International Business Machines Corporation

William Stuart Edwards

Lyle LeRoy Merithew, Jr

Gerard Maclean Dearing

Thomas Alexander Mahon

Elmer Enrique Latorre

Ronald E Bretschneider

Marc Kenneth Duquette

Ruth Leslie Ferziger

Peter Verl Gibson

Michelle Parks Dais, Legal Representative

The invention provides an apparatus, system, and method for cluster-wide peer recovery in the event of a computer failure. A failure of a first computer is detected and a recovery module is registered as the first computer. In one embodiment, the recovery module is a peer computer. The recovery module retrieves a privately held undo log data through the authorized assumption of the failure identity associated with the failed first computer, backs out in-flight transaction updates of the first computer, and frees up data resources locked by the first computer.

Apparatus, system, and method for transactional peer recovery in a data sharing clustering computer system

An apparatus, system, and method are disclosed for preserving cluster level serialization during file server serialization reinitialization. The apparatus includes a permission request module, a cluster negotiation module, and a completion notification module. The permission request module communicates a permission request to a remote file server in anticipation of a reinitialization of a local file server. The cluster negotiation module implements a reinitialization protocol on the remote file server during the reinitialization of the local file server. The completion notification module notifies the remote file server when the reinitialization of the local file server is complete. The apparatus, system, and method beneficially facilitate continued serialization negotiation among the remote file servers during the reinitialization of the serialization data on the local file server and, thereby, preserve the integrity of shared data resources.

Apparatus, system, and method for preserving cluster level serialization during file server serialization reinitialization

An apparatus, system, and method are disclosed for suspending a data access request during serialization reinitialization of a file server. The apparatus includes a request recognition module, an availability module, and a suspension module. The request recognition module recognizes a request to be processed by a file server. The availability module determines if the file server is available. The suspension module suspends the data access request if the file server is not available due to serialization reinitialization. In one embodiment, the suspension module implements a hardware interrupt delay loop to suspend an interruptible data access request, such as an application request. In another embodiment, the suspension module queues a non-interruptible data access request and notifies the operating system, for example, that the non-interruptible request has been initiated. One advantage of various embodiments of the present invention is to allow interruptible and non-interruptible data access requests to be suspended during serialization reinitialization and processed promptly after the serialization information is reinitialized.

Apparatus, system, and method for suspending a request during file server serialization reinitialization

An apparatus, system, and method are disclosed for reinitializing serialization data in a file server. The apparatus includes a failure recognition module, a discard module, and a serialization module. The failure recognition module recognizes a file system serialization failure on a file server. Upon recognition of the serialization failure, the discard module discards existing serialization data located in a first memory address space, such as a file server address space. In certain embodiments, the entire file server address space may be destroyed by the operating system. The serialization module then generates new serialization data from existing connection/position data. The connection/position data is located in a second address space, such as a client address space, that is maintained during the serialization reinitialization process. Containing and rebuilding the serialization data in this manner beneficially prevents system outages, reduces downtime, and decreases the likelihood of subsequent serialization deadlocks.

Apparatus, system, and method for file system serialization reinitialization

An apparatus, system, and method are disclosed for preserving connection/position data integrity during reinitialization of serialization information in a file server. The apparatus includes a completion rights module, a completion termination module, and a postponement module. The completion rights module grants a completion right to a sensitive process, which is characterized by an associated period of data instability. The completion termination module terminates a grant of the completion right to the sensitive process in anticipation of a reinitialization of a file server. The completion right may be terminated after the connection/position data is stable or, if necessary, in response to completion of a time out period. The postponement module postpones the reinitialization of the file server and the serialization information until after the completion rights are terminated. The apparatus, system, and method advantageously maintain the connection/position data stable during the file server reinitialization so that the connection/position data may be reliably used to rebuild the serialization information.

Growing community of inventors

San Jose, CA, United States of America

William Stuart Edwards