Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Bringing SSD Performance to the DIMM form factor

sandisk.com.br

Post reply on HN
Print view View original

11–20 of 205 posts

Re: Bringing SSD Performance to the DIMM form factor

#11

Post by gnufied »

zitterbewegung wrote: post #2

Is the advantage the low latency because the rest of the specifications seem to be pretty standard for an SSD. Does this require a BIOS patch of some sort?

I suppose the main usage will be a RAMDISK mounted partition which will not lose its data on Server reboot, power loss or when program is not running.

I don't think this SSD can be accessed through regular SCSI, IDE, AHCI controllers. http://www.sandisk.com.br/enterprise/ulltradimm-ssd/

Re: Bringing SSD Performance to the DIMM form factor

#12

Post by rplnt »

brink wrote: post #6
zitterbewegung wrote: post #2

Is the advantage the low latency because the rest of the specifications seem to be pretty standard for an SSD. Does this require a BIOS patch of some sort?

Here's something similar that we've had in the past. http://en.wikipedia.org/wiki/RAM_drive A bios patch is probably not necessary.

So if you don't install drivers it would act as a regular RAM? Thus ruining your performance..

I don't think it will work out of the box on regular systems. Also, isn't pcie better for this?

Re: Bringing SSD Performance to the DIMM form factor

#14

Post by sfilipov »

zitterbewegung wrote: post #2

Is the advantage the low latency because the rest of the specifications seem to be pretty standard for an SSD. Does this require a BIOS patch of some sort?

Yes, the advantage of the SSD it that it "scales IO performance in a linear fashion while keeping latency constant". [0]

[0] http://youtu.be/dGfpdciV9B4?t=1m32s

Re: Bringing SSD Performance to the DIMM form factor

#15

Post by saticmotion »

zitterbewegung wrote: post #2

Is the advantage the low latency because the rest of the specifications seem to be pretty standard for an SSD. Does this require a BIOS patch of some sort?

If it behaves like RAM, from the POV of the OS, I'd imagine the advantage to be the large size. There's also the fact that it won't lose its data on power loss.

Of course, if it behaves like a regular SSD, the read speeds still exceed SATA3.0 speed.

Re: Bringing SSD Performance to the DIMM form factor

#16

Post by throwaway_yy2Di »

petercooper wrote: post #4

I appreciate this might not be the right way to look at it, but from a trivia POV, in terms of raw performance, what era of regular memory would be comparable with it? (i.e. "typical desktop memory in 2004", say.)

The read latency is about as slow as the earliest RAM ever used -- tubes of liquid mercury used as acoustic delay lines. (150 us vs. 222 us (microseconds))

https://en.wikipedia.org/wiki/Delay_line_memory#Mercury_dela...

Re: Bringing SSD Performance to the DIMM form factor

#17

Post by toyg »

zrail wrote: post #8

I don't quite understand. Does this act like a stick of memory or an SSD? Is it just using the memory controller as a super fast parallel bus? If it does act like normal memory, what happens at reboot?

> Does this act like a stick of memory or an SSD?

Like an SSD.

> Is it just using the memory controller as a super fast parallel bus?

Afaik, it's this.

Re: Bringing SSD Performance to the DIMM form factor

#19

Post by Xylakant »

film42 wrote: post #5
NamTaf wrote: post #3

I can't wait to see the programming paradigm of memory vs permanent storage begin to blur in the next 5 or so years. It's going to make some major assumptions about how you program stuff change quite significantly and it's really exciting.

I agree! I wonder what will happen when memory and IO are essentially the same speed. Will we still need complex cache stores?

I doubt that will happen ever, there's always a tradeoff between cost, speed and space (on the die, ...), otherwise we'd all be running machines with 1TB L1 Cache.

Re: Bringing SSD Performance to the DIMM form factor

#20

Post by gnufied »

zrail wrote: post #8

I don't quite understand. Does this act like a stick of memory or an SSD? Is it just using the memory controller as a super fast parallel bus? If it does act like normal memory, what happens at reboot?

Answer is there in FAQ. Written data is not lost on reboot, so basically you can mount it as a `ramdisk` partition and use that as data directory for your database. I have used this approach in past to speed up large test suite of a web application, except it required restoring from some sort of backup on reboot. Which won't be necessary in this case.
Post reply on HN