International Business Machines Corporation

Jason A Keenaghan

Robert O Dryfoos

Peter Grimm Sutton

Shawfu Chen

Mei-Hui Wang

Allan Feldman

David Y Hu

Peter A Lewis

Alice M Williams-Obleton

Michael J Shershin

Kenneth H Warner

Lisa D Banks

A process thread locking operations includes defining a lock structure having data fields that include a process thread identifier and a shared object identifier that uniquely identifies a shared object subject to lock operations and using the lock structure to build a lock table. The lock table includes lock structures for each process thread in the process and is searchable in response to a request for a shared object from a calling thread. The method also includes determining a lock status of the shared object. The lock status indicates whether the shared object is currently locked by the calling process thread. In response to the lock status, the method includes obtaining a lock on the shared object when the request is for a lock, and releasing a lock on the shared object when the request is to unlock the shared object.

Recursive locking of a thread-shared resource

A plurality of batch lists are maintained by a channel in order to improve the efficiency of the channel in performing messaging between a sender and a receiver. For example, a Next Batch list is used to prefetch messages to be sent to the receiver from the sender; a Current Batch list includes the messages currently being transmitted to the receiver or waiting confirmation; and an Acknowledged Batch List includes the messages confirmed by the receiver. This allows the functions of prefetching messages, sending messages and deleting confirmed messages to be performed in parallel.

Method, system and program storage device for accessing memory to perform messaging using a channel coupled to a sender and a receiver

Dynamically allocated memory is managed in real-time. This real-time management capability enables an invalid access of the dynamically allocated memory to be detected at the time the invalid access occurs, rather than at some later point in time. This real-time management capability can be dynamically activated/deactivated on a per process basis.

Dynamic and real-time management of memory

Performance of channels used in communicating between senders and receivers

A highly available, high-performance memory queue. Locking of the queue is minimized in order to provide a highly available queue and to improve performance of the queue. Multiple updates of the queue can occur under a single lock. Further, messages of the queue are persistent. A time-initiated checkpointing process, as well as the storing of message information on a recovery log, ensures the persistence of the queue messages.

High-performance memory queue

Memory resident queues are monitored at predefined time intervals. When the monitoring indicates that a particular queue is not being serviced at a desired level, then action is taken to sweep one or more messages from the queue. The sweeping of the messages frees up system resources associated with the messages, thus allowing other tasks to be serviced. If, after the sweeping, it is determined that the queue can handle additional messages, then one or more messages are placed back on the queue.

Managing memory resident queues to control resources of the systems using the queues

When a processor becomes inactive, queues resident in the memory of that processor become inaccessible. Thus, in order to access those queues, an active processor takes over ownership of one or more of the inaccessible queues. Each queue may be rebuilt prior to its take over to ensure that it has up-to-date information.

Growing community of inventors

Wappingers Falls, NY, United States of America

Jason A Keenaghan