Dear Zhou, Thanks for your interest in CloudSuite. Let me take this opportunity to inform you about the release of CloudSuite 3.0. We have a new website (cloudsuite.ch<http://cloudsuite.ch>), modified & updated benchmarks, and we now also offer Docker images for all workloads, to ease deployment.
Now, to answer your question: most of CloudSuite benchmarks operate on real-world data. Specifically for the workloads you mentioned (Data Analytics and Data Caching) we use crawled Wikipedia pages and a Twitter dataset, respectively. However, the applications are not bound to a specific dataset. If you have a different dataset that you would like to use, it should not be hard to make the change. You just have to make sure that the input format is compatible. Finally, if you find a publicly available dataset which you believe would be more representative for some of the CloudSuite applications, please don’t hesitate to let us know. The benchmarks are also available on GitHub, so you can directly open issues or directly contribute to CloudSuite. All feedback is welcome. Regards, Alex On Jan 15, 2016, at 6:26 AM, 周子博 <[email protected]<mailto:[email protected]>> wrote: Dear Sir or Madma, I am learning to use cloudsuite these days. When I have finished installing the hadoop, mahout, memcached. I try to download some cloud resource request information data in the real network for the further study , from like facebook or twitter. I was told that Facebook announced some of their data in 2012 for research, it can be downloaded by cloudsuite, how can I download it? If the mentioned above is not true, how can I get some data from the real network by using cloudsuite? Thank you very very very much. Yours , Zhou
