International Business Machines Corporation

John W Doxtader

Robert Francis Bartfai

Kevin J Reilly

Nicholas P Rash

John Divirgilio

Laura J Merritt

Peter J LeVangia

Chetan Mehta

Mark G Atkins

Patrick John Sugrue

LeRoy R Lundin

Dawn S Moyer

Michal B Cohen

A system, method, and computer-readable medium for detecting errors on a network. According to a preferred embodiment of the present invention, a network error manager retrieves a network topology from a master subnet manager, wherein the network includes a collection of devices coupled by a first interconnect type. When a connectivity failure is detected in the first interconnect type, the network error manager receives from the master subnet manager at least one event notification via a second interconnect type. An error log analysis component identifies at least one device among the collection of devices as a possible cause of the connectivity failure in the first interconnect type. The network error manager retrieves events from at least one device among the collection of devices that can influence a state of the first interconnect type.

Implementing an error log analysis model to facilitate faster problem isolation and repair

Adapters, which provide message communications capabilities in a multinode data processing network, are provided with a mechanism for indicating critical errors from which recovery may ultimately be possible. Error handling capabilities are incorporated which operate both globally and locally to insure, to the greatest extent possible, that applications running on the network are not prematurely terminated and that the node with the error affected adapter is not prematurely removed from its connectivity with the other nodes within it network group.

Critical adapter local error handling

Messages are sent from a primary node of a computer system to one or more distribution nodes of the system. Each of the distribution nodes then further sends the message to one or more other nodes of the computer system. After receipt of the message, the other nodes forward an acknowledgement to the particular distribution node, which sent the message. The distribution nodes collect their respective acknowledgements, and when all of the expected acknowledgements are received by a distribution node, the distribution node sends one acknowledgement to the primary node. The one acknowledgement indicates receipt of the message by the other nodes.

Message distribution capability which uses distribution nodes to collect

An apparatus for synchronizing operator commands with a failover process in a distributed system having a control workstation and a plurality of nodes. One of the nodes of the distributed system is designated a primary node and one of the nodes is designated a backup node. The backup node includes a backup daemon for performing a failover process if the primary node fails such that the backup node becomes the primary node. Shell scripts send a command string to be synchronized with the operation of the backup daemon from the control workstation to the backup node. The backup daemon is then checked to determine if the backup daemon is sleeping, and, in the event the backup daemon is sleeping, commands derived from the command string are enqueued in a work queue for processing by the backup daemon. The backup daemon is then awakened such that the derived commands in the work queue are processed. In the event that the backup daemon is busy, commands derived from the command string are failed, thereby synchronizing the derived commands with the processing of the backup daemon.

Apparatus for synchronizing operator initiated commands with a failover

A method and program product for synchronizing operator commands with a failover process in a distributed system having a control workstation and a plurality of nodes. One of the nodes of the distributed system is designated a primary node and one of the nodes is designated a backup node. The backup node includes a backup daemon for performing a failover process if the primary node fails such that the backup node becomes the primary node. Shell scripts send a command string to be synchronized with the operation of the backup daemon from the control workstation to the backup node. The backup daemon is then checked to determine if the backup daemon is sleeping, and, in the event the backup daemon is sleeping, commands derived from the command string are enqueued in a work queue for processing by the backup daemon. The backup daemon is then awakened such that the derived commands in the work queue are processed. In the event that the backup daemon is busy, commands derived from the command string are failed, thereby synchronizing the derived commands with the processing of the backup daemon.

Growing community of inventors

Hurley, NY, United States of America

John W Doxtader