Cluster Storage

Cluster Storage Consulting Services

An essential building block for any Data Grid infrastructure is the storage server. The model of Grid referred to is a collection of clusters located in supercomputing centers or high performance computing labs with high speed connectivity to regional or national backbones such as the Internet2. Some of the clusters are used for computation, while others are dedicated to data storage following distributed data manipulation models proposed by the Data Grid community. The specific requirements that need to be addressed are large cluster-to-cluster throughput, high I/O performance delivered to the application, scalable disk bandwidth, good matching of disk and network throughput.

For the latest information about Cluster Storage

Cluster Storage Overview

By leveraging the high-speed communication afforded by the Cluster Storage interconnect, large files can be stored in a scalable fashion by striping the data across multiple nodes. With single disk capacities of 160 GB and prices as low as $1/GB, 10 TB of disk storage can be added to a small cluster for less than $10,000. At the current rate growth of disk size, inexpensive 50-100 TB clusters will be realistic in another year or so. By distributing the disks across a sufficient number of cluster nodes, aggregate bandwidth in excess of 1 GB/s can be easily obtained with current hardware, a two orders of magnitude improvement over single disk performance.

For the latest information about Cluster Storage Overview

Who uses Cluster Storage

Data-intensive applications constitute an increasing share of high performance computing (HPC). An increasing number of applications in domains such as genomics/proteomics, astrophysics , geophysics , computational neuroscience , or volume rendering , need to archive, retrieve, and process increasingly large datasets. These applications are prime candidates for Grid computing as they involve remote access and extensive computation to many data repositories. The concept of cluster-based server has already been proposed in connection with specific domains of applications such as video servers and Internet data caches for large dataset acquisition.

For the latest information about Who uses Cluster Storage