Dear John,I'll submit the final result in the coming week.BTW, my name is Ruibo, not Rubio. Thank you.It seems that the mail list here is not very active. Are you using the slack to communicate with each other? If so, please update the slack invitation link in your web page. That is not active now.Ruibo WangJohn Bent <johnbent@gmail.com> 于2019年11月2日周六 上午7:38写道:Hello Rubio,Thank you for your email. We look forward to your submission and will conduct our analysis of the "shift" effects once all SC19 submissions have been received.Thanks,The IO500 CommitteeOn Wed, Oct 30, 2019 at 10:03 PM Ruibo Wang via IO-500 <io-500@vi4io.org> wrote:_______________________________________________Dear All,I've built a cluster to test the IO500 benchmark.The preliminary results showed that the new "shift" parameter did influence the stat result badly.If I use "-N" parameter, the mdtest result is:mdtest_easy_stat 1429.930 kiops : time 253.86 secondsmdtest_hard_stat 962.500 kiops : time 191.10 secondsIf I don't use "-N" parameter, the mdtest result is:mdtest_easy_stat 200250.000 kiops : time 1.84 secondsmdtest_hard_stat 51038.200 kiops : time 4.47 secondsIt is clear that the "shift" parameter change will impact the stat result with the same hardware and software configuration. Now I'm still trying to optimize the test. Hope I'll deliver a better result later.Ruibo Wang
IO-500 mailing list
IO-500@vi4io.org
https://www.vi4io.org/mailman/listinfo/io-500