address space OS's from the early 90s to the late 00's, http://www.ertos.nicta.com.au/research/old/mungi//manifesto.... , and yep, these ideas have been around for a long time.

Looks like IBM i is still/currently shipping with a single address space.

Wouldn't surprise me if Oracle and HP also have something similar.