News Column

Patent Application Titled "Cache Layer Optimizations for Virtualized Environments" Published Online

May 6, 2014



By a News Reporter-Staff News Editor at Information Technology Newsweekly -- According to news reporting originating from Washington, D.C., by VerticalNews journalists, a patent application by the inventors Hildebrand, Dean (Sumas, WA); Povzner, Anna S. (San Jose, CA); Tewari, Renu (San Jose, CA), filed on October 15, 2012, was made available online on April 24, 2014.

The assignee for this patent application is International Business Machines Corporation.

Reporters obtained the following quote from the background information supplied by the inventors: "The present invention relates to cache data storage. More specifically, the invention relates to a method, system, and computer program product for optimization of cache data storage across a system of virtual machines.

"With the rapid development of server workload virtualization, there exists a demand for effective caching in storage systems. Caching can reduce the latency of systems as well as increase the input and output operations per second. Caching is considered to be effective when items placed in the cache have a greater likelihood of access than data placed in persistent storage. Virtual machines cache data in their own operating system caching layer. This cached data is often stored both in the virtual machine as well as in a remote storage system. As a result, cached data, especially data cached on read requests, is almost always accessed from the cache of the virtual machine and is likely never accessed from the storage system cache.

"While the virtualization of data centers offers increased support for applications, these data centers are restricted by a limited quantity of server memory. Specifically, as the number of virtual machines in a system increases, there is an increased pressure placed on shared storage arrays. In larger systems, while the individual memory of a virtual machine is typically smaller than the memory of a storage system, the total memory of all virtual machines in the system is greater than the memory of the storage system.

"Virtual machines are unique in that each virtual machine accesses its own disk image data, and while a virtual machine may access common data blocks in the server storage system via de-duplication and cloning, it does not share its data across other virtual machines. Consequently, the storage system cache can end up thrashing; caching and evicting data before it is even accessed a second time. This thrashing is wasteful and possibly detrimental by evicting shared data to make room for unshared and unaccessed data."

In addition to obtaining background information on this patent application, VerticalNews editors also obtained the inventors' summary information for this patent application: "This invention comprises a method, system, and article for optimization of a cache storage layer of a data storage system.

"In one aspect, a method is provided for optimizing a cache storage layer of a storage system. More specifically, a method is provided for classifying the cache storage layer into at least two sections, including a primary cache section and a secondary cache section. Blocks of data are differentiated based on an inherent sharing characteristic of the data block. The optimized cache storage layer is utilized responsive to the inherent characteristic of the data block. More specifically, one or more data blocks are selectively placed into one of the classified sections of the cache storage layer based on the characteristics of the data block(s). The placement of the data blocks reflects sharing of the data blocks among virtual disk images access by virtual machines.

"In another aspect, a system is provided having a storage system with an optimized cache storage layer. The storage system includes a cache layer and persistent storage. The cache layer is separated into two sections, including a primary cache section and a secondary cache section. A functional unit is provided in communication with one or more tools to optimize read and write transactions with the cache layer. The tools include, but are not limited to, an identification manager and a placement manager. The identification manager differentiates blocks of data based on an inherent sharing characteristic of the data block. The placement manager places one or more data blocks into one of the classified sections of the cache layer based on the differentiation placed on the blocks by the identification manager. More specifically, the placement of the data blocks into one of the classified sections of the cache layer reflects a sharing characteristic of the data blocks.

"In yet another aspect, a computer program product is provided for optimization of a cache layer. The computer program product comprises a computer readable storage medium having program code embodied thereon. The program code is executable by a processor to optimize a cache storage layer in a storage system, and to store blocks of data responsive to the optimization. More specifically, the program code classifies the cache layer into a primary cache section and a secondary cache section. The program code differentiates blocks of data based on an inherent sharing characteristic of the data block. The program code utilizes the optimized cache storage layer responsive to the inherent characteristic of the data block. More specifically, the program code places one or more data blocks into one of the classified sections of the cache storage layer with the placement of the data blocks reflecting sharing of the data blocks among virtual disk images accessed by virtual machines.

"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.

"FIG. 1 is a flow chart illustrating a method for the placement of data into storage, including persistent and volatile storage sections.

"FIG. 2 is a flow chart illustrating a method for classifying data in storage responsive to a write transaction.

"FIG. 3 is a flow chart illustrating a method for accessing read data responsive to a read transaction.

"FIG. 4 is a flow chart illustrating a method for accessing data responsive to a read transaction.

"FIG. 5 depicts a cloud computing node according to an embodiment of the present invention.

"FIG. 6 depicts a cloud computing environment according to an embodiment of the present invention.

"FIG. 7 depicts abstraction model layers according to an embodiment of the present invention.

"FIG. 8 depicts a block diagram illustrating tools embedded in a computer system to support optimization of a cache storage layer, and read and write transactions responsive to the optimized cache storage layer for use within a shared pool of resources."

For more information, see this patent application: Hildebrand, Dean; Povzner, Anna S.; Tewari, Renu. Cache Layer Optimizations for Virtualized Environments. Filed October 15, 2012 and posted April 24, 2014. Patent URL: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&u=%2Fnetahtml%2FPTO%2Fsearch-adv.html&r=548&p=11&f=G&l=50&d=PG01&S1=20140417.PD.&OS=PD/20140417&RS=PD/20140417

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