Hewlett-packard Development Company, L.p.

Hewlett Packard Enterprise Development LP

Vmware, Inc.

Sujata Banerjee

Puneet Sharma

Sung-Ju Lee

Praveen Yalagandula

Ying Zhang

Sujoy Basu

Parthasarathy Ranganathan

Zhichen Xu

Yoshio Frank Turner

Wenfei Wu

Jeffrey Clifford Mogul

Jean Tourrilhes

Jung Gun Lee

Kyu Han Kim

Joon-Myung Kang

Lucian Popa

Parameswaran Ramanathan

Chunqiang Tang

Junggun Lee

Yadi Ma

Zhiheng Wang

Michael S Schlansker

James Scott Hiscock

Ram Swaminathan

Charles F Clark

Xiaoyun Zhu

Priya Mahadevan

Paul T Congdon

Jayaram Mudigonda

Yaniv Ben-Itzhak

Alvin AuYoung

Jose Renato G Santos

Pranshu Jain

Anu Mercian

David Andrew Thomas

Ran-Fun Chiu

Aditi Ghag

Pramila Mullan

Mark Peek

Yotam Harchol

Alvin Auyoung

Chaithan M Prakash

Amit Kumar Mondal

Alok Shriram

Shishir Garg

Amy Csizmar Dalal

Yongzhe Fan

Joseph P Chabarek

Arjun Singhvi

Pontus Rydin

Dave Lenrow

Manish Jain

Sukesh Garg

Joon Myung Kang

Rita Wouhaybi

Anubhavnidhi Abhashkumar

Brandon Heller

Mario Antonio Sanchez

Raphael Amorim Dantas Leite

David Lenrow

Kim Kyu-Han

A method for containerized workload scheduling can include monitoring network traffic between a first containerized workload deployed on a node in a virtual computing environment to determine affinities between the first containerized workload and other containerized workloads in the virtual computing environment. The method can further include scheduling, based, at least in part, on the determined affinities between the first containerized workload and the other containerized workloads, execution of a second containerized workload on the node on which the first containerized workload is deployed.

Containerized workload scheduling

In some implementations, a method includes conducting, by a network device, a query associated with a network function chain comprising a plurality of switches and middleboxes to verify whether a service performed by the network function chain complies with a Service Level Agreement (SLA); computing, by the network device, based on a result of the query, a difference in metric value between an actual performance metric of a packet passing through a path in the network function chain and an expected performance metric of the packet passing through the path; deriving, by the network device, a probability of SLA violation associated with the path based on the difference in metric value; and selectively monitoring, by the network device, a network of network function chains by monitoring the path for passive performance measurements based on the probability of SLA violation.

Selectively monitoring a network of network function chains based on probability of service level agreement violation

The disclosure provides an approach for enabling network functions to be executed in serverless computing environments. One embodiment employs a per-packet architecture, in which the trigger for launching a serverless computing instance is receipt of a packet. In such a case, each received packet is packaged into a request to invoke network function(s) required to process the packet, and a serverless computing environment in turn executes the requested network function(s) as serverless computing instance(s) that process the packet and return a response. Another embodiment employs a per-flow architecture in which the trigger for launching a serverless computing instance is receipt of a packet belonging to a new traffic flow. In such a case, a coordinator identifies (or receives notification of) a received packet that belongs to a new sub-flow and launches a serverless computing instance to process packets of the sub-flow that are redirected to the serverless computing instance.

Network functions support for serverless and granular computing environments

Example implementations disclosed herein can be used to generate composite network policy graphs based on multiple network policy graphs input by network users that may have different goals for the network. The resulting composite network policy graph can be used to program a network so that it meets the requirements necessary to achieve the goals of at least some of the network users. In one example implementation, a method can include receiving multiple network policy graphs, generating composite endpoint groups based on relationships between endpoint groups and policy graph sources, generating composite paths based on the relationships between the endpoints and the network policy graphs, generating a composite network policy graph based on the composite endpoint groups and the composite paths, and analyzing the composite network policy graph to determine conflicts or errors.

Network policy graphs

In some examples, a system can verify a network function by inquiring a model using a query language is described. In some examples, the system can include at least a memory and a processor coupled to the memory. The processor can execute instructions stored in the memory to transmit a plurality of packets into at least one network function that is unverifiable; describe the at least one network function using a model comprising a set of match action rules and a state machine; inquire the model using a query language comprising a temporal logic to obtain a query result indicating an expected behavior of the plurality of packets; and verify the at least one network function based on the query result and the expected behavior of the plurality of packets.

Verify a network function by inquiring a model using a query language

Example method includes: receiving, by a network device in a network, a first network policy and a second network policy configured by a network administrator, wherein the first network policy comprises a first metric and the second network policy comprises a second and different metric; detecting, by the network device, a conflict between the first network policy and the second network policy; determining, by the network device, a relationship between the first metric and the second metric; modifying, by the network device, at least one of the first network policy and the second network policy to resolve the conflict based on the relationship between the first metric and the second metric; and combining, by the network device, the first network policy and the second network policy to generate a composite network policy that is represented on a single policy graph.

Generating composite network policy

In some examples, a method includes parsing, by a network device, a section of source code associated with a network function provided by a middlebox in a network; extracting, by the network device, a packet processing slice and a state transition slice from the section of source code; generating, by the network device, a plurality of execution paths from the packet processing slice and the state transition slice; and modeling the middlebox by inserting, by the network device, the plurality of execution paths to a match-action table that describes a packet processing model for the middlebox.

Middlebox modeling

Example method includes: receiving, by a network device, a plurality of input policy graphs and a composed policy graph associated with the input policy graphs; dividing the composed policy graph into a plurality of sub-graphs, each sub-graph comprising a plurality of edges and a plurality of source nodes and destination nodes that the edges are connected to; selecting a first subset of sub-graphs that include, as a source node, a disjoint part of an original source EPG for each input policy graph; identifying a second subset within the first subset of sub-graphs that include, as a destination node, a disjoint part of an original destination EPG for the each input policy graph; and verifying whether connectivity in the composed policy graph reflects a corresponding policy in the plurality of input policy graphs for each sub-graph in the second subset.

Verifying whether connectivity in a composed policy graph reflects a corresponding policy in input policy graphs

Example implementations disclosed herein can be used to allocate network resources in a software defined network (SDN). In one example implementation, a method can include receiving a plurality of resource allocation proposals from a plurality of controller modules, instructing the controller modules to generate votes for the plurality of resource allocation proposals, and selecting one of the plurality of resource allocation proposals based on the votes to instantiate the selected resource allocation proposal in the SDN.

Network resource allocation proposals

Systems, methods, and computer-readable executable instructions are provided for implementing an energy proportional network architecture. Implementing an energy proportional network architecture can include determining a number of desired network criteria and a desired number of access ports. A number of switches for the energy proportional network architecture can be calculated from the desired number of access ports and the number of desired network criteria. Implementing an energy proportional network architecture can also include using the number of calculated switches to form the energy proportional network.

Implementing an energy proportional network architecture from desired network criteria

An electronic device has a plurality of environments including respective communication stacks. The environments correspond to respective different user personas. Data associated with the different user personas are communicated in corresponding separate transport flows over the network.

Communicating data associated with different personas of a user

Example embodiments relate to work conserving bandwidth guarantees using priority, and a method for determining VM-to-VM bandwidth guarantees between a source virtual machine (VM) and at least one destination VM, including a particular VM-toVM bandwidth guarantee between the source VM and a particular destination VM. The method includes monitoring outbound network traffic flow from the source VM to the particular destination VM. The method includes comparing the outbound network traffic flow to the particular VM-to-VM bandwidth guarantee. When the outbound network traffic flow is less than the particular VM-to-VM bandwidth guarantee, packets of the flow are directed according to a first priority. When the outbound network traffic flow is greater than the particular VM-to-VM bandwidth guarantee, packets of the flow are directed according to a second priority.

Priority assessment of network traffic to conserve bandwidth guarantees in a data center

A system, method, and non-transitory computer readable medium for virtualizing battery in a personal mobile device or across a group of personal mobile devices controlled by a user are provided. The user specifies a set of power management policies for applications running in the personal mobile device(s). Battery usage per application is monitored and resources for the applications are scheduled based on the monitored battery usage and the power management policies.

Virtualizing battery across a group of personal mobile devices

Identifying a component within an application executed in a network includes obtaining a traffic matrix, the traffic matrix defining a rate for which packets of data are exchanged between VMs corresponding to an application, analyzing the traffic matrix to identify VMs within a component, modifying the traffic matrix to create a modified traffic matrix, and defining, for the application, a tenant application graph (TAG) model based on the modified traffic matrix.

Identifying a component within an application executed in a network

Growing community of inventors

Palo Alto, CA, United States of America

Sujata Banerjee