Teradata Us, Inc.

Ncr Corporation

Eric M Shank

Gary Lee Boggs

Donald Raymond Pederson

Steven Bart Cohen

Philip Jason Benton

Wayne R Boyle

Albert O Lam

J Mark Morris

Brian J Raccuglia

Franklin F Meng

A method of operating a data store system may include identifying a non-responsive processing node from a plurality of processing nodes. The method may further include generating a new registration key in response to identifying the non-responsive processing node. The method may further include providing the new registration key to the other processing nodes of the plurality of processing nodes excluding the identified non-responsive node. Each processing node provided the new registration key may be authorized to access a plurality of storage devices of a storage array in communication with the plurality of processing nodes. A system and computer-readable medium may also be implemented.

Non-responsive node activity avoidance

A combination of non-persistent-based and persistent-based schemes are used to effectively manage volatile storages which are conventionally managed solely by using non-persistent schemes (e.g., LRU schemes in cache memory). Generally, the persistent-based schemes can be based on persistent information associated with a non-volatile storage environment (e.g., persistent data temperatures associated with data stored in non-volatile storages). In this context, a persistent-based scheme can, for example, be effectively used in addition or combination with a conventional scheme provided for volatile memory. By way of example, a LRU scheme can be combined with a scheme based on persistent data temperatures in order to more effectively manage cache memory provided to enhance the performance of a system. As another example, a LRU, a LFU aging schemes can be combined with a scheme based on persistent data temperatures.

Management of data in multi-storage systems that can include non-volatile and volatile storages

Techniques for management of data in multi-storage systems allow managing storage of data in one of the multiple storages (e.g., a HDD) based on the information associated with the storage and/or access of data (e.g., logical hits of data in a cache memory) in another one of the storages (e.g., a cache memory) of the multi-storage system. In one aspect, information associated with storage and/or access of data in a volatile (or non-persistent) storage environment is provided for managing the storage of data in a non-volatile (or persistent) storage environment. By way of example, data access information associated with a volatile storage environment (e.g., logical hits of data in a cache) can be effectively communicated to a non-volatile storage environment, for example, as information that can be indicative of data temperatures. Moreover, the information obtained from a non-volatile storage environment can be persistently stored for and/or in the non-volatile environment (e.g., stored as persistent data temperatures), thereby preserving and allowing the information to be used to more effectively manage the storage of the data in the non-volatile storage itself and/or the multi-storage system including the (volatile storage) as a whole.

A method, computer program, and computer system are disclosed for managing data corruption identified by an application in a storage subsystem. Data requested of the application by a process is copied from a primary storage device in the storage subsystem to a memory. A data integrity check is performed on the data stored in the memory. If the data integrity check succeeds, the data is provided from the application to the process. If the data integrity check fails: the data requested by the process and stored on the primary storage device in the storage subsystem is identified; the data requested by the process and stored on a redundant storage device in the storage subsystem is identified; the data stored in the memory, the identified data stored on the primary storage device, and the identified data stored on the redundant storage device are compared as the first, second, and third copies, respectfully; and at least one of a group of instructions is chosen to be transmitted from the application to the storage subsystem based at least in part on the comparison of the first, second, and third copies.

Method and system for managing detected corruption in stored data

A method, apparatus and article of manufacture for hardware independent system level control of storage units in an array is disclosed. The method comprises the steps of scanning the array of storage devices to find available I/O paths, storing a list of available I/O paths to each storage device in a memory, receiving an I/O request directed at a virtual disk memory location, mapping the virtual disk memory location to a corresponding storage device, selecting an I/O path for the I/O request from the list of available I/O paths in stored in the memory, and transmitting the I/O request to the storage device over the selected I/O path. The apparatus comprises a virtual disk driver functionally coupled between the computer and the disk array with a core driver and a subordinate driver customized for storage device arrays from different hardware vendors. Selection of the subordinate driver is accomplished via a switch table stored in the computer memory.

Growing community of inventors

San Diego, CA, United States of America

Eric M Shank