Feeds

IBM lets HPC storage get some sleep

DCS9900 orders pyjamas

The essential guide to IT transformation

IBM has updated its high-performance computing storage array - so it can go to sleep.

In an implementation of MAID technology, IBM's DCS9900 HPC storage product can spin down tiers of SATA drives to save power. It gives the 9900 a capability the preceding DCS9550 array had, but which was not inherited by the original 9900 product.

Massive Array of Idle Disks (MAID) technology spins down disks which are not in use to conserve energy. It has been popularised most notably by Copan, and by Nexsan. Effectively, drives are temporarily offline and consume no power, But they have to be spun up when needed, which delays data access.

IBM says the DCS9900 is designed for the storage needs of highly scalable, data streaming applications served by Deep Computing systems, System p High Performance Computing (HPC) systems, Broadcast Video, and System x 1350 Linux Cluster systems.

It connects by eight 8Gbit/s Fibre Channel or eight 4X DDR InfiniBand ports to its host servers, and consists of a CP2 controller model, with dual controllers inside it, and expansion units.

These can be up to 20 Model 3S1 SAS/SATA Storage Expansion Units, scalable from 150 disks (21.9TB) to 1,200 disks (1.2PB with 1TB SATA Drives), or up to 20 Model 3S2 SAS Storage Expansion Units, scalable from 80 disks (11.68TB) to 320 disks (144TB). The SATA drives spin at 7,200rpm and the SAS ones at 15,000rpm, providing a focus for either disk I/O performance or capacity. The I/O performance scales up to 5.6GB/sec throughput.

This DCS9900 product incorporates hardware RAID 6 to protect against double drive failures in a redundancy group. It groups drives in sets of ten disks. These sets are known as RAID-6 ranks and disks in a rank must be the same type and capacity. In sleep mode, idle SATA drive ranks are placed in standby mode, meaning non-rotating platters with heads parked to save power.

IBM asserts that: "In contrast to competing systems offering MAID capability that do not have all drives operational at the same time, the DCS9900 system maintains full performance capabilities, and is designed for use as both primary and secondary near-line storage."

This seems to be a dig at Copan, which packs its drives so closely together that they cannot all be active at once, as the Revolution array might over-heat. It is a deliberate Copan design choice and enables its MAID product to offer a far higher storage density than others.

IBM says the DCS9900 controller supports "managed Quality of Service to provide uninterrupted data delivery, as well as source all of its performance from multiple target LUNs or a single target "PowerLUN," reducing the need for host-based striping software." There is no news about IBM using solid state drives in this product.

A precursor to the DCS9900, the DCS9550, also had spin down. This used a CP1 controller and supported Fibre Channel or SATA drives and, after an mid-life upgrade, a maximum capacity of 960TB and 2.8GB/sec throughput. The DCS9900 (pdf) was announced as a bigger and faster brother of the 9550 in October last year, but came with no spin-down capability. This announcement fixes that gap.

The system is available from 29 May onwards. No pricing information was revealed. More details here (pdf). &reg

Boost IT visibility and business value

More from The Register

next story
Pay to play: The hidden cost of software defined everything
Enter credit card details if you want that system you bought to actually be useful
Shoot-em-up: Sony Online Entertainment hit by 'large scale DDoS attack'
Games disrupted as firm struggles to control network
HP busts out new ProLiant Gen9 servers
Think those are cool? Wait till you get a load of our racks
Silicon Valley jolted by magnitude 6.1 quake – its biggest in 25 years
Did the earth move for you at VMworld – oh, OK. It just did. A lot
VMware's high-wire balancing act: EVO might drag us ALL down
Get it right, EMC, or there'll be STORAGE CIVIL WAR. Mark my words
Forrester says it's time to give up on physical storage arrays
The physical/virtual storage tipping point may just have arrived
prev story

Whitepapers

Top 10 endpoint backup mistakes
Avoid the ten endpoint backup mistakes to ensure that your critical corporate data is protected and end user productivity is improved.
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.
Backing up distributed data
Eliminating the redundant use of bandwidth and storage capacity and application consolidation in the modern data center.
The essential guide to IT transformation
ServiceNow discusses three IT transformations that can help CIOs automate IT services to transform IT and the enterprise
Next gen security for virtualised datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.