International Business Machines Corporation

Gang Lyu

Chao Li

Yang Liu

Xue Qiang Zhou

Hong Qing Zhou

Bo Zou

Yongjie Gong

Jun Gu

Yicheng Feng

Feng Shao

Si Cong Zhou

Yao Zhang

Nicolas Marc Clayton

Ke Chen

Geng Hu

Dong Ping Song

Wei Xian

A system and related method identify a weakness of a workflow in a complex system. The method collects runtime data about the complex system. The complex system comprises a plurality of subcomponents, and the method identifies an abnormal operation in the complex system. The method constructs a multi-dimensional cause-and-effect relation matrix among the plurality of subcomponents, and filters one or more related operations using the multi-dimensional cause-and-effect relation matrix.

Fault diagnosis in complex systems

Operating a data mirroring system comprising a primary storage and a secondary storage that maintains a synchronous copy of data in the primary storage by detecting at least one disk array of the primary storage is overdriven, determining one or more primary volumes mapped into the at least one disk array, identifying sequential read commands to the primary volumes, at least one sequential read stream comprising a series of sequential read commands to one of the primary volumes, and redirecting at least one sequential read stream to the secondary storage.

Distributing sequential read streams across synchronous mirror pairs

Solutions for processing a redundant array of storage drives receiving a rebuilding request of a redundant array of storage drives. The redundant array has a first storage drive to be replaced. In response to no spare storage drive being available to logically replace the first storage drive, a second storage drive is identified, which is a source storage drive of a disk balance process being performed. A rebuilding of the redundant array is initiated by reconstructing data of the first storage drive on the second storage drive during the disk balance process.

Storage performance enhancement

A method for operating a storage controller reduces a probability of data loss in a storage system having redundant arrays of independent storage volumes (RAID) by identifying an old storage volume in a first location of a first RAID array of the storage system, and further by exchanging the old storage volume in the first location of the first RAID array with a second storage volume in a second location of a second RAID array of the storage system.

Dynamic storage volume distribution according to wearing level

Described are techniques for dynamic rebalancing in storage systems. The techniques including a method comprising calculating an estimated time to storage fullness for respective storage pools in a space balance group, the estimated time to storage fullness based on an allocation speed of the respective storage pools. The method further comprises classifying a first storage pool having a first estimated time to storage fullness below a migration time threshold as a first migration source storage pool. The method further comprises classifying a second storage pool having a second estimated time to storage fullness above the migration time threshold as a first migration target storage pool. The method further comprises rebalancing free space in the space balance group by migrating storage volumes from the first migration source storage pool to the first migration target storage pool.

Dynamic rebalancing of free space between storage pools

Embodiments of the disclosure provide a computer-implemented method for data replication from a first storage to a second storage. In the method, data replication control blocks for data blocks stored in the first storage and needed to be transmitted may be generated. The data replication control blocks may be sorted in an ascending order of probabilities of expected overwrites of the respective data blocks. The data blocks may be transmitted from the first storage to the second storage according to the sorted data replication control blocks.

Data copy amount reduction in data replication

A computer-implemented method for dropped write error detection is proposed. In the method, a read request for a stride stored in an array of storage drives is received. The stride includes segments of a data and a first parity associated with the data spreading across the storage drives in the array of the storage drives. In response to the read request being a predefined sequential read request and a state of the stride being a first state, a parity check is performed on the stride. The first state indicates that no parity check has been performed after the data is written into the array of storage drives. The state of the stride is changed to a second state, and the second state is different with the first state.

Dropped write error detection

A method for recovering modified data lost from cache includes maintaining, in a cache of a primary storage system, a destage data structure indicating which modified data in the cache has been destaged. The method further maintains, in cache of a secondary storage system, a change recording data structure indicating which modified data has been replicated from the primary storage system to the secondary storage system. The method further merges the destage data structure with the change recording data structure to yield an updated change recording data structure. In the event modified data in the cache of the primary storage system is lost, the method utilizes the updated change recording data structure to determine which modified data in the secondary storage system is needed to restore the modified data lost from cache at the primary storage system. A corresponding system and computer program product are also disclosed.

Restoring data lost from battery-backed cache

A computer-implemented method, according to one embodiment, includes: detecting an outage at a production site, and transferring I/O functionality to a first recovery site. In response to resolving the outage, first and second out-of-sync bitmaps are received from the first and second recovery sites, respectively. The out-of-sync bitmaps are merged together. Performance data which corresponds to achievable throughput is received from each of the first and second recovery sites, and the performance data is used to divide the merged out-of-sync bitmap into two portions. A request is sent to the first recovery site for data which corresponds to the first portion of the merged out-of-sync bitmap. Similarly, a request is sent to the second recovery site for data which corresponds to the second portion of the merged out-of-sync bitmap. Finally, data is received which corresponds to the first and second portions of the merged out-of-sync bitmap respectively, in parallel.

Dynamic data restoration from multiple recovery sites implementing synchronous remote mirroring

This disclosure relates to a method, a system and a computer program product for tracking heat values. The method includes monitoring a first number of access operations to first data in each of a plurality of first source storage units during a cycle. The method further includes, for each of the plurality of first source storage units, calculating a first heat value based on the first number of access operations. Additionally, the method includes, in response to source data being moved from one of the first source storage units to a first target storage unit during the cycle, decreasing a calculated heat value of the one first source storage unit by a first value and increasing a calculated heat value of the first target storage unit by the first value.

Heat value tracking

This disclosure provides a method, a computing system and a computer program product for allocating write data in a storage system. The storage system comprises a Non-Volatile Write Cache (NVWC) and a backend storage subsystem, and the write data comprises first data whose addresses are not in the NVWC. The method includes checking fullness of the NVWC, and determining at least one of a write-back mechanism or a write-through mechanism as a write mode for the first data based on the checked fullness.

Write data allocation in storage system

Disclosed is a method, system and computer program product for forming a consistency group to define a dataset of point-in-time data to be copied from a source volume to a target volume; setting copy priorities for respective data in the dataset; and transmitting the respective data in the order of the copy priorities from the source volume to the target volume, wherein the copy priorities are dynamically adjusted in response to arrival of write data during transmission of the data.

Reducing write collisions in data copy

A method for efficiently managing extents of backup volumes in a tiered storage system is disclosed. In one embodiment, such a method includes identifying a lifespan associated with a backup volume. The lifespan indicates how long extents of the backup volume are retained in a tiered storage system before being released. The method further assigns a temperature value to the extents that determines where the extents are stored in the tiered storage system. The method utilizes the lifespan to determine the temperature value, where the temperature value is inversely proportional to the lifespan. The method places the extents on tiers of the tiered storage system in accordance with their temperature value, such that higher temperature extents are placed on higher tiers of the tiered storage system, and lower temperature extents are placed on lower tiers of the tiered storage system. A corresponding system and computer program product are also disclosed.

Growing community of inventors

Shanghai, China

Gang Lyu