I am working on a load balancer that schedules tasks that communicate over network. I want to test its performance, but I'm struggling to find test data for it. Currently I try to extract relevant data from google-cluster 2019 (https://github.com/google/cluster-data), microsoft azure (https://github.com/Azure/AzurePublicDataset) and alibaba (https://www.alibabacloud.com/blog/594340). Maybe there is already such test data that I can use?

  • $\begingroup$ I'm not sure this is the perfect site for this interesting question. $\endgroup$ Commented Feb 11, 2021 at 8:28
  • $\begingroup$ @YuvalFilmus can you suggest a site where I can ask? $\endgroup$
    – asdfasdf
    Commented Feb 11, 2021 at 11:19
  • $\begingroup$ I'm not sure. Perhaps someone else will have a suggestion. $\endgroup$ Commented Feb 11, 2021 at 11:21
  • $\begingroup$ Even if I had test data (which I don't), how would you know whether it is representative of the type of data you are going to experience in your particular use scenario? I don't think there are any shortcuts; to be useful, you'll probably have to gather data on the kinds of workloads that it will experience when it is used. $\endgroup$
    – D.W.
    Commented Feb 12, 2021 at 3:34


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.