Brocade Communications Systems, Inc.

Avago Technologies International Sales Pte. Limited

Sathish Kumar Gnanasekaran

Badrinath Kollu

Vineet M Abraham

Rishi Amit Sinha

Dennis Hideo Makishima

Amit Kanda

Daniel Ji Yong Park Chung

Subramanian Lakshmanan

Balakumar N Kaushik

Vincent W Guan

Ganesh Kumar Murugesan

Saumitra Buragohain

Christopher A Del Signore

Vidya Sagar Ravipati

Pranab Patnaik

Shashank R Tadisina

Vinodh Ravindran

Howard Lynn Johnson

Michael W Atkinson

Ponpandiaraj Rajarathinam

Nhan Trong Pham

Qingyuan Ma

Michael Gee

Nadeem Kattangere

Srikara Subramanyan

Vidya Renganarayanan Vineet

Blayne Rawsky

Richard L Hammons

Ramkumar Vadivelu

Chao Zhang

Dan Norbert Retter

Abhijit Seal

Ethan John Cardwell

Xupei Liang

Varghese Kallarackal

Vidya Renganarayanan

Prasanta Kumar David Bhuyan

Bei Wang

Raymond Yimin Lai

Prasanta Kumar David Bhuya

Anil Kumar Chintalapati

Daniel Ji Young Park Chung

Tarun Bhatia

Amit Kumar Tyagi

Leifang Hu

Sharanappa Ijeri

Jianqiang Zhou

Gokila Thirumoorthy

Kumar Ghanta

Vardhan Vinay Thigle

Vidhyashankar Gowrisankaran

An interfabric link between two separate Fibre Channel fabrics so that devices in one fabric can communicate with devices in another fabric without requiring the merger of the two fabrics. The interfabric switch performs a conversion or a translation of device addresses in each fabric so that they are accessible to the other fabric. This translation is preferably done using a private to public loop address translation. In a first embodiment the external ports of the interfabric switch are configured as E_ports. A series of internal ports in each interfabric switch are joined together forming a series of virtual or logical switches. The virtual switches are then interconnected using private loops. The use of the private loop is enabled by the presence of translation logic which converts fabric addresses to loop addresses and back so that loop and fabric devices can communicate. Because each port can do this translation and the private loop addressing does not include domain or area information, the change in addresses between the fabrics is simplified. In a second embodiment the external ports are configured as NL_ports and the connections between the virtual switches are E_ports. Thus the private to public and public to private translations are done at the external ports rather than the internal ports as in the prior embodiment. The virtual switches in the interfabric switch match domains with their external counterparts so that the virtual switches effectively form their own fabric, connected to the other fabrics by the private loops.

Method and apparatus for routing between fibre channel fabrics

A Layer 2 network switch is partitionable into a plurality of switch fabrics. The single-chassis switch is partitionable into a plurality of logical switches, each associated with one of the virtual fabrics. The logical switches behave as complete and self-contained switches. A logical switch fabric can span multiple single-chassis switch chassis. Logical switches are connected by inter-switch links that can be either dedicated single-chassis links or logical links. An extended inter-switch link can be used to transport traffic for one or more logical inter-switch links. Physical ports of the chassis are assigned to logical switches and are managed by the logical switch. Legacy switches that are not partitionable into logical switches can serve as transit switches between two logical switches.

Partitioning of switches and fabrics into logical switches and fabrics

A hypervisor preferably provides VM (virtual machine) identification, priority and LUN/LBA range information to the HBA (hoist bus adapter) when a VM is created. Alternatively, the HBA can determine that a LUN/LBA range is new and request VM identity, priority and LUN/LBA range from the hypervisor. The HBA creates a table containing the VM identification, priority and LUN/LBA range. The HBA then detects operations directed to the LUN/LBA range and does a lookup to determine VM identification and priority. VM identification and priority are then mapped into a field in a frame using a unique identifier. The unique identifier can be placed using reserved bits on the existing Fiber Channel (FC) header or can use bits in an additional header, such as a modified IFR header or an optional device header. The VM identification aware HBAs register with the NS.

Method and apparatus for registering and storing virtual machine unique information capabilities

A hypervisor preferably provides VM (virtual machine) identification, priority and LUN/LBA range information to the HBA (host bus adapter) when a VM is created. Alternatively, the HBA can determine that a LUN/LBA range is new and request VM identity, priority and LUN/LBA range from the hypervisor. The HBA creates a table containing the VM identification, priority and LUN/LBA range. The HBA then detects operations directed to the LUN/LBA range and does a lookup to determine VM identification and priority. VM identification and priority are then mapped into a field in a frame using a unique identifier. The unique identifier can be placed using reserved bits on the existing Fiber Channel (FC) header or can use bits in an additional header, such as a modified IFR header or an optional device header. The VM identification aware HBAs register with the NS.

Method and apparatus for providing virtual machine information to a network interface

An interfabric link between two separate Fiber Channel fabrics so that devices in one fabric can communicate with devices in another fabric without requiring the merger of the two fabrics. The interfabric switch performs a conversion or a translation of device addresses in each fabric so that they are accessible to the other fabric. This translation is preferably done using a private to public loop address translation. In a first embodiment the external ports of the interfabric switch are configured as E_ports. A series of internal ports in each interfabric switch are joined together forming a series of virtual or logical switches. The virtual switches are then interconnected using private loops. The use of the private loop is enabled by the presence of translation logic which converts fabric addresses to loop addresses and back so that loop and fabric devices can communicate. Because each port can do this translation and the private loop addressing does not include domain or area information, the change in addresses between the fabrics is simplified. In a second embodiment the external ports are configured as NL_ports and the connections between the virtual switches are E_ports. Thus the private to public and public to private translations are done at the external ports rather than the internal ports as in the prior embodiment. The virtual switches in the interfabric switch match domains with their external counterparts so that the virtual switches effectively form their own fabric, connected to the other fabrics by the private loops.

An analytics and diagnostic node according to the present disclosure monitors oversubscription and determines flow metrics by receiving mirror command frames from one or more switching nodes. The mirror command frames could correspond to a multiple flows traversing over a connection within a network. The analytics and diagnostic node collects at least one latency metric for each of the flows using timestamps found within the mirror command frames. Based on the latency metrics and timestamps, the analytic diagnostic node determines an average data rate for each of the flows. The analytics and diagnostic node also computes the cumulative data rates corresponding to different bucket intervals based on the average data rates. To detect oversubscription, the analytics and diagnostic node compares the cumulative data rates with one or more oversubscription rules.

Command response and completion determination

A hypervisor preferably provides VM identification, priority and LUN/LBA range information to the HBA when a VM is created. Alternatively, the HBA can determine that a LUN/LBA range is new and request VM identity, priority and LUN/LBA range from the hypervisor. The HBA creates a table containing the VM identification, priority and LUN/LBA range. The HBA then detects operations directed to the LUN/LBA range and does a lookup to determine VM identification and priority. VM identification and priority are then mapped into a field in a frame using a unique identifier. The unique identifier can either be placed using reserved bits on the existing Fibre Channel (FC) header or can use bits in an additional header, such as a modified IFR header.

Fabric latency determination

High granularity link oversubscription detection

A hypervisor preferably provides VM identification, priority and LUN/LBA range information to the HBA when a VM is created. Alternatively, the HBA can determine that a LUN/LBA range is new and request VM identity, priority and LUN/LBA range from the hypervisor. The HBA creates a table containing the VM identification, priority and LUN/LBA range. The HBA then detects operations directed to the LUN/LBA range and does a lookup to determine VM identification and priority. VM identification and priority are then mapped into a field in a frame using a unique identifier. The unique identifier can either be placed using reserved bits on the existing Fiber Channel (FC) header or can use bits in an additional header, such as a modified IFR header.

Method and apparatus for determining the identity of a virtual machine

Back pressure is mapped within a network, and primary bottlenecks are distinguished from dependent bottlenecks. Further, the presently disclosed technology is capable of performing network healing operations designed to reduce the data load on primary bottlenecks while ignoring dependent bottlenecks. Still further, the presently disclosed technology teaches identifying and/or suggesting a switch port for adding a node to the network. More specifically, various implementations analyze traffic load and back pressure in a network, identify primary and dependent bottlenecks, resolve the primary bottlenecks, collect new node parameters, and/or select a switch port for the new node. Further, a command can be sent to a selected switch to activate an indicator on the selected port. New node parameters may include new node type, maximum load, minimum load, time of maximum load, time of minimum load and type of data associated with the new node.

Back pressure remediation

One embodiment of the present invention provides a system that facilitates congestion management in a Fibre Channel (FC) network. During operation, the system determines a threshold data rate on an outgoing link coupled to an FC switch. The system further determines the number of sources that send data to the outgoing link and an aggregate arrival rate of data for the outgoing link. Next, the system determines an injection data rate for a respective source based on the threshold data rate on the outgoing link, the number of sources transmitting data to the outgoing link, and the aggregate arrival data rate for the outgoing link. Subsequently, the system communicates the injection data rate to the source, thereby allowing the source to throttle its data injection in the FC network to prevent network congestion.

Method and system for congestion management in a fibre channel network

One embodiment of the present invention provides a system that facilitates traffic isolation (TI) in a network. During operation, the system configures a set of switch ports as members of a TI zone. The switch ports are part of an end-to-end path across one or more switch domains between a source and a destination. The switch ports within the TI zone and outside the TI Zone belong to a common storage area network (SAN) zone which compartmentalizes data for security purposes. The system then determines whether a data flow entering a switch domain belongs to the TI zone. The system subsequently forwards the data flow to the next port within the TI zone if the data flow belongs to the TI zone.

Method and system for traffic isolation in a network

One embodiment of the present invention provides a system for mapping all possible paths between a source node and a destination node. During operation, the system receives a management frame, determines all possible next-hop nodes based on a destination address carried in the payload of the management frame. The system then selects one of the next-hop nodes, and modifies payload of the received management frame to include information associated with the next-hop nodes and the selected next-hop node. The system then forwards the modified data frame to the selected next-hop node.

Path diagnosis in communication networks

A port monitor monitors network traffic that passes through a port of a switch. Frame flows routed through the switch are counted by hardware frame counting logic, which includes a content-addressable memory (CAM) and counters corresponding to various frame flows. Port monitor software includes logical containers ('buckets'), which are used to record and sort counts of the frame flows from hardware based on activity of the frame flows. Frame flow sorting is based on confidence building algorithms such that the thrashing of frame flows between buckets is reduced. Storage and sorting of the frame flows in software allows the activity level of any number of frame flows associated with the switch to be counted, regardless of hardware limitations on how many frame flows can be counted. This allows a real-time analysis of frame flows and a determination of frame flows that are major users of Fiber Channel bandwidth.

Method and apparatus for determining bandwidth-consuming frame flows in a network

Growing community of inventors

Sunnyvale, CA, United States of America

Sathish Kumar Gnanasekaran