Low-cost MLC NAND flash gains in enterprise solid-state storage
New solid-state drives (SSDs) coming onto the market will challenge the notion that only single-level cell (SLC) flash SSDs are fit for true enterprise applications.
By submitting your personal information, you agree that TechTarget and its partners may contact you regarding relevant content, products and special offers.
Until recently, the conventional wisdom has been that only SLC has the performance and reliability required for the enterprise, while multi-level cell (MLC) NAND flash is more suited for consumer devices.
However, Fusion-io Inc. is planning a new class of enterprise-class NAND flash that it calls single mode level cell (SMLC) that could give customers faster and lower-cost PCI Express-based solid-state storage to plug directly into their servers. And STEC Inc., which supplies SSDs for most of the major storage array vendors, is sampling what it calls enterprise-ready MLC drives with capacities up to 800 GB to its OEM partners.
Now it's a question of how much performance organizations are willing to trade for the cheaper solid-state drive alternatives.
"The best way to take the cost out of enterprise SSD is to use MLC chips that are two to three times cheaper than SLC," wrote Joseph Unsworth, research director at Stamford, Conn.-based Gartner Inc., in an email interview. "The caveat is that the quality must be good enough to last in the enterprise SSD environment."
Read up on when to recommend solid-state disks.
Fibre Channel switch options for SMBs
SMBs often examine different cost-effective solutions for all of their data storage aspects, including choosing between a Fibre Channel switch or an iSCSI switch. So, which is the better deal for an SMB: an 8-port Fibre Channel (FC) switch for $4,000 or a 24-port iSCSI switch from the same vendor for about the same cost? That was the question faced by St. Cloud Orthopedics Specialist, St. Cloud, Minn.
"In terms of port count, the Fibre Channel switch was three times the cost, but that's not the whole story," said Roger Lund, systems information specialist at St. Cloud Orthopedics Specialist. Whether or not the Fibre Channel switch is a good deal depends on a number of factors ranging from your reasons for opting for FC in the first place to your estimates of storage area network (SAN) traffic.
Since the Fibre Channel switch in question was modular, "we didn't have to buy all the FC ports at once. We bought just one shelf of ports," said Lund.
Read up on optimizing customers' iSCSI SANs with the right Ethernet switch.]
Companies struggle to make time for DR tests
There are two things that are obvious about disaster recovery (DR) testing: everybody with a DR plan should test, and most don't test frequently enough.
During a time when IT people are often asked to do more with less, full-blown DR testing can fall by the wayside although administrators may target key pieces of their plans.
Surveys make the first point clear. Symantec Corp.'s annual disaster recovery survey this year found 35% of respondents worldwide with a DR plan do not test it more than once a year, and that number is actually a 12% improvement from 2008. Lack of IT staff time was the top reason given for not testing more, with 48% pointing to that. Disruption to employees, budget restraints, and disruption to customers were all mentioned by at least 40% of respondents.
Find out the differences in disaster recovery testing methods.
Tennis Channel doubles down on tape to prevent fault during live coverage
Data protection became critical for Tennis Channel this year as the cable TV channel broadcast all four Grand Slam events live, including the U.S. Open that began this week.
In anticipation of its first live coverage, the network strengthened the reliability and restore capabilities of data backups as well as archiving and disaster recovery when it built a new broadcast facility last year.
Read the rest of this article on data protection at Tennis Channel.
VMworld 2009: VMware and Cisco support distance VMotion
SAN FRANCISCO -- Cisco Systems Inc. and VMware Inc. pledged support for distance VMotion between data centers up to 200 kilometers apart for its joint customers, although that support remains limited to a specific network configuration while the vendors work out remaining data migration kinks.
The two vendors first published a proof of concept of distance VMotion in late June via the blog of VMware's senior technical marketing architect for networking Guy Brunsdon.
If it can achieve practical applicability, distance VMotion has the potential to let customers carry out disaster avoidance plans when hurricanes or other disasters are forecasted rather than waiting until after a failure. It could also enable workload balancing over multiple data centers automatically and easily move applications in and out of internal and external clouds.
At the time of the first proof of concept, Brunsdon wrote that there were several networking and storage challenges between distance VMotion and practical deployment. At this week's conference, VMware and Cisco officials said Cisco's Data Center Interconnect could be used to extend the Layer 2 networking domain between physically separated data centers. This knocks down the chief networking obstacle to making VMotion work over distance, since VMotion requires virtual servers be migrated within the same IP address space.
Read the rest of this article on VMworld 2009.
Additional storage news