The single-root I/O virtualization (SR-IOV) standard allows an I/O device to be shared by multiple Virtual Machines (VMs), without losing runtime performance. Virtualization architectures which include SR-IOV virtual functions (VFs) are highly portable and agnostic of underlying virtual machines. SR-IOV can achieve line rate (9.48Gbps) and scale network up to 60 VMs at the cost of only 1.76% additional CPU overhead per VM resulting better throughput, scalability, and lower CPU utilization than other I/O virtualization techniques for networking. Here is an SR-IOV primer and series of videos to help you get started, beginning with the most recent Open vSwitch conference last fall. The videos cover important topics for your virtualization environment such as VXLAN Tunnel End Point (VTEP), live VM migration, and HPC clustering.
Thomas Graf of Noiro Networks presents the next generation of host NICs which will provide stateful encap offload combined with filtering capabilities on the inner header as well as steering of the eSwitch. Combining these features allows for a partial offload of the flow table to hardware even in complex network virtualization context. Allowing OVS to manage the eSwitch of the NIC will allow to use SR-IOV and hardware queue redirection with OVS to accelerate the communication to guests and services.
From September 12th 2013 HPC Advisory Spain Conference, Vangelis Tasoulas from Simula Research Laboratory presents: Virtual Machine Migration with SR-IOV Over InfiniBand, originally presented by Wei Lin Guay from Oracle at the Open Fabrics Workshop on March 26, 2012 in Monterey, CA.
Presented by Glenn Lockwood of SDSC, in the Mellanox theatre during the Supercomputing Conference 2013 in Denver, CO
A simple to understand video explaining how Intel VMDq technology actually works.
IMG Half Float LeftSimple explanation of how Intel's Ethernet Controllers provide SR-IOV support in an Virtualized Environment.
Explanation and demonstration of Intel Flexible Port Partitioning, which uses SR-IOV to partition an Ethernet port within your bare-metal Open Source Operating System.
Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.
Notice revision #20110804