Multiple Diskless-based PC Clusters with Condor Schedulers to Form Grid Computing Environments
碩士 === 東海大學 === 資訊工程與科學系 === 94 === In this thesis, we introduce our experiments on implementing multiple diskless PC clusters to form a grid computing environment. We construct a grid environment in a more efficient way, and use those PCs which have not been used all the time. First, we construct t...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2006
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/10699983040875864392 |
| Summary: | 碩士 === 東海大學 === 資訊工程與科學系 === 94 === In this thesis, we introduce our experiments on implementing multiple diskless PC clusters to form a grid computing environment. We construct a grid environment in a more efficient way, and use those PCs which have not been used all the time. First, we construct three kinds of diskless PC clusters to evaluate the system performance. Matrix multiplication program and bioinformatics software are used to evaluate the computing performance. Then, SPM2 and ntop are used to monitor the system status during applications running to find out the difference of performance between those diskless PC clusters.
We construct four DRBL PC clusters. The IP addresses of slave nodes in each cluster are private. We install Globus Toolkit 4.0.1 and Condor 6.6.10 on the master node of each cluster. All the clusters can be merged into one powerful grid environment. The only restriction is that the job only can be submitted to a single cluster. It can not be run over two or more PC clusters simultaneously. To utilize the computing power, we propose a jobs allocation strategy for program execution. We use HPL to conduct some performance evaluations and analyze those data to form a formula. Users only need to decide how many processors need to be used. The information server will calculate the value of computing power based on our formula and find the most appropriate cluster to execute the job. It can make our grid environment execute the jobs in a more efficient way. We also use Heartbeat technology to make sure that our computer classroom can switch to grid environment in any situations.
|
|---|