Abstract: In one example, a system is disclosed, which may include a network device, a new server connected to the network device, and a management server communicatively connected to a cloud-based service and the network device. The management server may include a server deployment engine to discover the new server in the system using the network device; obtain an encrypted data blob associated with the new server from the cloud-based service; establish a trust, via a secure protocol, with the new server using the encrypted data blob; and deploy the new server in the system upon establishing the trust with the new server.

Abstract: Examples of transceiver module assemblies may comprise a first transceiver module engaged with a first electrical device and including a first transceiver, a second transceiver module engaged with a second electrical device and including a second transceiver, and an electro-optical cable to connect the first transceiver module to the second transceiver module. The first transceiver module may receive an electrical signal and electrical power from the first electrical device, and the first transceiver may convert the electrical signal to an optical signal. The electro-optical cable may separately transmit the optical signal and the electrical power from the first transceiver module to the second transceiver module. The second transceiver may convert the optical signal back to the electrical signal and provide the converted electrical signal to the second electrical device.

Abstract: In one example in accordance with the present disclosure, a subsystem is provided. The subsystem includes a signal driver/receiver capable of sending and receiving data and signals over a passive cable. The subsystem includes a connection discovery engine to access a low-level enable or disable control of the signal driver/receiver and a low-level loss-of-signal (LOS) control of the signal driver/receiver. The connection discovery engine modulates the enable or disable control to send a local unique ID of the signal driver/receiver over the passive cable. The connection discovery engine monitors timings of transitions on the LOS control to receive, over the passive cable, a remote unique ID of a signal driver/receiver in a second subsystem connected by the passive cable.

Abstract: In one example in accordance with the present disclosure, a system is provided. The system includes a first subsystem and a second subsystem, connectable to each other via a passive cable, and each connected to a high-level management tool. Each subsystem includes a signal driver/receiver capable of sending and receiving data and signals over the passive cable and a connection discovery engine to access low-level power up/down controls of the signal driver/receiver. The connection discovery engine is to, via physical layer communication, send a local unique identifier (ID) of the particular signal driver/receiver over the passive cable. The connection discovery engine is further to, via physical layer communication, receive, over the passive cable, a remote unique ID of the signal driver/receiver in the other connected subsystem. The connection discovery engine is further to send the local unique ID and the remote unique ID to the high-level management tool.

Abstract: Examples of transceiver module assemblies may comprise a first transceiver module engaged with a first electrical device and including a first transceiver, a second transceiver module engaged with a second electrical device and including a second transceiver, and an electro-optical cable to connect the first transceiver module to the second transceiver module. The first transceiver module may receive an electrical signal and electrical power from the first electrical device, and the first transceiver may convert the electrical signal to an optical signal. The electro-optical cable may separately transmit the optical signal and the electrical power from the first transceiver module to the second transceiver module. The second transceiver may convert the optical signal back to the electrical signal and provide the converted electrical signal to the second electrical device.

Abstract: In one example, a system is disclosed, which may include a network device, a new server connected to the network device, and a management server communicatively connected to a cloud-based service and the network device. The management server may include a server deployment engine to discover the new server in the system using the network device, obtain an encrypted data blob associated with the new server from the cloud-based service, establish a trust, via a secure protocol, with the new server using the encrypted data blob, and deploy the new server in the system upon establishing the trust with the new server.

Abstract: In one example in accordance with the present disclosure, a subsystem is provided. The subsystem includes a signal driver/receiver capable of sending and receiving data and signals over a passive cable. The subsystem includes a connection discovery engine to access a low-level enable or disable control of the signal driver/receiver and a low-level loss-of-signal (LOS) control of the signal driver/receiver. The connection discovery engine modulates the enable or disable control to send a local unique ID of the signal driver/receiver over the passive cable. The connection discovery engine monitors timings of transitions on the LOS control to receive, over the passive cable, a remote unique ID of a signal driver/receiver in a second subsystem connected by the passive cable.

Abstract: In one example in accordance with the present disclosure, a system is provided. The system includes a first subsystem and a second subsystem, connectable to each other via a passive cable, and each connected to a high-level management tool. Each subsystem includes a signal driver/receiver capable of sending and receiving data and signals over the passive cable and a connection discovery engine to access low-level power up/down controls of the signal driver/receiver. The connection discovery engine is to, via physical layer communication, send a local unique identifier (ID) of the particular signal driver/receiver over the passive cable. The connection discovery engine is further to, via physical layer communication, receive, over the passive cable, a remote unique ID of the signal driver/receiver in the other connected subsystem. The connection discovery engine is further to send the local unique ID and the remote unique ID to the high-level management tool.

Abstract: Fault-tolerant power control in a computer system is described. In an example, a power controller to control power applied to an enclosure having a plurality of computing devices includes: first and second alternating current (AC) primary power meters respectively measuring first and second input power feeds to the enclosure; a first alternative power meter to measuring power supplied by the first input power feed; a second alternative power meter to measure power supplied by the second input power feed; a first controller coupled to the first primary power meter and the second alternative power meter; and a second controller coupled to the second primary power meter and the first alternative power meter; wherein the first controller is coupled to the second controller.

Abstract: A power capping system (10) and method (200) are provided. In one embodiment, a power capping system (10) includes a power controller (16) configured to calculate an error between a predefined maximum desired power and a power feedback signal associated with actual power consumption of a server (12) and to provide a power capping signal that substantially limits the power consumption of the server (12) based on a predetermined gain constant and the error. The system also includes a management interface (18) configured to generate a normalization factor based on the power feedback signal. The normalization factor can be implemented to normalize the error.

Abstract: Systems, methods, and other embodiments associated with automatically detecting and characterizing a power topology are described. One example system includes a topology logic that identifies connections between PDUs and computers that receive power from the PDUs. The example system may include a data store that receives PDU/computer association data from the topology logic. A computer may communicate with a power providing PDU over a power line connecting the two devices. The computer and the power providing PDU may be configured with network interface devices (e.g., Ethernet switches) configured to communicate over the power line using, for example, EoP. The topology logic may discover a PDU/CE association by examining data transmitted over a network to which the computer and/or the PDU are connected.

Abstract: Fault-tolerant power control in a computer system is described. In an example, a power controller to control power applied to an enclosure having a plurality of computing devices includes: first and second alternating current (AC) primary power meters respectively measuring first and second input power feeds to the enclosure; a first alternative power meter to measuring power supplied by the first input power feed; a second alternative power meter to measure power supplied by the second input power feed; a first controller coupled to the first primary power meter and the second alternative power meter; and a second controller coupled to the second primary power meter and the first alternative power meter; wherein the first controller is coupled to the second controller.

Abstract: An example system includes a power capping controller to assert an output based on exceeding a power threshold for a computer system. A central processing unit (CPU) core is provided to enter a low-power C-state based on the output being asserted via a control path that bypasses an operating system command.

Abstract: Systems, methods, and other embodiments associated with event based correlation of power events are described. One example method includes storing a power distribution unit (PDU) event data that identifies an occurrence of a suspected power event associated with a device. The method can then provide a PDU-server correlation signal that identifies a connection between a PDU and a device.

Abstract: A method for real-time server management may include determining a server architecture model based on performance characteristics of a component of a server. The method may further include determining a real-time model of the server from the server architecture model based on real-time server operation data, and adapting a performance controller for the server to operational characteristics of the server based on the real-time model.

Abstract: A method and apparatus for controlling the power usage of a processor is disclosed. The power usage of the processor is monitored. When the power usage of the processor exceeds a threshold power usage value, the power used by the processor is reduced or limited. A processor utilization value is also monitored. When the processor utilization value is above a threshold utilization value, the processor is ramped to a higher performance state. When power to the processor is being limited, a first rate is used to ramp the processor to the higher performance state. When power to the processor is not being limited, then a second rate, different from the first rate, is used to ramp the processor to the higher performance state.

Abstract: An example system includes a power capping controller to assert an output based on exceeding a power threshold for a computer system. A central processing unit (CPU) core is provided to enter a low-power C-state based on the output being asserted via a control path that bypasses an operating system command.

Abstract: A power capping system (10) and method (200) are provided. In one embodiment, a power capping system (10) includes a power controller (16) configured to calculate an error between a predefined maximum desired power and a power feedback signal associated with actual power consumption of a server (12) and to provide a power capping signal that substantially limits the power consumption of the server (12) based on a predetermined gain constant and the error. The system also includes a management interface (18) configured to generate a normalization factor based on the power feedback signal. The normalization factor can be implemented to normalize the error.

Abstract: A method and apparatus for controlling the power usage of a processor is disclosed. The power usage of the processor is monitored. When the power usage of the processor exceeds a threshold power usage value, the power used by the processor is reduced or limited. A processor utilization value is also monitored. When the processor utilization value is above a threshold utilization value, the processor is ramped to a higher performance state. When power to the processor is being limited, a first rate is used to ramp the processor to the higher performance state. When power to the processor is not being limited, then a second rate, different from the first rate, is used to ramp the processor to the higher performance state.

Abstract: Systems, methods, and other embodiments associated with event based correlation of power events are described. One example method includes storing a power distribution unit (PDU) event data that identifies an occurrence of a suspected power event associated with a device. The method can then provide a PDU-server correlation signal that identifies a connection between a PDU and a device.