Nicira, Inc.

Vmware, Inc.

Sreeram Kumar Ravinoothala

Ronghua Zhang

Yong Wang

Ganesan Chandrashekhar

Ankur Dubey

Dexiang Wang

Kai-Wei Fan

Jerome Catrouillet

Serge Maskalik

Xuan Zhang

Anirban Sengupta

Sami Boutros

Xinhua Hong

Yu Ying

Cheng-Chun Tu

Liwen Wu

Peng T Li

Mani Kancherla

Xinghua Hu

Kevin Rayfeng Li

Mochi Xue

Some embodiments of the invention provide a method for implementing an edge device that handles data traffic between a logical network and an external network. The method monitors resource usage of a node pool that includes multiple nodes that each executes a respective set of pods. Each of the pods is for performing a respective set of data message processing operations for at least one of multiple logical routers. The method determines that a particular node in the node pool has insufficient resources for the particular node's respective set of pods to adequately perform their respective sets of data message processing operations. Based on the determination, the method automatically provides additional resources to the node pool by instantiating at least one additional node in the node pool.

Scaling for split-networking datapath

A network system that implements quality of service (QoS) by rate limiting at a logical network entity is provided. The logical network entity includes multiple transport nodes for transporting network traffic in and out of the logical network entity. The system monitors traffic loads of the multiple transport nodes of the logical network entity. The system allocates a local CR and a local BS to each of the multiple transport nodes. The allocated local CR and the local BS are determined based on the CR and BS parameters of the logical network entity and based on the monitored traffic loads. Each transport node of the logical network entity in turn controls an amount of data being processed by the transport node based on a token bucket value that is computed based on the local CR and the local BS of the transport node.

Virtualized QoS support in software defined networks

Some embodiments provide, for a gateway datapath that executes on a gateway device to implement tenant logical routers for multiple different tenant logical networks and process traffic between the tenant logical networks and an external network, a method for managing QoS for the plurality of tenant logical networks. The method receives a data message for a particular tenant logical network. The method executes a set of processing stages to process the data message. The set of processing stages includes a processing stage for a particular tenant logical router of the particular tenant logical network. As part of the processing stage for the particular tenant logical router, the method uses a QoS data structure specific to the particular tenant logical router to determine whether to allow the data message. The gateway device stores at least one separate QoS data structure for each of a set of the tenant logical routers.

Tenant-specific quality of service

Some embodiments provide a method for a gateway datapath that executes on a gateway device to implement logical routers for a set of logical networks and process traffic between the logical networks and an external network. The method receives a data message at the gateway device. To process the data message, the method executes a set of processing stages that includes a processing stage for a particular logical router. As part of the processing stage for the particular logical router, the method (i) uses an access control list (ACL) table to determine whether the data message is subject to rate limiting controls defined for the particular logical router and (ii) only when the data message is subject to rate limiting controls, determines whether to allow the data message according to a rate limiting mechanism for the particular logical router.

Determining whether to rate limit traffic

Some embodiments provide a method for configuring a logical router that interfaces with an external network. The method receives a configuration for a logical network that includes a logical router with several interfaces that connect to at least one physical router external to the logical network. The method selects a separate host machine to host a centralized routing component for each of the interfaces. The method selects a particular one of the host machines for operating a dynamic routing protocol control plane that receives routing protocol data from each of the centralized routing components and updates routing tables of each of the centralized routing components.

Route server mode for dynamic routing between logical and physical networks

Some embodiments of the invention provide a system for implementing multiple logical routers. The system includes a Kubernetes cluster that includes multiple nodes, with each node executing a set of pods. The set of pods include a first pod for performing a first set of data message processing operations for the multiple logical routers and at least one respective separate pod for each respective logical router of the multiple logical routers. Each respective pod is for performing a respective second set of data message processing operations for the respective logical router.

Edge node with datapath split between pods

Some embodiments provide a method for handling failure at one of several peer centralized components of a logical router. At a first one of the peer centralized components of the logical router, the method detects that a second one of the peer centralized components has failed. In response to the detection, the method automatically identifies a network layer address of the failed second peer. The method assumes responsibility for data traffic to the failed peer by broadcasting a message on a logical switch that connects all of the peer centralized components and a distributed component of the logical router. The message instructs recipients to associate the identified network layer address with a data link layer address of the first peer centralized component.

Logical router with multiple routing components

Some embodiments provide a method for updating a core allocation among processes of a gateway datapath executing on a gateway computing device having multiple cores. The gateway datapath processes include a first set of data message processing processes to which a first set of the cores are allocated and a second set of processes to which a second set of the cores are allocated in a first core allocation. Based on data regarding usage of the cores, the method determines a second core allocation that allocates a third set of the cores to the first set of processes and a fourth set of the cores to the second set of processes. The method updates a load balancing operation to load balance received data messages over the third set of cores rather than the first set of cores. The method reallocates the cores from the first allocation to the second allocation.

Dynamic core allocation

Some embodiments provide method for implementing a logical router of a logical network. The method receives a configuration for a first logical router. The configuration includes a static route for the first logical router. The method defines several routing components with separate routing tables for the logical router. The method adds a first route, having a first static route type, for the static route to the routing tables of at least a first subset of the routing components. Based on the connection of a second logical router to the first logical router, adding a second route, having a second static route type, to the routing tables of at least a second subset of the routing components.

Static route types for logical routers

Example methods are provided for a network device to perform adaptive polling in a software-defined networking (SDN) environment. One example method may comprise: operating in a polling mode at a current polling round to detect zero or more packets that require packet processing by the network device. The method may also comprise: determining packet characteristic information associated with multiple polling rounds that include the current polling round and one or more previous polling rounds; and based on the packet characteristic information, determining whether a resource performance condition associated with the network device is satisfied. In response to determination that the resource performance condition is satisfied, the network device may operate in the polling mode at a subsequent polling round; but otherwise, switch from the polling mode to an interrupt mode.

Growing community of inventors

San Jose, CA, United States of America

Sreeram Kumar Ravinoothala