International Business Machines Corporation

Rong Zeng

Lance Warren Russell

Rainer Wolafka

William Boyd Brown

Poornima Gupte

Frank Marschollek

Srikrishan Malik

Xin Wang

John Lewars

D Scott Guthridge

Lin Feng Shen

Limei Shaw

Jonathan Terner

Che Lui Shum

Lucy Ya Mei Kung

Hunny Wiratchada Kershaw

Pinshan Jiang

Jamee Kim Lee

Stanley Yi-Hsiung Wu

A computer-implemented method, according to one embodiment, includes receiving, by a server from a client application, a read request for a data block. The method further includes, reading, by the server, data of the data block and checksums associated with the data block, from a data storage drive, and storing, by the server, the data of the data block and the associated checksums in a buffer. A client node is caused, by the server, to use the associated checksums to perform a validity check for the data of the data block and a transmission from the server to the client node. A computer program product, according to another embodiment, includes a computer readable storage medium having program instructions embodied therewith. The program instructions are readable and/or executable by a server to cause the server to perform the foregoing method.

Offloading a validity check for a data block from a server to be performed by a client node

A computer program product is provided for extending network services addresses, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, where the program instructions are executable by a processor to cause the processor to identify, by the processor, an event affecting a node, wherein the node provides external access to a network using an Internet Protocol (IP) address, in response to identifying the event, identify, by the processor, an attribute associated with the IP address, and based on the attribute associated with the IP address, determine, by the processor, whether to move the IP address to another node.

Cluster file system support for extended network service addresses

A computer program product is provided for extending a clustered file system. The computer program product comprises a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a processor to cause the processor to build a central cluster repository, establish a service-specific interface for accessing non-file system data in the central cluster repository, and extend a clustered file system with the service-specific interface.

Maintaining service configuration consistency across nodes of a clustered file system

A computer-implemented method according to one embodiment includes receiving, via an interface of a clustered file system, callback registration information from an external service, identifying a plurality of parameters associated with the callback registration information, constructing a service registration within the clustered file system, based on the plurality of parameters, identifying the service registration in response to an occurrence of one or more events, and performing one or more callbacks, according to the service registration.

Integrating external services with a clustered file system

A computer program product is provided for extending network services addresses, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, where the program instructions are executable by a processor to cause the processor to identify, by the processor, a network event affecting a node of a network, wherein the node provides external access to the network using an Internet Protocol (IP) address, in response to identifying the network event, identify, by the processor, an attribute associated with the IP address, and based on the attribute associated with the IP address, determine, by the processor, whether to move the IP address to another node of the network.

A computer program product is provided for extending a clustered file system. The computer program product comprises a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a processor to cause the processor to define functions required by external services implemented on top of a clustered file system, identify at least one function that is not provided by the clustered file system, and extend the clustered file system to provide the at least one function.

A computer program product is provided for extending network services addresses. The computer program product comprises a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to identify a network event affecting a node of a sub-cluster of nodes of a network, wherein the node provides external access to the network using an Internet Protocol (IP) address. The program instructions are also executable by the processor to cause the processor to, in response to identifying the network event, identify an attribute associated with the IP address of the node. Finally, the program instructions are executable by the processor to cause the processor to, based on the attribute associated with the IP address of the node, determine whether to move the IP address of the node to another node of the sub-cluster.

A mechanism is provided a data processing system for protocol servicing in network-attached storage. A protocol service executing in the data processing system in a clustered file system establishes a high priority recovery thread. The high priority recovery thread monitors health counters that count total requests in and total requests out for a client accessing a network-attached storage device via the protocol service. The high priority recovery thread determines a category of health of the protocol service based on the health counters. The mechanism takes corrective action based on the category of health of the protocol service.

Highly resilient protocol servicing in network-attached storage

A mechanism is provided in a data processing system for unobtrusive failover in a clustered file system. A node in the clustered file system periodically monitors publicized resource events from a cluster manager in the clustered file system for a triggering event that triggers a grace period. Responsive to detecting a triggering event, the node enters a grace period without restarting. During the grace period, the node processes a state request from a first client.

Unobtrusive failover in clustered network-attached storage

A mechanism is provided in a data processing system for protocol servicing in network-attached storage. A protocol service executing in the data processing system in a clustered file system establishes a high priority recovery thread. The high priority recovery thread monitors health counters that count total requests in and total requests out for a client accessing a network-attached storage device via the protocol service. The high priority recovery thread determines a category of health of the protocol service based on the health counters. The mechanism takes corrective action based on the category of health of the protocol service.

Provided are a method, system, and program for configuring a device using information from a device table. Device information is obtained for a device coupled to a system. The device information is provided to a device driver executing in the system. The device driver calls a method in response to determining the device driver does not support the device identified by the device information. The method provides device configuration information from a device table to the device driver. The device driver uses the device configuration information in the device table to configure the device for use in the system.

Configuring a device using information from a device table

In accordance with a computer program product, apparatus and a method there is provided a redundant network wherein a host computer operates with a plurality of storage devices by monitoring conditions of the multipath storage network and controlling a storage multipath device driver in conjunction with an associated storage multipath device input/output (I/O) pending queue to increase I/O throughput to a storage device driver, such as a disk device driver, when I/O demand increases, and to decrease I/O throughput to the storage device driver in the event of an I/O error condition.

Growing community of inventors

San Jose, CA, United States of America

Rong Zeng