Abstract: Virtual machines are managed on the basis of data obtained from a management information database of a network switch having a plurality of Ethernet links coupled to compute nodes running a plurality of virtual machines. A management entity, such as a provisioning manager, determines the amount of network bandwidth being utilized through each of the first and second Ethernet links and the amount of network bandwidth being utilized by the Internet Protocol addresses attributable to each of the virtual machines. Accordingly, one of the virtual machines may be migrated from one compute node to another compute node coupled to an Ethernet link having a greater amount of unutilized network bandwidth. Virtual machines may be dynamically migrated in order to provide each virtual machine with a required amount of network bandwidth.

Abstract: One embodiment provides an error detection method wherein single-bit errors in a memory module are detected and identified as being a random error or a repeat error. Each identified random error and each identified repeat error occurring in a time interval is counted. An alert is generated in response to a number of identified random errors reaching a random-error threshold or a number of identified repeat errors reaching a repeat-error threshold during the predefined interval. The repeat-error threshold is set lower than the random-error threshold. A hashing process may be applied to the memory address of each detected error to map the location of the error in the memory system to a corresponding location in an electronic table.

Abstract: A system comprises a server chassis and first and second hard disk drive carriers, wherein each carrier supports a hard disk drive. A first hinge rotatably connects a distal end of the first hard disk drive carrier to a first side of the chassis, wherein the first hinge allows the carrier to rotate about a first hinge axis between an open position and a closed position. The first hard disk drive carrier rotates in a first plane between an open position extending beyond the front of the chassis and a closed position within the chassis. A second hinge rotatably connects a distal end of the second hard disk drive carrier to a second side of the chassis that opposite the first side of the chassis, wherein the hinge allows the carrier to rotate about a second hinge axis between an open position and a closed position.

Abstract: Wake on local area network (LAN) functionality is provided in a multi-root environment. An I/O device, which is share by a plurality of physical hosts, receives the MAC address contained in the wake up packet, then prepares and sends an appropriate wake signal to the targeted host. In one embodiment, the shared I/O device sends an out-of-band wake up signal to each of the physical host computers, wherein the wake up signal is a serial bit stream encoded with the MAC address so that only the physical host having a MAC address matching the MAC address in the wake up signal will be turned on. In another embodiment, the shared I/O device sends a binary ON/OFF signal directly to the targeted physical host computer over a signal line associated with the MAC address.

Abstract: Method and computer program for managing the network response times experienced by virtual machines. Traffic is routed within an Ethernet network through a network switch according to IP addresses identified within Ethernet frames. A plurality of compute nodes are each coupled to the network switch via a separate Ethernet link. A response time is determined for each virtual machine running on the compute nodes, wherein the response time for a particular virtual machine is the difference between a time stamp in a TCP/IP Request message and a time stamp in a TCP/IP Response message for an IP address assigned to the particular virtual machine. The particular virtual machine may then be migrated to a target compute node in response to a particular one of the virtual machines on a particular one of the compute nodes having a response time that exceeds a response time setpoint.

Abstract: In one embodiment, a communication system for a multi-blade server system includes a multi-drop serial bus network interconnecting a management module with each of a plurality of servers in a multi-server chassis. A first transceiver subsystem is configured for communicating over the serial bus network between the management module and each server within a first frequency band. A second transceiver subsystem is configured for simultaneously communicating over the serial bus network between the management module and the servers within a second frequency band higher than the first frequency band. A first signal-filtering subsystem substantially filters out signals in the second frequency band from the first transceiver subsystem. A second signal-filtering subsystem substantially filters out the signals in the first frequency band from the second transceiver subsystem.

Abstract: The stopband characteristics of an electromagnetic bandgap structure in a printed circuit board may be preserved by selectively forming slots in an additional conductive layer of the printed circuit board. For example, an electromagnetic bandgap structure may include a layer with a continuous conductive region and another layer with a periodically patterned region having a plurality of spaced-apart patches interconnected by branches. Additional conductive layers may be included within the printed circuit board without neutralizing the bandgap by forming slots in the conductive layers in general alignment with spaces between the patches.

Abstract: A method forming a fastener in-situ for fastening two parts at abutting surfaces. A through hole may be formed on each of the first and second parts such that the diameters of the through holes at the abutting surfaces are smaller than the diameters at opposing surfaces. The first and second parts are abutted with the through hole on the first part in fluid communication with the through hole on the second part. A flowable and hardenable material is injected into the first through hole while closing flow out of the second through hole. The flowable and hardenable material contained within the through holes is allowed to harden, thus forming a unitary fastener that fastens the parts.

Abstract: One embodiment provides a computer-implemented method for enforcing a temperature limit of a client computer. The method includes receiving a request for computer-executable work to be executed on a client computer. If executing all of the requested work on the client computer would cause the client computer to exceed the temperature limit, a portion of the requested work may be selectively redirected to a remote computer in an amount selected to enforce the temperature limit of the client computer. Simultaneously, the remainder of the requested work may be executed on the client computer. The output of the redirected work may be communicated from the remote computer back to the client computer over a network.

Abstract: In one embodiment, ambient sound in audible range of a telephone is electronically sampled, and an audible alert is automatically generated in response to an incoming call signal as a function of the sampled ambient sound. The ambient sound sample may be analyzed in terms of selected parameters such as frequency, amplitude, and tempo. The audible alert may then be generated as a function of the selected parameters in such a way that the audible alert is more noticeable in the presence of the ambient sound. For example, an alert frequency that is dissonant with an identified frequency of the ambient sound may be generated.

Abstract: One embodiment provides a computer-implemented method for providing controlled access to electronic content. A password is associated with electronic content, such as by password-protecting an electronic file that contains the electronic content. At least one password attempt is received in an effort to access the electronic content. Each password attempt is compared to the password at a selected subset of “trap” character positions. Up to a threshold number of password entries is allowed that have incorrect characters at any of the trap character positions. A greater number or even an unlimited number of incorrect password entries are allowed having incorrect characters at non-trap character positions. Access to the electronic content is allowed only if one of the password entries exactly matches the password.

Abstract: According to one embodiment, a selectively-expandable speakerphone system allows one or more portable computers to automatically, wirelessly interface with a speakerphone console via an audio access point. A scheduling module initiates the conference call at a scheduled time, whereupon the wireless network interface of each portable computer is automatically switched to an SSID uniquely associated with the audio access point, for connecting to the speakerphone console. The audio signals generated by the laptop microphones are mixed with any audio signal generated by an optional microphone on the speakerphone console, and the mixed audio signals are transmitted over the telephone line. Incoming audio signals are passed to the speakerphone console and wirelessly transmitted to the portable computers for substantially simultaneous playback on the respective loudspeakers.

Abstract: Embodiments of the present invention include computer-implemented methods for selectively applying remedial actions, according to a predefined order, for reducing the error rate in a computer memory system. In one embodiment, an ordered set of remedial actions are sequentially invoked in response to a single-bit error (SBE) in a DIMM reaching successive error thresholds. For example, in an air-cooled system, the remedial actions may include dynamically increasing a DIMM refresh rate, dynamically increasing a rate of airflow used to cool the DIMMs, and dynamically throttling the DIMMs. The remedial actions may be layered as they are successively invoked, to provide a cumulative remedial effect. At least two of the remedial actions may be simultaneously invoked in response to a multi-bit error rate reaching an associated threshold.

Abstract: According to one embodiment, an apparatus has first and second connectors configured for removably connecting to one another. The first connector circuit has a first differential amplifier, a first differential signal path, a first capacitor section capacitively coupling the first differential amplifier to the first differential signal path, and a first DC biasing circuit for imparting a first DC bias to the first differential signal path opposite the first capacitor section. The second connector circuit has a second differential amplifier, a second differential signal path, a second capacitor section capacitively coupling the second differential amplifier to the second differential signal path, and a second DC biasing circuit for imparting a second DC bias to the second differential signal path opposite the second capacitor section having a different magnitude than the first DC bias when the first and second connector are not connected.

Abstract: A method of managing power consumption by a plurality of blade servers within a processing system. The speed of at least one of the plurality of blade servers is reduced in response to the processing system reaching a power or thermal threshold. At least one of the plurality of blade servers is identified as not being critical to maintain in a working state and the critical blade server is put in a sleep state. A satellite management controller may control blade server power consumption and heat generation in various ways that combine processor speed-stepping and control of processor sleep states. Known sleep states save more power than speed-stepping by turning off the processor and/or volatile memory. The processor speed and sleep-states of at least one non-critical blade server, and optionally the processor speed of a critical processor, may be changed in order to control the power consumption below a power threshold or control the temperature below a thermal threshold.

Abstract: Method and computer program product for supplying power in a computing system, and computer program product implementing the method. The method comprises monitoring power consumption of the computing system, supplying power to the computing system using only a first power supply over a first range of power consumption, and supplying power to the computing system using a combination of the first power supply and a second power supply over a second range of power consumption. The first power supply provides greater efficiency than the combination of the first and second power supplies over the first lower range of power consumption, the combination of the first and second power supplies provides greater efficiency than the first power supply over the second higher range of power consumption.

Abstract: An electronic device may be provided with more than one industry-standard type of AC power connector. The electronic device may be powered in any of a variety of locations by selectively exposing one of the power connectors selected according to an AC power outlet available at that location. A location-specific power cord may be used to connect the exposed power connector to the AC power outlet. The location-specific power cord may have, for example, a line socket at one end of a type that matches the exposed power connector, and a power plug at the other end of a type that matches the AC power outlet at the location. Predefined power settings appropriate for use with the AC power outlet and the exposed power connector may be automatically invoked.

Abstract: Method, computer program product and apparatus for physically securing a server in response to detecting an unauthorized intrusion event. The method comprises detecting an unauthorized physical intrusion event to a data center, rack or chassis including a plurality of servers, communicating the detected unauthorized intrusion event to a management module that manages the plurality of servers, and automatically physically securing one or more of the plurality of servers against manual removal. Optionally, the step of physically securing may include disabling one or more front panel controls on the plurality of servers, such as a physical power switch. In a further option, the step of physically securing may include disabling one or more external ports on the plurality of servers, such as a keyboard-video-mouse port. A preferred method allows the one or more physically secured servers to continue to operate.

Abstract: In one embodiment, a fan is used to generate airflow through a computer chassis to a fan air inlet. An audible frequency component of the airflow is identified and selected. A sound wave is generated having a generated frequency equal to the selected audible frequency component of the airflow. The generated sound wave is introduced into the airflow with the generated frequency out of phase with the audible frequency component of the airflow. The magnitude of the generated frequency may be selected as a function of fan speed and/or air sensed pressure within the airflow. The frequency, phase, and magnitude of the generated sound wave may be selected and enforced by a baseboard management controller.

Abstract: According to one embodiment, a corrupted network hardware device may be automatically inspected and repaired. A default boot sequence may be suspended, and an external recovery device may inspect and repair the corrupted code by selectively repairing files and configuration settings in a minimally invasive manner, to preserve as many user settings as practicable. The network hardware device may then be re-booted from the repaired firmware.