Our theme this month is intelligent data center management software tools. Data center management technologies have come a long way, as companies find themselves having to manage ever bigger and more diverse environments. From using machine learning to improve data center efficiency to using automation to manage everything from servers to cooling systems, we explore some of the latest developments in this space.
Mesosphere’s promise to give enterprises the hyper-scalable distributed technology stack Google has built for itself has vowed a range of heavyweight investors, from some of Silicon Valley’s top IT vendors and venture capital firms to the CIA.
While its technology surely isn’t simple, the idea is: all your IT resources, be they bare-metal servers and VMs in your own data center or virtual infrastructure in Amazon’s cloud, should be managed as a single system. That’s what the company built its Data Center Operating System to do – it’s quite literally an OS for the entire data center, abstracting disparate resources into unified pools applications can call on.
DC/OS, which San Francisco-based Mesosphere recently open sourced, covers a wide scope of infrastructure types, but it’s hard to call it truly comprehensive because it’s missing one crucial part: the physical and starkly finite data center infrastructure resources – space, power, and cooling capacity.
Mesosphere’s partnership with the Austin-based startup Vapor IO, announced last week, is about filling that gap. The two companies will integrate DC/OS with Vapor’s OpenDCRE, its up-to-date take on a nearly 20-year-old server management protocol that feeds data on hardware vitals – such as power, system temperature, and even a box’s on/off status – to any system that needs it via a modern open API.
OpenDCRE is Vapor’s answer to IPMI (Intelligent Platform Management Interface), the group of server management and monitoring specs that came out in 1998 and continues to be in widespread use, supported by virtually all major hardware vendors. OpenDCRE basically offers the same functionality but provides it in a way a DevOps engineer can understand and use.
Cole Crawford, Vapor founder and CEO, says the integration of this physical server management functionality into DC/OS is only part of the partnership with Mesosphere. Vapor is working on a product called Mist, which will combine the two but also provide infrastructure cost analysis and the ability to set up and enforce IT policies using all the operational data the combination provides.
“If you think of DC/OS as an engine, Mist would be a car,” Crawford said. “You can think of it as a distribution of DC/OS.”
One of the goals is to give IT teams visibility into the real cost of running any particular application on any type of infrastructure so they can decide which is the most cost-effective way to go while complying with policies. An application may be running in a company-owned data center taking up costly resources while its security and performance requirements can be perfectly met by a public cloud provider at a lower cost for example. Mist will be able to give that insight, Crawford said.
It will also give users the ability to automate workload scheduling based on policy they set up. If a server crosses a pre-defined temperature threshold, for example, Mist will be able to spin down some Docker containers running on that server and launch them on a different machine that has more headroom or in a cloud.
“We apply a much more granular and vigorous policy rule set to federated cloud (than DC/OS does),” Crawford said.
Mist is still in the works, but he expects the company to start private beta deployments quickly, planning for the first general-availability release before the end of the year. “We’re working with a company right now on the first implementation of Mist,” he said.