XenServer 6.5 brings Docker support, GPU improvements

XenServer isn't the hypervisor of choice for most IT shops, but Citrix's hypervisor can play a major role in XenApp and XenDesktop environments.

ORLANDO – It's no secret that most Citrix customers use VMware for server virtualization, and industry watchers...

have wondered whether Citrix will continue to invest in XenServer.

The company keeps on keeping on with its hypervisor and recently launched a 64-bit architecture version that offers faster, more efficient VMs and better scalability and density of VM farms.

However, Citrix hasn't made these improvements to compete with VMware or Microsoft's hypervisors for enterprise workload virtualization.

"We aren't trying to get people to take their Oracle databases and run them on XenServer," said Kedar Poduri, senior director of product management for Citrix cloud platforms group.

Instead, Citrix is squarely focused on making XenServer the ideal platform for XenApp and XenDesktop, he said.

It's a strategy that makes sense for Citrix. VMware is the most common server virtualization environment used to host XenDesktop, but by enhancing the VDI experience with features such as improved graphics support and Docker integration, XenServer is more attractive to Citrix's existing XenDesktop customers, said Steve Brasen, an analyst with Enterprise Management Associates, Inc. in Boulder, Colo. 

Indeed, even here in the Synergy bubble where Citrix reigns supreme, attendees prefer VMware for server virtualization. But one IT manager in the healthcare industry said he relies on XenServer for his Citrix virtual desktop and application publishing environment.

"VMware may have more bells and whistles, but XenServer has what you need for XenApp and XenDesktop," he said.

What's new in XenServer 6.5 SP1

XenServer 6.5 became available in January and the first service pack (SP1) launched this week. Many of the new features improve virtual desktop and application performance, particularly for graphics acceleration.

The latest release includes NVIDIA vGPU scalability improvement, now at 96 vGPU sessions per host, in-memory read-cache, workload balancing, workload automation and networking and storage performance improvements.

SP1 also supports Intel GVT-d GPU pass-through for Windows and NVIDIA GPU pass-through for Linux. Intel’s GVT-d support means IT shops that deliver virtual desktops can deploy GPU pass-through to VMs using the natively embedded GPU on the server, without additional hardware. This will improve the end user experience for industries that need to deliver graphic-intensive apps to remote users.

"The graphics acceleration in particular is becoming increasingly important to healthcare organizations to support radiological and other imaging software and education institutions for hosting online classes," Brasen said.

This update also allows IT to double their VM density -- up to 1,000 VMs per host, according to Citrix (though that density varies based on workload demands).

In addition, Docker container support in XenServer 6.5 SP1 lets IT run containers in VMs and use XenCenter for lifecycle management operations, and XenCenter improvements include per-VM visibility of in-memory read-cache usage.

XenServer 6.5 SP1 also brings CoreOS support and Windows 10 template enablement, with official support upon Windows 10 general availability.

XenServer is still available as a free, open source version. XenServer Standard costs $625 or Enterprise Edition for $1,250, plus support.

Additional features available in the enterprise version include in-memory read caching, Dynamic Workload Balancing, GPU Virtualization with NVIDIA GRID, VMware vSphere to XenServer Conversion utilities, Intel Secure Measured Boot and Export Resource Data.

IT shops with XenApp or XenDesktop licenses have an entitlement to XenServer, which includes the enterprise features listed above.

Bridget Botelho is Senior News Director for TechTarget's Data Center Virtualization and End User media groups. Contact her or follow her on Twitter @BridgetBotelho.

PRO+

Content

Find more PRO+ content and other member only offers, here.

Conference Coverage

Citrix Synergy 2015 conference coverage

Join the conversation

1 comment

Send me notifications when other members comment.

By submitting you agree to receive email from TechTarget and its partners. If you reside outside of the United States, you consent to having your personal data transferred to and processed in the United States. Privacy

Please create a username to comment.

Certainly, as you pointed out, enterprises are using GPU pass-through for virtualized graphics processing tasks. And, many enterprises are now starting to use NVIDIA GRID which you mentioned is available in the enterprise edition. Certainly, GPU pass-through will continue to be used. However, the benefit of NVIDIA GRID is that NVIDIA purposely engineered its most recent generation GPU, Kepler, to be the world's first truly virtualizable GPU. Kepler implements a Memory Management Unit (MMU) that maps and translates a host’s virtual address to the system’s physical address. This virtualized GPU is designed to serve multiple concurrent users without performance or latency issues.

This white paper - http://bit.ly/1IMEBRr - NVIDIA GRID: Graphics Accelerated VDI with the Visual Performance of a Workstation - explains the power and design of NVIDIA GRID in depth.

Jeff Rutherford, commenting on behalf of IDG, NVIDIA, VMware, and Dell
Cancel

-ADS BY GOOGLE

SearchVMware

SearchWindowsServer

SearchCloudComputing

SearchVirtualDesktop

SearchDataCenter

Close