Abstract: A system with a local data collector that collects power management data for a subsystem. The local data collector can determine whether a first formatting associated with a first channel between the local data collector and a system power management data collector is equivalent to a second formatting associated with a second channel between the local data collector and the system power management data collector, and in response to a determination that the first formatting and second formatting are not equivalent format the power management data according to the first formatting; store the power management data formatted according to the first formatting in a first location in a memory; format the power management data according to the second formatting; and store the power management data formatted according to the second formatting in a second location the memory.

Abstract: Memory bandwidth allocations for a plurality of tenants on a processor socket may be managed by determining a total memory bandwidth for the processor socket, determining a respective share of the total memory bandwidth for each tenant, and determining a respective dynamic memory bandwidth budget for the each tenant. The memory bandwidth allocations may be controlled based on the determined respective dynamic memory bandwidth budgets, wherein the each respective dynamic memory bandwidth budget supports utilizing the each respective share and supports sharing unused memory bandwidth of the each respective tenant with a different tenant included in the plurality of tenants.

Abstract: A method and apparatus for adjusting a frequency of a processor is disclosed herein. In one embodiment, the method includes inhibiting one or more processor cores from exiting an idle state. The method further includes determining a number of processor cores requesting exit from the idle state and a number of non-idle processor cores. The method also includes selecting a maximum frequency for the inhibited processor cores based on the number of inhibited processor cores requesting exit from the idle state and the number of non-idle processor cores. The method includes setting the maximum frequency for the inhibited processor cores, and then uninhibiting the processor cores requesting exit from the idle state.

Abstract: A computer controls power distribution. The computing system determines a topography for a power delivery system that powers a group of computing devices. The computing system determines a number of worker programs for a pool of worker programs based on the topography. The computing system generates the pool of worker programs. The pool of worker programs includes both the number of worker programs and a number of back-up worker programs. The computing system generates a number of power management tasks to manage power consumption through one or more power elements included in the topography of the power delivery system. The computing system sends one or more power management tasks to a worker program included in the pool of worker programs.

Abstract: Utilizing a computing device to determine and enforce limits on cloud computing containers transmitting data over a network. A determination is made of total container time remaining available for a first container to execute in a computing environment, the first container utilizing one or more processor threads executing on a computing device. Processor packet transmission time is determined for processing and transmission of a packet or a batch of packets via a network stack associated with the computing device by the one or more processor threads utilized by the first container. An updated total container time remaining for the first container is calculated, accounting for the processor packet transmission time. The updated total container time remaining is enforced by descheduling all processor threads utilized by the first container if the updated total container time remaining is insufficient.

Abstract: A mechanism is provided for enforcing power caps within a power consumption device with multiple power supplies. Utilizing a minimum power error value from a set of error values, the minimum power error value is multiplied by a factor k to translate the minimum power error value to an internal power error value. The internal minimum power error value is multiplied by a number of working power supply units (M) of the power consumption device, resulting in an internal minimum power error value for multiple power supply units. The internal minimum power error value for the multiple power supply units is summed with a present power cap value thereby forming a summed power cap value. Responsive to the summed power cap value being between a power cap maximum and a power cap minimum, the computing load is throttled using the summed power cap value.

Abstract: A distributed power management system is configured determine a node power consumption of a node during a first time interval. The system can determine a node power cap. The system can determine a proportional component power budget for a component of the node based, at least in part, on the node power consumption and a component power consumption. The system can determine a power budget for the component for a second time interval based, at least in part on the proportional component power budget.

Abstract: A device may monitor a communication between network devices for an error associated with the communication. The device may detect the error associated with the communication between the network devices. The device may perform a comparison of an error metric and a threshold error metric. The error metric may be associated with the error. The device may determine whether the comparison indicates that the error metric satisfies the threshold error metric. The device may identify a source of the error using a loopback test based on determining whether the comparison indicates that the error metric satisfies the threshold error metric. The device may provide error source information based on identifying the source of the error. The error source information may identify the source of the error.

Abstract: A system with a local data collector that collects power management data for a subsystem. The local data collector can determine whether a first formatting associated with a first channel between the local data collector and a system power management data collector is equivalent to a second formatting associated with a second channel between the local data collector and the system power management data collector, and in response to a determination that the first formatting and second formatting are not equivalent format the power management data according to the first formatting; store the power management data formatted according to the first formatting in a first location in a memory; format the power management data according to the second formatting; and store the power management data formatted according to the second formatting in a second location the memory.

Abstract: A mechanism is provided for power capping power consumption devices with multiple power supplies. A set of power supplies supplying power to a power consumption device having stranded power is determined. A power budget of one or more power supplies in the set of power supplies is adjusted to match a power budget of a power supply in the set of power supplies with a limiting power budget among the power budgets computed for each power supply in the set of power supplies. Responsive to identifying at least one power supply in the one or more other power supplies of one or more different power consumption devices having an initially allocated power budget below their corresponding demand, at least a portion of the stranded power is allocated to the power budget of the at least one power supply.

Abstract: A distributed power management system is configured determine a node power consumption of a node during a first time interval. The system can determine a node power cap. The system can determine a proportional component power budget for a component of the node based, at least in part, on the node power consumption and a component power consumption. The system can determine a power budget for the component for a second time interval based, at least in part on the proportional component power budget.

Abstract: A system with a local data collector that collects power management data for a subsystem. The local data collector can determine whether a first formatting associated with a first channel between the local data collector and a system power management data collector is equivalent to a second formatting associated with a second channel between the local data collector and the system power management data collector, and in response to a determination that the first formatting and second formatting are not equivalent format the power management data according to the first formatting; store the power management data formatted according to the first formatting in a first location in a memory; format the power management data according to the second formatting; and store the power management data formatted according to the second formatting in a second location the memory.

Abstract: Examples of techniques for a built-in self-test (BIST) for embedded spin-transfer torque magnetic random access memory (STT-MRAM) are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method may include: initiating, by a processor, a BIST for the STT-MRAM; performing, by the processor, an error-correcting code (ECC) test for a portion of the STT-MRAM; responsive to the ECC test not being passed, determining whether a maximum signal is reached; responsive to the maximum signal not being reached, increasing the signal and performing the ECC test again; and responsive to the maximum signal being reached, determining that the portion of the STT-MRAM is bad.

Abstract: Utilizing a computing device to determine and enforce limits on cloud computing containers transmitting data over a network. A determination is made of total container time remaining available for a first container to execute in a computing environment, the first container utilizing one or more processor threads executing on a computing device. Processor packet transmission time is determined for processing and transmission of a packet or a batch of packets via a network stack associated with the computing device by the one or more processor threads utilized by the first container. An updated total container time remaining for the first container is calculated, accounting for the processor packet transmission time. The updated total container time remaining is enforced by descheduling all processor threads utilized by the first container if the updated total container time remaining is insufficient.

Abstract: Utilizing a computing device to determine and enforce limits on cloud computing containers receiving data over a network. A determination is made of total container time remaining available for a first container to execute in a computing environment. Processor packet receipt time is determined for receiving and processing of a packet or a batch of packets via a network stack associated with the computing device. An updated total container time remaining is calculated for the first container accounting for the processor packet receipt time. The updated total container time remaining is enforced by dropping a subsequent packet or batch of packets received at the network stack if the updated total container time remaining is insufficient.

Abstract: Utilizing a computing device to determine and enforce limits on cloud computing containers transmitting data over a network. A determination is made of total container time remaining available for a first container to execute in a computing environment, the first container utilizing one or more processor threads executing on a computing device. Processor packet transmission time is determined for processing and transmission of a packet or a batch of packets via a network stack associated with the computing device by the one or more processor threads utilized by the first container. An updated total container time remaining for the first container is calculated, accounting for the processor packet transmission time. The updated total container time remaining is enforced by descheduling all processor threads utilized by the first container if the updated total container time remaining is insufficient.

Abstract: Utilizing a computing device to determine and enforce limits on cloud computing containers transmitting data over a network. A determination is made of total container time remaining available for a first container to execute in a computing environment, the first container utilizing one or more processor threads executing on a computing device. Processor packet transmission time is determined for processing and transmission of a packet or a batch of packets via a network stack associated with the computing device by the one or more processor threads utilized by the first container. An updated total container time remaining for the first container is calculated, accounting for the processor packet transmission time. The updated total container time remaining is enforced by descheduling all processor threads utilized by the first container if the updated total container time remaining is insufficient.

Abstract: Utilizing a computing device to determine and enforce limits on cloud computing containers transmitting data over a network. A determination is made of total container time remaining available for a first container to execute in a computing environment, the first container utilizing one or more processor threads executing on a computing device. Processor packet transmission time is determined for processing and transmission of a packet or a batch of packets via a network stack associated with the computing device by the one or more processor threads utilized by the first container. An updated total container time remaining for the first container is calculated, accounting for the processor packet transmission time. The updated total container time remaining is enforced by descheduling all processor threads utilized by the first container if the updated total container time remaining is insufficient.

Abstract: A processor system tracks, in at least one counter, a number of cycles in which at least one execution unit of at least one processor core is idle and at least one thread of the at least one processor core is waiting on at least one off-core memory access during run-time of the at least one processor core during an interval comprising multiple cycles. The processor system evaluates an expected performance impact of a frequency change within the at least one processor core based on the current run-time conditions for executing at least one operation tracked in the at least one counter during the interval.

Abstract: A method includes monitoring power usage for a storage system that includes a set storage units at a first level of storage granularity and a set of storage sub-units at a second level of storage granularity, wherein the second level of storage granularity is finer than the first level of storage granularity. The method further includes assigning a non-uniform power budget to the set of storage units and adjusting a power budget for the storage sub-units according to the non-uniform power budget assigned to the storage units. A corresponding computer program product and computer system are also disclosed herein.