International Business Machines Corporation

Sven Oehme

Wayne A Sawdon

Marc Adam Kaplan

Gregory Tad Kishi

Frank Bernhard Schmuck

M Corneliu Constantinescu

Leo S Luan

Daniel James Winarski

Nils Haustein

Anna Wanda Topol

Ulf Troppens

Rainer Wolafka

Stephen Leonard Schwartz

Deepavali M Bhagwat

Marc Thadeus Roskow

Embodiments relate to policy-based, multi-scheme data reduction for a computer memory. An aspect includes receiving a plurality of policy rules by a policy engine of the computer memory, wherein a first policy rule specifies applying a first data reduction scheme to data in the computer memory based on the data matching first characteristics, wherein a second policy rule specifies applying a second data reduction scheme to data in the computer memory based on the data matching second characteristics, wherein the first data reduction scheme is different from the second data reduction scheme. Another aspect includes determining, by the policy engine, that first data in the computer memory matches the first characteristics, and that second data in the computer memory matches the second characteristics. Yet another aspect includes applying the first data reduction scheme to the first data, and applying the second data reduction scheme to the second data.

Policy-based, multi-scheme data reduction for computer memory

A computer-implemented method according to one embodiment includes identifying an event associated with a high speed storage tier of a data storage system, determining a policy rule that is triggered in response to the event, and implementing one or more data management actions associated with the high speed storage tier according to the policy rule.

Dynamically managing a high speed storage tier of a data storage system

A mechanism is provided for reducing the backup time of data files from a memory. Data files are pre-staged by identifying the data files in the memory to be backed up to a backup storage system, sorting the data files by size thereby forming a set of small data files and a set of large data files, and copying the set of small data files to a cache while leaving the set of large data files in a disk subsystem. The set of small data files are then backed-up from the cache and the set of large data files are backed-up from the disk subsystem to a backup storage system. Thus, the time required to backup the set of small data files from the cache is performed at a faster rate as compared to backing up the set of large data files from the disk subsystem.

Reducing a backup time of a backup of data files

Embodiments of the disclosure relate to storing and sharing data in a scalable distributed storing system using parallel file systems. An exemplary embodiment may comprise a network, a storage node coupled to the network for storing data, a plurality of application nodes in device and system modalities coupled to the network, and a parallel file structure disposed across the storage node and the application nodes to allow data storage, access and sharing through the parallel file structure. Other embodiments may comprise interface nodes for accessing data through various file access protocols, a storage management node for managing and archiving data, and a system management node for managing nodes in the system.

Highly scalable and distributed data sharing and storage

The present invention can include an automated method that optimizes the selection of a node in a distributed file system (DFS) to fulfill a client request. Such a method can begin when a client request is received by a master node of a distributed file system (DFS). The DFS can include a multitude of DFS nodes capable of accessing various resources. Two or more DFS nodes can be preselected to fulfill the client request. Each preselected DFS node can then participate in a voting process to dynamically determine the response DFS node that can optimally respond to the client request. The client request can be fulfilled by response DFS node, utilizing the DFS node best capable of servicing the client request.

Optimizing node selection when handling client requests for a distributed file system (DFS) based on a dynamically determined performance index

Growing community of inventors

Morgan Hill, CA, United States of America

Sven Oehme