International Business Machines Corporation

Harshad S Padhye

Amitabha Biswas

Sushma Anantharam

Vijoy A Pandey

Keshav G Kamble

Abhijit Prabhakar Kumbhare

Jayakrishna Kidambi

Nirapada Ghosh

John I Buswell

Dorit Rond

Embodiments of the invention provide a method for data replication in a networking system comprising multiple computing nodes. The method comprises maintaining a data set on at least two computing nodes of the system. The method further comprises receiving a data update request for the data set, wherein the data update request includes a data update for the data set. The data set on the at least two computing nodes is updated based on the data update request received.

Data replication for a virtual networking system

In one embodiment, an apparatus includes a buffer memory, at least one ingress port, at least one egress port, at least one processor, and logic integrated with and/or executable by the at least one processor, the logic being configured to communicate with a software-defined network (SDN) controller, store one or more look-up tables in a first portion of the buffer memory, receive a packet using an ingress port, and determine an egress port for the packet. In another embodiment, a method for switching packets in a SDN includes storing one or more look-up tables in a first portion of a buffer memory of a SDN-capable switching device, receiving a packet using an ingress port of the switching device, and determining an egress port for the packet.

Dual purpose on-chip buffer memory for low latency switching

Embodiments of the invention provide a method for load balancing a networking system comprising multiple computing nodes. The method comprises maintaining one or more data sets on at least one computing node. The method further comprises receiving, from each computing node, a load information unit for the computing node, wherein the load information unit relates to resource usage on the computing node. For each computing node, the method determines whether the load information for the computing node exceeds a corresponding load threshold for the computing node. A data set on at least one computing node is transferred to another computing node when the load information for the at least one computing node exceeds a corresponding load threshold for the at least one computing node.

Load balancing for a virtual networking system

In the context of a client sub-system that requires the use of directory services on behalf of a tenant (such as an overlay tenant), learning an identity of a server node, that can provide such directory services by: (i) sending, by the client sub-system to a first server node, a first directory service request for directory service for a first tenant; (ii) receiving, by the client sub-system, a first acknowledgement from a second server node; and (iii) learning, by the client sub-system, that the second server node can provide directory service for the first tenant based upon the first acknowledgement.

Directory service discovery and/or learning

In one embodiment, an apparatus includes a buffer memory, ingress ports, egress ports, at least one processor, and logic integrated with and/or executable by the at least one processor. The logic is configured to communicate with a software-defined network (SDN) controller, store a look-up table in a first portion of the buffer memory, receive a packet using an ingress port of the apparatus, start an egress timer upon receipt of the packet, process the packet in order to finish processing prior to the egress timer expiring, determine an egress port for the packet, determine a packet size from information in a header of the packet when packet size information is available in the header, begin to route the packet via the egress port once the egress port is determined, and send the packet to the egress port upon expiration of the egress timer without further processing.

In a method for providing communication integrity within a distributed database computer system, a first node of a plurality of nodes transmits a change notification to a second node of the plurality of nodes. The change notification indicates that the first node has changed from a first version to a second version. The first node receives at least one change confirmation from the second node. The change confirmation confirms acknowledgment of the change notification by the second node and by a third node of the plurality of nodes. The first node updates a version table of the first node to show that the second node and the third node know that the first node has changed from the first version to the second version.

Mechanism for communication in a distributed database

In a method for providing communication integrity within a distributed database computer system, a first node of a plurality of nodes transmits a change notification to a second node of the plurality of nodes. The second node is a neighbor of the first node. The first node receives at least one change confirmation from the second node. The change confirmation confirms acknowledgment of the change notification by the second node and by a third node of the plurality of nodes. The third node is not a neighbor of the first node. Responsive to receiving the at least one change confirmation, the first node determines that all the plurality of nodes have acknowledged the change notification.

In one embodiment, an apparatus includes a buffer memory, at least one ingress port, at least one egress port, at least one processor, and logic integrated with and/or executable by the at least one processor, the logic being configured to communicate with a software-defined network (SDN) controller, store one or more look-up tables in a first portion of the buffer memory, receive a packet using an ingress port, and determine an egress port for the packet. In another embodiment, a method for switching packets in a SDN includes storing one or more took-up tables in a first portion of a buffer memory of a SDN-capable switching device, receiving a packet using an ingress port of the switching device, and determining an egress port for the packet.

A method for providing location independent dynamic port mirroring on distributed virtual switches is disclosed. A controller is provided to configure one or more virtual switches within a group of physical machines to appear as a set of distributed virtual switches. In response to the receipt of a data packet at a port of a physical machine, a determination is made whether or not the port has a monitor port located on the physical machine. If the port has a monitor port located on the same physical machine, a copy of the data packet is sent to the monitor port of the physical machine. If the port has a monitor port located on a different physical machine, a copy of the data packet along with an identification (ID) of the port and an ID of the monitor port are encapsulated, and the encapsulated information are sent to a controller.

Method for providing location independent dynamic port mirroring on distributed virtual switches

Techniques for providing location independent dynamic port mirroring on distributed virtual switches is disclosed. A controller is provided to configure one or more virtual switches within a group of physical machines to appear as a set of distributed virtual switches. In response to the receipt of a data packet at a port of a physical machine, a determination is made whether or not the port has a monitor port located on the physical machine. If the port has a monitor port located on the same physical machine, a copy of the data packet is sent to the monitor port of the physical machine. If the port has a monitor port located on a different physical machine, a copy of the data packet along with an identification (ID) of the port and an ID of the monitor port are encapsulated, and the encapsulated information are sent to a controller.

Growing community of inventors

Santa Clara, CA, United States of America

Harshad S Padhye