Abstract: In an approach for determining a location of failure between interconnects/controller, a computer collects debug information simultaneously at a plurality of nodes coupled to an interconnect. Subsequent to collecting debug information, the computer analyzes the debug information collected simultaneously thereby determining which end of the interconnect caused the failure.

Abstract: In an approach for determining a location of failure between interconnects/controller, a computer collects debug information simultaneously at a plurality of nodes coupled to an interconnect. Subsequent to collecting debug information, the computer analyzes the debug information collected simultaneously thereby determining which end of the interconnect caused the failure.

Abstract: In an approach for determining a location of failure between interconnects/controller, a computer collects debug information simultaneously at a plurality of nodes coupled to an interconnect. Subsequent to collecting debug information, the computer analyzes the debug information collected simultaneously thereby determining which end of the interconnect caused the failure.

Abstract: In an approach for determining a location of failure between interconnects/controller, a computer collects debug information simultaneously at a plurality of nodes coupled to an interconnect. Subsequent to collecting debug information, the computer analyzes the debug information collected simultaneously thereby determining which end of the interconnect caused the failure.

Abstract: A mechanism, in a data processing system, is provided for logical partition defragmentation. The mechanism gathers resource requirements for a plurality of logical partitions running in a plurality of power domains within one or more servers. The mechanism determines optimal hardware utilization for the plurality of logical partitions. The mechanism migrates one or more of the plurality of logical partitions to run in a subset of the plurality of power domains such that at least one power domain within the plurality of power domains is unused. The mechanism puts the at least one unused power domain in a low power state.

Abstract: A mechanism, in a data processing system, is provided for logical partition defragmentation. The mechanism gathers resource requirements for a plurality of logical partitions running in a plurality of power domains within one or more servers. The mechanism determines optimal hardware utilization for the plurality of logical partitions. The mechanism migrates one or more of the plurality of logical partitions to run in a subset of the plurality of power domains such that at least one power domain within the plurality of power domains is unused. The mechanism puts the at least one unused power domain in a low power state.

Abstract: Various systems, processes, products, and techniques may be used to manage failure data for a distributed computer system. In particular implementations, a system and process for managing distributed data for a distributed computer system may include the ability to determine at a service processor of a first node in a distributed computer system that comprises a plurality of nodes whether a failure has occurred in the first node and identify a service processor of a second node in the distributed computer system in which to store failure data if a failure has occurred. The system and process may also include the ability to store at least part of the failure data in the identified service processor and determine whether there is more failure data to store than the identified service processor can store.

Abstract: A method for replacing a current security certificate includes producing a security certificate request at a first device that includes a request for a replacement security certificate. The method additionally includes sending the security certificate request to a security certificate vendor and receiving a replacement security certificate from the security certificate vendor. The method further includes installing the replacement security certificate within a verification layer of the client device and transmitting the replacement security certificate to the server. The method additionally includes verifying that the server has installed the replacement security certificate, wherein the verification further verifies that the replacement security certificate enables encrypted communication between the client device and the server.

Abstract: A distributed system provides error handling wherein the system includes multiple nodes, each node being coupled to multiple node controllers for control redundancy. Multiple system controllers couple to the node controllers via a network bus. A particular node controller may detect an error of that particular node controller. The particular node controller may store error information relating to the detected error in respective nonvolatile memory stores in the system controllers and node controllers according to a particular priority order. In accordance with the particular priority order, for example, the particular node controller may first attempt to store the error information to a primary system controller memory store, then to a secondary system controller memory store, and then to sibling and non-sibling node controller memory stores. The primary system controller organizes available error information for use by system administrators and other resources of the distributed system.

Abstract: Various systems, processes, products, and techniques may be used to manage failure data for a distributed computer system. In particular implementations, a system and process for managing distributed data for a distributed computer system may include the ability to determine at a service processor of a first node in a distributed computer system that comprises a plurality of nodes whether a failure has occurred in the first node and identify a service processor of a second node in the distributed computer system in which to store failure data if a failure has occurred. The system and process may also include the ability to store at least part of the failure data in the identified service processor and determine whether there is more failure data to store than the identified service processor can store.

Abstract: A mechanism, in a data processing system, is provided for logical partition defragmentation. The mechanism gathers resource requirements for a plurality of logical partitions running in a plurality of power domains within one or more servers. The mechanism determines optimal hardware utilization for the plurality of logical partitions. The mechanism migrates one or more of the plurality of logical partitions to run in a subset of the plurality of power domains such that at least one power domain within the plurality of power domains is unused. The mechanism puts the at least one unused power domain in a low power state.

Abstract: A mechanism, in a data processing system, is provided for logical partition defragmentation. The mechanism gathers resource requirements for a plurality of logical partitions running in a plurality of power domains within one or more servers. The mechanism determines optimal hardware utilization for the plurality of logical partitions. The mechanism migrates one or more of the plurality of logical partitions to run in a subset of the plurality of power domains such that at least one power domain within the plurality of power domains is unused. The mechanism puts the at least one unused power domain in a low power state.

Abstract: A computer implemented method monitors activity within a device driver layer of a computer. An arrival rate is identified within a device driver for the node. The arrival rate is a rate at which packets arrive at a network adapter of the node from all other nodes within a network. If the arrival rate exceeds at least one threshold, the node undergoes a state change. The at least one threshold delineates between a plurality of states for the node.

Abstract: Disclosed is a computer implemented method and apparatus for establishing a redundant channel from an application to a peer data processing system. The interrupt-driven hot standby program receives, through the operation of a data processing system, a communication channel status corresponding to an application. The application has a first channel using local access across a first physical conduit to a first switch. In addition the communication channel status is, in part, an interrupt. The interrupt-driven hot standby program determines whether the redundant channel is present. The redundant channel is configured to use a second physical conduit distinct from the first physical conduit for traffic of the application. Responding to a determination that the redundant channel is present, the interrupt-driven hot standby program determines whether the redundant channel is configured to use the second physical conduit as local access to a redundant switch, wherein the redundant switch is not the first switch.

Abstract: A distributed system provides error handling wherein the system includes multiple nodes, each node being coupled to multiple node controllers for control redundancy. Multiple system controllers couple to the node controllers via a network bus. A particular node controller may detect an error of that particular node controller. The particular node controller may store error information relating to the detected error in respective nonvolatile memory stores in the system controllers and node controllers according to a particular priority order. In accordance with the particular priority order, for example, the particular node controller may first attempt to store the error information to a primary system controller memory store, then to a secondary system controller memory store, and then to sibling and non-sibling node controller memory stores. The primary system controller organizes available error information for use by system administrators and other resources of the distributed system.

Abstract: Generally speaking, systems, methods and media for detection and network reconfiguration upon changes in dynamic host configuration protocol (DHCP) IP addresses are disclosed. Embodiments of a method may include setting a renew time and a rebind time of a DHCP configuration and establishing an IP address with a first DHCP server. Embodiments may also include, after passage of the renew time, transmitting a renew request to the first DHCP server at its IP address and, in response to failure to receive an acknowledgement message from the first DHCP server, determining if the first DHCP server IP address is still valid. Embodiments may also include, in response to determining that the first DHCP server IP address is not still valid, retrieving a second, different DHCP server IP address from a network change event signal and configuring a network adapter based on the second DHCP server IP address.

Abstract: Disclosed is a computer implemented method and apparatus for establishing a redundant channel from an application to a peer data processing system. The interrupt-driven hot standby program receives, through the operation of a data processing system, a communication channel status corresponding to an application. The application has a first channel using local access across a first physical conduit to a first switch. In addition the communication channel status is, in part, an interrupt. The interrupt-driven hot standby program determines whether the redundant channel is present. The redundant channel is configured to use a second physical conduit distinct from the first physical conduit for traffic of the application. Responding to a determination that the redundant channel is present, the interrupt-driven hot standby program determines whether the redundant channel is configured to use the second physical conduit as local access to a redundant switch, wherein the redundant switch is not the first switch.

Abstract: A method, system and computer program product for remotely debugging a malfunctioning node controller of a node in a distributed node network through a functioning node controller of the same node. The method comprises establishing a serial link between the malfunctioning node controller and a functioning node controller and configuring the functioning node controller as a virtual console by the remotely-located central data processing system (DPS). The method further includes receiving, via an internal Fru Support Interface (FSI) link, serial data from the malfunctioning node controller through the virtual console, and debugging, by the DPS, a failure condition of the malfunctioning node controller, in response to receipt of the serial data through the virtual console.

Abstract: One embodiment for dynamically loading a service onto a node includes requesting, by a service requester, of a service from a service broker. Further, the method includes selecting, by the service broker, of the node among the nodes. Further still, the method includes re-booting, by the service broker, of the node based on the selecting, and then requesting, by the node, of an image from a TFTP relay agent for the service for the node. Yet further, the method includes querying, by the TFTP relay agent, for a type of the service from the service broker for the node, and then downloading of the image for the type of the service from a software repository accessed by the TFTP relay agent to the node. Finally, the method includes booting, by the node, to the image, informing the service requester that the service is ready for use, and using the service.

Abstract: Generally speaking, systems, methods and media for detection and network reconfiguration upon changes in dynamic host configuration protocol (DHCP) IP addresses are disclosed. Embodiments of a method may include setting a renew time and a rebind time of a DHCP configuration and establishing an IP address with a first DHCP server. Embodiments may also include, after passage of the renew time, transmitting a renew request to the first DHCP server at its IP address and, in response to failure to receive an acknowledgement message from the first DHCP server, determining if the first DHCP server IP address is still valid. Embodiments may also include, in response to determining that the first DHCP server IP address is not still valid, retrieving a second, different DHCP server IP address from a network change event signal and configuring a network adapter based on the second DHCP server IP address.