Cloud // Software as a Service
01:26 AM
Connect Directly
Repost This

When Big Data Needs Bare Metal, SoftLayer Fits

SoftLayer touts bare metal cloud service for big data analytics, offers MongoDB with the push of a button.

Cloud Computing Comparison: PaaS Providers
Click above for detailed features matrixes on PaaS vendors
SoftLayer is a different kind of cloud service provider. For one thing, it's smaller than most, with only about 100,000 servers spread across 13 locations around the world. For another, it provides bare metal servers as a service and will move customer workloads from virtual machines to bare metal or back again.

That positions the company to offer a specialized service for users of big data. Big data customers who want to do time-sensitive analytics need not only the CPU power of a host in the cloud without virtualization's overhead but also full access to the data transport bus and I/O ports of the server. On a multi-tenant server, users share those facilities with other users. If the analytic task commands resources frequently the other users can be shortchanged, or else the big data customer's response times would be slowed or paused.

Wednesday at Cloud Connect, a UBM Tech event in Santa Clara, Calif., SoftLayer chief scientist Nathan Day had no comment on recent reports that IBM or EMC is interested in buying SoftLayer, but he was eager to confirm where SoftLayer is making its mark: Bare metal servers for self-provisioning big data users.

Customers using the NoSQL system MongoDB on SoftLayer's bare metal servers prefer the service to the virtualized servers of a big, virtual machine commodity cloud supplier, Day said in an interview on the expo floor. He said customers tell him "bare metal blows away virtualized cloud servers."

[ Want to learn how SoftLayer encourages use of bare metal servers among its cloud services? Read SoftLayer, A New Kind Of Cloud Service. ]

Bare metal is well suited to tasks that require frequent imports of large amounts of data, such as applying inserts and updates to the database and doing quick analyses with export of results, such as analyzing activity on a social networking or large e-commerce site. In other words, bare metal shines on big data tasks associated with lots of I/O.

"Primarily, bare metal beats virtualized servers because virtual servers use shared I/O versus dedicated I/O," explained Harold Hannon, senior software architect at SoftLayer. Leading the effort to establish SoftLayer as a big data analytics vendor, Hannon plans to step up his blogging efforts on the company's website advocating bare metal for analytics.

When handling large amounts of data, Hannon said, it also helps on a bare metal server if the hypervisor's software switch doesn't need to manage the communications inflow and outflow, which can create another slowdown point.

Through its partnership with NoSQL developer 10Gen, SoftLayer also offers MongoDB solutions. According to SoftLayer's website, this solution provides "all the advantages the cloud has to offer but with the performance only we can provide. More RAM capacity. More Storage. More CPU speed. Bare-metal." SoftLayer offers a version of MongoDB that can be automatically configured through an easy-to-use user interface and set up with the push of a button.

SoftLayer lets customers choose and self-provision bare-metal servers as it does virtual servers, although in a throwback to a managed application or hosted service approach, the company charges for bare metal by the month rather than by the hour. It has offered bare-metal servers since 2006.

That said, SoftLayer has not yet established a large presence among other NoSQL system providers or big data users, so it has work to do in order to become known as a differentiated service noted for big data analytics hosting capabilities. But it's intriguing that a service provider may be carving out a niche for keeping bare metal in the cloud.

Attend Interop Las Vegas May 6-10 and learn the emerging trends in information risk management and security. Use Priority Code MPIWK by March 22 to save an additional $200 off the early bird discount on All Access and Conference Passes. Join us in Las Vegas for access to 125+ workshops and conference classes, 300+ exhibiting companies, and the latest technology. Register today!

Comment  | 
Print  | 
More Insights
The next wave in APM
The next wave in APM
Find out how to get the benefits of application monitoring while avoiding the complexity and performance headaches.
Register for InformationWeek Newsletters
White Papers
Current Issue
InformationWeek Government, May 2014
NIST's cyber-security framework gives critical-infrastructure operators a new tool to assess readiness. But will operators put this voluntary framework to work?
Twitter Feed
Audio Interviews
Archived Audio Interviews
GE is a leader in combining connected devices and advanced analytics in pursuit of practical goals like less downtime, lower operating costs, and higher throughput. At GIO Power & Water, CIO Jim Fowler is part of the team exploring how to apply these techniques to some of the world's essential infrastructure, from power plants to water treatment systems. Join us, and bring your questions, as we talk about what's ahead.