Microsoft Technology Licensing, LLC

Daniel Max Firestone

Harish Kumar Chandrappa

Sambhrama Madhusudhan Mundkur

Somesh Chaturmohta

Norman C Lam

Milan Dasgupta

Alec Kochevar-Cureton

Deepak Bansal

Jitendra Dattatraya Padhye

Rishabh Tewari

Andrew Richard Putnam

Xinyan Zan

Young Lee

Albert Gordon Greenberg

Michal Czeslaw Zygmunt

Khoa Anh To

Fengfen Liu

Adarsh Kirnelli Rangaiah

Alireza Dabagh

Lihua Yuan

Pankaj Garg

Shachar Raindel

George Varghese

Anil A Ingle

Madhan Sivakumar

Jayesh Kumaran

Sheng Lu

Eric Lawrence Albert Lantz

Rohan Gandhi

Murari Sridharan

Parag Sharma

Omar Cardona

Narasimhan Agrahara Venkataramaiah

Vivek Bhanu

Derek Chiou

Jonathan Paul Rosenberg

Yimin Deng

Mahmoud S Elhaddad

Bryan William Tuttle

Yue Zuo

Keith Loren Mange

Yu-Shun Wang

James Wesley Boerner

Neeraj Motwani

Ranjit Puri

HoYuen Chau

David Michael Brumley

Jack Thomas Lavier

Anish Sagar Narsian

Abhijeet Kumar

Deepak Narula

Anitha Adusumilli

Xuan Zou

Vikas Bhardwaj

Hoyuen Chau

Manish Tiwari

Arjun Roy

Rishbah Tewari

Keerthi Shankar

Anil Ingle

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

Described herein are systems and methods for supporting multicast for virtual networks. In some embodiments, a native multicast approach can utilized in which packet replication is performed on a host node of a virtual machine (VM) with a multicast data packet encapsulated in uniquely address unicast packets. In some embodiments, a network virtual appliance can be utilized. A multicast packet sent from the VM can be unicasted to the network virtual appliance. The multicast appliance can then replicate the packet into multiple copies and send the packets to the receivers in the virtual network as unicast data packets encapsulating the multicast packet.

Multi-cast support for a virtual network

A virtual network comprising virtual machines executing at a computing environment is implemented. A software defined networking (SDN) appliance is configured to provide a connection to computing resources via a virtual network of a virtual computing environment. The SDN appliance includes a network interface card that are operable to interact with multiple field-programmable gate array (FPGA) devices are configured to be a hardware acceleration device for processing data traffic, and the FPGA device is configured to ingress a packet to a dataflow on one port and egress the packet from a different port associated with a different dataflow.

Fault tolerance for SDN gateways using network switches

A physical server with an offload card including a SoC (system-on-chip) and a FPGA (field programmable gate array) is disclosed. According to one set of embodiments, the SoC can be configured to offload one or more hypervisor functions from a CPU complex of the server that are suited for execution in software, and the FPGA can be configured to offload one or more hypervisor functions from the CPU complex that are suited for execution in hardware.

Server offload card with SoC and FPGA

Described herein is a system and method for flow state save/restore of a virtual filtering platform. A first instance of a driver manages policy and flow state for ongoing flows between client device(s) and virtual machine(s). The virtual filtering platform is transitioned from the first instance of a driver to a second instance of the driver by serializing the policy and state for the ongoing flows on the first instance of the driver using a one pass algorithm. The serialized policy and state for the ongoing flows can be de-serialized with the ongoing flows re-established and/or reconciled on the second instance of the driver in accordance with the de-serialized policy and state for the plurality of ongoing flows. In some embodiments, a memory management technique can use a single operating system memory allocation call to allocate memory for the transition, with the technique managing utilization of the allocation memory.

Network policy and flow state save/restore for highly available servicing

A network appliance is configured to receive a packet having an address of a custom device as a source address. Policies are accessed that are applicable to a virtual network associated with the custom device. The policies are applied to the packet. A hairpin layer redirects the packet to a destination address contained in the packet. For subsequent packets, application of the policies is bypassed to the subsequent packets. Application of the policies is offloaded to an acceleration device.

Third-party hardware integration in virtual networks

Described herein is a system and method for managing network flow state for ongoing flows (connectionless protocol flows and connection-based protocol flows) between client device(s) and a virtual machine using a flow collection data structure (e.g. hash table) having a predefined maximum quantity of ongoing flows that can be managed. When it is determined that the flow collection data structure is managing greater than an acceptable threshold of connectionless protocol flows, at a dynamically adjustable frequency, flow state for more connectionless protocol flow(s) having an unexpired time-to-live are expired. The frequency can be adjusted based upon a rate at which new flows are being created and/or a rate at which flows are being deleted. Also described herein is a system and method in which, at a particular frequency, only a portion of the flows in the flow collection data structure are evaluated in order to minimize impact on packet processing.

Network flow state management for connectionless protocol(s)

Techniques for facilitating load balancing in distributed computing systems are disclosed herein. In one embodiment, a method includes receiving, at a destination server, a request packet from a load balancer via the computer network requesting a remote direct memory access ('RDMA') connection between an originating server and one or more other servers selectable by the load balancer. The method can also include configuring, at the destination server, a rule for processing additional packets transmittable to the originating server via the RDMA connection based on the received reply packet. The rule is configured to encapsulate an outgoing packet transmittable to the originating server with an outer header having a destination field containing a network address of the originating server and a source field containing another network address of the destination server.

Load balancing in distributed computing systems

A DHCP server implementation includes transmission of a DHCP packet from a virtual machine executing on a server node to a node agent executing on the server node, generation, by the node agent, of a DHCP response packet based on the DHCP packet and on DHCP information previously stored in a local memory of the server node, and transmission of the DHCP response packet from the node agent to the virtual machine. Neither the DHCP packet transmitted by the virtual machine nor the DHCP response packet are transmitted out of the server node.

On-node DHCP implementation for virtual machines

Techniques are described herein that are capable of monitoring connectivity and latency of network links in virtual networks. For instance, a ping agent injects first ping packets into network traffic on behalf of hosts in the virtual network. The ping agent monitors incoming packets to identify first ping response packets, which are in response to the first ping packets, among the incoming packets. A ping responder rule that is included in inbound packet filter rules for a port in a virtual switch intercepts second ping packets in the network traffic. The ping responder rule converts the second ping packets into second ping response packets and injects the second ping response packets into outbound packet filter rules to be transferred to sources from which the second ping packets are received.

Monitoring connectivity and latency of a virtual network

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

Methods and devices for determining settings for a virtual machine may include partitioning a physical network into a plurality of traffic classes. The methods and devices may include determining at least one virtual enhanced transmission selection (ETS) setting for one or more virtual machines, wherein the virtual ETS setting includes at least one virtual traffic class that corresponds to one of the plurality of traffic classes. The methods and devices may include transmitting a notification to the one or more virtual machines identifying the virtual ETS setting.

Virtualizing datacenter bridging settings for virtual network adapters

Growing community of inventors

Seattle, WA, United States of America

Daniel Max Firestone