International Business Machines Corporation

Carl Edward Clark

Steven Jay Greenspan

Casper A Scalzi

Michael Gerard Mall

Jeffrey Douglas Haggar

Danny R Sutherland

Jeffrey Alan Frey

Kenneth E Plambeck

Hiren Ramlal Shah

Alan G Ganek

Bhaskar Sinha

Justin R Butwell

Richard I Baum

Richard J Schmalz

Alan I Alpert

Terry L Borden

James Lum

David Richard Page

Donald W Schmidt

John Ted Rodell

Ronald M Smith

Christopher Meyer

David B Emmes

Jeffrey David Aman

David E Stucki

Julian Thomas

Steven Edward Rosengren

John L Burk

Frank S Samuel, Jr

Richard J Schmalz, Deceased

Michel Henri Hack

Thomas J Szczgielski

Satwinder S Kahlon

A secured subspace facility is provided for ensuring isolated storage for transactions running under an operating system main task. Isolation is achieved by attaching, from an operating system task, subtasks that will restrict application addressing. The attaching includes defining a subspace address environment as home space within a dispatchable unit access list (DU-AL) associated with each attached subtask. Multiple subtasks can be attached with each subtask running applications in an isolated address subspace, notwithstanding execution of the applications in address register addressing mode.

Storage isolation employing secured subspace facility

Managing a log stream of a computer system. An entry of a log stream, desired to be removed from the log stream, but not eligible for removal, is logically deleted. Logical deletion keeps the entry on the log stream and indicates that the entry can be removed from the log stream when it is eligible. When the entry is eligible, it is removed. If a desired entry remains at the tail of the log stream for a given period of time, thus not all owing the removal of one or more undesired entries, the desired entry is rewritten to the head of the log stream and deleted from the tail. Thereafter, other logically deleted entries eligible for deletion are removed from the log stream.

System of compressing a log stream using a scratch pad of logically deleted entries

A multisystem log stream of a multisystem environment is compressed. The oldest record needed for each system that can write or delete entries from the multisystem log stream is tracked, and that information is used in compression of the log stream. The block ids associated with those oldest records are maintained within a vector, and when the vector is updated, a determination is made as to whether the entry in the vector that it replaced previously contained the lowest block id in the vector. If so, all the records having block ids lower than the new lowest block id in the vector are deleted.

System of compressing the tail of a sparse log stream of a multisystem

Managing a log stream of a computer system. An entry of a log stream, desired to be removed from the log stream, but not eligible for removal, is logically deleted. Logical deletion keeps the entry on the log stream and indicates that the entry can be removed from the log stream when it is eligible. When the entry is eligible, it is removed. If a desired entry remains at the tail of the log stream for a given period of time, thus not allowing the removal of one or more undesired entries, the desired entry is rewritten to the head of the log stream and deleted from the tail. Thereafter, other logically deleted entries eligible for deletion are removed from the log stream.

System of compressing a log stream using a scratch pad of logically

One system of a multisystem environment takes over log entries owned by another system of the environment. When a system owning entries on a primary log stream is inactive (or a sync point manager on the system is inactive), another system of the multisystem environment writes the log entries corresponding to the inactive system to other locations. The entries within the other locations are not owned by any system. Thus, the resource managers associated with those log entries are eligible for restarting on any system of the multisystem environment. However, all resource managers involved in a common set of transactions are to restart on the same system. The other resource managers can restart on another system. When one of the resource managers restarts on a system, the system takes back ownership of the entries associated with the common set of transactions.

One system of a multisystem environment taking over log entries owned by

Method of one system of a multisystem environment taking over log

Distributed computing environment (DCE) remote procedure calls (RPCs) are integrated with an advisory work load manager (WLM) to provide a way to intelligently dispatch RPC requests among the available application server processes. The routing decisions are made dynamically (for each RPC) based on interactions between the location broker and an advisory work load manager. Furthermore, when the system contains multiple coupled processors (tightly coupled within a single frame, or loosely coupled within a computing complex, a local area network (LAN) configuration, a distributed computing environment (DCE) cell, etc.), the invention extends to balance the processing of RPC requests and the associated client sessions across the coupled systems. Once a session is assigned to a given process, the invention also supports performance monitoring and reporting, dynamic system resource allocation for the RPC requests, and potentially any other benefits that may be available through the specific work load manager (WLM).

Integrating distributed computing environment remote procedure calls

Tail compression of a sparse log stream of a multisystem environment

Tail compression of a log stream using a scratch pad of logically

When a log stream has a determined amount of reusable space, the log stream is compressed in order to free up the reusable space. Compression of the log stream includes rewriting one or more active entries located at one or more positions of the log stream to one or more other locations, either within the same log stream or on another log stream. Thereafter, the rewritten entries are deleted from their previous positions within the log stream. Additionally, one or more logically deleted entries of the log stream is removed from the log stream. The resulting log stream is a compressed log stream.

System of compressing the tail of a sparse log stream of a computer

Tail compression of a sparse log stream of a computer system

A method and system for providing a PROGRAM CALL to a dispatchable unit's base space is described herein. A program call to a dispatchable unit's (PC to DU) base space bit is added to each entry-table entry in order to determine whether a PROGRAM CALL to a base space is to be made. Should the bit indicate that a PROGRAM CALL to a dispatchable unit's base space is to be made, then in one embodiment, the base address space number-second-table entry origin (BASTEO) and base address space number (BASN) stored in the dispatchable unit control table (DUCT) are used in identifying the base space and accessing associated control information for the identified base space. In another embodiment, the BASN stored in the DUCT is used in ASN translation to identify the base space and access the associated control information for the base space.

Method and system for providing a program call to a dispatchable unit's

Provides a dynamic execution link between an analyzer program and each hook instruction in a program. Special types of hook instructions are provided for use in a hooked program. The link causes the analyzer program to execute as part of a continuous uninterrupted execution for each hook instruction. The link uses hardware and/or internal code to access a hook control area which provides linkage information needed to invoke the execution of the analyzer program upon completion of the hook instruction and to continue the execution of the hooked program following the completion of the analyzer program. The linkage information includes the entry location into the analyzer program, and also locates the first hook work area (HWA) of a sequence of HWAs, from which an HWA is assigned to each current hook instruction. The assigned HWA stores a return point location in the hooked program at an instruction following the current hook instruction. One or more hooked programs may concurrently use the same analyzer program. As soon as execution by the analyzer program ends for a hook instruction, its assigned HWA is released for use by another hook instruction.

Dynamic program analyzer facility

A Branch in Subspace Group (BSG) instruction is executed in problem state (for example by an application program) for providing a fast instruction branch between address spaces within a restricted group of address spaces called a subspace group. The subspace group contains two types of address spaces: a base space and any number of subspaces. The subspace group is set up in a control table associated with each dispatchable unit (DU). This DU control table contains: an identifier of a base space, an identifier of an access list that contains identifiers of all subspaces in the subspace group, an indicator of whether CPU control was last given to a subspace or to the base space, and an identifier of a last entered subspace in the group. The BSG instruction has an operand defining a general register containing the target virtual address and an associated access register containing an access-list-entry token (ALET) defining the target address space. The ALET indexes to a target subspace identifier in the access list, and then the associated virtual address locates the target instruction in the identified target address space. BSG instruction execution controls restrict the BSG branching only to an instruction in the subspace group.

Storage isolation with subspace-group facility

An application, executing on a first processing element in a MP system without an asymmetric feature, issues an instruction requiring that feature to complete. A program check interruption gives control to interrupt handlers, which create a high-priority, non-preemptable work unit control block and enters the dispatcher to enqueue the work unit on a processor-related queue associated with a second processing element having the asymmetric feature. When the dispatcher executes in the second processing element, it executes the non-preemptable work unit, which transfers control to the application at the point of interruption. Subsequently the application has only whatever processor affinity obtained prior to the program check.

Method and apparatus for dispatching tasks requiring short-duration

Growing community of inventors

Poughkeepsie, NY, United States of America

Carl Edward Clark