International Business Machines Corporation

Roman Anthony Bobak

David Lee Meck

Scott Brady Compton

William Robert Richardson

Jon Kim Johnson

Michael Allen Wright

Max M Maurer

Alan F Martens

Peter Bergersen Yocom

Harris M Morgenstern

Robert R Rogers

Charles E Mari

Danny R Sutherland

Mythili Venkatakrishnan

Jim H Mulder

John Thomas Schmidt

A service processor communication method includes establishing a communication channel between a service processor and a central processor in a computing system, wherein communication on the communication channel is independent of processing by the central processor, monitoring an operating system that is under control by the central processor, defining a source designator associated with state information of the operating system, and that is passed via the communication channel between the service processor and the central processor; and announcing the state information to a resource external to the computing system.

Operating system state communication

In a computing system having swappable and non-swappable address spaces, wherein the computing system includes an operating system that includes a Real Storage Manager (RSM), a Systems Resource Manager (SRM) and a Region Control Task (RCT), a method for recovering swappable fixed non-preferred memory is provided which includes receiving a request from the operating system to configure an area of real memory to create an intercepted swappable address space, wherein the intercepted swappable address space includes a flagged fixed frame element identified for configuration, examining the intercepted swappable address space so as to determine if the intercepted swappable address space will remain swappable, requesting the SRM to coordinate the swapping process, quiescing the intercepted address space, generating a first return code responsive to the intercepted swappable address space remaining swappable, communicating the first return code to the RCT so as to cause the RCT to respond to the first return code, instructing the RSM to proceed based on the first return code, examining the intercepted swappable address space so as to identify the flagged frame elements, exchanging the flagged frame elements with unflagged frame elements, updating dynamic address translation tables, and returning a performance code to the RCT so as to indicate recovery success or recovery failure. A method for recovering swappable fixed non-preferred memory where the originally swappable address space has been converted into non-swappable address space is also provided.

Method for recovering memory

A method for using ancillary processors and memory to speed critical data capture includes building a list memory address ranges associated with a secondary partition. The memory address ranges are located in central storage memory and contain the data to be captured. The method also includes reading the data from the memory address ranges and writing the data to a portion of memory reserved by a first partition as a capture pool. The capture pool is also located in central storage memory and is not accessible by the secondary partition. The invention also includes a system for using ancillary processors and storage to speed time critical data captured.

System and method for using ancillary processors and storage to speed time critical data capture

A management facility for managing concurrently executable computer processes. The management facility includes a registration mechanism, which enables a plurality of interdependent processes to be considered a part of a topology of logically dependent execution groups, and a termination synchronization mechanism that synchronizes the completion of termination for the processes within the topology. Termination synchronization prevents a process within the topology from completely terminating, even if it has entered normal termination, until all of the processes within the topology have normally terminated. If one of the processes within the topology has abnormally terminated, then notification of this abnormal termination can be propagated to all of the processes within the topology of logically dependent execution groups, since none of them have completely terminated.

Method and system for managing concurrently executable computer processes

When applications connect to a data pipe, which is located on the same system as the connecting applications, the data pipe is considered a local pipe. That is, local media is used to pipe the data. If, however, an application on a different system is to access the pipe, the pipe is transitioned from a local pipe to a cross-system pipe, in which an alternative non-local media is used to pipe the data. The application causing the transition and any other applications to subsequently connect to the pipe use the cross-system pipe. Any local applications still allocated to the pipe are transitioned, such that they now access the cross-system pipe, instead of the local pipe. Likewise, when an application disconnects from a cross-system pipe, such that all remaining connections to the pipe are local connections, the pipe is transitioned from a cross-system pipe to a local pipe.

Dynamic transitioning from a local pipe to a cross-system pipe

A technique for selectively dummying a data pipe transparent to a writer application is provided. A writer application writes data to a local data pipe or a cross-system data pipe and one or more reader applications read data from the data pipe. The technique involves determining when a last reader application of the at least one or more reader applications closes the data pipe before the writer application has completed writing data to the data pipe. Upon determining this condition, further writing of data to the data pipe by the writer application is transparently prevented. While transparently preventing writing to a dummied data pipe, writing of data to a fitting, e.g., for a permanent record, can proceed.

Selectively dummying a data pipe transparent to a writer application

Data is written to and read from a shared pipe by applications of multiple systems. At least one shared pipe is located within an external shared memory coupled to one or more central processing complexes. Each of the central processing complexes has one or more operating system images, which controls execution of one or more piping applications. At least one piping application corresponding to at least one operating system image writes data to a shared pipe located in the external shared memory and at least one other application corresponding to one or more other operating system images reads data from the same shared pipe, thereby providing cross-system data piping.

Growing community of inventors

Wappingers Falls, NY, United States of America

Roman Anthony Bobak