International Business Machines Corporation
Caching file data within a clustered computing system

Abstract:

A computer-implemented method according to one embodiment includes receiving, from an application at a metadata node of a clustered computing system, a request for a file, identifying, by the metadata node, a subset of data nodes within the clustered computing system where a portion of the file is stored, determining, by the metadata node, a data node within the subset of data nodes storing the portion of the file in a cache of the data node, and returning to the application, by the metadata node, a location of the portion of the file at the data node storing the portion of the file in the cache of the data node.