International Business Machines Corporation

Zhiyong Tian

Yong Sen Zheng

Jin Cheng

Cheng Ding

Yan Zhang

Yuri L Volobuev

Jia Wei Zhou

Kuei-Yu Wang-Knop

Shuo Feng

Zhi Hong Ma

Zi Qiang Gu

A pinned memory space for caching data can be provided in a data node. The data that is cached in the pinned memory space can be prevented from being swapped out. A virtual address can be assigned to the data. The virtual address can be mapped to a memory address of the data in the pinned memory space for accessing the data by an application. A first command can be received from the application for caching the data. The first command can indicate an attribute associated with the caching of the data. Responsive to receiving the first command from the application for caching the data, the data associated with the first command can be cached by storing the attribute in association with the data in the pinned memory space.

Unified in-memory cache

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

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

In-memory caching can include providing, in a data node, a pinned memory space for caching data in a distributed file system. The data that is cached in the pinned memory space is prevented from being swapped out. A virtual address is assigned to the data. The virtual address is mapped to a memory address of the data in the pinned memory space for accessing the data by an application.

Embodiments relate to dynamically allocating access to a shared resource based on quota shares. An aspect includes computing, by a client node, an expected size of quota shares needed by the client node based on a historical rate of resource consumption by the client node. The client node transmits a request for a count of quota shares based on the expected size. The client node receives an indication that the request for the count of quota shares is one of: granted, denied, and granted-in-part. The client node self-rules the shared resource based on the indication.

Growing community of inventors

Beijing, China

Zhiyong Tian