International Business Machines Corporation

Michael K Coffey

Manjunath Basappa Muttur

Steven E Froehlich

Paul D Moyer

Brent A Anderson

A method, information processing system, and computer program storage product for determining if an application has become unresponsive. Network traffic at a receiver node is monitored. The receiver node is determined to have generated a window probe response indicating a predetermined window size. A threshold associated with the window size of the receiver node is set in response to the receiver node having generated the window probe response. The window size of the receiver is determined to have been at the predetermined size for at least one of a time period greater than the threshold and a count greater than the threshold. An application associated with the receiver node is classified as unresponsive in response to the window size of the receiver node having been the predetermined size for at least one of a timer period greater than the threshold and a count greater than the threshold.

Detection of an unresponsive application in a high availability system

A method, information processing system, and computer program storage product manage network layer addresses in a cluster multi-processing environment. Network address assignment in a cluster multi-processing environment is monitored. A network address currently assigned to a first network interface is determined, in response to monitoring network address assignment, to have been assigned to a second network interface. The first network interface is triggered to send an update message to at least one computing node communicatively coupled to the first network interface triggering in response to determining that a network address currently assigned to a first network interface has been assigned to a second network interface. The update message informs the computing node to transmit data associated with the network address to the first network interface.

High availability of internet protocol addresses within a cluster

A system and method are provided for improving recovery times in fallover conditions in a multinode data processing system by sending notification of the failure of a server node, which is acting as server for a client application running on a client node, to the client application. In the present invention, this notification is provided by the fallover node acting as backup for the server node. When a client application receives no response from a server for a long time, it assumes that the server has failed and initiates reconnection. The present invention speeds-up the reconnect initiated by the client application by having system level software proactively notify the client application about the server failure. This results in faster recovery for client applications.

Method for enabling faster recovery of client applications in the event of server failure

An updating capability updates a component of a computing environment, while maintaining the availability of the computing environment. In particular, a component of the computing environment which is associated with at least a portion of a unit of work is updated from one version to another version. Subsequently, the updated component emulates the original version, or operates in a compatibility mode, while other components of the computing environment, which are similarly associated with the same unit of work, remain at the original version.

Method, system and program products for operationally migrating a cluster through emulation

A method and rotational mask scanning apparatus for exposing a plurality of images on a workpiece, include a rotatable mask having a pattern of image segments thereon, an optical system for projecting the image segments onto the workpiece, and a device for at least one of rotating the mask and for moving the workpiece so as to continuously expose a plurality of regions on the workpiece with the pattern of image segments.

Rotational mask scanning exposure method and apparatus

A backing out capability backs out a component of a computing environment, while maintaining the availability of the computing environment. In particular, a component of the computing environment which is associated with at least a portion of a unit of work is backed out from one version to another version. In addition, the backed out component is capable of emulating the other version.

Growing community of inventors

Shokan, NY, United States of America

Michael K Coffey