Tandem Computers Incorporated

Microsoft Technology Licensing, LLC

Matthew C McCline

William J Carley

Michael John Skarpelos

James M Lyon

Robbert Van Der Linden

Patrick James Helland

Mohsen M Al-Ghosein

Gagan Chopra

Robert Van Der Linden

James A Lyon

In a computing environment containing a plurality of state machines that communicate by passing messages on connections, a construct called a clique controls access into a set of the state machines by worker threads that deliver the messages arriving on the connections. A clique is a collection of connections into the set of the state machines that have a common relationship for which concurrency isolation is required. Each clique has a message queue and a guard for marking the clique as busy or not busy, The guard prevents more than one thread at a time from delivering messages that arrive on connections in the clique to the set of state machines, thus ensuring concurrency isolation of the set of state machines. Messages that arrive on a connection in the clique while the clique is marked as busy are queued in the clique's message queue. The queued messages are delivered one at a time by a same worker thread that is currently busy in the clique. This operation can save a thread switch when a state machine generates an outgoing message that results in an immediate incoming message to the state machine, such as a buffer full message, and thus makes efficient use of the worker threads.

Concurrency control of state machines in a computer system using cliques

A fault tolerant computer system distributes audit trail files containing audit records, across an arbitrary number of disk volumes. After one audit trail file becomes full, audit records are directed toward a next audit trail file stored on a different disk volume. Storage of newly generated audit rotates through the disk volumes in round-robin fashion. Full audit trail files are eventually archived and their space becomes available again for renaming and storage of newly generated audit records. The number of audit records available for on-line recovery after a failure is not limited to the storage capacity of any single disk volume. Furthermore, there is no contention for disk access between archiving of full audit trail files and storage of newly generated audit records.

Multi-volume audit trails for fault tolerant computers

System-critical files are protected from being inadvertently modified or deleted by placing them in a Reserve name space of storage that requires any process seeking modifying access to the Reserve name space to have a 'Right' to do so. The right to modifying access is garnered by a process first making a call to a system library procedure that causes a memory-stored data structure associated with the calling process to be modified, identifying the process as one with a Right to make modifying access to the Reserve name space. Any attempt to modify, delete, or create any file residing in the Reserve name space without the Right will be refused.

Method and apparatus for preventing inadvertent changes to

A fault tolerant computer system distributes audit trail files containing audit records, across an arbitrary number of disk volumes. After one audit trail file becomes full, audit records are directed toward a next audit trail file stored on a different disk volume. Storage of newly generated audit rotates through the disk volumes in roundrobin fashion. Full audit trail files are eventually archived and their space becomes available again for renaming and storage of newly generated audit records. The number of audit records available for on-line recovery after a failure is not limited to the storage capacity of any single disk volume. Furthermore, there is no contention for disk access between archiving of full audit trail files and storage of newly generated audit records.

A multiple processor system includes at least one process pair each including a plurality of modules. The modules perform functions related to multiple independent threads, and are arranged in a predetermined order such that higher modules are dependent upon lower modules, and lower modules are independent from higher modules. Each process pair is initially unaware of the number and order of the modules. The order of the modules is related to dependency and interdependency between the modules so that there is a portion of higher modules and a portion of lower modules. Multiple independent threads process the modules to cause activities in the portions of higher modules to take place before activities in the portions of lower modules.

Growing community of inventors

Bellevue, WA, United States of America

Matthew C McCline