Abstract: A method for processing interrupt requests in a processor is suitable for executing at least two threads in parallel, wherein an instruction pipeline is provided for each of the at least two threads. One of the at least two threads is defined as a main thread for processing programs. Another thread of the at least two threads is assigned to the main thread as an interrupt thread. After an interrupt request is received, the processor stores interrupt data in a register assigned to the interrupt thread. Subsequently, the processing of an interrupt routine is started in the interrupt thread and at least part of the interrupt routine is executed in the interrupt thread.

Abstract: An aseismic (earthquake-secure) server rack is fastened to an earthquake frame in order to increase rigidity and is fixed to the floor at least via the earthquake frame.

Abstract: A method, a cluster system, and a computer-readable medium for distributing data packets addressed to at least one virtual address over a communication network using a protocol, which allows for at least some content of the data packet to be encrypted, to a multiplicity of service nodes. The method includes receiving incoming data packets addressed to a virtual address through a packet analyzer and identifying whether the incoming data packets are encrypted. Each encryption data packet is forwarded to a decryption module and a decrypted data packet is returned. Based on the decrypted data packet, a scheduling decision is made by a scheduling module. Scheduling data is then combined with the originally received encrypted data packet such that the encrypted data packet can be forwarded to one service node for further processing.

Abstract: An electronic device (1), which can assume an operating state and at least one energy-saving state, with a power supply (7) that can be connected to a mains voltage, and an evaluation unit (4), which can control the electronic device (1) from the operating state into the energy-saving state and vice versa, wherein the evaluation unit (4) is connected to the power supply (7) in such a way that the power supply (7) can be turned off by the evaluation unit (4) for assuming the energy-saving state and can be turned on again for assuming the operating state, and the evaluation unit (4) can be supplied, at least in the turned-off state of the power supply (7), with energy from another electronic device, which is connected via a standard interface to the electronic device, and/or with energy from a capacitor and/or with energy from an accumulator and/or with energy from a solar cell.

Abstract: A method for data transmission in a system is disclosed. The system includes a computer (1) and a peripheral device (9), which are connected to each other via a network (8). The computer has hardware resources (2), including a network interface (2.3) and a controller (4), which is designed to provide a virtual machine system in that it maps the hardware resources (2), including the network interface (2.3) onto logical interfaces (5, 5.3) in virtual machines (4). A peripheral device adapter (10) provided in the computer (1) is mapped by the controller (3) onto a logical peripheral device interface (11) in one of the virtual machines (4) and data is exchanged between the peripheral device (9) and the virtual machine (4) via the network (8), the peripheral device adapter (10), and the logical peripheral device interface (11) while bypassing the logical interfaces (5.3) mapping the network interface (2.3) into the virtual machines (4).

Abstract: The invention relates to a circuit unit for driving an electronically commutated fan motor with a power stage for driving windings of the fan motor and with a control stage for driving the power stage. The circuit unit is distinguished in that an operating voltage of the control stage is separated from an operating voltage of the power stage by a diode and in that an arrangement is provided for smoothing the operating voltage of the control stage.

Abstract: A cluster arrangement having a first network, at least two data processing systems which each form an application node and which each have an operating system, and an application agent on each application node, which application agent is operable to monitor and identify entities executed on the application node; start a new entity or restart an entity which has been terminated prematurely on the application node; assess and decide whether it is possible to execute a new entity on the application node; send a request for execution of an entity to application agents at application nodes connected to the network; and report to application agents at application nodes connected to the network following an acceptance of the request for execution of an entity.

Abstract: A method for maintaining a computer system on the basis of an access profile and a change profile is disclosed. The computer system includes at least one workstation computer and a maintenance computer. The invention further relates to a method for providing an access profile and a method for assessing a software correction.

Abstract: Installation and configuration of user-specific software and a computer system is performed such that individual computers in a group is prepared by transmitting the installation packages for a predetermined set of software products and a configuration program to the individual computers. In response to a computer being started for the first time, the configuration program loads a user-specific configuration file from a database system. According to the information contained in the configuration file, software products are subsequently installed and configured on the computer on a user-specific basis using the installation packages.

Abstract: A monitoring device and a method for monitoring at least two resources at a node in a cluster system are provided. A priority is allocated to each of the at least two resources. In the monitoring device and in the method, one of the at least two resources to be monitored is selected on the basis of the associated priority, and a monitoring detector which is required for the monitoring is selected for the resource. Furthermore, the monitoring detector is run, and the monitoring of the resource is performed once by the monitoring detector. The result of the monitoring performed by the monitoring detector is signaled. Selection via the associated priority and the single monitoring save computation time at the node. The monitoring detector can be a dynamic library.

Abstract: The invention relates to a data processing system with a main board, in which main board has at least one multipoint connector, in which at least one riser card is accommodated, and a first daughter card is accommodated in first riser card in such a manner that first daughter card is arranged parallel to main board. The data processing system further comprises a second multipoint connector, wherein a second riser card is accommodated in second multipoint connector, and a second daughter card is accommodated in second riser card in such a manner that second daughter card is arranged parallel to main board. The First multipoint connector and the second multipoint connectors are arranged on opposite outer sides of the main board. Each daughter card comprises a respective I/O interface which each cooperates with a common rear panel and is pointed towards the common rear panel. Relative to second daughter card, first daughter card is arranged rotated by 180° about an axis running parallel to main board.

Abstract: A method for the alternating operation of power supply units for a device which has at least two power supply units is disclosed. An alternating operation of the at least two power supply units is supplied by a switchover between the two power supply units if the two power supply units are functional. With alternating operation, the power supply unit that is in operation contributes to the power supply for the device, whereas the power supply unit that is not in operation, is cut off from supplying power to the device. In the case of a failure of the power supply unit which is in operation at the moment, an immediate switchover between the at least two power supply units is provided for.

Abstract: According to the method for configuring an information system (1), components (2) are provided for the information system (1) and component-specific error susceptibility data (3) on the individual components (2). For a given system configuration (5), error susceptibility information (7) is determined for the information system (1) in this given system configuration (5) as a function of the component-specific error susceptibility data (3). The error susceptibility information (7) is evaluated with reference to given evaluation criteria (8). In a subsequent step, the information system (1) is configured in the given system configuration (5) if the error susceptibility information (7) satisfies the given evaluation criteria (8). By means of the method, it is achieved that only system configurations are accepted that satisfy requirements specified by the evaluation criteria (8) with respect to the reliability of the information system (1).

Abstract: A housing with a sliding switch with at least three positions and a sliding element that partially projects through an opening in the housing as provided. In order to protect the sliding element against accidental activation, on both sides of the opening, parallel to the direction of movement of the sliding switch, there are flanks.

Abstract: A method for fault handling of a data processing unit is disclosed. The method includes automatic acquisition of input information and/or output information of a user at at least one user interface of the data processing unit; automatic detection of a fault message that indicates a fault of the data processing unit; transmission of the acquired fault message together with the input information and/or the output information to a fault handling center; and evaluation of the transmitted fault message in the fault handling center.

Abstract: A computer system includes: a processor for executing a program code, a first non-volatile memory for storing a first program code for starting the computer system, the first non-volatile memory being functionally connected to the processor, and a system monitoring module which is functionally connected to the processor and to the first non-volatile memory and is configured to monitor the computer system for the occurrence of a predetermined condition. The system monitoring module includes a second non-volatile memory for storing a second program code for starting the computer system and is configured to copy the second program code from the second non-volatile memory into the first non-volatile memory when the predetermined condition occurs, so that the second program code replaces the first program code and is available for subsequent starting of the computer system.

Abstract: A computer system having at least one hardware unit, a control device and a plurality of virtual computer units, and a method for allocating total available computational power within such a computer system, wherein a plurality of virtual computer units can be respectively associated with a group. The computational power is allocated in a plurality of stages by using prescribed rules and taking into account allocation parameters so as to, first, split the available computational power and to allocate the split computational power to the groups and those virtual computer units which do not belong to a group, and then to split the computational power allocated to a group and to allocate the split computational power to each of the plurality of virtual computer units which belong to this group.

Abstract: In a cluster system comprising at least two nodes connected via a communication network and having a name and a host weight assigned to it, a method is implemented comprising the steps of inspecting the communication link, determining which node has to be shut down after a failure, creating an advertisement report for the node to be shut down, sending the advertisement report to at least one node of the cluster system, calculating a delay time depending on the weight of the first node and sending the shut down command to the node for which a failure report was received. In one embodiment of the invention the advertisement reports include a master node, which allows identifying and specifying the surviving subcluster. The method will send shut down signals to those nodes of a subcluster with lower weight than the surviving subcluster. A failsafe mechanism is implemented.

Abstract: A fault-tolerance management of a software component is disclosed. A number of instances of the software component are executed in at least somewhat different execution environments. A local error susceptibility register and a global error susceptibility register are assigned to each software component. An error of first instance of the software component is detected. The local error susceptibility register of the first instance is updated based on the detected error and the content of the local error susceptibility register of the first instance. The global error susceptibility register of each instance is also updated based on the detected error and the content of the global error susceptibility register of each instance. The difference between the respective local error susceptibility register and the respective global error susceptibility register is determined, and the fault tolerance value of the software component in the respective execution environment is determined based on the determined difference.

Abstract: A backplane for use in a push-in rack for peripherals includes slots with plug connectors that connect with peripherals which have been pushed into the push-in rack, and at least one further plug connector that connects the backplane to a control apparatus. An assigned optical signaling device is also provided for each slot. The backplane further includes a monitoring device operable to determine, for each connected peripheral, whether a peripheral is compatible with the connected control apparatus and, if the peripheral is incompatible, the monitoring device activates the respective optical signaling device assigned to the slot for the incompatible peripheral. The backplane is suitable for use in data processing apparatuses in conjunction with peripherals which are designed in accordance with the SAS (Serial Attached Small Computer System Interface) or SATA (Serial Advanced Technology Attachment) specification.