September 09, 2008
NEC is ratcheting up its grid storage platform with new nodes designed to put more data in less space faster.
Relatively speaking, the new HYDRAstor HS8-2000, officially announced today, beats the heck out of the HS8-1000, introduced about a year ago. NEC says the second generation boosts performance by about 300 percent and improves disk capacity by 400 percent, while also consuming less power. The system is optimized for backup and archiving purposes, but nearline storage is where NEC is taking it next.
Two types of nodes comprise a HYDRAstor grid: storage nodes and accelerator nodes. NEC's two-headed approach enables organizations to scale performance and capacity independently in order to meet their particular demands. "The nodes are the building blocks, and you can mix and match them to construct the storage system you need," says Karen Dutch, vice president of advanced storage products for NEC America. "If you have to make adjustments to meet demand, you can add new pieces. Over the last 10 months we've been shipping, we've had many customers add capacity and performance with nodes and did it without disruption. No provisioning, no group creation. And any data that existed in the grid was automatically load balanced."
"The HYDRAstor implementation is full of promise as an approach to storage," says Mark Peters, an analyst with Enterprise Strategy Group who covers storage and datacenter issues. "It is scalable, self-tuning, self-healing and self-managing. Since both the processing side and the capacity side can be scaled independently, it allows for a very flexible single pool of storage. The NEC engineers were basically allowed to start from scratch -- allowing them to really consider how things should be done and what should be included, rather than worry about how things have been."
The new storage nodes, made up of 1TB SATA disk drives, have capacity of 12TB (or "effective capacity" of 157.5TB with a 20:1 deduplication rate). Accelerator nodes, based on 3GHz Xeon quad-core processors, improve data throughput with performance of 300MB per second, NEC says. A starter kit, for example, would bundle one accelerator node and two storage nodes, for raw capacity of 24TB and backup speed of about 16,500MB per second.
The nodes themselves are standard NEC servers, but the "real value-add is the software smarts" that takes HYDRAstor "beyond clustered storage systems," Dutch says. "It's a distributed system, DynamicStor, that gets loaded on all the nodes at set-up and creates a self-managing, self-healing, self-expanding infrastructure. The nodes are self-aware. When you add a node, capacity is automatically discovered. Our software provides the intelligence to manage it all, and from one central location."
NEC describes its storage platform as "self-evolving," meaning owners of the older version can plug the new nodes into their current grid and move up to a higher level of performance without having to replace any hardware or software or do any data migration or provisioning.
Distributed Reduction and Resiliency
NEC says the key to its efficient data storage -- how it gets more data on a platter than competing approaches -- is its brand of data deduplication (which it calls DataRedux). Deduplication, simply put, reduces storage needs by not storing redundant data. Instead, the system saves only one instance of the data; redundant material is replaced with a pointer to the saved copy. The classic example is the e-mail joke attachment that multiplies around the office; deduping would maintain just one copy of that attachment and ditch the rest. HYDRAstor uses distributed technology to "dedupe globally," across the entire grid, which can cut storage capacity needs by as much as 95 percent, Dutch says.
"Competitor solutions deduplicate data separately within each instance of their solution," she explains. "However, once their solution reaches its capacity or performance limitations, a new instance of their solution must be deployed. With no communication or deduplication capability across multiple instances of those solutions, the customer is virtually guaranteed to have multiple copies of some data across different instances of the solution, reducing the overall efficiency and deduplication ratio."
HYDRAstor, however, "deduplicates data globally across the entire grid, ensuring that only unique data is stored once across the entire datacenter. Regardless which accelerator node or which filesystem the data comes from, it gets deduplicated across the entire common pool of storage on the backend to ensure only unique data is stored," she says. "As HYDRAstor scales to larger grid configurations, so does the deduplication engine through automatic re-distribution of the deduplication processing responsibilities across all the storage nodes in the grid."
With all the deduplication, though, data integrity is more important than usual. One lost file could be disastrous in case of rebuild or recovery. NEC says it addresses that with its protection scheme called Distributed Resilient Data (DRD), a patent-pending technology that Dutch says can provide a higher level of protection than RAID 5. "Our default level of 3 provides 300 percent more resiliency than RAID 5," she says. "At that level, the system can withstand three node failures." But if it's RAID 5 you want, you can dial that in, as well, via the management software's GUI. NEC also says data rebuild operations are quicker with DRD.
For disaster recovery, NEC has an optional feature for DynamicStor called RepliGrid Asynchronous Grid-to-Grid Replication. "RepliGrid determines what data being replicated does not already exist on the disaster recovery (DR) site grid, and then compresses and sends only new unique data over the WAN to the DR site grid. This minimizes the amount of bandwidth to reduce DR costs," Dutch says.
RepliGrid is licensed on a per accelerator node basis, so users have the flexibility to only license it for the parts of the infrastructure that need to replicate. RepliGrid supports 1-1 replication as well as N-to-1 Grid-to-Grid Replication. This enables concurrent replication of multiple grids to a single DR site grid, which deduplicates data globally from all sources (both local and remote) to ensure that only unique data is actually stored.
With the considerable compression capabilities, it is apparent NEC's first target is backup and archiving. Dutch says that backup, in particular, benefits from global deduplication and compression since it involves so many repetitious files. "DataRedux coupled with data compression delivers greater than 20:1 capacity space reduction for backup data," Dutch says. "And DRD protection ensures the deduped data is safe at all times."
"We expect more growth in backup and archive environments" she says, "and will also expand into nearline applications, such as Web 2.0, which require affordable enterprise storage that is highly scalable, reliable and delivers high performance."
NEC has tried to make a system that plays well all around. A HYDRAstor grid will work with existing network gear and storage software. "On the front end, we provide the standard protocols, we work with NFS or CICS, we can communicate with any backup or archive software," says Gideon Senderov, director of technical marketing.
Installation also is pretty easy, the company says. According to Dutch, customers are "unboxing and backing up archival data in about 45 minutes."
Coming Up: Geographic Reach
Grid storage has been emerging since the earlier part of the decade, and big players like HP and IBM have systems of similar intent. NEC doesn't seem to pitch HYDRAstor against other solutions, but says its automated management features and storage optimization set it apart. "Other storage capacity optimization solutions may deliver similar space reduction and capacity optimization," Dutch says, "but they lack HYDRAstor's massive scalability, data protection, automatic self-management, and ability to evolve over time. And, finally, HYDRAstor includes data protection technologies that go beyond the limits of RAID and guarantee that deduplicated data is safe."
"NEC is smart to not try, at least initially, to compete head-on with the big boys like EMC, NetApp, HP and IBM in terms of saying HYDRAstor is an 'XYZ killer,'" analyst Peters says. "However, if it can get more traction with the product, the basic architecture could be extended in many ways, and be an approach that morphs into a number of products or simply one very flexible product. NEC's issue is to become a recognized and serious player in storage. With its sheer size, high R&D spend, and strong Japanese market share -- not to mention excellent products -- it clearly has the credibility."
As for the next version, Dutch says "NEC will continue to optimize HYDRAstor for multiple I/O patterns ... and support implementation of multiple storage tiers with different performance and availability characteristics within a single grid." And, she says, the system will evolve "to support geographically dispersed grids that span multiple datacenters and deliver a paradigm shift from disaster recovery to data resiliency."
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
May 10, 2013 |
Australian visual effects company, Animal Logic, is considering a move to the public cloud.
May 10, 2013 |
Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
May 08, 2013 |
For engineers looking to leverage high-performance computing, the accessibility of a cloud-based approach is a powerful draw, but there are costs that may not be readily apparent.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.