Abstract:
Techniques are presented herein for enabling performance monitoring of flows within a management and provisioning tunnel used for communicating packets between a wireless controller and wireless access point devices. A wireless controller that is configured to communicate with at least one wireless access point obtains a packet to be sent to the wireless access point for wireless transmission in a wireless network by the wireless access point. The wireless controller identifies, based on the packet, traffic session flow information associated with the packet. The wireless controller encapsulates the packet with a tunneling header that comprises the traffic session flow information and sends the encapsulated packet to the wireless access point. The tunneling header may also comprise an application identifier (ID) associated with the packet.
Abstract:
Presented herein are techniques for managing a plurality of machine learning engines. A method includes receiving at an orchestration entity information descriptive of attributes of a plurality of machine learning engines, generating, based on the information, a unique signature for each machine learning engine of the plurality of machine learning engines, creating, based on the unique signature for each machine learning engine, an ensemble of machine learning engines configured to operate on a predetermined task, causing the ensemble of machine learning engines to operate on the predetermined task, and monitoring performance metrics of the machine learning engines in the ensemble of machine learning engines while the ensemble operates on the predetermined task.
Abstract:
A method is provided in one example embodiment and includes generating at a first network device Virtual Private Network (“VPN”) encapsulated packets with anonymized headers; maintaining a table mapping the anonymized headers to original headers of the VPN encapsulated packets; receiving a trace request from an initiator; generating from the received trace request an out-of-tunnel trace request toward a second network device via at least one intermediate network device using the anonymized headers; and forwarding the received trace request as an in-tunnel trace request through a VPN tunnel.
Abstract:
Techniques are presented herein for enabling performance monitoring of flows within a management and provisioning tunnel used for communicating packets between a wireless controller and wireless access point devices. A wireless controller that is configured to communicate with at least one wireless access point obtains a packet to be sent to the wireless access point for wireless transmission in a wireless network by the wireless access point. The wireless controller identifies, based on the packet, traffic session flow information associated with the packet. The wireless controller encapsulates the packet with a tunneling header that comprises the traffic session flow information and sends the encapsulated packet to the wireless access point. The tunneling header may also comprise an application identifier (ID) associated with the packet.
Abstract:
A method is provided in one example embodiment and includes generating at a first network device Virtual Private Network (“VPN”) encapsulated packets with anonymized headers; maintaining a table mapping the anonymized headers to original headers of the VPN encapsulated packets; receiving a trace request from an initiator; generating from the received trace request an out-of-tunnel trace request toward a second network device via at least one intermediate network device using the anonymized headers; and forwarding the received trace request as an in-tunnel trace request through a VPN tunnel.
Abstract:
The present disclosure describes methods and systems for providing and enforcing scalable federated policies for network-provided flow-based performance metrics. Due to different security concerns related to different domains, varying group policies can be applied to different domains to ensure proper sharing and receipt of flow-based performance metrics. Some policies can limit the type of performance metric being shared among the nodes in the domain. Some policies allow less information to be exposed by specifying aggregated performance metrics to be shared among the nodes in the domain. A group key management infrastructure can be provided to enforce these group policies in the network in a scalable manner.
Abstract:
The present disclosure describes methods and systems for providing and enforcing scalable federated policies for network-provided flow-based performance metrics. Due to different security concerns related to different domains, varying group policies can be applied to different domains to ensure proper sharing and receipt of flow-based performance metrics. Some policies can limit the type of performance metric being shared among the nodes in the domain. Some policies allow less information to be exposed by specifying aggregated performance metrics to be shared among the nodes in the domain. A group key management infrastructure can be provided to enforce these group policies in the network in a scalable manner.
Abstract:
The present disclosure describes a technique for performing performance monitoring of service chains. Variations on performance monitoring can include: passive monitoring, active monitoring, or hybrid monitoring. To provide performance monitoring, the Network Service Header (NSH) is modified to include telemetry information usable for monitoring the performance of a particular traffic flow being transported over a service path.