Hewlett Packard Enterprise Development LP

Jonathan Michael Seely

Mark Shillingburg

Giuseppe Scaglione

Brian Peter L'Ecuyer

Sergio Jesus Guillen Hernandez

Eric Pelletier

Paymon Ghamami

Steven Glen Jorgensen

Jonathan Manuel Watts

Joseph D Gleason

One aspect of the instant application provides a system and method for managing a switch buffer. During operation, the system establishes a hierarchical accounting structure to determine utilizations of different elements of a buffer on the switch. The hierarchical accounting structure comprises one or more parent elements, and each parent element is associated with one or more child elements. The system determines a base utilization of a child element based on an amount of buffer space allocated to the child element and an amount of buffer space used by the child element, and determines an adaptive utilization of the child element based at least on the base utilization of the child element and a congestion state of a corresponding parent element. Determining the adaptive utilization of the child element comprises performing a table lookup operation. The system then stores a received packet associated with the child element in the buffer in response to the adaptive utilization of the child element being less than a predetermined threshold.

System and method for adaptive buffer management

A system for facilitating an integrated traffic profile for indicating congestion and packet drop is provided. During operation, the system can determine a first traffic profile indicating whether to drop a packet based on the utilization of a queue. The packets from the queue can be forwarded via an egress port reachable via a fabric. The system can also determine a second traffic profile indicating whether to indicate congestion in the packet based on the utilization. The system can then determine a third traffic profile by combining the first and second traffic profiles. The third traffic profile can indicate acceptance at the queue for a subset of packets being selected for dropping based on the utilization. Subsequently, the system can, if the packet is selected for dropping, determine whether to accept the packet at the queue and set a congestion indicator in the packet based on the third traffic profile.

Integrated traffic profile for indicating congestion and packet drop for congestion avoidance

A system for facilitating an enhanced traffic profile is provided. During operation, the system can determine a first traffic profile indicating whether to drop a packet based on the utilization of a queue. The packets from the queue can be forwarded via an egress port reachable via a fabric. The system can also determine a second traffic profile indicating whether to indicate congestion in the packet based on the utilization. The system can then determine a third traffic profile by combining the first and second traffic profiles. The third traffic profile can indicate acceptance at the queue for a subset of packets with a low-level congestion indicator or selected for dropping based on the utilization. Subsequently, the system can, if the packet is selected for dropping, determine whether to accept the packet at the queue with a high-level congestion indicator in the packet based on the third traffic profile.

Integrated traffic profile for indicating multi-level congestion and packet drop for congestion avoidance

Example implementations relate to segment size determination. In an example, the system may include a processing resource and a memory resource storing machine-readable instructions to cause the processing resource to determine a quantity of segments to be generated from a packet, and alter, in response to the determined quantity of segments and a memory block size of a destination port, a segment size for each of the quantity of segments.

Segment size determination

A plurality of work requests may be received from a plurality of clients. A plurality of credits may be distributed among the plurality of clients. The plurality of credits may be distributed in response to a refreshed credit cycle. At least one of the work requests to be processed may be selected based on an amount of the credits available for the clients. An amount of credits to distribute to the clients may be determined in response to the refreshed credit cycle based on an amount of the credits used to process the at least one work request during a last credit cycle compared to a system credit capacity of the system.

Credit distribution to clients

Examples include sampling a transmit rate of an egress port queue on a destination node, determining a utilization percentage of the egress port queue based on the transmit rate and a total rate capacity of the egress port, and determining a backlog percentage of the egress port queue. Examples also include determining an output rate for a virtual output queue on a source node based on the utilization percentage and the backlog percentage. The virtual output queue is for the egress port queue.

Output rates for virtual output queses

Example implementations relate to packet transmission credit allocation. In some examples, a system may include a processing resource and a memory resource storing instructions executable by the processing resource to allocate a first amount of packet transmission credits from a destination node to a source node; determine a modification to the first amount of packet transmission credits allocated from the destination node to the source node based on a comparison of a quantity of redeemed packet transmission credits by the source node to a packet transmission credit threshold of the source node; adjust the modification based on a condition at a buffer associated with the destination node; and apply the adjusted modification to the first amount of packet transmission credits to produce a second amount of packet transmission credits to allocate from the destination node to the source node.

Packet transmission credit allocation

An example of a system may include a processing resource and a controller including a memory resource storing instructions executable by the processing resource to determine a rate of traffic communication at each of a plurality of ingresses participating in a communication of a packet flow context, determine a rate of traffic communication at each of a plurality of egresses participating in the communication of the packet flow context, determine a target packet admission rate applicable to each of the plurality of ingresses from the rate of traffic communication at each of the plurality of ingresses and the rate of traffic communication at each of the plurality of egresses, and communicate the target packet admission rate to an ingress of the plurality of ingresses.

Growing community of inventors

Roseville, CA, United States of America

Jonathan Michael Seely