International Business Machines Corporation

Globalfoundries Inc.

Hai Bo Qian

Xue Feng Gao

Yang Liu

Bo Cheng

David Ray Kahler

Chiahong Chen

Mei Mei

Karl Allen Nielsen

Jun Wei Zhang

Fang Quan Xie

Bo Zou

Chuan Li

Jeffrey R Steffan

Min Long

Embodiments of the present invention provide systems and methods for dynamically modifying data scrub rates based on RAID analysis. The method includes determining a grouping for an array based on a temperature for the array, a configurable threshold temperature range for the array, and an I/O distribution of the array. The method further includes modifying the data scrub rate for the array based on the grouping.

Dynamically restoring disks based on array properties

In one embodiment, a method includes moving data from an original, unmoved stride from an original array to target stripes of a target stride in a distributed array in response to a determination that all target stripes of the target stride are in a blank state indicating no data is stored therein, delaying movement of the data from the original stride to the target stripes of the target stride in response to a determination that any of the target stripes of the target stride are in an old state indicating unmoved data is stored therein, and moving the data from the original stride to the target stripes of the target stride after delaying and in response to a determination that all the target stripes of the target stride that were in the old state have switched to the blank state.

System and method for transferring traditional raid to distributed array

In one embodiment, a method includes iteratively selecting an original, unmoved stride from an original array until all original strides have been moved, determining a target stride location in a distributed array, determining a state of the target stride from the following states: an old state indicating unmoved data, a blank state indicating no data, and a new state indicating migrated data, determining that all target stripes are blank, moving data from the original stride to the target stripes when all the target stripes are blank, delaying the moving of the data from the original stride to the target stripes in the target stride when any of the target stripes of the target stride are in the old state and waiting until all the target stripes of the target stride are in the blank state, and determining that all original strides from the original array have been moved.

System and method for transferring traditional RAID to distributed array

For semiconductor memory garbage collection, an identification module identifies a garbage collection time window for at least one block of a flash memory array. A garbage collection module garbage collects a first block of the flash memory array with a highest garbage collection level and an open garbage collection time window.

Semiconductor memory garbage collection

The present invention discloses a method and apparatus for rebuilding a storage array. The method comprises: replacing, in response to a failing storage device occurs in the storage array, the failing storage device with a first spare storage device; performing component rebuild by using other storage devices in the storage array than the first spare storage device, so as to restore within the first spare storage device data in the failing storage device; performing, in parallel with the component rebuild, smart rebuild by using a second spare storage device, so as to copy data in the failing storage device to the second spare storage device; replacing the first spare storage device with the second spare storage device in the storage array upon completion of the smart rebuild.

Rebuilding a storage array

A method for data migration between storage devices according to an embodiment of the invention comprises: collecting an original time domain sequence of workload parameters of a data volume in a low speed storage device; evaluating a workload period of the data volume based on the collected original time domain sequence of the workload parameters; and migrating the data in the data volume according to the evaluated workload period so that the data is located in a high speed storage device during a workload peak of the data volume. The embodiments of the invention can improve a data access speed in the storage devices.

Growing community of inventors

Shanghai, China

Hai Bo Qian