Hewlett-packard Company

Hewlett-packard Development Company, L.p.

Elizabeth Lynn Borowsky

Richard Andrew Golding

Arif Abdulhusein Merchant

John Wilkes

Mirjana Spasojevic

Dushyanth Narayanan

Pat Jacobson

Elizabeth A Shriver

Tim Sullivan

Data storage devices of an enterprise system are tested to determine whether the enterprise system is optimally configured. Each data storage device is tested to determine whether it can satisfy a performance requirement for an assigned group of n workloads. A group of n inequalities are generated, and only up to n of the inequalities may be evaluated to determine whether the device satisfies the performance requirement for the assigned group of workloads. The inequalities are based on a phased, correlated model of I/O activity.

Acceptability testing for capacity planning of data storage system

A data storage system is provided in which a migration plan generates migration plans for reaching a goal configuration from an initial configuration in a predetermined period of time. The migration plan initially makes terminal moves until no further terminal moves can be made. A shunt move is then made based on reducing the contention (the total size of the data stores that need to be moved onto a particular data stores device divided by the amount of excess capacity on the data storage device). The shunt is selected to lead to the lowest contention for the data storage system. Subsequently, the migration plan returns to making terminal moves to develop a migration plan. By determining existence and utilization dependencies of the various moves, independent moves are determined to be implemented in parallel with moves having dependencies. This produces parallelized migration plans which run much faster than sequential migration plans.

Computer data storage system with parallelization migration plan generator

A distributed data storage system is provided with a mechanism for determining data storage resource availability during data system failures. When a partition occurs, a coordinator requests all reachable replicas to begin a new epoch and each replica responds with its most recent epoch number and the list of replicas that it believes were active in that epoch. From the responses, the coordinator finds the maximum epoch number and the list of replicas in that epoch is taken as the list from which a quorum must be drawn. The coordinator establishes a quorum when, for each byte in the virtual store, the coordinator receives responses from more than half of the replicas for that byte. The coordinator then determines resource availability and sends out a message to all the reachable replicas with a new epoch number greater than the previous epoch number and the list of replicas active in this new epoch. The replicas receive this message, record the epoch number and the list of replicas, and proceed.

Resource availability determination mechanism for distributed data storage system

An apparatus for and a method of non-linear constraint optimization in a storage system configuration. In accordance with the primary aspect of the present invention, the objective function for a storage system is determined, the workload units are selected and their standards are determined, and the storage devices are selected and their characteristics are determined. These selections and determinations are then used by a constraint based solver through non-linear constraint integer optimization to generate an assignment plan for the workload units to the storage devices.

Non-linear constraint optimization in storage system configuration

A data storage system is provided in which a migration plan generates migration plans for reaching a goal configuration from an initial configuration in a predetermined period of time. The migration plan initially makes terminal moves until no further terminal moves can be made. A shunt move is then made based on reducing the contention (the total size of the data stores that need to be moved onto a particular data stores device divided by the amount of excess capacity on the data storage device). The shunt is selected to lead to the lowest contention for the data storage system. Subsequently, the migration plan returns to making terminal moves to develop a migration plan. Further migration plans are provided.

Computer data storage system with migration plan generator

Apparatus for and method of non-linear constraint optimization in storage system configuration

An apparatus for and a method of multi-dimensional constraint optimization in a storage system configuration. In accordance with the primary aspect of the present invention, the objective function for a storage system is determined the workload units are selected and their standards are determined, and the storage devices are selected and their characteristics are determined. These selections and determinations are then used by a constraint based solver through constraint integer optimization to generate an assignment plan for the workload units to the storage devices.

Apparatus for and method of multi-dimensional constraint optimization in storage system configuration

The value of a p-quantile of a workload distribution is computed to determine whether a data storage system satisfies a quality-of-service guarantee desired by a client. The quality-of-service guarantee may be a predetermined percentage of a workload being serviced by a device within a predetermined response time. A p-quantile value is set to be equal of the predetermined percentage of the quality-of-service guarantee, and a bound is set to be equal to the predetermined response time. A distribution for the workload arriving at the device during an interval of time equal to the bound is then estimated. It is then determined whether a p-quantile of the workload distribution is less than the bound. In cases where the p-quantile of the workload distribution is computed directly, then the p-quantile of the workload distribution is directly compared to the bound. In cases where the p-quantile of the workload distribution is not computed directly, then the p-quantile of the workload distribution is estimated, with the estimated value the compared to the bound.

Growing community of inventors

Brookline, MA, United States of America

Elizabeth Lynn Borowsky