International Business Machines Corporation

Globalfoudries Inc.

Chao G Li

Yang Liu

Paul Henri Muench

Xue Feng Gao

Lawrence Yiumchee Chiu

Sangeetha Seshadri

Yong Guo

Zhi Jun Wang

Chao Li

Cheng-Chung Song

Stephen LaRoux Blinick

Yao Peng

Daniel W Fok

GuoFeng Zhu

JiaYang Zheng

Embodiments of the present invention provide methods, systems, and program products for concurrent data retrieval from multiple loud storage devices. Embodiments of the present invention can be used to retrieve stripes of target data from at least a first network device, retrieve redundancy data of the target data from a second network storage device that is different from the first network storage device concurrently and reconstructing the target data based on the stripes of the target data and the redundancy data.

Concurrent data retrieval in networked environments

A method to optimize workload across a plurality of storage devices of a storage system, where the method monitors a workload of a first storage device belonging to a first tier of the storage system, calculates a performance of the workload of the first storage device belonging to a first tier of the storage system, interpolates a performance threshold for the first storage device using the workload pattern of the first storage device and a profile of the first storage device, the profile identifying a benchmark performance of the first storage device, and optimizes a usage of the first storage device within the storage system to improve a performance of the first storage device.

Apparatus and method to manage device performance in a storage system

A mechanism is provided for managing a high speed memory. An index entry indicates a storage unit in the high speed memory. A corresponding non-free index is set for a different type of low speed memory. The indicated storage unit in the high speed memory is assigned to a corresponding low speed memory by including the index entry in the non-free index. The storage unit in the high speed memory is recovered by demoting the index entry from the non-free index. The mechanism acquires a margin performance loss corresponding to a respective non-free index in response to receipt of a demotion request. The margin performance loss represents a change in a processor read operation time caused by performing a demotion operation in a corresponding non-free index. The mechanism compares the margin performance losses of the respective non-free indexes and selecting a non-free index whose margin performance loss satisfies a demotion condition as a demotion index. The mechanism selects an index entry from the demotion index to perform the demotion operation.

Managing high speed memory

Systems and methods are provided for managing storage cache resources among all servers within the cluster storage environment. A method includes partitioning a main cache of a corresponding node into a global cache and a local cache, sharing each global cache of each node with other ones of the nodes of the multiple nodes, and dynamically adjusting a ratio of an amount of space of the main cache making up the global cache and an amount of space of the main cache making up the local cache, based on access latency and cache hit over a predetermined period of time of each of the global cache and the local cache.

Managing and sharing storage cache resources in a cluster environment

A mechanism is provided for managing a high speed memory. An index entry indicates a storage unit in the high speed memory. A corresponding non-free index is set for a different type of low speed memory. The indicated storage unit in the high speed memory is assigned to a corresponding low speed memory by including the index entry in the non-free index. The storage unit in the high speed memory is recovered by demoting the index entry from the non-free index. The mechanism acquires a margin performance loss corresponding to a respective non-free index in response to receipt of a demotion request. The mechanism compares the margin performance losses of the respective non-free indexes and selecting a non-free index whose margin performance loss satisfies a demotion condition as a demotion index and selects an index entry from the demotion index to perform the demotion operation.

For optimizing data placement in a multi-tiered storage system, system configuration data and system performance data is collected. A plurality of data movement plans are generated, based in part on the system configuration data and the system performance data. A conflict between the plurality of data movement plans are arbitrated to form an execution plan. The data movement plans are performed according to the execution plan.

Systems, methods, and physical computer storage media to optimize data placement in multi-tiered storage systems

A system includes a data collector, a plurality of data placement optimizers, a data placement arbitrator, and a data mover. The data collector is configured to collect system configuration data and system performance data. The plurality of data placement optimizers are each configured to analyze the system configuration data and the system performance data for developing a corresponding data movement plan. The data placement arbitrator is configured to arbitrate conflicts between at least two data movement plans of generated by the plurality of data placement optimizers to form an execution plan. The data mover is configured to perform the data movement plans according to the execution plan.

A method for improving the performance of a RAID under rebuild is disclosed. In one embodiment, such a method includes identifying a RAID requiring rebuild, such as by identifying a RAID having one or more failed storage-drive components. The method then automatically performs the following in response to identifying the RAID: the method identifies hot extents (i.e., extents most heavily accessed) in the RAID; the method migrates the hot extents from the identified failed RAID to a normal RAID not requiring rebuild, such as to an underused RAID; and the method rebuilds the failed RAID. The migration of the hot extents will ideally occur while the RAID is being rebuilt but may also be performed prior to the rebuild process. A corresponding apparatus and computer program product are also disclosed.

Growing community of inventors

Shanghai, China

Chao G Li