Abstract: An example system may include a first rack including a first access node and a second rack including a second access node and a storage node. The first and second racks are included within a multi-rack distributed storage system. The first access node is configured to receive over a connection with a client a first request for an object data. The connection with the client is uniquely identified by a connection ID independent of source and destination addresses and ports. The first access node is further configured to determine object data locality details of the object data and relocate the connection to the second access node in the second rack when the object data locality details of the object data indicate the object data is located within the second rack.

Abstract: Technology for establishing network communications over an overlay network among nodes of configurable network computer systems, such as the storage system nodes of a hyper-converged infrastructure system is disclosed. The nodes are configured for communication over an overlay network and overlay endpoints corresponding to the nodes are enabled for encapsulating network communications between overlay endpoints. The nodes may then communicate over a common overlay subnetwork even though they operate in different local subnetworks with different subnetwork configurations. An installer may be similarly configured for network communications with the nodes over the overlay subnetwork.

Abstract: An example system comprises a first access node in a first rack configured to engage in a connection with a client, and a second access node in a second rack. The first and second racks form a multi-rack distributed storage system. The system includes a distributed database including a first load indicator designating a first processing load of the first access node and a second load indicator designating a second processing load of the second access node. The distributed database is accessible to the first and second access nodes. The system further includes a connection relocation manager configured to relocate the connection with the client from the first access node to the second access node when the second processing load is less than the first processing load.

Abstract: Technology for installing operating configurations in nodes of configurable network computer systems, such as the storage system nodes of a hyper-converged infrastructure system is disclosed. The node is configured with network addresses for two different network protocols. An installer identifies a change in the first network address, then uses the second network address and protocol to change the first network address to a default value. Using the default value, the installer can then install an operating configuration using the first network address and protocol.

Abstract: An example system comprises a first access node in a first rack configured to engage in a connection with a client, and a second access node in a second rack. The first and second racks form a multi-rack distributed storage system. The system includes a distributed database including a first load indicator designating a first processing load of the first access node and a second load indicator designating a second processing load of the second access node. The distributed database is accessible to the first and second access nodes. The system further includes a connection relocation manager configured to relocate the connection with the client from the first access node to the second access node when the second processing load is less than the first processing load.

Abstract: An example system may include a first rack including a first access node and a second rack including a second access node and a storage node. The first and second racks are included within a multi-rack distributed storage system. The first access node is configured to receive over a connection with a client a first request for an object data. The connection with the client is uniquely identified by a connection ID independent of source and destination addresses and ports. The first access node is further configured to determine object data locality details of the object data and relocate the connection to the second access node in the second rack when the object data locality details of the object data indicate the object data is located within the second rack.

Abstract: Technology for establishing network communications over an overlay network among nodes of configurable network computer systems, such as the storage system nodes of a hyper-converged infrastructure system is disclosed. The nodes are configured for communication over an overlay network and overlay endpoints corresponding to the nodes are enabled for encapsulating network communications between overlay endpoints. The nodes may then communicate over a common overlay subnetwork even though they operate in different local subnetworks with different subnetwork configurations. An installer may be similarly configured for network communications with the nodes over the overlay subnetwork.

Abstract: Technology for installing operating configurations in nodes of configurable network computer systems, such as the storage system nodes of a hyper-converged infrastructure system is disclosed. The node is configured with network addresses for two different network protocols. An installer identifies a change in the first network address, then uses the second network address and protocol to change the first network address to a default value. Using the default value, the installer can then install an operating configuration using the first network address and protocol.

Abstract: An operating system agnostic task scheduler executes on a top of the rack device. The task scheduler receives from each of multiple nodes an operating system agnostic description of the node's computational resource capability and availability. The task scheduler uses the received information to maintain a resource accounting for each node. Requests to execute tasks are received by the task scheduler from external sources. The task scheduler matches specific tasks to specific nodes, based on the resource accounting. In response to matching a given task to a specific one of the nodes, the scheduler assigns the task to the node, and the task executes thereon. The task scheduler updates the maintained accounting based on computational resources allocated to the task by the node to which it was assigned.

Abstract: Technology for partitioning nodes based on capabilities in a hyper-converged infrastructure is disclosed. In an example computer system, the system detects connection of a new node element to the computer system. The system assigns the new node element an electronic address in the computer system. The computer system then boots the new node element using a pre-existing bootable image stored at the hyper-converged infrastructure system. The computer system uses a federated control plane to discover the new node element. The federated control plane determines a capability of the new node element. The federated control plane assigns the new node element to a global storage pool.

Abstract: An operating system agnostic task scheduler executes on a top of the rack device. The task scheduler receives from each of multiple nodes an operating system agnostic description of the node's computational resource capability and availability. The task scheduler uses the received information to maintain a resource accounting for each node. Requests to execute tasks are received by the task scheduler from external sources. The task scheduler matches specific tasks to specific nodes, based on the resource accounting. In response to matching a given task to a specific one of the nodes, the scheduler assigns the task to the node, and the task executes thereon. The task scheduler updates the maintained accounting based on computational resources allocated to the task by the node to which it was assigned.

Abstract: Technology for partitioning nodes based on capabilities in a hyper-converged infrastructure is disclosed. In an example computer system, the system detects connection of a new node element to the computer system. The system assigns the new node element an electronic address in the computer system. The computer system then boots the new node element using a pre-existing bootable image stored at the hyper-converged infrastructure system. The computer system uses a federated control plane to discover the new node element. The federated control plane determines a capability of the new node element. The federated control plane assigns the new node element to a global storage pool.

Abstract: Embodiments of the present disclosure relate to systems and methods for updating a System on Chip (SOC) image without using direct memory access (DMA) programming. A target SOC monitors a target mailbox to determine reception of a data packet of an SOC image received from a host computer, wherein the SOC image includes a plurality of data packets. The target SOC reads the data packet from a buffer of the target SOC and writes a status message to a host mailbox of the target SOC, wherein the status message is indicative of a reception status of the data packet.

Abstract: Embodiments of the present disclosure relate to systems and methods for updating a System on Chip (SOC) image without using direct memory access (DMA) programming. A target SOC monitors a target mailbox to determine reception of a data packet of an SOC image received from a host computer, wherein the SOC image includes a plurality of data packets. The target SOC reads the data packet from a buffer of the target SOC and writes a status message to a host mailbox of the target SOC, wherein the status message is indicative of a reception status of the data packet.