Due to the ever-widening performance gap between processors and disks, I/O operations tend to become the major performance bottleneck of data-intensive applications on modern clusters. CEFT-PVFS (a RAID 10 style parallel file system that extends the original PVFS), as one such system, divides the cluster nodes into two groups, stripes the data across one group in a round-robin fashion, and then duplicates the same data to the other group to provide storage service of high performance and high reliability. This paper presents another benefit of CEFT-PVFS in which the aggregate peak read performance can be improved by as much as 100% over that of the original PVFS by exploiting the increased parallelism.
Did you find this white paper useful?
24 out of 50 users found this white paper useful
Related white papers
Massively Scalable NAS - Pre-Empting Tomorrow's Data Overload with Today's Technology
HP is launching the HP StorageWorks 9100 Extreme Data Storage System that solves challenges such as extreme scability, manageability and affordability and creates new business opportunities. HP is going to...
Texas Tech University Performs Stock Price Analysis in Hours Instead of Days
Texas Tech University (TTU) developed statistical resampling methods to determine whether announcements and other historical events affect stock prices. TTU deployed a SAS compute grid to optimize resources campus-wide. TTU...
Deutsche Bank's Securities Custody Reporting System - Technical Details
Deutsche Bank's Securities Custody System is among the earliest examples of successfully using grid computing for large-scale financial data processing. Base One began developing its grid and cluster computing software...
The Write Solution
Founder of Australian Corporate Writing, Keir Wells, was looking for a secure and powerful computing solution that was also reliable, flexible, and easy and cost-effective to administer. Keir Wells chose...
Bank of Montreal Banks on Sun for Risk Analysis
BMO Financial Group is one of the largest financial services provider in North America. Their challenge was to give Bank of Montreal's Market Risk Assessment Group the power to run...
Gartner: Mastering Master Data Management
Despite vendor claims, master data management (MDM) has more to do with governance, process, data quality, metadata management, and stewardship than simply technology. Download this Gartner white paper to learn the...
IBM Energy Efficiency Self-Assessment Tool
How energy-efficient is your data center? This self-assessment tool is designed to identify areas where you can improve the operational effectiveness of your systems. Take the Energy Efficiency Self-Assessment now.
