Cisco Technology, Inc.

Yoann Desmouceaux

Pierre Pfister

William Mark Townsley

Guillaume Ruty

Mohammed Hawari

Marcel Paul Sosthène Enguehard

Aloÿs Christophe Augustin

David Delano Ward

Andre Jean-Marie Surcouf

Jerome Tollet

Aloys Augustin

Andre Surcouf

Jacques Olivier Samain

Kyle Andrew Donald Mestery

Ian James Wells

Edward Albert Warnicke

Jordan Augé

Giles Douglas Yorke Heron

Mark Townsley

Marcel Enguehard

Marcel Paul Enguehard

Hugo Latapie

Enzo Fenoglio

Eric Philippe Hamel

Eric G Vyncke

W Mark Townsley

Benoît Pit-Claudel

Guillaume Gottardi

Marcel Paul Sosthéne Enguehard

Murali Muniraman

Rucha Sanjay Vaidya

Zhiyuan Yao

Eric Vyncke

Embodiments of the present disclosure provide a stateless, load-aware, hardware load balancer that can be implemented in networking environments such as Data Centers. Exemplary systems and apparatuses are able to fairly distribute connection requests while guaranteeing per-connection consistency (PCC) and minimizing processing latency.

Load-aware hardware load balancer

This disclosure describes methods and systems to externally manage network-to-network interconnect configuration data in conjunction with a centralized database subsystem. An example of the methods includes receiving and storing, in the centralized database subsystem, data indicative of user intent to interconnect at least a first network and a second network. The example method further includes, based at least in part on the data indicative of user intent, determining and storing, in the centralized database subsystem, a network intent that corresponds to the user intent. The example method further includes providing data indicative of the network intent from the centralized database subsystem to a first data plane adaptor, associated with the first network, and a second data plane adaptor, associated with the second network.

Method and system for managing network-to-network interconnection

Techniques are described for providing a distributed application load-balancing architecture that supports multipath transport protocol for client devices connecting to an application service. Rather than having client devices generate new network five-tuples for new subflows to the application servers, the techniques described herein include shifting the burden to the application servers to ensure that the new network five-tuples land in the same bucket in the consistent hashing table. The application servers may receive a hashing function utilized by the load balancers to generate the hash of the network five-tuple. By having the application servers generate the hashes, the load balancers are able to continue stateless, low-level processing of the packets to route them to the correct application servers. In this way, additional subflows can be opened for client devices according to a multipath transport protocol while ensuring that the subflows are routed to the correct application server.

Distributed resilient load-balancing for multipath transport protocols

Systems, methods, and computer-readable media for reducing distributed storage operation latency using segment routing. In some examples, a method can involve receiving, from a client, a message identifying an intent to store or retrieve data on a distributed storage environment, and sending to the client a segment routing (SR) list identifying storage node candidates for storing or retrieving the data. The method can involve steering a data request from the client through a path defined by the SR list based on a segment routing header (SRH) associated with the request, the SRH being configured to steer the request through the path until a storage node from the storage node candidates accepts the request. The method can further involve sending, to the client device, a response indicating that the storage node has accepted the request and storing or retrieving the data at the storage node that accepted the request.

Reducing distributed storage operation latency using segment routing techniques

This disclosure describes techniques for providing a distributed scalable architecture for Network Address Translation (NAT) systems with high availability and mitigations for flow breakage during failover events. The NAT servers may include functionality to serve as fast-path servers and/or slow-path servers. A fast-path server may include a NAT worker that includes a cache of NAT mappings to perform stateful network address translation and to forward packets with minimal latency. A slow-path server may include a mapping server that creates new NAT mappings, depreciates old ones, and answers NAT worker state requests. The NAT system may use virtual mapping servers (VMSs) running on primary physical servers with state duplicated VMSs on different physical failover servers. Additionally, the NAT servers may implement failover solutions for dynamically allocated routeable address/port pairs assigned to new sessions by assigning new outbound address/port pairs when a session starts and broadcasting pairing information.

Highly-available distributed network address translation (NAT) architecture with failover solutions

According to certain embodiments, a system comprises one or more processors and one or more computer-readable non-transitory storage media comprising instructions that, when executed by the one or more processors, cause one or more components of the system to perform operations. The operations comprise receiving a packet comprising a source address; selecting an uplink for the packet, the uplink selected from a plurality of uplinks based on an uplink selection policy; determining whether the source address is valid on the selected uplink; determining whether to keep or re-write the source address based on whether the source address is valid on the selected uplink; keeping the source address when the source address is valid on the selected uplink or re-writing the source address when the source address is not valid on the selected uplink; and sending the packet to the selected uplink.

Adaptive source address rewrite

Systems, methods, and computer-readable media for migrating an application container between nodes in a network are disclosed. An interest for an application container may be received by an origin node and, in response, the origin node may transfer a copy of the application container over the network and to a destination node. The origin node can then shut down the application container and transmit any remaining container state and received requests to the destination node. The destination node may then update a routing plane for the network to provide delivery of service requests to the migrated application.

System and method for migrating a live stateful container

Systems, methods, and computer-readable storage media are provided to populate databases with routing data for containers to eliminate the need for continuously accessing a global discovery service. An example method includes initiating, from a source container operating on a first machine in a first rack, a communication with a destination container operating on a second machine on a second rack, wherein a local database on the first machine does not know an address of the destination container. The method includes accessing a global discovery service to provide the address of the destination container, populating the local database on the first machine with the address of the destination container and routing a packet from the source container to the destination container according to the address of the destination container.

System and method of using a global discovery service to enable routing of packets from a source container to a destination container

The present technology provides a system, method and computer readable medium for steering a content request among plurality of cache servers based on multi-level assessment of content popularity. In some embodiments a three levels of popularity may be determined comprising popular, semi-popular and unpopular designations for the queried content. The processing of the query and delivery of the requested content depends on the aforementioned popularity level designation and comprises a acceptance of the query at the edge cache server to which the query was originally directed, rejection of the query and re-direction to a second edge cache server or redirection of the query to origin server to thereby deliver the requested content. The proposed technology results in higher hit ratio for edge cache clusters by steering requests for semi-popular content to one or more additional cache servers while forwarding request for unpopular content to origin server.

Efficient and flexible load-balancing for clusters of caches under latency constraint

This disclosure describes techniques for providing a distributed scalable architecture for Network Address Translation (NAT) systems with high availability and mitigations for flow breakage during failover events. The NAT servers may include functionality to serve as fast-path servers and/or slow-path servers. A fast-path server may include a NAT worker that includes a cache of NAT mappings to perform stateful network address translation and to forward packets with minimal latency. A slow-path server may include a mapping server that creates new NAT mappings, depreciates old ones, and answers NAT worker state requests. The NAT system may use virtual mapping servers (VMSs) running on primary physical servers with state duplicated VMSs on different physical failover servers. Additionally, the NAT servers may implement failover solutions for dynamically allocated routable address/port pairs assigned to new sessions by assigning new outbound address/port pairs when a session starts and broadcasting pairing information.

Growing community of inventors

Paris, France

Yoann Desmouceaux