Cisco Technology, Inc.

Kui Zhang

Satyanarayana Rao Raparla

Frank Gerard Bordonaro

John Lautmann

Virgil Nicolae Mihailovici

Alpesh S Patel

Abhay Kumar Roy

Benoit Claise

Christian Posse

Petre Dini

Ashutosh Arwind Malegaonkar

Satish K Gannu

Masum Z Hasan

Praveen Joshi

Syam Sundar Appala

Sonali Mihir Sambhus

Biren Fondekar

Feng Ye

Thangavelu Arumugam

Jayashree Jagannath

Rajeev Koripalli

Nitasha Walia

Kurella Murty

Bharat D Rathi

A method is provided in one example and includes receiving data propagating in a network environment, separating the data into one or more fields, evaluating at least some of the fields in order to identify nouns and noun phrases within the fields, and identifying selected terms within the nouns and noun phrases to be tagged. The selected terms are tagged with respective expertise tags. The method may also include receiving a search query for a particular expertise, the search query includes the selected terms. The method may also include matching the expertise tags to an end user in order to generate a response to the search query, the response includes an identifier of the end user. In more specific embodiments, the identifying of the selected terms includes using synaptic analysis or word occurrence counting. The expertise tags can be provided in a profile for the end user.

System and method for deriving user expertise based on data propagating in a network environment

A method is provided in one example and includes receiving data propagating in a network environment and separating the data into one or more fields. At least some of the fields are evaluated in order to identify nouns and noun phrases within the fields. The method also includes identifying selected words within the nouns and noun phrases based on a whitelist and a blacklist. The whitelist includes a plurality of designated words to be tagged and the blacklist includes a plurality of rejected words that are not to be tagged. A resultant composite is generated for the selected nouns and noun phrases that are tagged. The resultant composite is incorporated into the whitelist if the resultant composite is approved.

System and method for generating vocabulary from network data

A data processing apparatus comprises instructions to perform sending and receiving one or more messages conforming to a network routing protocol, such as Open Shortest Path First (OSPF); obtaining one or more information elements that specify one or more capabilities of the apparatus; creating a particular routing protocol message comprising an opaque advertisement that includes the one or more information elements; and sending the particular message on one of the network interfaces. For example, a router or switch that implements a network routing protocol can use OSPF Opaque Link State Advertisements to advertise and discover services and capabilities of other routers or switches.

Network element discovery using a network routing protocol

A device for measuring network performance in an Internet protocol (IP) network including a counter generating a send sequence number representing a relative send timing indicator for a data packet sent to a respondent network address. The counter generates a receive sequence number representing a relative receive timing indicator for a return data packet received by the device. A comparator compares the send sequence number with the receive sequence number to measure data packet loss.

Method and apparatus for measuring network data packet delay, jitter and loss

A method for operating a computer network has a source router transmit a first message to be received by an intermediate router of the computer network, the first message to activate the intermediate router to listen for a designated time period for the intermediate router to receive a second message. Upon receiving a second message by the intermediate router during the designated time period, the intermediate router responds to the second message in response to receiving the second message during the designated time period.

Method and apparatus for measuring latency of a computer network

A method of managing performance data and accounting data that are generated in a computer network comprises collecting performance data from the network using one or more collector blades that are installed into a data collection manager at a time when the data collection manager is executed; determining whether the performance data satisfies one or more thresholding rules, and if so, generating and sending one or more performance messages; filtering the performance data using one or more filters; aggregating the performance data; and correlating the performance data with other data received from one or more network management subsystems.

Method and apparatus for collecting network performance data

A method for generating a traffic matrix is provided that includes receiving a first set of data from a first provider edge element and a second set of data from a second provider edge element, the first and second sets of data including border gateway protocol (BGP) next hop information. The first and second sets of data may then be aggregated. Information that is associated with one or more customer network elements is then filtered out in order to produce a traffic matrix.

System and method for generating a traffic matrix in a network environment

The invention is directed to a system and method for accurately determining the latency of a selected path within a computer network. First, a setup or signaling protocol is used to establish a bi-directional path state that is associated with a given traffic flow having predefined parameters at each intermediary node along the selected path. Once the path states are established, a source entity disposed at a first end of the selected path formulates and transmits a test message carrying a time record or time stamp to a receiver disposed at the opposite end of the selected path. The test message is configured in accordance with the predefined traffic flow parameters, but does not include any options. By virtue of the previously established path states at each node, the message is forwarded along the selected path without incurring any route or option processing delays. Upon receipt of the test message at the receiver, it is returned back to the source, and again follows the selected path. By comparing the time at which the test message is returned with the time record contained within the message, an accurate determination of the latency of the selected path may be determined.

System and method for measuring latency of a selected path of a computer network

An apparatus for measuring data transmission performance through a packet switched network, the apparatus having a time of day (TOD) clock for determining a send TOD timestamp, and for determining a present TOD when a data packet returns to the sending apparatus. The apparatus further comprising a counter that is incremented by a send sequence number each time data is sent, and one or more subtractors for calculating a first time difference between the send TOD timestamp and a receive TOD timestamp, and for calculating a second time difference between the receive TOD and the present TOD. Additionally, one or more comparators of the apparatus compare a sequence difference between the send sequence number and a receive sequence number in order to measure data transmission performance.

A control mechanism enables a destination router to authenticate a response time request issued by a source router. The control mechanism uses a control message that is transmitted by the source router to the destination router. Receipt of the control message by the destination router causes the destination router to listen for a server request message for a designated response time. The source router, after sending the control message, transmits a server request message to the destination router. In the event that the destination router receives the server request message within the designated response time, then the destination router responds to the server request message by providing the request to service software. The control message may encapsulate a message that holds the response time request. The request message may be encrypted.

A method and apparatus for accurately calculating packet loss along a communication channel using data in a pair of measuring packets is disclosed. The invention calculates packet loss between a first and second node over a communication circuit. A first known quantity of packets is communicated from the first node to the second node at a first known time. A first actual count of packets received by the second node from the first known quantity of packets is then determined. A second known quantity of packets is then communicated from the first node to the second node at a second known time. A second actual count of packets received by the second node from the second known quantity of packets is then determined. The difference between the first known quantity of packets communicated at the first known time and the second known quantity of packets communicated at the second known time is calculated to obtain a value for 'packets sent'. The difference between the first actual count of packets received and the second actual count of packets received is calculated to obtain a value for 'packets received'. The difference between the packets sent and the packets received provides a value for &#x201c;packet loss&#x201d; between the first known time and second known time.

Method and apparatus for calculating packet loss for a communication circuit

Internet protocol (IP) performance monitoring method and apparatus generate a timing probe data to be sent over the network, the timing probe data packet containing at least a send time of day (STOD) stamp for a sender of the timing probe data packet. The timing probe data packet is sent over the network from the sender to a receiver. The timing probe data packet contents including at least the STOD stamp are analyzed as a performance measure of the network. After sending and before analyzing, data including at least a receive time of day (RTOD) stamp is written into the probe data packet at the receiver, and probe data packet is echoed by the receiver. In this way, the probe packet sender performs the analysis based upon the STOD stamp and the RTOD stamp.

The invention provides a control mechanism that enables a destination router to authenticate response time requests issued by a source router before providing the requests to service software for processing. The control mechanism comprises a Network Endpoint Control Protocol (NECP) message format that is exchanged between the source and destination routers when measuring response time throughout the network. The NECP message format encapsulates a Command Length Status Data (CLSD) message that actually holds the response time requests. A collector router issues a novel control message to a responder router over a default responder port. If the responder is enabled for encryption communication, it will decrypt the control message according to the specified key and algorithm. If the responder is not so configured, it will check a conventional ACL to determine whether the client is authorized to communicate with the server. If permitted, the responder then responds to the collector in a manner dependent upon the particular protocol. In the case of a request to enable a UDP port for a particular time period, the responder processes a request and then sends back an acknowledgment to the collector. The collector receives the acknowledgment and then sends out a UDP probe packet to the responder. The responder then &ldquo;echoes&rdquo; the packet back to the collector, which keeps the result.

Protocol to coordinate network end points to measure network latency

According to an embodiment of the present invention, a router is converted into a bulk call generator which generates packets with Internet protocol (IP) addresses for the purpose of simulating network traffic. These packets are initially either captured or created. When the packets are captured, they are captured from actual network traffic and rerouted to various selected IP addresses which are used for simulation purposes. Alternatively, when the packets are created, they are created within the converted router and various selected IP addresses, reserved for simulation purposes, are assigned to the packets. The various selected IP addresses may be in a range which is user configurable. The IP addresses may be selected from this range by any method, such as incrementation, decrementation, or random selection. Connections are set up according to a routing table based on the IP addresses of the various data packets.

Growing community of inventors

Cupertino, CA, United States of America

Kui Zhang