Re: [IO-500] github

Thank you John and everybody for the feedback. Just to mention my script is far from final version. I plan to invest some time later on July to finish a first version. Personally I would be happy to have a first version 1st September. It does not mean that it will contain all the advanced features. Some of them they could be included in the extended version. Just my concerns as that I would like to be able to see all the issues gathered and GitHub helps. I know that even if we finish a first version there will be some issues with more weird file systems (I will address the Cray DW) extra code, we need to add some modifications for special requirements that maybe some sites have. DDN IME needs to recompile for example and for native mode modify the file path etc. At one point we will need your support to execute the benchmark on more weird configurations, if you have one, and give us feedback, of course modify if you want, and push back to GitHub. This way the benchmark will support many platforms fast. However, for the most basic file systems the benchmark should work straight forward. I suppose we need a calibration tool for using appropriate file size regarding execution duration etc. We could integrate a tool in IOR to start calibration with a special flag and using same number of MPI processes and same reservation. This way we avoid to maintain two codes. Best regards, George Sent from my iPhone ________________________________ This message and its contents including attachments are intended solely for the original recipient. If you are not the intended recipient or have received this message in error, please notify me immediately and delete this message from your computer system. Any unauthorized use or distribution is prohibited. Please consider the environment before printing this email.