Unlike many of the companies in today’s flash-based solid state disk (SSD) market, Texas Memory Systems has been in the SSD business for more than 30 years. Back in the late 70s they were building SSDs for seismic field data collection, and in the 80s the company’s gear found its way into supercomputers from makers like Floating Point Systems and, later, Cray.
In 2000 Texas Memory Systems (TMS) began to focus on the enterprise SSD market with RAM-based devices (flash memory was still too expensive to build large drives from). These devices needed batteries to preserve data in the event of a system interruption, and some versions even included hard drives to maintain critical data. But they had application in the enterprise where they were just what the CIO ordered, for example storing and providing super fast access to metadata for large filesystems. San Diego Supercomputer Center deployed a RamSan 325 as the metadata server in its 500 TB SAM-QFS filesystem, and dramatically improved its performance — in one specific example from that case study, backup time fell from 21 hours to 34 minutes. Over the next several years this line of products was improved by the addition of native Fibre Channel and then InfiniBand interfaces, but the cost of RAM kept the capacities relatively low compared to hard drives and kept a lid on the market.
As the consumer digital media market pushed down the price of flash memory, many companies started to take advantage of this new platform to build SSDs. In 2007 TMS joined them with the RamSan 500, a 2 TB device in a system form factor with RAID protection for its flash modules, a Fibre Channel interface and a RAM cache. The RamSan solution is different from some of the other less expensive offerings in the market in that it uses single-level cell (SLC) flash memory, which is faster and more reliable than its consumer-oriented cousin, multi-level cell (MLC) flash (it’s MLC that you’ve got in your digital camera).
The RamSan 500 allowed TMS to give its customers higher bandwidth and more capacity for a lower price and opened up new markets and applications for its customers. Where its RAM-based SSD cost $300/GB and put 2 TB in 16U, the new flash-based product costs only $75/GB and put the same amount of storage in 4U. This price/performance opened new applications, and customers are today using the RamSan 500 on clusters for working storage, to host metadata for large filesystems, and to hold very large datasets in memory for data-intensive computing applications. Customers are also using RamSan devices to host video on demand application (large block random reads) and in render farms (small block random reads).
The RamSan 500 remains the core of the TMS product offering for SSD today, but the company is building out new solutions for broader application. The RamSan 20 was announced in March, and is currently shipping. The 20 is a PCI-Express-based SSD that presents with 450 GB of storage for $40/GB. It is designed for smaller clusters and can allow large memory jobs (search databases, for example) to move in core, or to be run on smaller clusters when the number of nodes in the cluster is driven by the amount of memory needed for a job. Woody Hutsell, president at Texas Memory Systems, explained that they’ve received a lot of interest from application vendors who are interested in selling both their software and the hardware to run it effectively. We’ve seen a similar model for GPU-based hardware acceleration plus application software from Acceleware. Hutsell says that this solution can make a lot of sense, especially for non-traditional HPC users where “solutions are more important than pieces.”
Although fast for reads, flash-based memory is still usually slower on writes, and this creates a problem of balance in the system. TMS addresses part of this difference in the RamSan 20 by over-provisioning capacity. Although the card presents as 450 GB of storage to the system, it actually has 640 GB of capacity. The extra chips lets the company’s support software on the PCI card accelerate writes by doing more work in parallel (TMS claims that it can support 40,000 to 50,000 IO/s on write on this device), and the extra chips also allow for better wear leveling. TMS is also concerned about eliminating the impact on host resources of the RamSan 20. The card doesn’t require system memory or CPU from its host, relying instead on its own onboard PPC processor and RAM for functions like flash table management.
Rounding out the company’s SSD offerings today is the RamSan 620, just announced this month. This is a 2U rackmount Fibre Channel device (with IB expected not later than Q3 according to Hutsell) that provides 5 TB of storage for $44/GB.
Although these devices present new opportunities for users and system architects to achieve great performance, it’s still important to remember that flash isn’t for every application today. It is still more expensive than hard disks, and there are situations where they outperform their flash-based cousins. And applications need to have a requirement for very fast random access to data sets to make flash-based SSDs the right decision. Also, error detection and correction, a technology well-understood for RAM, is even more important with flash than with RAM because flash chips are delivered with known bad blocks. As companies look at MLC and higher density SLC, they will have to deploy better ECC algorithms.