News Column

Patent Issued for Snapshot Based Replication

February 4, 2014



By a News Reporter-Staff News Editor at Information Technology Newsweekly -- International Business Machines Corporation (Armonk, NY) has been issued patent number 8635421, according to news reporting originating out of Alexandria, Virginia, by VerticalNews editors.

The patent's inventors are Gupta, Karan (San Jose, CA); Haskin, Roger L (Morgan Hill, CA); Sarkar, Prasenjit (San Jose, CA); Subhraveti, Dinesh K. (Milpitas, CA).

This patent was filed on July 16, 2012 and was published online on January 21, 2014.

From the background information supplied by the inventors, news correspondents obtained the following quote: "This invention relates to data storage in a computer system environment. More specifically, the invention relates to data replication and block allocation in a file system to support read and write transactions.

"A data storage block or a storage block, herein after referred to as a block, refers to specific areas of address space on a storage device. For example, one data block may be a collection of sectors or bytes in an area of disk space. Blocks are manipulated as units. Large block allocations allow a large amount of data to be retrieved in a single I/O transaction. In one embodiment, a block is a fixed-size unit of data that is transferred together. A file system is a collection of file data maintained by an implementation that stores, organizes, and maintains file data in a file and/or directory hierarchy. File systems employ techniques to write data to storage media using block allocation techniques. Typically, a storage system provides access to information that is stored on one or more storage devices connected to the storage system. Access to the information is possible by organizing the storage devices into volumes, which logically organize the information stored on the storage devices.

"The storage system may be further configured to operate according to a client/server model of information delivery to thereby allow many clients to access data containers stored on the system. In this model, the client may employ an application, such as a database application, executing on a computer that connects to the storage system over a computer network. Each client may request the services of the storage system by issuing file-based protocol messages to the system over the network. A plurality of storage systems may be interconnected to provide a storage system environment configured to service many clients. Each storage system may be configured to service one or more volumes, wherein each volume stores one or more data containers."

Supplementing the background information on this patent, VerticalNews reporters also obtained the inventors' summary information for this patent: "This invention comprises a method for pipelining replication of data across a cluster file system.

"In one aspect, a method is provided for writing multiple copies of data across servers of the cluster file system. Initially, a first copy of data is written from a client machine to a first data storage local to a first server node in the cluster. Replication of the first copy of data is pipelined from the first server node to a second and third server node. The pipeline replication process includes allocation of storage space. More specifically, storage for a second copy of the data is allocated on a second data storage local to the second server node, and storage for a third copy of the data is allocated on a third data storage local to the third server node. Following the allocation of storage, population of the first copy of the data is scheduled on the second data storage and the third data storage based upon network characteristics.

"In another aspect, a method is provided for writing multiple copies of data across servers of the cluster file system. A first copy of data is written to a first data storage local to a first server. Storage is then allocated in the system for both a second copy of the data and a third copy of the data. More specifically, the second copy of the data is allocated on data storage local to a second server and the third copy of the data is allocated on data storage local to a third server. Following the data allocation, replication of the first copy of the data is pipelined on both the second and third servers, which are populated with the first copy of the data with respect to network characteristics.

"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."

For the URL and additional information on this patent, see: Gupta, Karan; Haskin, Roger L; Sarkar, Prasenjit; Subhraveti, Dinesh K.. Snapshot Based Replication. U.S. Patent Number 8635421, filed July 16, 2012, and published online on January 21, 2014. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=16&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=765&f=G&l=50&co1=AND&d=PTXT&s1=20140121.PD.&OS=ISD/20140121&RS=ISD/20140121

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