Cisco Technology, Inc.

International Business Machines Corporation

Lenovo (singapore) Pte. Ltd.

Barefoot Networks, Inc.

Intel Corporation

Ethan M Spiegel

Ashok N Chippa

Claude Basso

Vijoy A Pandey

Natarajan Vaidhyanathan

Subrata Banerjee

Daljeet Singh

Marek Tomaszewski

Ioana M Costea

Colin Beaton Verrilli

Changhoon Kim

Jeongkeun Lee

Josep Cors

David Alan Shedivy

Sukhdev S Kapur

Ashok Ganesan

Venkatesh K Janakiraman

Sze-Wa Lao

Sameer M Shah

Dar-Ren Leu

Debojyoti Dutta

Sumeet Singh

Joseph Allen Kirscht

Michel Poret

Xiaozhou Li

Masoud Moshref Javadi

Georgios Nikolaidis

Anthony L Alles

Vipin K Garg

Robert E Zagst, Jr

Abhijit Patra

Paul M Quinn

Nagaraj Bagepalli

Anurag Agrawal

Rong Pan

Surendra M Kumar

Nilanjan Mukherjee

Kaushik Narayan

Ashutosh Agrawal

Senhua Huang

Arpan K Ghosh

Rakesh M Pathak

Joshua Merrill

Michael V Dvorkin

Rajendra Shinde

Bobby Nakamoto

Sid Ray

Erik David Ludvigson

Jeremias Blendin

Sze W Lao

Examples described herein relate to a network element comprising an ingress pipeline and at least one queue from which to egress packets. The network element can receive a packet and generate a congestion notification packet at the ingress pipeline to a sender of the packet based on detection of congestion in a target queue that is to store the packet and before the packet is stored in a congested target queue. The network element can generate a congestion notification packet based on a queue depth of the target queue and likelihood the target queue is congested. The likelihood the queue is congested can be based on a probabilistic function including one or more of Proportional-Integral (PI) or Random Early Detection (RED). The network element can determine a pause time for the sender to pause sending particular packets based at least on a time for the target queue to drain to a target level.

Congestion management techniques

Some embodiments of the invention provide a method for reporting congestion in a network that includes several forwarding elements. In a data plane circuit of one of the forwarding elements, the method detects that a queue in the switching circuit of the data plane circuit is congested, while a particular data message is stored in the queue as it is being processed through the data plane circuit. In the data plane circuit, the method then generates a report regarding the detected queue congestion, and sends this report to a data collector external to the forwarding element. To send the report, the data plane circuit in some embodiments duplicates the particular data message, stores it in the duplicate data message information regarding the detected queue congestion, and sends the duplicate data message to the external data collector.

Identifying congestion in a network

Techniques are disclosed for notifying network control software of new and moved source MAC addresses. In one embodiment, a switch may redirect a packet sent by a new or migrated virtual machine to the network control software as a notification. The switch does not forward the packet, thereby protecting against denial of service attacks. The switch further adds to a forwarding database a temporary entry which includes a 'No_Redirect' flag for a new source MAC address, or updates an existing entry for a source MAC address that hits in the forwarding database by setting the 'No_Redirect' flag. The &#x201c;No_Redirect&#x201d; flag indicates whether a notification has already been sent to the network control software for this source MAC address. The switch may periodically retry the notification to the network control software, until the network control software validates the source MAC address, depending on whether the &#x201c;No_Redirect&#x201d; is set.

Network control software notification and invalidation of static entries

Techniques are disclosed for notifying network control software of new and moved source MAC addresses. In one embodiment, a switch detects packets sent by a new or migrated virtual machine, and sends a copy of a detected packet to the network control software as a notification. The switch further learns the source MAC address, thereby permitting the entry to be used for normal forwarding prior to validation of the entry and the VM associated therewith by the network control software. Until the network control software has validated the VM, the switch may periodically retry the notification to the network control software. 'No_Redirect' and 'Not_Validated' flags may be used to indicate whether a notification has already been attempted and thus no retry is necessary, and that the VM associated with the VM has not yet been validated, respectively.

Network control software notification with advance learning

A tool for partitioning a switch into one or more logical switches in a distributed system. The tool creates, by one or more computer processors, one or more logical switch routers, based, at least in part, on a user configuration. The tool assigns, by one or more computer processors, based, at least in part, on a user configuration, one or more ports to the one or more logical switch routers. The tool manages, by one or more computer processors, the one or more logical switch routers.

Logical switch architecture for network virtualization

A tool for assigning virtual port channels to one or more logical switch routers in a distributed system. The tool receives, by one or more computer processors, a request to assign a virtual port channel to a second logical switch router. The tool sends, by one or more computer processors, a request to negotiate a link-down on the channel on a first logical switch router to a universal fiber port on the first logical switch router for processing. The tool sends, by one or more computer processors, a request to create the channel on the second logical switch router to a second interface manager on the second logical switch router for processing. The tool sends, by one or more computer processors, a request to negotiate a link up on the channel on the second logical switch router to the universal fiber port on the first logical switch router for processing.

Virtual port support in a logical switch architecture

A tool for forwarding plane support in a distributed system utilizing a three-tiered architecture. The tool receives one or more messages, wherein the one or more messages include a plurality of state information. The tool determines a distribution scope for the one or more messages based, at least in part, on the plurality of state information. The tool determines a destination endpoint ID for the one or more messages, wherein the destination endpoint ID identifies one or more switch units to receive the one or more messages. The tool sends the one or more messages to a forwarding plane agent for distribution to the one or more switch units based, at least in part, on the distribution scope and the destination endpoint ID.

Abstraction layer and distribution scope for a logical switch router architecture

Embodiments presented herein describe techniques for isolating multicast and broadcast frames to a traffic class that is separate from a traffic class used for unicast frames. According to one embodiment, a network switch receives an incoming Ethernet virtual local area network (VLAN)-tagged frame. The switch evaluates priority bits of the VLAN tag of the frame. The switch also determines a type of frame (e.g., whether the frame is unicast, broadcast, multicast, or flood). Based on the priority field values and the type of the frame, the switch identifies a mapping of the frame to a particular traffic class. The network switch assigns the frame to the traffic class.

Unified framework for isolating multicast and broadcast frames to a traffic class separate from a traffic class used for unicast frames

A tool for forwarding plane support in a distributed system. The tool receives, by one or more computer processors, one or more messages. The tool determines, by one or more computer processors, a distribution scope for the one or more messages. The tool determines, by one or more computer processors, a destination endpoint ID for the one or more messages. The tool sends, by one or more computer processors, the one or more messages to one or more forwarding plane agents.

A networking system, and more particularly an interface management subsystem, offers logical interface abstraction for networking system software. The networking system generally transmits data via a hardware interface. All software components in the control and forwarding plane use a Logical Interface (LIF) that is a logical representation of the hardware interface. A mapping occurs between the LIF and hardware interface used to transmit the data. Each LIF is represented by an LIF identifier used to store and retrieve logical interface records to and from shared memory accessible to all protocols and applications in the control and forwarding plane. The efficient storage and retrieval of such logical interface records allows for a global unique view of network interfaces, avoidance of data replication in each networking system software application's memory space, etc.

Logical interface encoding

A first network device determines capabilities of resources in a section of a network that is accessible using the first network device. The first network device groups the resources into a resource cluster. The first network device advertises the resource cluster in the network, wherein each of a plurality of network devices advertise a resource cluster associated with sections of the network. A second network device receives a request for providing a service. The second network device groups the request into a plurality of request clusters. The second network device selects at least one resource cluster for providing the service based on information associated with the request clusters and the advertised resource clusters. The second network device allocates resources included in the at least one resource cluster for providing the service based on selecting the at least one resource cluster.

Resource allocation mechanism

In one embodiment, a service provider management device provides a plurality of redundant fabric motifs, each indicating a subgraph pattern of logical connections for network segments of a virtual data center, and receives virtual data center tenant selection of one or more of the redundant fabric motifs for particular pairs of data center segments of the virtual data center. After determining available physical data center resources that correspond to the tenant selection of one or more of the redundant fabric motifs for particular pairs of data center segments, logical connections may then be established between particular network segments for the virtual data center according to the available physical data center resources corresponding to the tenant selection of one or more of the redundant fabric motifs for particular pairs of data center segments.

Policy-driven automatic redundant fabric placement mechanism for virtual data centers

Growing community of inventors

Mountain View, CA, United States of America

Ethan M Spiegel