International Business Machines Corporation

Scott Dennis Helt

Kristopher Craig Whitney

Gary Ross Ricard

Kiswanto Thayib

Glen Warren Nelson

Kevin Curtis Griffin

David Andrew Jones

Jennifer Anne Dervin

Mark Philip Piazza

Robert Dennis Miller

Balakrishna Raghavendra Iyer

Mark John Anderson

Yun Bj Wang

Michael James McDermott

Thomas Paul Giordano

Thuan Quang Bui

Philip M Albu

Curtis D Schemmel

Shauna Rollings

Micahel John Groeschel

Rebecca Nan Brady Legler

Embodiments of the present disclosure provide techniques to vary on and vary off databases simultaneously across a pair of nodes in a mirroring environment. A dual vary off operation is initiated at a first node of the pair of nodes, the dual vary off operation to be performed on copies of a database respectively stored on the pair of nodes, the operation to be performed in tandem with the second node. At the first node the copy of the database stored on the first node is informed of the dual vary off operation, and an operating system of the first node is also informed of the dual vary off operation. Upon receipt at the first node of an indication from the second node that it has completed its vary off operation, the first node completes the dual vary off operation. An analogous technique is performed for a dual vary on operation.

Ability to vary on and vary off databases simultaneously across two systems

Techniques for warm cloning of computing nodes are provided. A request to clone a first computing node is received. Upon determining that a first transaction of a plurality of transactions is ongoing, a first moment in time when data associated with the first transaction was coherent on the first computing node is identified. Tracking data related to the first transaction is collected, beginning at the first moment in time. Further, a first storage associated with the first computing node is copied to a second storage associated with a second computing node, where the first transaction continues during the copying. The tracking data related to the first transaction is then transmitted to the second computing node.

Coherent cloning of active compute nodes

In embodiments, the ability to have two separate Db2 Mirror pair environments, each providing HA, which have the capability to switch application spaces between the Db2 Mirror pairs, is presented. At least one IASP is registered to a first node of a first pair of nodes at a first HA mirroring environment at a first location. The at least one IASP is replicated to a second HA mirroring environment, the second HA mirroring environment including a second pair of nodes at a second location, the second location different than the first location. The at least one IASP is registered with one node of the pair of nodes of the second mirroring environment, the at least one IASP is switched offline at the first pair of nodes of the first mirroring environment, and subsequently switched online at the second pair of nodes of the second mirroring environment.

Ability to move application spaces between two separate independent high availability (HA) environments

A method backs up computer data by organizing update requests into groups. All update requests in one group complete concurrently before requests of a subsequent group complete.

Asynchronous hybrid mirroring system

An apparatus and method provides the capability of mirroring storage from a primary system to a mirrored system in a way that uses parallelism in the mirrored system to maximize the efficiency of writing data to the mirrored storage for operations that do not conflict while serializing operations that do conflict. The mirroring of the present invention is 'logical mirroring', which does not require identical disk drives, and which supports mirroring between geographically remote locations to protect against catastrophic site failure. Parallelism is achieved in the mirrored system by dividing the virtual address space into multiple ranges, and by assigning a group of tasks to each range. When an operation is received on the mirrored system, the virtual address range that the operation affects is determined, and the operation is then delegated to the task group that corresponds to the affected virtual address range. By dividing the virtual address space into ranges, tasks in different ranges (i.e., in different task groups) may execute in parallel without any threat of conflict, and even tasks within the same range may execute in parallel if they operate in different portions of the range.

Apparatus and method for writing data to mirrored storage using multiple tasks working in parallel

An apparatus, program product and method for estimating the number of keys within an index key range over an index using page pointers to pages in the index comprises a program configured for scanning the index, from a divergence point of the key range, until a page pointer is found and incrementing a counter for each found page pointer. The program is further configured for determining if the page pointer points to a leaf page in the index, and if it does, continuing the scan to find the next page pointer without going to the corresponding leaf page. Otherwise, the program continues the scan to find the next page pointer and continues the scan for page pointers and increments the counter until the index is scanned for the entire key range. Upon completion of the scan, the program determines an estimate of the number of keys utilizing the counter.

Apparatus, program product and method for estimating the number of keys within an index key range

A method for partitioning keys onto radix tree logical pages and a parallel index page build algorithm in order to provide radix tree build speedup proportional to the number of processors on the system and controlled efficient page utilization. Also, since keys are intelligently partitioned so that a complete set of keys is inserted into a logical page, there is no page overflow during the tree construction and thus page splitting is eliminated. Since radix index trees are really groups of logical pages in which each logical page contains a small tree, the tree is built (with respect to the logical pages) from the bottom up, while within each individual logical page the tree is constructed from the top down. The space required for a logical page is pre-allocated to allow construction of limbs to begin without waiting for the build of their underlying pages to complete.

Parallel bottom-up construction of radix trees

Growing community of inventors

Rochester, MN, United States of America

Scott Dennis Helt