Wednesday, December 30, 2009

Guest blog: SSDs on the cusp of the next big storage trend – By Jerome M. Wendt, DCIG

December 30, 2009 -- Ever since I’ve been involved with storage, the topic of solid-state disk (SSD) drives has come up in passing from time to time. But my first real hint at how disruptive SSDs were going to be came when I was attending C-Drive, Compellant's annual user conference, in the spring of 2008.

One of the speakers, a Compellent user, was lamenting how difficult it was to optimize a disk array for database performance and how Compellent’s storage system had helped him in that area by striping data across the array. One of the Compellent presenters then asked the user if he would consider using SSDs to improve performance and the user responded positively, which I think caught the presenter off-guard.

The presenter then turned to the audience of end-users and asked them how many would consider implementing SSD technology. Well over 50% of them raised their hands, which again appeared to catch the presenter by surprise. At that point I knew SSD technology was on the cusp of becoming the next big thing in storage, and it was not long after that conference that Compellent announced support for SSDs.

Heading into 2010, SSDs are gaining end-user interest, as well as vendor hype. Already they’re being hailed as the end to high-performance disk drives, and some observers predict that SSDs will eventually replace all disk drives - possibly as soon as the end of this coming decade.

Whether or not that comes to pass remains to be seen. SSD technology is still maturing, and prices have to come down to the point where most businesses can justify and afford deployment.

There are three notable ways that SSDs were positioned for use in the enterprise during 2009, making SSDs my third major trend of 2009. [To read about the other two trends, see “2009: The Beginning of the Corporate Love Affair with Cloud Storage” and “Deduplication is the Big Success Story of 2009.” ]

First, most SSDs are being initially deployed on external networked storage systems. Vendors such as Compellent, Dot Hill, EMC, HDS, Pillar Data Systems and others have added support for SSDs to their storage systems or can virtualize external SSD systems (e.g., NetApp's support for Texas Memory Systems’ RamSan 500).

Installing SSD drives, from providers such as STEC or Pliant Technologies, in existing storage systems was certainly one of the fastest and easiest ways to bring SSDs to market in 2009. However, I’m already questioning how long this trend of putting SSDs into storage systems lasts before companies figure out that they’re not getting the full range of anticipated benefits.

This scenario may take two or three years to play out, but what I eventually see emerging as the problem with putting SSDs into storage systems is the storage network itself.

Most networked storage infrastructures in use today are Ethernet, Fibre Channel, or a mix of both. Unfortunately, neither one of these technologies - even the latest versions - currently offers sufficient bandwidth to deliver on SSD's potential.

One technology that seems best positioned to break this bottleneck is InfiniBand. The problem is that no one outside of the high performance computing (HPC) space seems ready to commit to this protocol or even take a serious look at it. However, the forthcoming network bandwidth logjam is already recognized within storage circles and, in talking with CTOs of a number of storage providers, some are already testing InfiniBand with their storage systems.

Second, SSDs are showing up in servers. In a trend that runs counter to trends over the last decade, storage is moving back inside servers again. This trend is being largely (and I would say almost exclusively) driven by Fusion-io. While I have written a number of blogs about Fusion-io's ioDrives in the past, and their disruptive nature, that’s only part of the story. (Fusion-io puts SSDs on PCI-Express cards that are placed inside of a server to achieve higher performance than what high-end storage systems can achieve.)

The rest of the story has to do with the elimination of cost and complexity. Many storage networks are still neither easy nor intuitive to manage, especially in high-end storage environments.

Fusion-io eliminates the need, and associated expense, to deploy any storage network at all. While its ioDrive reintroduces the inability to easily share unused, excess storage capacity with other servers, its design is so compelling (especially when viewed in the context of cloud computing and cloud storage architectures) that the ioDrive will be a force in the coming years - maybe more so than any other SSD architecture.

Third, SSDs are moving into the storage network. This approach is currently being championed by Dataram with its XcelaSAN product. What makes this approach so different from the other SSD architectures is that it’s not inside the server or the storage system, but resides in the storage network between the servers and back-end storage.

The argument that Dataram makes for this implementation of SSD is that approximately 5% of data on a storage system is active at any one time. However, most storage systems only have a fraction of that much cache. For instance, a disk array with 20TB of active data should in theory have about 1TB of cache in order to provide the read and write performance that high-end applications need.

A quick check will reveal that many midrange storage systems are lucky to offer a fraction of that, with most supporting in the range of 3GB to 5GB of cache. Dataram argues that by putting its XcelaSAN in front of an existing midrange storage system, it can act as an alternative to cache while turning a midrange storage system into a high-end solution at a fraction of the cost.

Not a bad idea, but there are some hurdles to overcome. First, Dataram needs to convince users that placing its device inline between the server and back-end storage is a good idea.

Another hurdle the company faces is from midrange storage system providers. Depending on how Dataram positions its product, why should vendors such as Compellent, Pillar and other midrange providers agree to play second fiddle to Dataram and sit behind its solution, especially if they are offering SSD in their own systems? Further, SSD is becoming lucrative, which means that the disk-array providers would be giving up the big margins to Dataram.

Another potential obstacle Dataram faces is from traditional network storage providers such as Brocade and Cisco. These guys never take kindly to anyone intruding on what they view as their turf, so if Dataram garners any momentum at all, expect these heavyweights to step in and try to snuff it out. So while I like both Dataram's architecture and argument as to why deploying SSD in the network makes sense, convincing the channel to sell it, end-users to buy it, midrange storage system providers to endorse it, and storage networking providers to leave them alone is going to be an uphill challenge.

All this said, SSD gained solid momentum and mind share among end-users in 2009 and is poised to emerge as a major trend in 2010. However, which of these architectures becomes the predominant one remains to be seen. In the near term (2010 to 2011) I’m placing my bets on storage system solutions, but until technologies such as those from Fusion-io reach critical mass, and others from vendors such as Dataram are tested in the market, the real impact of SSD is yet to come.

To read more of Jerome Wendt’s blogs, visit the DCIG web site.

1 comment:

Larry said...

I agree that SSD is one of the next major storage trends. At Panasas, we also got feedback from many users that they would seriously consider SSD to augment storage IO performance. This was the basis for launching our Panasas ActiveStor 9-Series, a hybrid storage platform (DRAM Cache, SSD and traditional disk drives) with intelligent data management between all 3 tiers of storage. The critical component is not the new SSD hardware, but the file system which virtualizes the three tiers of storage and provides fully automatic data management to achieve optimal performance for a broad range of applications.

Larry Jones