Abstract: Management of power consumption in large computing clusters is disclosed herein. According to an aspect, a computing device comprising a power manager may be configured to receive, via a communication interface, information associated with the cluster of computing nodes. The power manager of the computing device may also be configured to determine whether a switch is coupled to an inactive computing node of the cluster of computing nodes based on the received information. Further, the power manager of the computing device may be configured to communicate a command to the switch to remove power supplied to a switch port of the switch coupled to the inactive computing node in response to determining that the switch is coupled to an inactive computing node of the cluster of computing nodes.

Abstract: An apparatus includes a chassis having longitudinal rails for guiding the chassis to move longitudinally into and out of a rack. A flexible sealing member is secured to at least one longitudinal surface of the chassis along a lateral pathway, wherein the flexible sealing member has a first side secured to the chassis, a second side secured to a rigid frame, and a central portion extending between the first and second ends. An actuator is positioned within the rack and is longitudinally aligned with the rigid frame. Accordingly, moving the chassis longitudinally into the rack causes the rigid frame to engage the actuator and then elastically flex the central portion of the flexible sealing member to extend outwardly from the longitudinal surface of the chassis.

Abstract: A method includes supplying power to a physical server from a plurality of power supplies, wherein operation of all hardware components of the server requires more power than any one of the power supplies can provide. A plurality of jobs are run on the server while the plurality of power supplies are supplying power to the physical server. The method further comprises identifying an amount of power required by each of the components, and identifying one or more components that are not required by one or more of the jobs that are running on the server. The method detects a loss of power from one of the power supplies and then selectively removes power from hardware components identified as not required so that at least a central processing unit and a memory device can continue running at least one job using power available from the operational power supplies.

Abstract: A component power cable having a pair of elongate conductive members each connected at a first end to a power distribution unit connector and at a second end to a component power supply connector, wherein the cable has sufficient resilience to impart a generally collapsed configuration to the component power cable, with the first end generally proximal to the second end. The component power cable is extendable from the collapsed configuration to an extended configuration by displacement of the first end to a position distal to the second end, wherein energy stored in the resilient cable by such displacement restores the component power cable to the collapsed configuration upon return of the first end to a position proximal the second end. The resilience may be provided by a spring element or by an elastomeric sheath.

Abstract: A system selectively cools a set of at least one rack-mounted server in a chassis. The system comprises: a chassis; a chassis manager; a set of at least one thermal sensor coupled to each rack-mounted server in the chassis; a cold air source; a cold air conduit coupled to the cold air source; a plurality of cold air valves coupled to the cold air conduit; and an expandable tube of flexible memory material coupled to each of the plurality of cold air valves, where the expandable tube inflates with cold air from the cold air source to expose directional holes, and thus cold air, across a specific predetermined sub-area of a particular overheating rack-mounted server in response to the chassis manager detecting that the particular overheating rack-mounted server is exceeding a predetermined temperature.

Abstract: A method of powering on a plurality of devices includes identifying a plurality of power distribution units (PDUs) disposed in a rack, wherein each PDU receives power from a main power source and includes a circuit breaker. A plurality of devices disposed in the rack are identified, wherein each device receives power from one of the PDUs, and wherein the plurality of devices are server nodes, network switches or external data storage devices. Vital product data (VPD) is obtained from a service processor in each device, wherein the VPD identifies the device by a model identification code. For each PDU, the plurality of devices connected to the PDU are powered on in a sequence to prevent an inrush current from tripping the circuit breaker within the PDU, wherein the sequence powers on devices in order of ascending commonality of the model identification code.

Abstract: A rack mountable network switch, the rack mountable network switch comprising: a faceplate; a switch chassis coupled to the faceplate, the switch chassis including a plurality of connector openings on a surface of the switch chassis that is perpendicular to the faceplate; a plurality of moveable plug receptacles coupled to a printed circuit board (‘PCB’) mounted inside the switch chassis; and a mechanical positioning component coupled to the moveable plug receptacles, the mechanical positioning component configured to position the moveable plug receptacles to extrude from the switch chassis via the connector openings when the mechanical positioning component is in a first position, the mechanical positioning component further configured to position the moveable plug receptacles inside the switch chassis when the mechanical positioning component is in a second position.

Abstract: Positioning autonomous vehicles based on field of view, including: identifying, by a vehicle management module, one or more critical sight lines for a subject vehicle, each critical sight line representing a boundary of an area of space surrounding the subject vehicle; determining, by the vehicle management module, physical location information for one or more surrounding vehicles; determining, by the vehicle management module in dependence upon the physical location information for one or more surrounding vehicles, whether one or more surrounding vehicles are located within the area of space surrounding the subject vehicle; and responsive to determining that one or more surrounding vehicles are located within the area of space surrounding the subject vehicle, altering a location of the subject vehicle relative to at least one of the surrounding vehicles.

Abstract: In one embodiment of the present invention, a system selectively cools a set of at least one rack-mounted server in a chassis. The system comprises: a chassis; a chassis manager; a set of at least one thermal sensor coupled to each rack-mounted server in a chassis; a trolley track oriented functionally proximate to the multiple rack-mounted servers; and a cold air trolley movably mounted to the trolley track. The cold air trolley moves along the trolley track in order to be selectively oriented next to a particular overheating rack-mounted server in the chassis, thus providing a fluid conduit from a cold air source to the particular overheating rack-mounted server in response to the chassis manager detecting that the particular overheating rack-mounted server is exceeding a predetermined temperature.

Abstract: A computer-implemented method obtains a correlation between percent utilization and noise level for a plurality of compute node types, and obtains an inventory of a plurality of compute nodes in a cluster, wherein the inventory identifies each compute node by a compute node type, and wherein the plurality of compute nodes includes two or more compute node types. The method further includes determining a percent utilization of each compute node, and, for each compute node of an identified compute node type, determining a noise level using the determined percent utilization for the compute node as input into the correlation between percent utilization and noise level for the identified compute node type. An overall noise level in the cluster is calculated using the noise level determined for each compute node, and workload is distributed among the plurality of compute nodes to reduce the calculated overall noise level in the cluster.

Abstract: A rear door heat exchanger is used to cool exhaust air as it exits a rack containing a plurality of computing devices. An air flow rate is determined for each of the plurality of computing devices within the rack, wherein each of the plurality of computing devices includes a fan drawing air through the computing device. The position of a baffle or louver is controlled to allow exhaust air to bypass the rear door heat exchanger in response to determining that the total air flow rate through the plurality of computing devices exceeds a predetermined air flow capacity threshold of the rear door heat exchanger.

Abstract: A method controls vehicular traffic on a one-way roadway. A hardware sensor detects vehicular traffic on a roadway. A hardware traffic control device determines whether the vehicular traffic on the roadway has been moving exclusively in a first direction during a preceding period of time, such that the roadway is a one-way roadway on which current vehicular traffic is authorized to travel only in the first direction. The hardware sensor detects an errant vehicle that is traveling on the one-way roadway in a second direction that is opposite the first direction. In response to determining that the errant vehicle is traveling in the second direction on the one-way roadway, a warning signal is transmitted to vehicles, other than the errant vehicle, on the one-way roadway.

Abstract: A computer-implemented method identifies the path of a first power circuit to a first power supply that is connected to supply power to an electronic device, and identifies the path of a second power circuit to a second power supply that is connected to supply power to the electronic device. The method then compares the path of the first power distribution circuit with the path of the second power distribution circuit to determine a measure of redundancy in the first and second distribution paths. A measure of redundancy may then be output to a user.

Abstract: A method and a computer program product for implementing the method are provided for wear leveling the physical servers or other components within a cluster. The method includes identifying uptime for each of a plurality of physical servers within a cluster and scheduling jobs on the physical servers within the cluster giving priority to the use of physical servers in order of increasing uptime. The physical servers within the cluster that have no assigned jobs are then powered off. As a result, physical servers having low uptime relative to other physical servers within the cluster will operate more so that their uptime increases, and physical servers having high uptime relative to other physical servers within the cluster will operate less so that their uptime does not increase. Over time, the method will narrow the range of uptime, which may be referred to as “wear leveling.

Abstract: A computer-implemented method obtains a correlation between percent utilization and noise level for a plurality of compute node types, and obtains an inventory of a plurality of compute nodes in a cluster, wherein the inventory identifies each compute node by a compute node type, and wherein the plurality of compute nodes includes two or more compute node types. The method further includes determining a percent utilization of each compute node, and, for each compute node of an identified compute node type, determining a noise level using the determined percent utilization for the compute node as input into the correlation between percent utilization and noise level for the identified compute node type. An overall noise level in the cluster is calculated using the noise level determined for each compute node, and workload is distributed among the plurality of compute nodes to reduce the calculated overall noise level in the cluster.

Abstract: Preventing changes to computing devices in a computing system servicing a critical job, including: identifying, by a job protection module, a critical job executing in the computing system; identifying, by the job protection module, one or more computing devices in the computing system utilized during execution of the critical job; and locking, by the job protection module, each of the one or more computing devices in the computing system utilized during execution of the critical job from undergoing a configuration change during execution of the critical job.

Abstract: A hardware traffic control device controls vehicular traffic on a one-way roadway. A hardware sensor detects vehicular traffic on a roadway in order to enable a hardware traffic control device to determine that the vehicular traffic on the roadway has been moving exclusively in a first direction during a preceding period of time, thus identifying the roadway as a one-way roadway in which current vehicular traffic is authorized to travel only in the first direction. The hardware sensor then detects an errant vehicle that is traveling in the opposite direction on the one-way roadway. A disabling electronic signal is then transmitted from the hardware traffic control device to disable a distracting electronic device within the errant vehicle.

Abstract: A method and computer program product are provided for controlling the airflow direction through a device enclosure. A first device enclosure is positioned adjacent a second device enclosure, wherein both enclosures have an airflow pathway extending from the front to the back, and a fan for moving air through the airflow pathway, wherein the fan of the first device enclosure is a reversible rotary fan. The method automatically determines whether the first device enclosure is in a first orientation with its front facing in the same direction as the front of the adjacent second device enclosure or in a second orientation with the front facing in the same direction as the back of the adjacent second device enclosure. The airflow direction imparted by a reversible rotary fan is then controlled according to the determined orientation of the first device enclosure relative to the second device enclosure.

Abstract: Anticipatory protection of critical jobs in a computing system, including: identifying, by a system management module, a problem computing component in the computing system; identifying, by the system management modules, all proximate computing components in the computing system, wherein each proximate computing component is within a predetermined physical proximity of the problem computing component; determining, by the system management module, whether the proximate computing components are executing one or more critical jobs; and responsive to determining that the proximate computing components are executing one or more critical jobs migrating, by the system management module, the one or more critical jobs to distant computing components in the computing system, wherein each distant computing component is not within the predetermined physical proximity of the problem computing component.

Abstract: An apparatus includes a chassis having longitudinal rails for guiding the chassis to move longitudinally into and out of a rack. A flexible sealing member is secured to at least one longitudinal surface of the chassis along a lateral pathway, wherein the flexible sealing member has a first side secured to the chassis, a second side secured to a rigid frame, and a central portion extending between the first and second ends. An actuator is positioned within the rack and is longitudinally aligned with the rigid frame. Accordingly, moving the chassis longitudinally into the rack causes the rigid frame to engage the actuator and then elastically flex the central portion of the flexible sealing member to extend outwardly from the longitudinal surface of the chassis.