Abstract: Techniques for combining the functionality of fabric interconnects and switches (e.g., Top-of-Rack (ToR) switches) into one network entity, thereby reducing the number of devices in a fabric and complexity of communications in the fabric. By collapsing FI and ToR switch functionality into one network entity, server traffic may be directly forwarded by the ToR switch and an entire tier is now eliminated from the topology hierarchy which may improve the control, data, and management plane. Further, this disclosure describes techniques for dynamically managing the number of gateway proxies running on one or more computer clusters based on a number of managed switch domains.

Abstract: Presented herein are systems and methods to enable simultaneous interoperability with policy-aware and policy-unaware data center sites. A multi-site orchestrator (MSO) device can be configured to obtain configuration information for each of a plurality of different data center sites. The data center sites may include one or more on-premises sites and one or more off-premises sites, each of which may include one or more policy-aware sites and/or one or more policy-unaware sites. The MSO can selectively use namespace translations to create a unified fabric across the different data center sites, enabling one or more hosts and/or applications at a first of the data center sites to communicate with one or more hosts and/or applications at a second of the data center sites, regardless of the sites' respective configurations.

Abstract: Techniques for reducing the latency in performing a failover from a protected connection to its backup connection when a network event is detected affecting the protected connection. In an MPLS network, techniques are provided for failing a protected LSP to a backup LSP in a fast and efficient manner. In one embodiment, the faster failover is facilitated by storing protected LSPs and their backup LSPs information in the data plane, such as locally on a linecard.

Abstract: Techniques for reducing the latency in performing a failover from a protected connection to its backup connection when a network event is detected affecting the protected connection. In an MPLS network, techniques are provided for failing a protected LSP to a backup LSP in a fast and efficient manner. In one embodiment, the faster failover is facilitated by storing protected LSPs and their backup LSPs information in the data plane, such as locally on a linecard.