Abstract: Techniques for ingesting data streams to a distributed-computing system using a multi-directional data ingestion pipeline are provided. In one embodiment, a method for ingesting data streams includes, at a client gateway, receiving a plurality of messages; assigning the plurality of messages to one or more data streams; obtaining stream routing configurations; and identifying one or more receivers. The method further includes determining whether at least one of the one or more data streams is to be delivered to one or more receivers operating in the first computing environment; and if so, delivering the at least one of the one or more data streams to the one or more receivers operating in the first computing environment. The method further includes delivering the one or more data streams to a data ingress gateway operating in a second computing environment.

Abstract: The present disclosure relates to techniques for handling of bidirectional command protocols via a unidirectional communication connection established between a client computing environment and a cloud-services computing environment. In one embodiment, a command request message is pushed from a service component of the cloud-services computing environment to a client gateway of the client computing environment via the unidirectional communication connection. A token indicating routing information to the service component is embedded in the pushed command request message. A command response message is received at the cloud gateway from the client gateway via a bidirectional communication connection established between the client computing environment and the cloud-services computing environment. The command response message includes the token and data associated with executing the command request message at the client computing environment.

Abstract: The present disclosure relates to techniques for handling of bidirectional command protocols via a unidirectional communication connection established between a client computing environment and a cloud-services computing environment. In one embodiment, a command request message is pushed from a service component of the cloud-services computing environment to a client gateway of the client computing environment via the unidirectional communication connection. A token indicating routing information to the service component is embedded in the pushed command request message. A command response message is received at the cloud gateway from the client gateway via a bidirectional communication connection established between the client computing environment and the cloud-services computing environment. The command response message includes the token and data associated with executing the command request message at the client computing environment.

Abstract: Techniques for providing virtualized entity-related services to a group of users are provided. The techniques include collecting entity-related data from multiple cloud providers. The data is collected via a data stream. Various portions of the data stream are stored in various databases. A portion of the data stream is stored in a graph database that stores relationships between the entities. A portion of the data stream is stored in a key-value database that persistently stores historical virtualized entity data for the group of users. A portion of the data stream is stored in a reverse-indexed database that stores globally-searchable entity data for the entities. A search query is received. Based on the content of the query, a combination of the databases searched. Search results are compared to policies or rules of the group. If an entity is out of compliance, a warning is issued and remedial action taken.

Abstract: The present disclosure relates to techniques for handling of bidirectional command protocols via a unidirectional communication connection established between a client computing environment and a cloud-services computing environment. In one embodiment, a command request message is pushed from a service component of the cloud-services computing environment to a client gateway of the client computing environment via the unidirectional communication connection. A token indicating routing information to the service component is embedded in the pushed command request message. A command response message is received at the cloud gateway from the client gateway via a bidirectional communication connection established between the client computing environment and the cloud-services computing environment. The command response message includes the token and data associated with executing the command request message at the client computing environment.

Abstract: The present disclosure relates to techniques for managing client computing systems, such as a client distributed-computing system. In one embodiment, a desired state of the client distributed-computing system and a current state of the client distributed-computing system are received. Measurement data generated by a plurality of components of the client distributed-computing system is received. The measurement data is processed using one or more analytical or statistical techniques to generate distilled data. Based on one or more policies and the desired state, the distilled data and the current state are analyzed to determine one or more actions predicted to converge the current state of the client distributed-computing system towards the desired state. One or more control commands corresponding to the one or more actions are provided to the client distributed-computing system. The one or more control commands cause the client distributed-computing system to perform the one or more actions.

Abstract: The present disclosure relates to techniques for managing client computing systems, such as a client distributed-computing system. In one embodiment, a desired state of the client distributed-computing system and a current state of the client distributed-computing system are received. Measurement data generated by a plurality of components of the client distributed-computing system is received. The measurement data is processed using one or more analytical or statistical techniques to generate distilled data. Based on one or more policies and the desired state, the distilled data and the current state are analyzed to determine one or more actions predicted to converge the current state of the client distributed-computing system towards the desired state. One or more control commands corresponding to the one or more actions are provided to the client distributed-computing system. The one or more control commands cause the client distributed-computing system to perform the one or more actions.

Abstract: The present disclosure relates to techniques for handling of bidirectional command protocols via a unidirectional communication connection established between a client computing environment and a cloud-services computing environment. In one embodiment, a command request message is pushed from a service component of the cloud-services computing environment to a client gateway of the client computing environment via the unidirectional communication connection. A token indicating routing information to the service component is embedded in the pushed command request message. A command response message is received at the cloud gateway from the client gateway via a bidirectional communication connection established between the client computing environment and the cloud-services computing environment. The command response message includes the token and data associated with executing the command request message at the client computing environment.

Abstract: Techniques for ingesting data streams to a distributed-computing system using a multi-directional data ingestion pipeline are provided. In one embodiment, a method for ingesting data streams includes, at a client gateway, receiving a plurality of messages; assigning the plurality of messages to one or more data streams; obtaining stream routing configurations; and identifying one or more receivers. The method further includes determining whether at least one of the one or more data streams is to be delivered to one or more receivers operating in the first computing environment; and if so, delivering the at least one of the one or more data streams to the one or more receivers operating in the first computing environment. The method further includes delivering the one or more data streams to a data ingress gateway operating in a second computing environment.

Abstract: Techniques for ingesting data streams to a distributed-computing system using a multi-directional data ingestion pipeline are provided. In one embodiment, a method for ingesting data streams includes, at a client gateway, receiving a plurality of messages; assigning the plurality of messages to one or more data streams; obtaining stream routing configurations; and identifying one or more receivers. The method further includes determining whether at least one of the one or more data streams is to be delivered to one or more receivers operating in the first computing environment; and if so, delivering the at least one of the one or more data streams to the one or more receivers operating in the first computing environment. The method further includes delivering the one or more data streams to a data ingress gateway operating in a second computing environment.

Abstract: The present disclosure relates to techniques for managing client computing systems, such as a client distributed-computing system. In one embodiment, a desired state of the client distributed-computing system and a current state of the client distributed-computing system are received. Measurement data generated by a plurality of components of the client distributed-computing system is received. The measurement data is processed using one or more analytical or statistical techniques to generate distilled data. Based on one or more policies and the desired state, the distilled data and the current state are analyzed to determine one or more actions predicted to converge the current state of the client distributed-computing system towards the desired state. One or more control commands corresponding to the one or more actions are provided to the client distributed-computing system. The one or more control commands cause the client distributed-computing system to perform the one or more actions.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to improve performance of cloud-based services across geographic regions. An example apparatus includes a response parser to, in response to obtaining an authorization token indicating to utilize a software-as-a-service (SaaS), determine a tenant identification code based on an authorization token, and determine a first point of presence in response to determining the tenant identification code, a shard analyzer to determine a second point of presence of a shard, the shard being a deployed instance of the SaaS, and a shard selector to assign the shard to a user when the first point of presence and the second point of presence are the same.

Abstract: The present disclosure relates to techniques for managing client computing systems, such as a client distributed-computing system. In one embodiment, a desired state of the client distributed-computing system and a current state of the client distributed-computing system are received. Measurement data generated by a plurality of components of the client distributed-computing system is received. The measurement data is processed using one or more analytical or statistical techniques to generate distilled data. Based on one or more policies and the desired state, the distilled data and the current state are analyzed to determine one or more actions predicted to converge the current state of the client distributed-computing system towards the desired state. One or more control commands corresponding to the one or more actions are provided to the client distributed-computing system. The one or more control commands cause the client distributed-computing system to perform the one or more actions.

Abstract: The present disclosure relates to techniques for managing client computing systems, such as a client distributed-computing system. In one embodiment, a desired state of the client distributed-computing system and a current state of the client distributed-computing system are received. Measurement data generated by a plurality of components of the client distributed-computing system is received. The measurement data is processed using one or more analytical or statistical techniques to generate distilled data. Based on one or more policies and the desired state, the distilled data and the current state are analyzed to determine one or more actions predicted to converge the current state of the client distributed-computing system towards the desired state. One or more control commands corresponding to the one or more actions are provided to the client distributed-computing system. The one or more control commands cause the client distributed-computing system to perform the one or more actions.

Abstract: Techniques for ingesting data streams to a distributed-computing system using a multi-directional data ingestion pipeline are provided. In one embodiment, a method for ingesting data streams includes, at a client gateway, receiving a plurality of messages; assigning the plurality of messages to one or more data streams; obtaining stream routing configurations; and identifying one or more receivers. The method further includes determining whether at least one of the one or more data streams is to be delivered to one or more receivers operating in the first computing environment; and if so, delivering the at least one of the one or more data streams to the one or more receivers operating in the first computing environment. The method further includes delivering the one or more data streams to a data ingress gateway operating in a second computing environment.

Abstract: The present disclosure relates to techniques for handling of bidirectional command protocols via a unidirectional communication connection established between a client computing environment and a cloud-services computing environment. In one embodiment, a command request message is pushed from a service component of the cloud-services computing environment to a client gateway of the client computing environment via the unidirectional communication connection. A token indicating routing information to the service component is embedded in the pushed command request message. A command response message is received at the cloud gateway from the client gateway via a bidirectional communication connection established between the client computing environment and the cloud-services computing environment. The command response message includes the token and data associated with executing the command request message at the client computing environment.

Abstract: Architecture that facilitates communications between two network nodes of the different networks by providing a routing mechanism that uses alternative modalities driven entirely by policies that are authored and stored in a computing cloud and enforced on the client. This allows the selection of one network path over another path based on criteria such as, physical location of the hosts and service level agreements (SLAs) to be provided, for example. With respect for path selection, a packet can be routed through a datacenter closest to the hosts. With respect to SLAs, there may be different SLAs available to different clients. For clients with the highest bandwidth/uptime or other guarantees, a network path different from other types of clients can be selected. Additionally, connectivity can be allowed or disallowed based on other kinds of policy rules such as a virtual circle to which the hosts may belong.

Abstract: Architecture that facilitates communications between two network nodes of the different networks by providing a routing mechanism that uses alternative modalities driven entirely by policies that are authored and stored in a computing cloud and enforced on the client. This allows the selection of one network path over another path based on criteria such as, physical location of the hosts and service level agreements (SLAs) to be provided, for example. With respect for path selection, a packet can be routed through a datacenter closest to the hosts. With respect to SLAs, there may be different SLAs available to different clients. For clients with the highest bandwidth/uptime or other guarantees, a network path different from other types of clients can be selected. Additionally, connectivity can be allowed or disallowed based on other kinds of policy rules such as a virtual circle to which the hosts may belong.