As data centers have increased in size, there has been a need to create clusters out of cheaper, more affordable commodity parts that can easily be replaced upon failure, and that create more affordable data centers overall. However, such large clusters are still outside of feasibility for individuals and small businesses. It is a worthwhile exercise to see if much smaller clusters could be created for such applications, and to compare their performance / price measure to that of the previous traditional data centers. For this paper, such a cluster is created using Raspberry Pis which are small-sized, single-board computers. A data sharing model is built in Python using message passing interface (MPI) that ran on the cluster of the four Raspberry Pis. So as to evaluate the performance of the system, some greedy algorithms are created. During the implementation process, previously unknown skills, including how to create a cluster, programming the infrastructure are learnt.
- raspberry Pi
- parallel processor