Cisco Technology, Inc.

Satyajit Das

Laxmikantha Reddy Ponnuru

Balaji Sundararajan

Ganesh Devendrachar

Vishali Somaskanthan

Saurabh Kumar

Priyanka Chidambar Patil

Anubhav Gupta

Ram Dular Singh

Samir D Thoria

Preety Mordani

Ajeet Pal Singh Gill

Srilatha Tangirala

Jigar Dinesh Parekh

Managa Sunitha Arun Kumar

Avinash Shah

Ajay Kumar Mishra

Prithvi Sharan

Satish Varadarajula

Michael John Moskal

Techniques are described for avoiding data packet fragmentation in a routing device such as a router or network switch. Path Maximum Transport Unit (PMTU) values are monitored for a plurality of egress links of a networking device. A statistical analysis of fragmentation rates is performed. The statistical analysis can be performed on a per-link basis, per-flow basis or both per-link and per-flow basis. If the packet fragmentation rate of data flows through a particular egress link exceeds a determined threshold value, one or more data flows can be re-routed to a different egress link having a higher PMTU, thereby preventing data packet fragmentation.

Packet fragmentation prevention in an SDWAN router

In one embodiment, a method includes determining, by a network node, that a first plurality of tunnel interfaces resides in a core region of a network and determining, by the network node, that a second plurality of tunnel interfaces resides in an access region of the network. The method also includes configuring, by the network node, a first tunnel interface as a core regional fallback path for the core region of the network and configuring, by the network node, a second tunnel interface as an access regional fallback path for the access region of the network.

Ultimate regional fallback path for hierarchical SD-WAN

In one embodiment, a method includes configuring a first application probe class and a second application probe class. The first application probe class may be associated with a first Differentiated Services Code Point (DSCP), and the second application probe class may be associated with a second DSCP. The method also includes determining an adaptive Forward Error Correction (FEC) data policy for the first application probe class and the second application probe class, calculating a first loss value associated with the first application probe class for a link between a first network node and a second network node, and comparing the first loss value to a first loss threshold. The method further includes determining whether to activate FEC processing for the first application probe class in response to comparing the first loss value to the first loss threshold.

Systems and methods for activating FEC processing per application probe class

Techniques for automatically providing per tenant weighted DCMP over shared transport interfaces and automated flow has load balancing are described. The techniques may include onboarding the tenant to the local multi-tenant edge device associated with a tenant, where the resource profile defines a traffic allowance per transport interface for the tenant. Local weight per transport interface is applied. Information including local weight per transport interface is transmitted to a remote device via an SD-WAN controller. Information including a remote weight per transport interface of the remote device is received via the SD-WAN controller. Traffic is routed from the tenant based on local weight per transport interface of the local device and remote weight per transport interface of the remote device.

Weighted ECPM over shared transport interfaces and per flow hash load balancing per tenant in a multi-tenant environment

The present disclosure is directed to a mechanism for optimized application performance in SD-WAN, and includes the steps of receiving initial traffic packets at a first site for transmission to a second site; determining whether a direct tunnel is established between the first site and the second site based on a state of the second site, the state comprising an active state indicating that a direct tunnel is established between the first and second sites or an inactive state indicating that the direct tunnel is not established between the first and second sites; and in response to determining that the direct tunnel is not established, determining that the initial packets satisfy a configured trigger; forwarding the initial packets to the second site via a backup path; establishing the direct tunnel between the first and second sites; and forwarding subsequent traffic packets to the second site via the established direct tunnel.

Scalable mechanism for optimized application performance in SD-WAN

A WAN controller can configure a first WAN interface on a first WAN edge device to connect to a first transport network. The WAN controller can configure a second WAN interface on a second WAN edge device to connect to a second transport network. The WAN controller or the first WAN edge device, connected to a first access device of an access network, can determine the first WAN edge device has no Layer 2 connectivity to the second WAN edge device, connected to a second access device of the access network. The WAN controller or the first WAN edge device can establish a tunnel between the first WAN edge device and the second WAN interface. The WAN controller can route a specified class of WAN traffic received by the first WAN edge device from the access network through the tunnel.

Wide area network edge device connectivity for high availability and extensibility

Growing community of inventors

Livermore, CA, United States of America

Satyajit Das