Cisco Technology, Inc.

Altera Corporation

Other

Cypress Semiconductor Corporation

Wei-Jen Huang

Chih-Tsung Huang

Sergey Yuryevich Shumarayev

Tony K Ngai

Rakesh H Patel

Bruce B Pedersen

Thomas James Edsall

Kelvin Chan

James G Schleicher

Victor Maruri

Jim Park

Yue J Yang

Keerthi Manjunathan Swarnamanjunathan

James Park

David Wolk Mendel

Michael David Hutton

Andrew Leaver

Peter J Kazarian

Putu Harry Subagio

Alessandro Fulli

Mingzhe Li

Christopher A Wildman

Yichou Lin

Chiapeng Wu

Tin H Lai

Sha Ma

Ganga Sudharshini Devadas

Sachin Agarwal

Dennis K D Nguyen

Haoxiang Zhao

Vuong Tran

Stephen D Brown

Claudio DeSanti

Vinson Chan

Kuang-Yu Chen

Bruce B Pederson

Jerry Vogler

The present technology is directed to a system and method for application aware management and recovery of link failures resulting from excessive errors observed on the link. One aspect of the proposed technology is based on identification of link errors associated with application-specific data patterns traversing link. Other aspects involve corrective actions based on relocation or modification of specific application traffic to thereby alleviate the observed excessive link errors and prevent a link failure or shut down. Relocation may involve moving the source application to a different virtual machine/container/physical device or rerouting application traffic by updating relevant routing protocols. Modification may involve harmlessly changing payload data pattern to remove data-pattern dependent signal attenuation. Information corresponding to identified faulty payload data patterns and associated frame data quality parameters maybe stored and utilized to provide analytics evaluation of network wide physical resource issues that maybe affecting application traffic.

Application-aware links

Techniques are presented herein to facilitate the monitoring of occupancy of a buffer in a network device. Packets are received at a network device. Information is captured describing occupancy of the buffer caused by packet flow through the buffer in the network device. Analytics packets are generated containing the information. The analytics packets from the network device for retrieval of the information contained therein for analysis, replay of buffer occupancy, etc.

Exporting real time network traffic latency and buffer occupancy

Disclosed are systems, methods, and non-transitory computer-readable storage media for monitoring application health via correctable errors. The method includes identifying, by a network device, a network packet associated with an application and detecting an error associated with the network packet. In response to detecting the error, the network device increments a counter associated with the application, determines an application score based at least in part on the counter, and telemeters the application score to a controller. The controller can generate a graphical interface based at least in part on the application score and a timestamp associated with the application score, wherein the graphical interface depicts a trend in correctable errors experienced by the application over a network.

System and method to measure and score application health via correctable errors

Techniques are presented herein to facilitate latency measurements in a networking environment. A first network device receives a packet for transport within a network domain that comprises a plurality of network devices. The plurality of network devices have a common time reference, that is, they are time synchronized. The first network device generates timestamp information indicating time of arrival of the packet at the first network device. The first network device inserts into the packet a tag that comprises at least a first subfield and a second subfield. The first subfield comprising a type indicator to signify to other network devices in the network domain that the tag includes timestamp information, and the second subfield includes the timestamp information. The first network device sends the packet from to into the network domain to another network device. Other network devices which receive that packet can make latency measurements.

Timestamping packets in a network

Presented herein are techniques for redacting mirrored network packets prior to providing the mirrored packets to an intended recipient application, such as a third-party analysis application. More specifically, a multi-destination packet redaction device obtains mirrored network traffic that comprises one or more mirrored network packets. The multi-destination packet redaction device filters the mirrored network traffic to determine an intended recipient application of the one or more mirrored network packets and applies a redaction process to redact one or more portions of at least one of the one or more mirrored network packets. The redaction process is customized based on one or more attributes of the intended recipient application.

Multi-destination packet redaction

Technologies for calibrated network interlink access. In some embodiments, a system can calculate a first communication latency of a first link between a first processing element in a first switch and a second processing element in a second switch, and a second communication latency associated with a second link between the first processing element and a third processing element in a third switch. The system can determine a delta between the first communication latency and the second communication latency, and whether respective clock rates of the first switch, second switch, and third switch have a clock rate variation, to yield a clock rate variation determination. Based on the delta and clock rate variation determination, the system can determine an offset value for synchronizing the first communication latency and second communication latency. Based on the offset value, the system can calibrate traffic over the first link and/or the second link.

Deterministic calibrated synchronized network interlink access

Disclosed are systems, methods, and non-transitory computer-readable storage media for monitoring application health via correctable errors. The method includes identifying, by a network device, a network packet associated with an application running on a node, detecting, by the network device, a correctable error associated with the network packet, and encoding, by the network device, a tag within the network packet, the tag including one or more fields for storing data associated with the correctable error.

A method is provided in one example embodiment that includes measuring a delay between a transmitter and a receiver in a network environment, where the receiver is associated with a buffer. A minimum absorption buffer size for lossless transmission to a queue may be determined based on the delay and a transmission bandwidth, and buffer units for the queue can be allocated based on the minimum absorption buffer size. The transmitter may also be rate-limited if the minimum absorption buffer size exceeds available storage of the buffer. In other embodiments, buffer units can be reclaimed if the available buffer storage exceeds the minimum absorption buffer size.

System and method for provisioning resources for lossless operation in a network environment

Growing community of inventors

Burlingame, CA, United States of America

Wei-Jen Huang