United States
Site Map Contacts Hitachi Global Community
Hu's Blog - Data Storage and Virtualization Thought Leader Hitachi - Inspire the Next

Hu Yoshida's Blog - Vice President | Chief Technology Officer

Home > Corporate > HDS Blogs > HDS Bloggers > Hu's Blog
Products, Solutions and more

Hu's Blog

Hitachi NAS Differences for Cloud and Big Data

by Hu Yoshida on Apr 6, 2012

The Hitachi NAS Platform (HNAS) is different from other NAS solutions in three major ways.

First, HNAS is a hardware-accelerated NAS solution based on FPGAs—Field Programmable Gate Arrays—and not an appliance. This is very similar in evolution to network routers. Initially, network routers were based on software, then they evolved to appliances and eventually to modern day hardware routers. HNAS has taken network attached storage to a similar level. The advantage of a hardware implementation is higher performance, greater reliability and scalability, all at a lower TCO. Hardware acceleration can drive 1.6 Gbps throughput for sequential workloads and up to 200,000 IOPs per node. See the latest SPECsfs NFS results here: http://www.spec.org/sfs97r1/results/sfs97r1.html

The second difference is the object-based file system that enables HNAS to scale to 16 PB of usable capacity, a file system size of 256 TB with 16 million file system objects per directory for “Big Data” requirements. This file system has a global name space and can automatically tier files across storage systems using a feature called “Cross Volume Links”, which is a zero length file on the primary file system that points at a file on a target file system. HNAS is also integrated with our content object store, HCP, for active archive, regulatory compliance, and large object storage for cloud infrastructure.

The third difference is seamless integration with Hitachi SAN storage with HItachi Command Suite and Hitachi Data Discovery Suite for advanced search and index across NAS platforms—including NetApp.

Check out HNAS and match it against your big data and cloud requirements.

Related Posts Plugin for WordPress, Blogger...

Comments (4 )

Roger on 06 Apr 2012 at 3:21 pm

Hi Hu, Would be cool if the HNAS would integrate with HDPS.. Can you disclose any roadmaps perhaps?

Regards,
Roger

John on 23 Apr 2012 at 9:04 pm

Its amusing they call it big data, but its more often big amounts of tiny files, something most filers and file systems choke on.
I’m in the HNAS class this week at the corporate office, and the more I learn about the internal design of the HNAS the more I am impressed.

Marcus Piper on 08 May 2012 at 7:31 am

Hi Hu,

I noticed that DCB is not supported on the network interfaces. When will DCB be supported, and if so, do you have a preferred networking vendor ??

Thanks, Marcus.

Hu Yoshida on 09 May 2012 at 3:21 pm

Hello Marcus,

We are beginning to see products available with the new DCB, Data Center Bridging, protocols. Recently we announced the new Hitachi Compute Blade 500, with an embedded 10 Gpbs Ethernet Fabric switch which we OEM from Brocade.
http://blogs.hds.com/hu/2012/04/hitachi-announces-hitachi-compute-blade-500-with-intel-xeon-e5-2600-processors-and-embedded-10-gig-ethernet-switch.html#more-5800

This is the Brocade VDX 6746 which includes the new DCB protocol with conventional Ethernet and FCoE. CISCO also supports this protocol in their NEXUS switches. There are a number of standards associated with full DCB support and implementation for storage networks will still take some time.

Thanks,
Hu

Hu Yoshida - Storage Virtualization Thought LeaderMust-read IT Blog

Hu Yoshida
Vice President and Chief Technology Officer

Connect with Us

     

Recent Videos

Switch to our mobile site