Feeds

Flash card latency: Time to get some marks on benches

Chuck out the slicks and platters, and MLC it

Boost IT visibility and business value

Fusion-io flash cards outperformed a slew of competitors in a Marklogic NoSQL benchmark reported by StorageReview - for which much thanks.

The benchmark rig is detailed in the article text and it notes that tested storage configs must have a more-than-650GB usable capacity, meaning individual flash devices can be bunched up.

Here's the chart graphing the overall latency results:-

MarkLogic small

Hurts your squinting eyes? Click on image for instant relief.

The chart ranks various flash products in order of overall latency on a MarkLogic NoSQL database benchmark and it looks like the top two results show Dell and Micron blowing virtually everybody else out of the water, and so they should. Both of them use fast SLC flash and the Dell one is based on Micron's P320h SSDs. So let's discount these as all the others, except 4th-placed Fusion-io (FIO) ioDrive2 Duo, are all slower multi-level or layer cell (MLC) flash.

FIO's 2.4TB MLC ioDrive2 Duo rules supreme with the lowest overall latency, 1.698ms - not that much slower than the two faster SLC products actually.

The bottom two results use Toshiba 2.5-inch disk drives, one with hardware RAID and the other, the slowest one, with software RAID.

The graph bunches up the MLC flash products. If we toss out the SLC flash products and the two disk drives we can better see how the MLC flash products stack up, by lengthening the horizontal axis.

MLC Only small

You know already; click on chart for larger view.

There is quite a degree of latency with the bottom four configs having at least twice the latency of the top three. The poor FIO result (third slowest) is based on the ioDrive2 and not the ioDrive2 Duo. The OCZ Z-Drive and Smart Optimus products do very well, better than Virident's FlashMAX II, which is unexpected. Intel does relatively poorly, as do the OCZ Talos and Deneva products.

Read the individual product reviews in the Storage Review article text for exhaustive discussions of the technology involved. Exhaustive I say - and that's me saying it! ®

The essential guide to IT transformation

More from The Register

next story
The Return of BSOD: Does ANYONE trust Microsoft patches?
Sysadmins, you're either fighting fires or seen as incompetents now
Microsoft: Azure isn't ready for biz-critical apps … yet
Microsoft will move its own IT to the cloud to avoid $200m server bill
Oracle reveals 32-core, 10 BEEELLION-transistor SPARC M7
New chip scales to 1024 cores, 8192 threads 64 TB RAM, at speeds over 3.6GHz
Docker kicks KVM's butt in IBM tests
Big Blue finds containers are speedy, but may not have much room to improve
US regulators OK sale of IBM's x86 server biz to Lenovo
Now all that remains is for gov't offices to ban the boxes
Gartner's Special Report: Should you believe the hype?
Enough hot air to carry a balloon to the Moon
Flash could be CHEAPER than SAS DISK? Come off it, NetApp
Stats analysis reckons we'll hit that point in just three years
Dell The Man shrieks: 'We've got a Bitcoin order, we've got a Bitcoin order'
$50k of PowerEdge servers? That'll be 85 coins in digi-dosh
prev story

Whitepapers

5 things you didn’t know about cloud backup
IT departments are embracing cloud backup, but there’s a lot you need to know before choosing a service provider. Learn all the critical things you need to know.
Implementing global e-invoicing with guaranteed legal certainty
Explaining the role local tax compliance plays in successful supply chain management and e-business and how leading global brands are addressing this.
Build a business case: developing custom apps
Learn how to maximize the value of custom applications by accelerating and simplifying their development.
Rethinking backup and recovery in the modern data center
Combining intelligence, operational analytics, and automation to enable efficient, data-driven IT organizations using the HP ABR approach.
Next gen security for virtualised datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.