International Business Machines Corporation

John S Trotter

Kenneth J Oakes

Harry M Yudenfriend

Leslie W Wyman

Tan Lu

Dale Francis Riedy, Jr

William J Rooney

Scott M Carlson

Greg A Dyck

Marten J Halma

Jeffrey Paul Kubala

Janet R Easton

Martin Taubert

Charles W Gainey, Jr

Steven G Glassen

Frank William Brice

Charles E Shapley

Hans-Helge Lehmann

John R Flanagan

Daniel Francis Casper

Beth A Glendening

Allan Samuel Meritt

Joachim Von Buttlar

Andrew W Piechowski

Andreas Kohler

Paul S Frazer

Ulrich Helmich

Peter Grimm Sutton

Eugene P Hefferon

Francis Gassert

Elke G Nass

Juergen Erwin Maergner

Wolfgang Eckert

Ambrose Verdibello

Robert A Smith

Robert M Whalen, Jr

David W Hollar

Rodney Allen Paul

Ugochukwo Njoku-Charles

Michael G Melendy

An Extended Input/output (I/O) measurement word facility is provided. Provision is made for emulation of the Extended I/O measurement word facility. The facility provides for storing measurement data associated with a single I/O operation in an extended measurement word associated with an I/O response block. In a further aspect, the stored data may have a resolution of approximately one-half microsecond.

Extended input/output measurement word facility for obtaining measurement data in an emulated environment

A computer system includes a processor configured for detecting initial command response times of a plurality of paths for transmitting signals from the processor to one or more external devices via a plurality of channels, assigning weighted values to the plurality of paths based on the detected initial command response times, and modifying a frequency at which respective paths among the plurality of paths are selected for transmitting the signals based on the weighted values assigned to the respective paths.

Communication path selection

Extended input/output measurement word facility for obtaining measurement data

Extended input/output measurement word facility and emulation of that facility

Disclosed are a method and system of tracking real time use of I/O control blocks on a processing unit basis, in a multiprocessing system, such that in the case of a processing unit failure, a list accurately and concisely identifies the control blocks that need to be recovered. This eliminates the need to scan all the I/O control blocks, greatly reducing the overall system recovery time and minimizing impact to the rest of the running system. The preferred embodiment of the invention uses a task control block structure to record which I/O control blocks are in use by each Processing Unit. Also, the lock word structure defined in the I/O control blocks is provided with an index back into the task control block to facilitate managing the task control block entries.

Method and system for state tracking and recovery in multiprocessing computing systems

Extended input/output measurement word facility, and emulation of that facility

A bi-directional and full duplex facility for permitting both the IO processor and the Channel to write CCA messages on their respective queues at the same time. IOP messages to the channel are stored on the TO_CHN queue and Channel messages to the IOP on the TO_IOP queue. CCA Queues replace hardware CCAs due to increasing transmission capabilities of current IO processors and Channel processors. Even though the mechanism is similar, the present invention provides some benefits in the use of signaling. The IOP does not have to signal the Channel each time it puts something on its outbound queue. Each queue contains multiple slots. This allows the IOP and Channel to write multiple messages on the targeted queue without encountering a CCA busy signal. The actual queues are now structured in hardware system memory.

Channel communication array queues in hardware system area

Disclosed are a method and system for parallel execution of recovery in a non-homogeneous multi-processor environment. The method defines criteria how to decide which recovery actions are to be performed, and on which processor. If multiple recovery actions are pending, the goal is to execute them in parallel on multiple processors. This is much more efficient than the traditional approach of one processor doing all the required recovery. In addition, in large, non-homogeneous systems such a single processor capable of doing the complete recovery might not be existing at all due to technical limitations. The method of this invention also defines rules and mechanisms how multiple processors executing recovery in parallel can access shared resources while avoiding deadlock situations. This includes accessing resources that are currently owned by another processor.

Method and system to execute recovery in non-homogenous multi processor environments

Disclosed are a method and system for detecting errors in a computer system including a processing unit to perform tasks to change items. The method comprises the steps of assigning a task control block to the processing unit, and using the task control block to keep track of items being changed by the processing unit. The method comprises the further steps of at defined times, checking the task control block to identify items being changed by the processing unit, and checking the states of said identified items to determine if those states are correct. The preferred embodiment of the invention detects an error when it arises (where possible), and utilizes an infrastructure that allows simple and periodic consistency checks (for example, at designated code points) that detect the error before it causes follow-on problems.

Method and system to detect errors in computer systems by using state tracking

An Extended Input/output (I/O) measurement block facility is emulated. The facility provides for the collection of relevant I/O measurement data, and the storing for later efficient retrieval of that data in an extended measurement block. The stored data relates to the performance of an I/O subchannel.

Emulation of extended input/output measurement block facilities

Operations in a multi-processor, multi-control block environment are timed using timing queues and instruction queues. Upon receipt of a request for a subchannel control block (SCB) to perform an operation that needs to be timed, the SCB is queued on one of multiple timing queues based on an elapsed timeout limit (ETL) of the operation. There is an ETL for each operation, and each one the multiple timing queues is associated with an ETL for completing an operation. The SCB may be placed at the bottom of the timing queue, the timing queue ordered from oldest to youngest which allows for quickly checking large numbers of SCBs without having to check every element queue and without having to dequeuing the elements from this queue. Upon receipt of a request to perform a high-priority operation, the SCB may be queued in a high priority instruction queue. The SCB may remain the timing queue to retain its order and be placed on a high priority instruction queue for retrying an operation. Upon completion of the operation or occurrence of a timeout, the SCB is dequeued. The SCB may be requeued if it was dequeued upon occurrence of a timeout. One or more timing queues may be checked for SCB operation timeouts by one or more SAPs in a round robin fashion.

Method, system, and computer program product for timing operations of different durations in a multi-processor, multi-control block environment

An input/output subsystem is configured as a plurality of input/output subsystem images, each of which appears to a program as an independent input/output subsystem. An input/output subsystem image is identified by an input/output subsystem image identifier, which is used by various programs to designate the particular input/output subsystem image for which an I/O operation is to be performed. An input/output subsystem image includes, for instance, one or more input/output paths. An input/output path of an input/output subsystem image is identified by an input/output path identifier, as well as a physical input/output path identifier.

Multiple logical input/output subsystem facility

I/O measurement data for channels attached to logical control unit queues is obtained related to a plurality of logical control unit queues. A store secondary queue measurement data instruction specifies a range of queues for which extended secondary measurement blocks derived from the I/O measurement data are stored at a memory address specified by the store secondary queue measurement data instruction.

Obtaining extended queue measurement data for a range of logical control unit queues

Growing community of inventors

Pleasant Valley, NY, United States of America

John S Trotter