International Business Machines Corporation

Robert K Gjertsen

David Jones Craft

Manoj N Kumar

Gokul Bhargava Kandiraju

Joon Chang

Janet Elizabeth Adkins

William Boyd Brown

Ninad S Palsule

According to one aspect of the present disclosure, a method and technique for hierarchical network failure handling in a clustered node environment is disclosed. The method includes: detecting a network failure by a node in a cluster, the cluster having plural nodes arranged in a hierarchy, wherein the network failure is associated with a subordinate node in the hierarchy to the detecting node; communicating the network failure from the detecting node to a superior node in the hierarchy; determining whether the network failure affects nodes higher than the detecting node in the hierarchy; and responsive to determining that the network failure does not affect nodes higher than the detecting node in the hierarchy, the detecting node initiating a protocol to expel the subordinate node from the cluster.

Hierarchical network failure handling in a clustered node environment

Hierarchical recovery of failed computing nodes to operative computing nodes within a cluster of computing nodes is managed by initiating a recovery leader at an operative node that retrieves management information from the operative nodes and applies the management information to recover filesets of a meta-fileset in a hierarchical filesystem. The use of hierarchical filesets throughout the cluster provides more rapid failover by distributing recovery load across computing nodes and supporting recovery of nodes in parallel.

System and method for hierarchical recovery of a cluster file system

A client node on which a file system is mounted can be configured to efficiently handle content access requests after a snapshot is created. The client node can maintain generation numbers at a data block, a file, and a fileset level to determine whether a data block is part of a snapshot generation and consequently whether the data block is writable in a current generation. Data block mappings and write access permissions associated with the data blocks need not be revoked at the client node prior to creating the snapshot. Cached data block mappings can be accessed to identify data blocks for servicing a read request. The data block can be updated in place if the data block is not part of the snapshot generation. The write request can be serviced at a new data block if the data block is part of the snapshot generation.

Managing data access requests after persistent snapshots

Growing community of inventors

Austin, TX, United States of America

Robert K Gjertsen