News Column

"Enhancing Analytics Performance Using Distributed Multi-Tiering" in Patent Application Approval Process

July 8, 2014



By a News Reporter-Staff News Editor at Information Technology Newsweekly -- A patent application by the inventors Gupta, Karan (San Jose, CA); Pucha, Himabindu (San Jose, CA); Sarkar, Prasenjit (San Jose, CA), filed on December 14, 2012, was made available online on June 26, 2014, according to news reporting originating from Washington, D.C., by VerticalNews correspondents.

This patent application is assigned to International Business Machines Corporation.

The following quote was obtained by the news editors from the background information supplied by the inventors: "Embodiments of the invention relate to an architecture addressing limitations in shared nothing clusters. More specifically, this invention implements cluster-centric tiered storage with a flexible tier definition to support performance of transactions.

"A shared nothing computer cluster is a distributed computing architecture where each computer node is independent and tasks are divided between computers. No one computer node in the cluster has to wait for another computer node in the cluster to perform a task. In other words, there is no single point of failure, as known in a storage area network.

"Each node in the shared nothing cluster has some form of data storage, including volatile and persistent. As data is created, it is stored in at least one data storage location, including volatile and/or persistent. The goal in storing data is to decrease the response time to read that data in support of a read transaction. Different formations of the data storage have different levels of performance, and are generally arranged in some form of a hierarchy so that frequently accessed data may be present on a faster form of memory than infrequently accessed data."

In addition to the background information obtained for this patent application, VerticalNews journalists also obtained the inventors' summary information for this patent application: "A method, system, and computer program product are provided for optimizing placement of data in a multi-tier storage system in a shared-nothing computer cluster.

"In one aspect, a method is provided for placing an object in a storage tier within the multi-tier system. A computer cluster is provided in communication with a storage system organized in a hierarchy, with different roles assigned to each storage tier within the hierarchy while supporting global management of the storage tiers across the computer cluster. Management of the storage tiers takes place responsive to a flexible tier definition within the hierarchy. As an object is designated for placement in data storage, a tier within the hierarchy is selected responsive to the flexible tier definition. Placement of new data within the hierarchy is based on an evaluation to minimize system runtime in response to an access request.

"In another aspect, a computer program product is provided to optimize placement of an object in a shared-nothing computer cluster having multi-tiered storage. A computer-readable medium is provided with program code executable by a processor. When executed, the program code organizes a storage system within the cluster in a hierarchy. The organization includes assigning different roles to storage tiers within the hierarchy. Program code is provided to address a flexible tier definition provided within the hierarchy, and to place one or more objects in a select storage tier within the hierarchy responsive to the flexible tier definition. The location of object placement in the hierarchy is optimized in response to an access request. Program code is also provided to place new data within the hierarchy so that system runtime is minimized. This includes optimization of an object in response to an access request. Accordingly, the computer program product recognizes the hierarchy of the storage system, and utilizes the different roles of the tiers within the hierarchy for placement of data

"In yet another aspect, a system is provided with a shared-nothing computer cluster having a storage system organized into a hierarchical structure; the storage system having a flexible tier definition within the hierarchical structure. At least two computer nodes are provided in the computer cluster and in communication with the storage system. Each tier in the storage system hierarchy is assigned a different role. A functional unit is provided in communication with the storage system and includes tools to manage an object within the hierarchy. The tools include, but are not limited to, a placement manager and a computation manager. The placement manager functions to place one or more objects in a select storage tier in the hierarchy responsive to the flexible tier definition, and the computation manager computes new data placement within the hierarchy to minimize system runtime. The computation manager further optimizes the location of an object in response to an access request. Accordingly, one or more objects are intelligently managed within the hierarchy to optimize the efficiency of the storage system.

"Other features and advantages of this invention will become apparent from the following detailed description of the presently preferred embodiment of the invention, taken in conjunction with the accompanying drawings.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

"The drawings referenced herein form a part of the specification. Features shown in the drawings are meant as illustrative of only some embodiments of the invention, and not of all embodiments of the invention unless otherwise explicitly indicated. Implications to the contrary are otherwise not to be made.

"FIG. 1 depicts a cloud computing node according to an embodiment of the present invention.

"FIG. 2 depicts a cloud computing environment according to an embodiment of the present invention.

"FIG. 3 depicts abstraction model layers according to an embodiment of the present invention.

"FIG. 4 is a block diagram illustrating a storage system hierarchy for a cluster.

"FIG. 5 depicts a flow chart illustrating a method for choosing an instance of an object with minimum predicted fetch latency.

"FIG. 6 depicts a flow chart illustrating a method for evicting an object from a tier.

"FIG. 7 depicts a flow chart illustrating a method for skipping a tier upon eviction and placement of an object in a different tier.

"FIG. 8 depicts a flow chart illustrating a method for demoting an object to a different tier.

"FIG. 9 is a block diagram illustrating a system for a multi-tiered cluster having optimized data storage placement."

URL and more information on this patent application, see: Gupta, Karan; Pucha, Himabindu; Sarkar, Prasenjit. Enhancing Analytics Performance Using Distributed Multi-Tiering. Filed December 14, 2012 and posted June 26, 2014. Patent URL: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&u=%2Fnetahtml%2FPTO%2Fsearch-adv.html&r=600&p=12&f=G&l=50&d=PG01&S1=20140619.PD.&OS=PD/20140619&RS=PD/20140619

Keywords for this news article include: Information Technology, Information and Data Storage, International Business Machines Corporation.

Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2014, NewsRx LLC


For more stories covering the world of technology, please see HispanicBusiness' Tech Channel



Source: Information Technology Newsweekly


Story Tools






HispanicBusiness.com Facebook Linkedin Twitter RSS Feed Email Alerts & Newsletters