International Business Machines Corporation

Shuo Feng

Yong Sen Zheng

Xin Wang

Yan Zhang

Jia Wei Zhou

Zhiyong Tian

Lin Feng Shen

Zheng Cai Yuan

Zhi Hong Ma

Guang Han Sui

Li Liu

Ji Dong Li

Xue Li

Fang Cheng

Cheng Ding

Hai Zhong Zhou

Yu Bing Tang

Zi Qiang Gu

Tian Feng

Wu Xu

In response to receiving a request for an identity key from a first entity, an identity key for the first entity is generated. A first request from the first entity to replicate a set of data is received. The generated identity key for the first entity is added to the metadata of the set of data requested to be replicated. A determination is made whether a replication rule exists for the first entity. In response to determining that a replication rule exists for the first entity, the set of data is replicated according to the replication rule for the first entity.

Dynamic replication based on identity

A computer-implemented method comprises initializing a plurality of segment lists. Each segment list of the plurality of segment lists corresponds to a respective one of a plurality of disk drives. Each segment list divides storage space of the respective disk drive into a plurality of segments. The method further comprises, for each of the plurality of disk drives, identifying one or more candidate segments from the plurality of segments; calculating a respective segment distance variance for one or more combinations of identified candidate segments. Each combination of identified candidate segments includes one candidate segment for each of the plurality of disk drives. The method further comprises selecting a combination of the one or more combinations of identified candidate segments having the smallest respective segment distance variance; and storing data on the plurality of disk drives according to the selected combination of identified candidate segments.

Disk offset-distance awareness data placement for storage system data protection

Embodiments of the present disclosure relate to methods, systems, and computer program products for storage management. In one embodiment, a computer-implemented method is disclosed. According to the method, in response to receiving a request related to managing the at least one directory entry in the file system, at least one directory entry in a file system may be determined by a file system in a storage system, where each of the at least one directory entry is represented by digital numbers. An index for each of the at least one directory entry may be managed in the file system by the file system, where an index key for the index comprises the digital numbers themselves. In other embodiments, a computer-implemented system and a computer program product for managing the index are disclosed.

Index management in storage system

Data-locality-aware task scheduling on hyper-converged computing infrastructures is provided. A plurality of data blocks referenced in an input/output (I/O) request are identified. The I/O request is based on scheduling logic that executes within a container that is deployed on a hyper-converged infrastructure. A block-location mapping table is scanned using a data block identifier that is associated with a present data block of the plurality of data blocks. Physical node(s) of the hyper-converged infrastructure that store the present data block are identified. A container-instance mapping table is scanned using one or more physical node identifiers that are associated with the physical node(s) that store the present data block. Container(s) deployed on physical node(s) that store the present data block are identified. The scheduling logic is provided with a list of identifier(s) that are respectively associated with the containers that are deployed on the physical node(s) that store the present data block.

Data-locality-aware task scheduling on hyper-converged computing infrastructures

Detecting deadlock in a distributed computing environment. Potential deadlocks between resources of nodes in a computing cluster by determining resource reverse pairs of the resources for each transaction from trace or log files using data analytics. The potential deadlocks are identified offline by matching a global or local resource between the nodes in sub-transactions of each transaction as recursively identified from a transaction resource chain.

Detecting deadlock in a cluster environment using big data analytics

An approach, for fileset based data locality management in Distributed File Systems. A data locality manager receives fileset identifiers and associated block allocation information, for storing in data block locality tables. The data locality manager determines data block locality factors based on the fileset identifiers and the block allocation information, creating a collection of the data block locality factors. The data locality manager stores the collection of the data block locality factors in the data block locality tables. The data locality manager receives the fileset identifiers for determining the collection of the data block locality factors associated to the fileset identifiers and outputs the collection of the data block locality factors.

Fileset-based data locality enablement in distributed file systems

Growing community of inventors

Beijing, China

Shuo Feng