International Business Machines Corporation

Globalfoundries Inc.

Renu Tewari

Dean Hildebrand

Frank Bernhard Schmuck

Manoj Premanand Naik

Marc M Eshel

Roger Lee Haskin

Dinesh C Verma

Karan Gupta

Anna Povzner

Wayne A Sawdon

Deepavali M Bhagwat

Rajagopol Ananthanarayanan

Anees Abdul Shaikh

Aameek Singh

Vasily Tarasov

Himabindu Pucha

Sandeep R Patil

Riyazahamad Moulasab Shiraguppi

Douglas Morgan Freimuth

Seraphin Bernard Calo

Deepak R Ghuge

Wendy Ann Belluomini

Lawrence Carter Blount

Rajagopal Ananthanarayanan

Khalil S Amiri

Ashish Mehra

Mansi Ajit Shah

Sanghyun Park

Noah Watkins

Ronald Patrick Doyle

Yongcheng Li

Arup Acharya

Shah Mohammad R Islam

Thomas Francis McElroy

Thiemo Voigt

Dharmendra S Modha

Arun Kwangil Iyengar

Sambit Sahu

Rui Zhang

Divyesh Jadav

Prasenjit Sarkar

Sriram Kolinjivadi Padmanabhan

Donna N Dillenberger

Daniel Manuel Dias

Shah Mohammad Rezaul Islam

Hongzhi Wang

Daniela Rosu

Prashant Pandey

Anurag Sharma

Prashant Pradhan

Lukas Rupprecht

Subashini Balachandran

Richard Orville LaMaire

Pawan Goyal

Mansi A Shah

Khalil S c/o Ibm United Kingdom Limited Amiri

Sanghyun c/o Ibm United Kingdom Limited Park

One embodiment provides a method for storage management in a hierarchical file system that includes creating a structure for the hierarchical file system including a top-file system and sub-file systems that each include files and directories. Directories for the sub-file systems of the hierarchical file system are tracked. A request for creation of a unique directory in the hierarchical file system is received. Upon a request by a particular sub-file system for more inodes without any inodes available, inode numbers are revoked from at least one other sub-file system having unused inodes.

Global namespace for a hierarchical set of file systems

Various embodiments are provided for managing memory for image analysis in a computing environment by a processor. An estimated amount of memory may be reserved for an image analysis job. During a processing of the image analysis job, at least one thread of the image analysis job is partially suspended by restricting the image analysis job from requesting allocation of additional memory upon memory requirements for the image analysis job exceeding the estimated amount of memory. Commensurate with partially suspending the at least one thread, a state of the image analysis job is maintained in the memory notwithstanding the processing of the at least one thread associated with the state is suspended.

Memory management for complex image analysis

In response to an I/O request, a processor reconstructs a file system request by laying out a disk image, performing type-specific introspection on the disk image including determining disk image type and using a file system specific process for a particular type of file system located in the disk image for analyzing the disk image structure.

Disk image introspection for storage systems

The embodiments described herein relate to synchronization of data in a shared pool of configurable computer resources. One or more consistency points are created in a source filesystem. A first consistency point is compared with a second consistency point to detect a directory change at the source filesystem, which includes identifying at least one difference between the first and second consistency points. A file level change associated with an established directory at a target filesystem is identified responsive to the detection of the directory change. A link is established between the source filesystem and the target filesystem, and the established directory is updated based on the file level change.

Synchronizing updates across cluster filesystems

A system facilitates access to data in a network and includes a cache that stores instructions. A processor executes the instructions including: caching processing configured to integrate caching into a local cluster file system, and cache local file data in the cache based on fetching file data on demand from a remote cluster file system. The cache is visible to file system clients as a Portable Operating System Interface (POSIX) compliant file system. Applications execute on a multi-node cache cluster using POSIX semantics via a POSIX compliant file system interface. Data cache is locally and remotely consistent for updates.

Scalable caching of remote file data in a cluster file system

Methods, systems, and computer program products are provided for performing a secure delete operation in a wide area network (WAN) including a cache site and a home site. A method includes identifying a file for deletion at the cache site, determining whether the file has a copy stored at the home site, detecting a location of the copy at the home site prior to a disconnection event of the cache site from the home site, deleting the file from the cache site during the disconnection event, and in response to the secure deletion of the file not being complete during the disconnection event, indicating on a table a remote inode number assigned to the copy associated with the file at the home site, a name under which the copy is saved, and a list of data chunk tuples specifying selected data of the copy to undergo secure deletion.

Secure deletion operations in a wide area network

One embodiment provides a method for re-balancing data and metadata across multiple sub-file systems of a file system. The method includes determining sub-file systems including an amount of data that exceeds a threshold. At least one cell in the sub-file systems is identified as a candidate for re-balancing. A re-balance process is performed on the at least one cell that includes performing a flush operation to flush dirty data from file system buffers, copying an inode table for an independent set of files in the at least one cell to a destination sub-file system, notifying an allocation manager for the destination sub-file system of a new storage pool to manage, and performing an un-quiesce operation on I/O operations to each element in the at least one cell.

Storage space management in union mounted file systems

One embodiment provides a method for storage management in a hierarchical file system. The method includes tracking directories for sub-file systems of the hierarchical set of file systems and maintaining a corresponding directory in a top-file system and a number of symbolic pointers in the corresponding directory which each point from the corresponding directory to a sub-file system where any portion of the tracked directory resides. If available space in a first sub-file system is below a threshold, the system identifies a second sub-file system with available space above the threshold, wherein the first sub-file system contains a first portion of the directory. If a second portion of the directory does not exist in the second sub-file system, the system creates the second portion of the directory in the second sub-file system and creates a link from the first portion of the directory to the second portion of the directory.

Space management for a hierarchical set of file systems

One embodiment provides a method for storage management in a hierarchical file system. The method includes tracking directories for sub-file systems of the hierarchical file system. A request for a unique directory in the hierarchical file system is received. The sub-file system of the hierarchical file system containing the unique directory is provided while ensuring that each directory resides in only one sub-file system. The system also maintains, in a top-file system, a corresponding directory and a symbolic pointer which points from the corresponding directory to a sub-file system where a given directory resides. Creation of new directories in sub-file systems also includes creation of corresponding directories in the top-file system and symbolic pointers from corresponding directory to new directory.

One embodiment provides a method for storage management in a hierarchical file system. The method includes tracking directories for sub-file systems of the hierarchical file system. A request for creation of an additional directory in the hierarchical file system is received. In response to the request, the additional directory is created in a sub-file system of the hierarchical file system while providing that each directory resides in only one sub-file system. If the additional directory is a child directory, the additional directory is created in the sub-file system containing the parent directory of the child directory.

One embodiment provides a method for storage management in a hierarchical file system. The method includes tracking directories for sub-file systems of the hierarchical set of file systems and maintaining a directory while providing the directory is capable of residing in more than one sub-file system within the hierarchical file system. If available space in a first sub-file system is below a threshold, the system identifies a second sub-file system with available space above the threshold, wherein the first sub-file system contains a first portion of the directory. If a second portion of the directory exists in the second sub-file system, the system creates or expands a file in the second portion of the directory, otherwise the system first creates the second portion of the directory in the second sub-file system and then creates a link from the first portion of the directory to the second portion of the directory.

Embodiments of the invention relate to dynamic application migration in a shared pool of configurable computer resources with disaster recovery support. Write operations are executed by an application at a first data site. Data is generated and stored in first data storage local to the first data site. The stored data is replicated from the first data storage to a backup data storage, and a consistency point of the data is created in both the first data storage and the backup data storage. In response to a local hardware failure at the first data site, an unplanned migration protocol is initialized to migrate the application to a second data site remote from the first data site, which includes re-launching the application at the second data site. Data is transferred from the backup data storage to the second data storage local to the second data site from the consistency point.

Consistent data retrieval in a multi-site computing infrastructure

Embodiments relate to supporting transaction data committed to a stable storage. Committed data in the cluster is stored in the persistent cache layer and replicated and stored in the cache layer of one or more secondary nodes. One copy is designated as a master copy and all other copies are designated as replica, with an exclusive write lock assigned to the master and a shared write lock extended to the replica. An acknowledgement of receiving the data is communicated following confirmation that the data has been replicated to each node designated to receive the replica. Managers and a director are provided to support management of the master copy and the replicas within the file system, including invalidation of replicas, fault tolerance associated with failure of a node holding a master copy, recovery from a failed node, recovered of the file system from a power failure, and transferring master and replica copies within the file system.

Write performance in fault-tolerant clustered storage systems

Growing community of inventors

San Jose, CA, United States of America

Renu Tewari