Abstract: A system for interconnecting a plurality of computing nodes includes a plurality of optical circuit switches and a plurality of electrical circuit switches. A first network stage comprises a first plurality of circuit switches selected from among the plurality of optical circuit switches and the plurality of electrical circuit switches. Each computing node among the plurality of computing nodes is optically coupled to at least one of the first plurality of circuit switches. A second network stage comprises a second plurality of circuit switches selected from among the plurality of optical circuit switches and the plurality of electrical circuit switches. Each circuit switch among the first plurality of circuit switches is optically coupled to each circuit switch among the second plurality of optical circuit switches.

Abstract: A system for efficiently interconnecting computing nodes can include a plurality of computing nodes and a plurality of network switches coupled in parallel to the plurality of computing nodes. The system can also include a plurality of node interfaces. Each computing node among the plurality of computing nodes can include at least one node interface for each network switch among the plurality of network switches. The plurality of node interfaces corresponding to a computing node can be configured to send data to another computing node via the plurality of network switches. The system can also include a plurality of switch interfaces. Each network switch among the plurality of network switches can include at least one switch interface for each computing node among the plurality of computing nodes. A switch interface corresponding to the computing node can be coupled to a node interface corresponding to the computing node.

Abstract: A system for using free-space optics to interconnect a plurality of computing nodes can include a plurality of node optical transceivers that are electrically coupled to at least some of the plurality of computing nodes. The system can also include a plurality of router optical transceivers that facilitate free-space optical communications with the plurality of node optical transceivers. Each node optical transceiver among the plurality of node optical transceivers can have a corresponding router optical transceiver that is optically coupled to the node optical transceiver. The system can also include a router that is coupled to the plurality of router optical transceivers. The router can be configured to route the free-space optical communications among the plurality of computing nodes.

Abstract: A system for using free-space optics to interconnect a plurality of computing nodes can include a plurality of node optical transceivers that are electrically coupled to at least some of the plurality of computing nodes. The system can also include a plurality of router optical transceivers that facilitate free-space optical communications with the plurality of node optical transceivers. Each node optical transceiver among the plurality of node optical transceivers can have a corresponding router optical transceiver that is optically coupled to the node optical transceiver. The system can also include a router that is coupled to the plurality of router optical transceivers. The router can be configured to route the free-space optical communications among the plurality of computing nodes.

Abstract: In various examples there is a communications network comprising a plurality of nodes connected via an interconnection medium to form a receive-from-many communications network. The network has a synchronisation mechanism which synchronizes a signal frequency of the nodes. The network has at least one store holding signal amplitude data of signals previously sent between specified pairs of nodes of the communications network. An amplitude controller uses the stored data to adjust amplitudes of signals communicated between at least one of the pairs of nodes of the communications network.

Abstract: A wavelength switchable laser is described which has a multi-wavelength laser source configured to generate signals at different wavelengths. The wavelength switchable laser has a wavelength selector with a plurality of electro-optical switches, each electro-optical switch being configurable to transmit or block output of one of the signals from the multi-wavelength source according to the wavelength of the signal.

Abstract: In various examples there is a communications network comprising a plurality of nodes connected via an interconnection medium to form a receive-from-many communications network. The network has a synchronisation mechanism which synchronizes a signal frequency of the nodes. The network has at least one store holding signal amplitude data of signals previously sent between specified pairs of nodes of the communications network. An amplitude controller uses the stored data to adjust amplitudes of signals communicated between at least one of the pairs of nodes of the communications network.

Abstract: There is a communications network node comprising a transmitter or a receiver configured to communicate with a plurality of other nodes via an interconnection medium interconnecting the node and the other nodes. The node is frequency synchronized with regard to signal transmission or reception, via a frequency synchronization mechanism, with at least one of the other nodes. The node has at least one store holding phase data relating to an amount of phase asynchrony and path characteristics between the node and at least one of the other nodes. A phase controller uses the stored data to adjust phase used by the node such that the recovery of data when communicating with at least one other node is facilitated.

Abstract: Methods of predicting datacenter performance to improve provisioning are described. In an embodiment, a resource manager element receives a request from a tenant which describes an application that the tenant wants executed by a multi-resource, multi-tenant datacenter. The request that has been received is mapped to a set of different candidate resource combinations within the datacenter, where each candidate resource combination can be used to execute the application in a manner which satisfies a high level constraint specified within the request. This mapping may, for example, be performed using a combination of benchmarking and an analytical model. In some examples, each resource combination may comprise a number of virtual machines and a bandwidth between those machines. Data relating to at least a subset (and in some examples, two or more) of the candidate resource combinations is then presented to the tenant.

Abstract: Methods of offering network performance guarantees in multi-tenant datacenters are described. In an embodiment, a request for resources received at a datacenter from a tenant comprises a number of virtual machines and a performance requirement, such as a bandwidth requirement, specified by the tenant. A network manager within the datacenter maps the request onto the datacenter topology and allocates virtual machines within the datacenter based on the available slots for virtual machines within the topology and such that the performance requirement is satisfied. Following allocation, stored residual capacity values for elements within the topology are updated according to the new allocation and this updated stored data is used in mapping subsequent requests onto the datacenter. The allocated virtual machines form part of a virtual network within the datacenter which is allocated in response to the request and two virtual network abstractions are described: virtual clusters and virtual oversubscribed clusters.

Abstract: A deadline-aware network protocol is described. In an example, data transfer at a transport layer entity of a packet-based communication network is controlled by receiving a request for network resources for a data flow from a network element and allocating network resources to the data flow. The data flow comprises a number of data packets associated with an application, and the request comprises a factor relating to a time deadline associated with the application. The network resources allocated depend on the factor relating to the time deadline. In examples, the network resource can be a bandwidth or data rate allocated to the data flow, and the factor can be a data rate sufficient to complete the data flow within the time deadline. In examples, the network resources are allocated greedily, such that requests are fully satisfied whenever possible, and the network resources are fully utilized.

Abstract: Resource control for virtual datacenters is described, for example, where a plurality of virtual datacenters are implemented in a physical datacenter to meet guarantees. In examples, each virtual datacenter specifies a plurality of different types of resources having throughput guarantees which are met by computing, for individual flows of the virtual data centers implemented in the physical datacenter, a flow allocation. For example, a flow allocation has, for each of a plurality of different types of physical resources of the datacenter used by the flow, an amount of the physical resource that the flow can use. A flow is a path between endpoints of the datacenter along which messages are sent to implement a service. In examples, the flow allocations are sent to enforcers in the datacenter, which use the flow allocations to control the rate of traffic in the flows.

Abstract: Controlling data storage input/output requests is described, for example, to apply a policy to an end-to-end flow of data input/output requests between at least one computing entity and at least one store. In various examples a plurality of queues are configured at one or more stages of the end-to-end flow and controlled to adhere to a policy. In examples, each stage has a control interface enabling it to receive and execute control instructions from a controller which may be centralized or distributed. For example, the control instructions comprise queuing rules and/or queue configurations. In various examples queues and queuing rules are dynamically created and revised according to feedback about any of: flow behavior, changes in policy, changes in infrastructure or other factors. In examples, high level identifiers of the flow endpoints are resolved, on a per stage basis, to low level identifiers suitable for use by the stage.

Abstract: A deadline-aware network protocol is described. In an example, data transfer at a transport layer entity of a packet-based communication network is controlled by receiving a request for network resources for a data flow from a network element and allocating network resources to the data flow. The data flow comprises a number of data packets associated with an application, and the request comprises a factor relating to a time deadline associated with the application. The network resources allocated depend on the factor relating to the time deadline. In examples, the network resource can be a bandwidth or data rate allocated to the data flow, and the factor can be a data rate sufficient to complete the data flow within the time deadline. In examples, the network resources are allocated greedily, such that requests are fully satisfied whenever possible, and the network resources are fully utilized.

Abstract: A cloud statistics server generates statistics for a cloud service based on an identified data item and an identified operation. The cloud service may include various computing nodes and storage nodes. The cloud statistics may include expected completion times for the identified operation and the identified data item with respect to each of the computing nodes. A computing node may be selected to execute the identified operation based on the expected completion times. The generated statistics may be generated by the cloud statistics server using a network topology associated with the data item that is based on the latencies or expected transfer times between the various storage nodes and computing nodes, and a replication strategy used by the cloud service. The topology may be implemented as a directed graph with edge weights corresponding to expected transfer times between each node.

Abstract: A deadline-aware network protocol is described. In an example, data transfer at a transport layer entity of a packet-based communication network is controlled by receiving a request for network resources for a data flow from a network element and allocating network resources to the data flow. The data flow comprises a number of data packets associated with an application, and the request comprises a factor relating to a time deadline associated with the application. The network resources allocated depend on the factor relating to the time deadline. In examples, the network resource can be a bandwidth or data rate allocated to the data flow, and the factor can be a data rate sufficient to complete the data flow within the time deadline. In examples, the network resources are allocated greedily, such that requests are fully satisfied whenever possible, and the network resources are fully utilized.

Abstract: Controlling data storage input/output requests is described, for example, to apply a policy to an end-to-end flow of data input/output requests between at least one computing entity and at least one store. In various examples a plurality of queues are configured at one or more stages of the end-to-end flow and controlled to adhere to a policy. In examples, each stage has a control interface enabling it to receive and execute control instructions from a controller which may be centralized or distributed. For example, the control instructions comprise queuing rules and/or queue configurations. In various examples queues and queuing rules are dynamically created and revised according to feedback about any of: flow behavior, changes in policy, changes in infrastructure or other factors. In examples, high level identifiers of the flow endpoints are resolved, on a per stage basis, to low level identifiers suitable for use by the stage.

Abstract: Methods of classifying a storage traffic stream in a shared storage network are described. In an embodiment, an identifier for the entity generating the stream is generated, where this entity may, for example, indicate a virtual machine, program, session, physical machine, user or process. The identifier is then shared with at least one processing layer along a path of the storage traffic stream between the generating entity and the storage device which stores the file to which the traffic stream relates. In various embodiments, the identifier may then be used by any processing layers which receive it, to selectively handle traffic streams based on the generating entity. The identifier may be shared when the traffic stream is created or subsequently and in various embodiments, the identifier is shared in a second exchange of messages, following the creation of the traffic stream and prior to any other traffic.

Abstract: Methods of offering network performance guarantees in multi-tenant datacenters are described. In an embodiment, a request for resources received at a datacenter from a tenant comprises a number of virtual machines and a performance requirement, such as a bandwidth requirement, specified by the tenant. A network manager within the datacenter maps the request onto the datacenter topology and allocates virtual machines within the datacenter based on the available slots for virtual machines within the topology and such that the performance requirement is satisfied. Following allocation, stored residual capacity values for elements within the topology are updated according to the new allocation and this updated stored data is used in mapping subsequent requests onto the datacenter. The allocated virtual machines form part of a virtual network within the datacenter which is allocated in response to the request and two virtual network abstractions are described: virtual clusters and virtual oversubscribed clusters.

Abstract: Methods of offering network performance guarantees in multi-tenant datacenters are described. In an embodiment, a request for resources received at a datacenter from a tenant comprises a number of virtual machines and a performance requirement, such as a bandwidth requirement, specified by the tenant. A network manager within the datacenter maps the request onto the datacenter topology and allocates virtual machines within the datacenter based on the available slots for virtual machines within the topology and such that the performance requirement is satisfied. Following allocation, stored residual capacity values for elements within the topology are updated according to the new allocation and this updated stored data is used in mapping subsequent requests onto the datacenter. The allocated virtual machines form part of a virtual network within the datacenter which is allocated in response to the request and two virtual network abstractions are described: virtual clusters and virtual oversubscribed clusters.