International Business Machines Corporation

Kuei-Yu Wang-Knop

Robert J Curran

Frank Bernhard Schmuck

Roger Lee Haskin

Yuri L Volobuev

Zhiyong Tian

James Christopher Wyllie

Radha R Kandadai

Embodiments relate to dynamically allocating access to a shared resource based on quota shares. An aspect includes computing, by a client node, an expected size of quota shares needed by the client node based on a historical rate of resource consumption by the client node. The client node transmits a request for a count of quota shares based on the expected size. The client node receives an indication that the request for the count of quota shares is one of: granted, denied, and granted-in-part. The client node self-rules the shared resource based on the indication.

Dynamic and adaptive quota shares

A method for data access in a multinode, shared storage data processing environment is provided by enhancing the file locking mechanism structure so as to permit nodes not normally designated as metadata controller nodes to fulfill that function for limited times thus at least temporarily eliminating the need for continual node-to-node coordination. This is particularly advantageous in the access and transfer of large files such as video files or files containing complex visualization data.

Parallel metadata service in storage area network environment

The present invention is directed to a method for controlling file access in a multinode, shared storage, data processing system in which a one set of nodes is capable of acting as metadata controllers and a second set of nodes are tuned for running user applications. By providing two kinds of locks operative at the file level of granularity, a mechanism is produced which permits application programs to also run on their set of metadata controller nodes. One of the locks permits read and write access to existing data blocks but precludes operations such as file deletion or file truncation. The other lock is of lower authority and permits metadata controller nodes, which can provide time limited permissions to the application nodes, to withhold locks which authorize access when requests for access are made from application nodes.

Mechanism for running parallel application programs on metadata controller nodes

A method is provided for continuing node operations in quorum-based protocols. This is particularly valuable in the situation in which a group of nodes includes only two nodes and in which communications to a node is lost. Provision is made for adding additional status indications to each node indicating whether or not it is enabled for single-node quorum operation. Provision is also made for identifying one node as a primary node and another node as a secondary node for time-out response purposes.

Support for single-node quorum in a two-node nodeset for a shared disk parallel file system

A method is provided for limiting access to disks and files in the event of a system partitioning occurring as the result of a node failure in a data distributed processing system in which files are shared amongst a plurality of independently running nodes. The nodes in the system are provided with limited duration leases which permit data access and which have to be periodically renewed. Each partition is also associated with a quorum which is also a necessary element in providing access at proper times. The lease and quorum concepts work together to insure that recovery operations do not occur until recovery is possible. The lease concept thus is also seen as further operating in close cooperation with the quorum concept to prevent long delays in the recovery process that could otherwise occur.

Program support for disk fencing in a shared disk parallel file system across storage area network

This invention provides a defragmentation utility that works on-line in parallel with other file system activities. Thus, it avoids making the file system unavailable for periods of time which would, if not for this invention, slow down data communication exchange and the execution of other tasks dependent upon the data. In particular, this invention, steps through all of the valid inodes finding each of the fragments. The defragmentation engine decides which fragments must remain in their current location and which fragments should migrate to another disk block sub-block location. Since the data blocks span across multiple disks, for each valid disk of the file system a set of disk blocks are constructed that are chosen to be filled, herein called plates. When the plates become full or reach a certain fullness, they are removed from the set and replaced by other disk blocks. When a disk block is removed from the plate set, it is moved to a &ldquo;done&rdquo; list as it is considered &ldquo;full&rdquo;. While a disk block is in the done list the fragments that belong to that block are not allowed to migrate. Thus, a defragmentation utility that works on-line, avoids locking data structures for long periods of time, is memory efficient, uses sub-blocks for fragment analysis and migration as well as minimizes data movements has been summarized. This utility thereby provides a transparent defragmentation function that operates in the background seamlessly with other system file operations.

Growing community of inventors

Poughkeepsie, NY, United States of America

Kuei-Yu Wang-Knop