back to article OCZ joins PCIe flash fray

OCZ has joined in the PCIe flash market, the one led by Fusion-io, with card controllers that compress data and boost I/O to 1GB/sec speeds. The VeloDrive PCI-Express SSD uses 2-bit MLC flash with four Sandforce SF-1565 controllers, has four channels, comes in half-height or full-height form, and has on-board hardware RAID or …

COMMENTS

This topic is closed for new posts.
Silver badge

Consigned to a footnote in IT history

Hands up: who remembers Icebergs? Storagetek's (at the time) rather amazing RAIDed, compressed data storage with a whopping 77GB native capacity - or 200GB for compressed data. it also had a sort of built-in data optimisation scheme, so you were never really sure where your data was. And no, it wasn't SSD it was a pile of itsy-bitys little disks with some proprietary smarts to talk to your mainframe.

The thing is, while it was super hot tech at the time, it solved a problem that was fleetingly temporary. Within a year or two disk capacity had doubled and a year or two later had doubled again. That sorta kinda made all the fantastical innards of these things ever so slightly redundant.

That's what the makers and buyers of on-the-fly compression SSDs will find. In a short time their 2011 technology will be overtaken by smaller/cheaper/faster storage and they'll be the Icebergs of this decade.

1
0
Silver badge

Indeed

Im also surprised that we havent seen more battery backed RAM drives. There was one a few years ago that WAS lightning quick for the time.

0
0
Bronze badge

I agree

When I saw them I thought what a good idea but I suppose the biggest problem is when the battery dies and I'm not sure if its proven to last for years and years. I would always have an actual hard drive there (Maybe just have the ram drive copied directly the HD so if it fails to boot select the HD instead.

0
0

Re: I agree

Hold on ... since when did flash ever require a battery to back it up? This isn't volatile memory ya know ...

0
0
FAIL

Sorry, what?

"OCZ has joined in the PCIe flash market..."

Yeeeeeees...for quite a while, now. Google RevoDrive and Z-Drive, perhaps? Seriously, they're hardly newcomers.

0
0
Silver badge
Dead Vulture

Tables, please ?

This article would have been easier to read if you'd use a simple HTML table to present the data comparisons.

1
0
Coat

Agreed

And some additional maths too:

"That makes you suspicious, and then the numbers themselves are seriously weird: 64MB/sec for the 300GB card, 65MB/sec for the 600GB card and a near-derisory 19MB/sec for the 1.2TB card."

Assuming these are random 4k writes....

300GB drive: 64MB / 4K = 16384 IOPS

600GB drive: 65MB / 4K = 16640 IOPS

1.2TB drive: 19MB / 4K = 4864 IOPS

Yes, that 1.2TB drive is certainly very fishy. Likely, they quadruple-booked the flash channels on their cards. The older 1st-gen SandForce controllers (Sandforce SF-1565 cited in the article) could only drive 1 chip at a time per channel (not PCIe lanes, but the data channels to the chips, of which Sandforce only supports 8 per controller, hence 4 controllers per board in this design). The new 2nd-gen controllers can drive all chips in a channel simultaneously, so this bottleneck is/will be eliminated by bumping to a 2nd-gen controller (once they sell enough of these 1st-gen devices).

0
0

OCZ spokesperson says....

Sent to me by an OCZ spokesperson:-

(1) "OCZ joins PCIe flash fray" and "OCZ has joined in the PCIe flash market"

The language used in the article insinuates that we have just joined the PCIe market when in fact we've been in it for awhile now; our first PCIe SSD was in 2009:

http://www.ocztechnology.com/aboutocz/press/2009/337

We actually have a successful line of both enterprise and client PCIe SSDs which no other company can say:

http://www.ocztechnology.com/products/solid_state_drives/pci-e_solid_state_drives

(2) "Coupling software RAID with incompressible data reveals some even sillier numbers. The random write numbers are presented in MB/sec terms and not IOPS, which is the standard measure for virtually every other supplier and OCZ's previous SSDs. That makes you suspicious, and then the numbers themselves are seriously weird: 64MB/sec for the 300GB card, 65MB/sec for the 600GB card and a near-derisory 19MB/sec for the 1.2TB card."

This is because we have recently added benchmarking scores that focus on incompressible data and we and the rest of the industry feel AS-SSD does this well; Iometer does not offer the ability to have that much control over the type of data. The benchmark reports in MB/s which is why we've added MB/s to the compressible data specs as well (for easy comparison).

As with all enterprise-targeted products, we recommend that clients work with us to determine which SSD solution is right for their application/environment. In most cases, nobody comes close to our price/performance ratio.

- - - - - - -

Thank you OCZ,

Chris.

0
0
This topic is closed for new posts.

Forums