International Business Machines Corporation

Lee Charles LaFrese

Lokesh M Gupta

Michael T Benhase

Joseph S Hyde, Ii

Yan Xu

Olga Yiparaki

Christopher Michael Sansone

Dana Fairbairn Scott

Juan A Coronado

Lisa R Martinez

Sonny Earl Williams

Michael Edward Factor

David Blair Whitworth

Dalit Naor

Ronen Itshak Kat

Vernon Walter Miller

Justin Thomson Miller

Miriam Allalouf

Joshua Douglas Martin

James Russell Thompson

A method for upgrading microcode in a multi-module storage system may include selecting a first module from two or more modules and operating the first module using an upgraded microcode. The method may include monitoring the performance of the first module by a second module of the two or more modules and rendering an indication of performance of the first module. Further, the method may include determining whether the indication of performance of the first module is greater than or equal to a performance metric.

Microcode upgrade in a storage system

A storage controller receives a request that corresponds to an access of a track. A determination is made as to whether the track corresponds to data stored in a solid state disk. Record staging to a cache from the solid state disk is performed, in response to determining that the track corresponds to data stored in the solid state disk, wherein each track is comprised of a plurality of records.

Adaptive record caching for solid state disks

Host input/output (I/O) operations are performed via a file stored in a non-volatile storage coupled to a storage controller while data structures are being generated in the storage controller to copy data from source logical volumes to target logical volumes. The source logical volumes and the target logical volumes are logical representations of physical storage maintained in a plurality of direct access storage devices. The contents of the file are transferred from the non-volatile storage to one or more of the plurality of direct access storage devices, after the data structures have been generated, wherein the host I/O operations are performed via the file while the contents of the file are being transferred to the one or more of the plurality of direct access storage devices. The host I/O operations to the plurality of direct access storage devices are resumed, in response to transferring entire contents of the file to the one or more of the plurality of direct access storage devices.

Executing host data transfer operations during setup of copy services operations

A method for determining power consumption in a data storage system is provided. The method comprises determining data access patterns for at least a first storage device in a storage system based on operations performed by the first storage device; and calculating power consumption for the storage system by interpolating costs associated with the operations performed by the first storage device, wherein the cost associated with each operation is determined based on: (1) various levels of activities for the first storage device and a mix of workload characteristics, and (2) predetermined power consumption measurements obtained from one or more benchmarks for same operations performed by a second storage device in a test environment.

Estimating power consumption in a computing environment

An apparatus, system and method to optimize load distribution across logical and physical resources in a storage system. An apparatus in accordance with the invention may include an availability module and an allocation module. The availability module may dynamically assign values to resources in a hierarchical tree structure. Each value may correspond to an availability parameter such as allocated volumes, current resource utilization, and historic resource utilization. The allocation module may serially process the values and allocate a load to a least busy resource in the hierarchical tree structure based on the assigned values.

System and method for identifying least busy resources in a storage system using values assigned in a hierarchical tree structure

Provided are techniques for introducing a delay in responding to host write requests. A percentage of fullness of a write cache is determined. Based on the determined percentage of fullness of the write cache (f), a low cache threshold (L), alpha (&#x3b1;), and k, an amount of delay to introduce into responding to a host write request is determined. Techniques wait the amount of the delay before responding to the host write request although the host write request processing has completed.

Proactive technique for reducing occurrence of long write service time for a storage device with a write cache

Provided are techniques for transmitting blocks of data. It is determined whether any high priority out of sync (HPOOS) indicator is set to indicate that a number of modified segments associated with a block of data are less than or equal to a modified segments threshold. In response to determining that at least one high priority out of sync indicator is set, one or more sub-blocks of data in the modified segments associated with the block of data and with one set high priority out of sync indicator are transferred.

Computer program product and a system for a priority scheme for transmitting blocks of data

Priority scheme for transmitting blocks of data

Growing community of inventors

Tucson, AZ, United States of America

Lee Charles LaFrese