HDS' Victoria: One Storage Queen To Rule Them All!
Last month, Hitachi Data Systems unveiled the much-anticipated refresh of its USP-V enterprise storage platform. The new product, internally codenamed Victoria and officially named the Virtual Storage Platform (VSP), is packed with features and seems to me well worth the wait. The same day HDS made the VSP announcement, HP also announced the release of its P9500, which it OEMs from Hitachi; HP rebrands the VSP and uses its own management software.
Last month, Hitachi Data Systems unveiled the much-anticipated refresh of its USP-V enterprise storage platform. The new product, internally codenamed Victoria and officially named the Virtual Storage Platform (VSP), is packed with features and seems to me well worth the wait. The same day HDS made the VSP announcement, HP also announced the release of its P9500, which it OEMs from Hitachi; HP rebrands the VSP and uses its own management software.3D Without The Glasses
The VSP allows you to leverage storage in three main ways:
Scale Deep lets you leverage storage virtualization and virtualize all your storage infrastructures behind the VSP for a maximum capacity of 255 PB. The obvious benefits are storage consolidation, but it goes beyond that in its ability to use the virtualized storage in the second-dimension Scale Up.
Scale Up (and down) is probably THE coolest feature of the VSP; it allows you to dynamically and automatically move data between different storage tiers based on a configured policy. This feature is known as Dynamic Tiering, or Sub-LUN Tiering. It allows you to group SATA, SAS and SSD disks, for example, in a single large resource pool; the system will then move data between the tiers based on a "heat index" that determines which pages are being heavily utilized.
It moves the heavily utilized pages to tier 1 disks, thereby allowing them to gain the performance they need; as the heat index for these pages goes down, it moves them to lower-tier disks. This not only saves money on tier 1 disks and dedicating applications to this tier indefinitely, it allows all applications and workloads to more efficiently get access to the right storage tier at the right time. Furthermore, it allows external virtualized storage to participate in this technology, thereby maximizing your investment in external storage and treating these systems as raw resources.
Scale Out is a grid-type approach that allows you to add multiple physical resource modules (compute and capacity) and logically group them to act as a single entity.
SAS Back End
As of this writing, the VSP is the first enterprise-class storage array to have a SAS (Serial Attached SCSI) back end; this would replace the current Fibre Channel Arbitrated Loop (FC-AL). With this change, HDS also introduces the 2.5 inch disk drives to replace the 3.5 inch drives. While 3.5 inch drives currently have higher capacity, can save more on power, and deliver higher performance, the future is most definitely in the 2.5 inch disk drive, which can provide much more storage capacity in the same amount of space.
Secure MultiTenancy, or SMT, is a feature of the VSP that I am also particularly interested in as it would be an enabler of cloud technology, both public and private. While the benefits to public clouds are obvious for those providers that will host multiple clients' data, the benefits to private clouds are equally important as many organization require separation of data within the different departments of the organization, or they would require this separation as they interact with data they receive from their customers. Legal consulting and market research firms are among the many that come to mind right away.
The Command Suite Management Software
After seeing the software, one of my colleagues paused for a few minutes then said, "Wow, you guys went from having the worst software on the planet to having one of the best interfaces on the planet." This pretty much sums up the drastic change that was made to the management software.
You no longer have to install each piece separately; you install it once and enable the features you want based on a license key. The interface is very GUI-driven, very fast, and when the software is doing something, you will see an animation that tells you, in effect, "I'm still here, I'm executing your task."
I will write more about the management software soon, especially the orchestration piece, as it does an amazing job at provisioning resources from physical, to logical, all the way to a functional virtual machine.
One area of (limited) disappointment with the VSP announcement was that it did not include support for VMware's VAAI or vStorage APIs for Array Integration. In summary, VAAI makes storage arrays VM-aware and as a result improves performance greatly. That being said, HDS did promise support in the first code update, which is due about 60 days after the initial launch date.
To sum it all up, the VSP lives up to the expectations of an enterprise-class storage platform with flexibility, scalability, security, and performance at the core of its architecture.
There are tons more new features in the VSP, I make mention of my favorites in this post, but for more technical deep dive, check out Nigel Poulton's blog and StorageNerve's blog.
Disclaimer: I work for a system integrator that partners with HDS, HP, EMC, Dell, Xiotech and others. The opinions expressed here are my own and do not represent my employer.
Elias Khnaser is the practice manager for virtualization and cloud computing at Artemis Technology, a vendor-neutral integrator focused on aligning business and IT. Follow Elias on Twitter @ekhnaser
The Agile ArchiveWhen it comes to managing data, donít look at backup and archiving systems as burdens and cost centers. A well-designed archive can enhance data protection and restores, ease search and e-discovery efforts, and save money by intelligently moving data from expensive primary storage systems.
2014 Analytics, BI, and Information Management SurveyITís tried for years to simplify data analytics and business intelligence efforts. Have visual analysis tools and Hadoop and NoSQL databases helped? Respondents to our 2014 InformationWeek Analytics, Business Intelligence, and Information Management Survey have a mixed outlook.