Consolidate a Performance-Driven App: Virtualizing Infrastructure
Abstract
An end-user case study with Electronic Sports League (ESL) using VMware ES 3.5U1* with NetQueue feature running on Intel® Xeon® processor 7400 series-based servers with Intel® NICs supporting VMDq feature. Game servers are mission-critical, single-threaded, processor-intensive, and network-latency sensitive. They were previously believed to be “non-virtualizable” due to the overhead of virtualization. In this case, we will show that game QoS can be preserved on virtualized game servers when using the latest technologies noted above. We’ll also show that large server consolidation ratios and cost savings can be achieved at the same time.
Introduction—can we virtualize everything?
Virtualization of enterprise data center applications using hypervisors or VMMs is taking a predictable path. It started with the consolidation of the simplest, least performance-sensitive, and least mission-critical applications, many of which had hardware utilization figures in the 10 percent or less range. These applications were the “low-hanging fruit” of the first wave of application virtualization, and consolidation ratios were quite high while still delivering adequate performance. This consolidation wave delivered a significantly positive ROI to the organizations. IT organizations would like to have the benefits of virtualization across the entire spectrum of applications, but there are challenges to delivering on this potential.
“Non-virtualizable” applications
Not all enterprise applications fit the description above, of course. There are more complex, high-performance, and mission-critical applications, too. Many of these applications are very demanding of the hardware resources in state-of-the-art servers; therefore, we expect that it would be more difficult to virtualize them while retaining adequate performance. Examples of some of the generic types of applications that don’t fit the “low-hanging fruit” description are those characterized by the following characteristics.
From our experiences with virtualization, we know there are certain overheads involved with delivering the value that a VMM/hypervisor provides. These overheads can impact all the characteristics noted above. This leads to the perception that these types of applications “can’t be virtualized” because the tradeoffs would be too severe. Is this a perception or reality?
Read the full Consolidate a Performance-Driven App: Virtualizing Infrastructure Case Study.
694KB
We are sorry, This PDF is available in download format only
Consolidate a Performance-Driven App: Virtualizing Infrastructure
Abstract
An end-user case study with Electronic Sports League (ESL) using VMware ES 3.5U1* with NetQueue feature running on Intel® Xeon® processor 7400 series-based servers with Intel® NICs supporting VMDq feature. Game servers are mission-critical, single-threaded, processor-intensive, and network-latency sensitive. They were previously believed to be “non-virtualizable” due to the overhead of virtualization. In this case, we will show that game QoS can be preserved on virtualized game servers when using the latest technologies noted above. We’ll also show that large server consolidation ratios and cost savings can be achieved at the same time.
Introduction—can we virtualize everything?
Virtualization of enterprise data center applications using hypervisors or VMMs is taking a predictable path. It started with the consolidation of the simplest, least performance-sensitive, and least mission-critical applications, many of which had hardware utilization figures in the 10 percent or less range. These applications were the “low-hanging fruit” of the first wave of application virtualization, and consolidation ratios were quite high while still delivering adequate performance. This consolidation wave delivered a significantly positive ROI to the organizations. IT organizations would like to have the benefits of virtualization across the entire spectrum of applications, but there are challenges to delivering on this potential.
“Non-virtualizable” applications
Not all enterprise applications fit the description above, of course. There are more complex, high-performance, and mission-critical applications, too. Many of these applications are very demanding of the hardware resources in state-of-the-art servers; therefore, we expect that it would be more difficult to virtualize them while retaining adequate performance. Examples of some of the generic types of applications that don’t fit the “low-hanging fruit” description are those characterized by the following characteristics.
From our experiences with virtualization, we know there are certain overheads involved with delivering the value that a VMM/hypervisor provides. These overheads can impact all the characteristics noted above. This leads to the perception that these types of applications “can’t be virtualized” because the tradeoffs would be too severe. Is this a perception or reality?
Read the full Consolidate a Performance-Driven App: Virtualizing Infrastructure Case Study.
