Extreme Networks, Inc.

Justin N Chueh

Erik R Swenson

Rajarshi Gupta

Ravi Tangirala

Stephen R Haddock

Meera Kasinathan

Michael Yip

Shehzad T Merchant

Andrew H Smith

Herb Schneider

R Steven Smith

David K Parker

David Scott Parker

Meera Siva

A method and system is provided to enable quality of service across a backplane switch for multicast packets. For multicast traffic, an egress queue manager manages congestion control in accordance with multicast scheduling flags. A multicast scheduling flag is associated with each egress queue capable of receiving a packet from a multicast ingress queue. When the multicast scheduling flag is set and the congested egress queue is an outer queue, the egress queue manager refrains from dequeueing any marked multicast packets to the destination ports associated with the congested outer queue until the congestion subsides. When the congested egress queue is a backplane queue, the egress queue manager refrains from dequeuing any marked multicast packets to the destination ports on the destination blade associated with the congested backplane queue until the congestion subsides.

Method and apparatus for providing quality of service across a switched backplane for multicast packets

Methods, systems, and computer program products for allocating excess bandwidth of an output among network users are disclosed. According to one method, packets associated with a plurality of network users for forwarding to an output are received. The packets can include a first non-committed information rate (CIR) packet associated with a first network user. The method can include a step for maintaining a count of non-CIR packets sent for the first network user. Further, the method can include preventing the first non-CIR packet from being forwarded to the output in response to the count having a predetermined relationship with respect to a threshold level.

Methods, systems, and computer program products for allocating excess bandwidth of an output among network users

Methods and systems for fine grain bandwidth allocation are disclosed. According to one method, input is received from a user in a standard bandwidth denomination indicating bandwidth to be provided by a switched network element. The bandwidth is automatically converted into a base bandwidth value and a residual bandwidth value. The base bandwidth value is converted to a number of tokens to be placed in a token bucket every predetermined token bucket refresh interval. The residual bandwidth value is converted into a second number of tokens and a number of predetermined token bucket refresh intervals over which the second number of tokens is to be placed in the token buckets. The token buckets are then refreshed in accordance with the base and residual bandwidth values and the token bucket refresh intervals. The queue is serviced in accordance with available tokens in the token buckets.

Methods and systems for fine grain bandwidth allocation in a switched network element

A method and system is provided to enable quality of service across a backplane switch. An egress queue manager on one blade communicates with an ingress queue manager on the same or on another blade where each blade is connected via a backplane switch. The egress queue managers communicate the congestion to ingress queue managers using a messaging scheme. The ingress queue managers determine when to reduce or resume the packet sending rates of ingress queues mapped to congested egress queues or to destinations on congested blades. Each ingress queue manager maintains information about the status of egress queue congestion on its own blades. Normal rates of dequeuing packets from ingress queues are resumed only when the related congestion on all of the egress queues or related destinations has subsided.

Method and apparatus for providing quality of service across a switched backplane between egress and ingress queue managers

A method and system is provided to enable quality of service across a backplane switch. An egress queue manager on one blade communicates with an egress queue manager on another blade where each blade is connected via a backplane switch. When a blade becomes congested, egress queues mapped to a destination on the congested blade also become congested. The egress queue managers determine when to reduce or resume the packet sending rates of egress queues mapped to destinations on congested blades using a messaging scheme. Each egress queue manager maintains notifications of the status of egress queue congestion on its own and other blades. Normal rates of dequeuing packets are resumed only when the related congestion on all of the blades has subsided.

Method and apparatus for providing quality of service across a switched backplane between egress queue managers

A packet switching device having a central shared memory and a number of medium access controllers each coupled to a communications medium to exchange data packets, and a controller coupled to each medium access controller via a data path to exchange data packets with the media access controller. The controller has a number of data path controllers each connected to each medium access controller to exchange a corresponding portion of the data packets with the medium access controller. The data path controllers each have a number of buffers to hold the portion of the data packets exchanged with the corresponding medium access controller. Each data path controller has a selector that selects the buffer from which to exchange the portion of the data packets with the central shared memory and control logic that controls the selector to concurrently select the buffer corresponding to the same medium access controller.

Data path architecture for a LAN switch

A flexible, policy-based, mechanism for managing, monitoring, and prioritizing traffic within a network and allocating bandwidth to achieve true quality of service (QoS) is provided. According to one aspect of the present invention, a method is provided for managing bandwidth allocation in a network that employs a non-deterministic access protocol, such as an Ethernet network. A packet forwarding device receives information indicative of a set of traffic groups, such as: a MAC address, or IEEE 802.1p priority indicator or 802.1Q frame tag, if the QoS policy is based upon individual station applications; or a physical port if the QoS policy is based purely upon topology. The packet forwarding device additionally receives bandwidth parameters corresponding to the traffic groups. After receiving a packet associated with one of the traffic groups on a first port, the packet forwarding device schedules the packet for transmission from a second port based upon bandwidth parameters corresponding to the traffic group with which the packet is associated. According to another aspect of the present invention, a method is provided for managing bandwidth allocation in a packet forwarding device. The packet forwarding device receives information indicative of a set of traffic groups. The packet forwarding device additionally receives information defining a QoS policy for the traffic groups. After a packet is received by the packet forwarding device, a traffic group with which the packet is associated is identified. Subsequently, rather than relying on an end-to-end signaling protocol for scheduling, the packet is scheduled for transmission based upon the QoS policy for the identified traffic group.

Policy based quality of service

A packet switching device having a central shared memory and a number of medium access controllers each coupled to a communications medium to exchange data packets therewith, and a controller coupled to each medium access controller via a data path to exchange data packets with the media access controller. The controller has a number of data path controllers each connected to each medium access controller via a separate and like portion of the data path to exchange a corresponding portion of the data packets with the medium access controller. The data path controllers each have a number of buffers each connected to one of the medium access controllers to which the data path controller is connected, to hold the portion of the data packets exchanged with the corresponding medium access controller. Each data path controller has a selector that selects the buffer from which to transmit or receive the portion of the data packets with the central shared memory and control logic that controls the selector to concurrently select the buffer corresponding to the same medium access controller. A comparison engine associated with each data path controller detects the slice of a field in a data packet buffered in the corresponding data path controller and computes a hashing function on the contents of the slice of the field to generate a hash key. A packet forwarding controller reads one or more entries from a hash bucket in a forwarding database indexed by the hash key and sends the entries to the comparison logic. The comparison logic compares the slice of the field in the buffer to each of the entries and returns the results of the compare to a packet forwarding controller. The forwarding controller then forwards, filters or identifies packets based on the results of the comparisons done on each slice of a field in the packets.

Growing community of inventors

Palo Alto, CA, United States of America

Justin N Chueh