International Business Machines Corporation

Salesforce Com, Inc.

James John Seeger, Jr

Jason Christopher Young

Venkateswararao Jujjuri

Thomas K Clark

Ninad S Palsule

Malahal R Naineni

Stephen F Correl

Richard Sefton Sidle

Adam J Storm

Chandrasekaran Mohan

Steven Robert Pearson

Roger L Q Zheng

Walter Duke Alvey

Boaz Shmueli

Alexei Kojenov

Paul A Dorwin

David Maxwell Cannon

Murthy V Devarakonda

James Patrick Smith

Marc Adam Kaplan

Craig Fulmer Everhart

Patrick James Helland

Sameer Tiwari

Christian Bolik

Toby Lyn Marek

Martine Bruce Wedlake

Michael Wayne Young

David Macnaughton Wolfe

Frank Stewart Filz

David M Wolf

Austin Franky Manuel D'Costa

David Daniel Zimmermann

Provided are techniques for using parallel inserts to insert into a column store. A list of sub-ranges for a columnar table is created. A change statement for one or more rows to be inserted into the columnar table is received. For each of the received change statements, a sub-range from the list of sub-ranges is identified and data is serially inserted into the identified sub-range of the columnar table, while allowing parallel processing of each change statement for different sub-ranges of the columnar table.

Using parallel insert sub-ranges to insert into a column store

Log entries are provided with unique entry identifiers, which may be sequenced in an incremental or decremental order, to create or to update a distributed log which may be replicated and distributed to multiple servers in a network. The entry identifiers may be appended to their respective log entries. Files, records or data which are identified by their respective log entries may be transmitted regardless of the sequence of the entry identifiers.

Coherent distributed logging

A method, apparatus and program storage device for providing real-time file system charge-back accounting with real time historical minimum and maximum usage per user or group during a report cycle. In a first storage area of file system memory, space allocation data for a current accounting period is monitored and persistently maintained. A minimum, maximum and average space allocation is calculated for the management object during the current accounting period. The calculated minimum, maximum and average space allocation for the management object may be moved to a second storage area of the file system memory while beginning to monitor and persistently maintain space allocation data of the management object in the first storage area of the file system memory during a subsequent accounting period.

Real-time file system charge-back accounting per management object during a report cycle

There is provided, in a computer processing system, an apparatus for managing object data. The apparatus includes a changed objects manager for creating and managing a changed objects list that at least identifies the objects that have changed based on time of change. The changed objects list is associated with a plurality of time buckets. Each of the plurality of time buckets is associated with a respective date and time period and with object change records for objects having a timestamp falling within the respective date and time period. Each of the object change records is associated with a unique object identifier and the timestamp for a corresponding one of the objects. The timestamp specifies a date and a time corresponding to a latest one of a creation time or a most recent update time for the corresponding one of the objects.

Changed files list with time buckets for efficient storage management

A technique for implementing policy-aware backup and restore capability in a tiered storage system. If a data set's contents are backed up from the tiered storage system to a backup storage system, metadata for the data set may also be backed up. Prior to the data set being restored from the backup storage system to the tiered storage system, the backed up metadata is restored and processed to determine a tier among the tiered storage pools to which the data set will be restored.

Restoring a file to its proper storage tier in an information lifecycle management environment

File system objects of unknown type are backed up and restored. A list of file system objects is received from a file system. The file system objects are to be backed up. For each file system object that has a file type that is unknown, the following is performed. First, the file system is queried to obtain information regarding the file system object that is sufficient for the file system to later recreate the file system object if necessary. Second, the file system object and the information regarding the file system object are stored. Examples of file system object types of the file system that may be unknown to an application running on a Microsoft Windows&#xae; operating system include symbolic links, named pipes, and special device files.

Backup and restore of file system objects of unknown type

A method and system for allocating blocks of disk in persistent storage to requesting threads. A primary data structure is provided for organizing and categorizing blocks of disk space. In addition, a secondary data structure is provided for maintaining a list of all active file system processes and blocks of disk space used by those processes. Blocks of disk space are assigned to pages. At such time as a thread may request allocation of disk space, both data structures are reviewed to determine if the requested disk space is available and to limit access of available disk space to a single page of memory to a single thread at any one time.

Disk space allocation

A method, system, and article of manufacture, wherein a plurality of references to a plurality of files corresponding to a plurality of devices are stored in a data structure implemented in a computational device, wherein the computational device is coupled to the plurality of devices via a network. Access is enabled to the data structure to a distributed application, wherein the distributed application uses a stored reference in the data structure to determine a file corresponding to a device, and wherein the distributed application performs data transfer operations with the device via the determined file.

Method, system, and article of manufacture for storing device information

Provided are techniques for determining whether content of an object has changed. Under control of a backup system, opaque object attributes and a data identifier are received, wherein the data identifier is generated based on one or more relevant object attributes of the opaque object attributes that indicate whether at least one of the content of the object and one or more of the relevant object attributes has changed. The received data identifier is compared with a previously stored data identifier. In response to determining that the received data identifier and the previously stored data identifier do not match, it is determined that the content of the object has changed.

Controlling incremental backups using opaque object attributes

A method and system for managing availability of a dependent thread to service a nested request is provided. A plurality of reply threads are maintained in a single thread pool. In addition, a counter is provided to track availability of a reply thread from the thread pool. A service thread that requires at least one reply thread to complete execution of a request must check the counter to determine availability of the reply thread prior to execution of the request. The process of determining availability of a reply thread prior to execution of a service thread request avoids initiating execution of a request that cannot be completed in a timely manner, or at all.

Managing a nested request

Techniques are provided for processing an Input/Output (I/O) request. At least one data block is allocated for use in completing the I/O request. A current operations record is stored for the I/O request. It is determined whether the I/O request has been completed within a specified period of time. In response to determining that the I/O request has not been completed within the specified period of time, the allocated at least one data block is fenced.

System and article of manufacture for fencing of resources allocated to non-cooperative client computers

A process for quiescing a master (master) and a plurality of subordinate computer systems (subordinates) in a cluster. An original or a pending state may be entered that is a quiesce or an online state. The master instructs the subordinates the quiesce or online state be made the pending state. The subordinates prepare to change accordingly, determine whether successful, and vote to commit or abort. Based on whether all voted to commit, the master instructs the subordinates to either commit or abort. If to commit and the pending state is the quiesce state, an operation is performed in the subordinates. If to commit and the pending state is the online state, the subordinates prepare to resume the original state. The subordinates change from the original to the pending state. Otherwise, if to abort, the subordinates prepare to remain in the original state and reset the pending to the original state.

Coordinated quiesce of a distributed file system

Provided are a system and program maintaining information on a namespace comprised of filesets shared by clients over a network. Zone information is maintained on at least one zone, wherein each zone associates at least one client system, at least one fileset, and at least one storage pool. For one zone, the associated at least one fileset and at least one storage pool are accessible to the at least one client system. Clients are provided information on filesets included in a namespace, wherein each of a plurality of clients receive information on the at least one fileset associated with the client in the at least one zone including the client.

Growing community of inventors

Portland, OR, United States of America

James John Seeger, Jr