International Business Machines Corporation

Lenovo (singapore) Pte. Ltd.

Manjunath Basappa Muttur

Deepti Umarani

Chad J Larson

Daniel Gerard Thornton

Douglas J Griffith

Angela Astrid Jaehde

Michael K Coffey

James Allen Goodwin

Richard A Bloomer, Jr

Venkat Venkatsubra

Thomas V Weaver

Astrid Jaehde

Kavitha Ramalingam

Pramod Achyut Bhandiwad

Thomas Howard Smith

Alexander J Stundzia

Stephen N Abbot

Michael Coffey

A computer system is monitored for conditions bearing on the effective age of various hardware components of the system. Upon detecting an age adjustment condition, the affected hardware components are identified. An age adjustment is determined for each of the affected hardware components. The adjusted age is stored for reference when taking actions based on the adjusted age, such a component replacement and/or workload placement.

Predicting hardware failures in a server

Systems, methods, and computer program products to perform an operation comprising receiving, by a management console managing a server, a request to perform an operation on the server, determining that performance of the operation is associated with a deterministic failure in the server, and blocking performance of the operation by the management console, thereby preventing an occurrence of the deterministic failure in the server.

Preventing recurrence of deterministic failures

Based on a current activity running on a first selection of components operating in a primary mode from among redundant components within a high availability system, a separate power setting is selected for each separate type of redundant component from among the types of redundant components within the redundant components as specified in a high availability status specified for the current activity. At least one controller interface is called with a request to set the powered state of a particular component that is redundant to at least one of the first selection of components, from among a second selection of components operating in a standby mode from among the redundant components, to the separate power setting for the separate type of redundant component.

Managing power savings in a high availability system at a redundant component level of granularity

A method, system, and computer usable program product for predictively managing failover in a high availability system are provided in the illustrative embodiments. A disruptive activity occurring on the HA data processing system is detected. The disruptive activity has a potential to cause an operation of the HA data processing system to perform outside a specified parameter. A determination is made of a desired response in the HA data processing system should the disruptive activity disrupting the operation. A precautionary action is initiated with respect to the HA data processing system.

Predictively managing failover in high availability systems

An approach for management of boot time of a virtual machine is provided. In one aspect, a system boot time application identifies assigned resources of a virtual I/O server (VIOS) of a computing system. In addition, the system boot time application allocates additional resources from client logical partitions (LPARs) of the computing system to the assigned resources of VIOS during boot time of VIOS. The system boot time application further identifies cores of the computing system during the boot time of VIOS. The system boot time application also sets the cores in turbo core mode until boot time of VIOS is completed. In one aspect, the system boot time application reallocates the allocated additional resources from VIOS to the client LPARs once boot time of VIOS is completed.

System and method for expediting virtual I/O server (VIOS) boot time in a virtual computing environment

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

Embodiments that generate checkpoint images of an application for use as warm standby are contemplated. The embodiments may monitor accesses of external references by threads. An external reference may comprise a connection or use of services of an entity that is external to the set of processes that constitute the application, to which a process of the application attempts to connect by means of a socket or inter-process communication (IPC). Various embodiments comprise two or more computing devices, such as two or more servers. One of the computing devices may generate a checkpoint image of an application at a suitable point in time during initialization, when the state of the application is not yet dependent on interactions with external references. The second computing device may preload checkpoint image for the application and activate the checkpoint images when needed, following the specific resource management rules of the distributed subsystem.

Generation of standby images of applications

The method determines whether a particular node of a high availability cluster is functioning properly or is a failed node. The method dumps node process state information as a dump data for the failed or crashed node in a shared storage area of the high availability cluster. A high availability cluster manager identifies the dump data that corresponds to the failed node as the most recent dump data for that failed node. The high availability cluster manager interrogates the dump data using kernel debugger services to identify a process trace and thereby identify the crash-causing application for the failed node. The method determines if the dump data includes a process match for the failed node process. The high availability cluster manager may initiate a crash-causing application notification to administrators or other entities of the high availability cluster. The method provides relocation and restoration capability of applications from the failed node to a fallover node and returns those application resources to the user and other entities using the high availability cluster.

Fallover policy management in high availability systems

A computer implemented method, data processing system, and computer program product for efficiently using disk space when unarchiving files in the same file system. An archive file is read to identify a total number of data files in the archive file. The number of headers in the archive file is determined based on the total number of data files. A location in a first disk space of a largest data file in the archive file is determined from an offset in a header corresponding to the largest data file. The largest data file is then copied from the first disk space to a second disk space. The first disk space occupied by the largest data file is then released by truncating the archive file. The obtaining, copying, and releasing steps are repeated for each data file in the archive file until all of the data files are unarchived.

Method to efficiently use the disk space while unarchiving

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

Mechanisms are provided for performing a failover operation of an application from a faulty node of a high availability cluster to a selected target node. The mechanisms receive a notification of an imminent failure of the faulty node. The mechanisms further receive health information from nodes of a local failover scope of a failover policy associated with the faulty node. Moreover, the mechanisms dynamically modify the failover policy based on the health information from the nodes of the local failover scope and select a node from the modified failover policy as a target node for failover of an application running on the faulty node to the target node. Additionally, the mechanisms perform failover of the application to the target node based on the selection of the node from the modified failover policy.

Dynamic updating of failover policies for increased application availability

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.

Growing community of inventors

Karnataka, India

Manjunath Basappa Muttur