Microsoft Technology Licensing, LLC

Sambhrama Madhusudhan Mundkur

Daniel Max Firestone

Somesh Chaturmohta

Norman C Lam

Alec Kochevar-Cureton

Alireza Dabagh

Andrew Richard Putnam

Fengfen Liu

Davor Bonaci

Dustin Lyle Green

Sandeep Singhal

Pankaj Garg

Robert C Combs

Narasimha Rao S S Nagampalli

Luis M Hernandez

Techniques are disclosed for implementing direct memory access in a virtualized computing environment. A memory access policy of the virtualized computing environment is applied to a direct memory access connection request received from a first virtual machine via an exception path. The request is flagged to indicate that the request has been processed and the request is forwarded to a network interface device configured to execute offloaded network functions for one or more virtual machines. A memory access policy of the virtualized computing environment is applied to a direct memory access connection reply received from a second virtual machine on the exception path. The reply is flagged to indicate that the reply has been processed and the reply is forwarded to the network interface device. A direct memory access connection is established between first and second virtual machines in accordance with the request.

RDMA with virtual address space

Distributed computing systems, devices, and associated methods of packet routing are disclosed herein. In one embodiment, a method includes receiving, from a computing network, a packet at a packet processor of a server. The method also includes matching the received packet with a flow in a flow table contained in the packet processor and determining whether the action indicates that the received packet is to be forwarded to a NIC buffer in the outbound processing path of the packet processor instead of the NIC. The method further includes in response to determining that the action indicates that the received packet is to be forwarded to the NIC buffer, forwarding the received packet to the NIC buffer and processing the packet in the NIC buffer to forward the packet to the computer network without exposing the packet to the main processor.

Network traffic routing in distributed computing systems

Distributed computing systems, devices, and associated methods of packet routing are disclosed herein. In one embodiment, a computing device includes a field programmable gate array ('FPGA') that includes an inbound processing path and outbound processing path in opposite processing directions. The inbound processing path can forward a packet received from the computer network to a buffer on the FPGA instead of the NIC. The outbound processing path includes an outbound multiplexer having a rate limiter circuit that only forwards the received packet from the buffer back to the computer network when a virtual port corresponding to the packet has sufficient transmission allowance. The outbound multiplexer can also periodically increment the transmission allowance based on a target bandwidth for the virtual port.

Network traffic rate limiting in computing systems

Distributed computing systems, devices, and associated methods of remote direct memory access ('RDMA') packet routing are disclosed herein. In one embodiment, a server includes a main processor, a network interface card ('NIC'), and a field programmable gate array (&#x201c;FPGA&#x201d;) operatively coupled to the main processor via the NIC. The FPGA includes an inbound processing path having an inbound packet buffer configured to receive an inbound packet from the computer network, a NIC buffer, and a multiplexer between the inbound packet buffer and the NIC, and between the NIC buffer and the NIC. The FPGA also includes an outbound processing path having an outbound action circuit having an input to receive the outbound packet from the NIC, a first output to the computer network, and a second output to the NIC buffer in the inbound processing path.

Remote direct memory access in computing systems

Some embodiments of the invention provide a failover capability in a computer system that employs multiple paths to transfer information to and from a network, such as a computer system that performs virtualization, without introducing a new driver component to provide this capability. For example, some embodiments of the invention provide a networking virtual switch client capable of direct communication between a networking stack implemented by a virtual machine operating system and components comprising either a direct path or a synthetic path to a network interface controller coupled to a network. The networking virtual switch client may be capable of determining which of the paths to employ for a given communication, such as by determining that a synthetic path should be employed if a direct path is not available.

Failover mechanism

An extensible virtual switch allows virtual machines to communicate with one another and optionally with other physical devices via a network. The extensible virtual switch includes an extensibility protocol binding, allowing different extensions to be added to the extensible virtual switch. The extensible virtual switch also includes a miniport driver on which the extensions are loaded, tying the lifetimes of the extensions to the lifetime of the extensible virtual switch.

Virtual switch extensibility

Some embodiments of the invention provide a failover capability in a computer system that employs multiple paths to transfer information between virtual machines and a network, without introducing a driver component to provide this capability. For example, some embodiments of the invention provide a networking virtual switch client capable of direct communication between a networking stack implemented by a virtual machine operating system and components comprising either a direct path or a synthetic path to a network interface controller coupled to a network. The networking virtual switch client may be capable of determining which of the paths to employ for a given communication, such as by determining that a synthetic path should be employed if a direct path is not available.

Techniques are disclosed for the non-disruptive and reliable live migration of a virtual machine (VM) from a source host to a target host, where network data is placed directly into the VM's memory. When a live migration begins, a network interface card (NIC) of the source stops placing newly received packets into the VM's memory. A virtual server driver (VSP) on the source stores the packets being processed and forces a return of the memory where the packets are stored to the NIC. When the VM has been migrated to the target, and the source VSP has transferred the stored packets to the target host, the VM resumes processing the packets, and when the VM sends messages to the target NIC that the memory associated with a processed packet is free, a VSP on the target intercepts that message, blocking the target NIC from receiving it.

Non-disruptive, reliable live migration of virtual machines with network data reception directly into virtual machines' memory

Techniques are disclosed for increasing the security of a system where incoming network packets are directly placed into the memory space of a virtual machine (VM) operating system (OS) running on the system via direct memory access (DMA). In an embodiment, each packet is split into a first portion, which requires further processing, and a second portion, which may be immediately placed into the VM OS's memory address space. When the host OS running on the system completes processing the first portion, it places it directly before the second portion in the VM OS memory space and indicates to the VM OS that a packet is available. Techniques are further disclosed that mitigate the security risk in such systems related to VLAN ID configuration.

Growing community of inventors

Sammamish, WA, United States of America

Sambhrama Madhusudhan Mundkur