Abstract: A host computer acquires remote copy status information of storage subsystems that are not directly coupled to the host computer. Each storage subsystem includes: a unit which receives a status information acquisition command from the host computer; a unit which analyzes the received command to judge whether the storage subsystem in question is a target of the command; a unit which sends the command to a downstream storage subsystem connected to the storage subsystem in question when the storage subsystem in question is not the target; and a unit which sends status information to an upstream storage subsystem connected to the storage subsystem in question when the status information is received from the downstream storage subsystem.

Abstract: A host computer acquires remote copy status information of storage subsystems that are not directly coupled to the host computer. Each storage subsystem includes: a unit which receives a status information acquisition command from the host computer; a unit which analyses the received command to judge whether the storage subsystem in question is a target of the command; a unit which sends the command to a downstream storage subsystem connected to the storage subsystem in question when the storage subsystem in question is not the target; and a unit which sends status information to an upstream storage subsystem connected to the storage subsystem in question when the status information is received from the downstream storage subsystem.

Abstract: The invention provides a method of backing up data, in which plural information processing units connected to a network are not required to monitor each other, and autonomously send data to the other information processing units to buck up the data. The method, using the plural information processing units connected to the network collects information as to a possibility of backing up the data from the other plural information processing units connected to the network, adds addresses for identifying the other information processing units to collected information, and stores the collected information in a storage device. When the backup becomes necessary, the method sends a backup request to the other information processing units selected on the basis of the information stored in the storage device, and sends backup data to the other information processing units that returned to accept the backup request.

Abstract: A method of virtualizing memory through shadow page tables that cache translations from multiple guest address spaces in a virtual machine includes a software version of a hardware tagged translation look-aside buffer. Edits to guest page tables are detected by intercepting the creation of guest-writable mappings to guest page tables with translations cached in shadow page tables. The affected cached translations are marked as stale and purged upon an address space switch or an indiscriminate flush of translations by the guest. Thereby, non-stale translations remain cached but stale translations are discarded. The method includes tracking the guest-writable mappings to guest page tables, deferring discovery of such mappings to a guest page table for the first time until a purge of all cached translations when the number of untracked guest page tables exceeds a threshold, and sharing shadow page tables between shadow address spaces and between virtual processors.

Abstract: A method and computer program product for partitioning the columns of a matrix A. The method includes providing the matrix A in a memory device of a computer system. The matrix A has n columns and m rows, wherein n is an integer of at least 3, and wherein m is an integer of at least 1. The method further includes executing an algorithm by a processor of the computer system. Executing the algorithm includes partitioning the n columns of the matrix A into a closed group of p clusters, wherein p is a positive integer of at least 2 and less than n, wherein the partitioning includes an affinity-based merging of clusters of the matrix A, and wherein each cluster is a collection of one or more columns of A.

Abstract: A method and system for allowing nodes in a multi-node computer to be appropriated by a master node in the multi-node computer. The node to be appropriated is suspended into an ACPI S3 Sleep State, causing current system operations state information to be stored in a backup memory in the appropriated node. The master node then populated a primary memory in the appropriated node with OS and other information required to join a partition that includes the master node. When the master node no longer wishes to use the appropriated node, the backup memory in the appropriated node is mirrored back into the primary memory. When the appropriated node “wakes up” from the S3 state, it continues executing software commands where it left off, without knowing anything that had happened after going into the S3 state.