Most Read Latest News Blog Resources

Rekindling a GemFire


Distributed data manager sees cache, partitioning updates



November 15, 2007 — 
There’s been so much talk about the ways application development has to evolve in the modern era of multicore hardware and virtualized systems that it’s easy to forget data has its own issues to consider. This gets especially tricky as companies seek to build distributed, resilient data architectures as part of a next-generation disaster recovery scenario.

GemStone Systems announced on Oct. 30 the release of GemFire Enterprise 5.1, a distributed operational data management infrastructure that allows data sharing and event distribution in environments where clustered application processes need reliable and secure access to back-end data sources.

GemStone architect Jags Ramnarayan explained that the large number of variables inherent to distributed systems significantly increase the possibility of error. Such stress-inducing points range from missed event notification to data consistency failures, all the way to application, operating system or hardware failure.

GemStone claims to have improved the redundancy of data partitioning in GemFire Enterprise 5.1 by allowing multiple levels of redundant data. The partitioned data regions can be managed with user-defined policies, allowing events to be properly ordered without requiring locks or similar steps. This, the company claims, allows all data updates to be fed through the primary partition, for a balanced memory usage profile.

Evening Out Events
Event delivery is important in a clustered data environment, and GemFire Enterprise uses distributed event notification to permit the even spread of updates across a data grid for event processing. It also allows the use of Object Query Language as a way to execute “scatter-gather” algorithms.

Users can control the way a workload is spread across the system, parallelizing data traffic to peers in an attempt to provide better throughput with multihomed nodes. So-called “lazy” connections are also possible.

The persistence implementation is designed to allow every operation to be recorded, with log files designed to roll over at a configured size. The system also pulls log files back together to reclaim disk space, which the company claims results in a 50 percent gain in throughput for synchronous persistence, and full 100 percent gain for asynchronous persistence.

GemFire Enterprise 5.1 also implements new native C++/C# client cache behaviors designed to enhance data sharing and cross-application collaboration, important in today’s distributed environments. Since objects in the cache aren’t always the same size, it’s possible for a client cache to become fragmented; the GemFire update implements heap LRU (least recently used) algorithms at the cache level to alleviate this.

GemFire clients execute queries on the server side and are subscribed to event notifications; according to the company, this keeps client-side performance from bottlenecking the cache server and impeding a data grid’s ability to scale.


Share this link: http://www.sdtimes.com/link/31373
 

Add comment


Name*
Email*  
Country     


  • Comment
  • Preview
Loading



 
 
 
 
News on Monday
more>>
SharePoint Tech Report
more>>


   

 
 
Download Current Issue
ISSUE 3/15/2010 PDF

Need Back Issues?
DOWNLOAD HERE

Receive the print Edition?


 
blogs tab
Google Code turns 5
Google Code Turns 5, and adds a Paxos Algorithm to make the system more stable and reliable.
03/17/2010 11:16 AM EST

Test your Visual Studio 2010 know-how
Microsoft is offering free beta certification exams for Visual Studio 2010.
03/17/2010 11:08 AM EST

Microsoft lifts the hood on IE9
Microsoft is previewing IE9.
03/16/2010 01:10 PM EST

 

Events calendar tab
3/22/2010 to 3/25/2010
Santa Clara, Calif.
The Eclipse Foundation

4/12/2010 to 4/14/2010
Las Vegas
Penton Media

4/12/2010 to 4/15/2010
Santa Clara, Calif.
O'Reilly Media

4/19/2010
New York City
Flagg Management

4/25/2010 to 4/28/2010
Overland Park, Kans.
IIUG