[GitHub] [arrow] mayuropensource commented on pull request #7022: ARROW-8562: [C++] IO: Parameterize I/O Coalescing using S3 metrics

2020-05-01 Thread GitBox
mayuropensource commented on pull request #7022: URL: https://github.com/apache/arrow/pull/7022#issuecomment-622581788 thank you @wesm This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [arrow] mayuropensource commented on pull request #7022: ARROW-8562: [C++] IO: Parameterize I/O Coalescing using S3 metrics

2020-04-25 Thread GitBox
mayuropensource commented on pull request #7022: URL: https://github.com/apache/arrow/pull/7022#issuecomment-619456016 A better calculation for bandwidth (by removing TTFB from total time) is done using following script: curl --negotiate -u: -o /dev/null -w

[GitHub] [arrow] mayuropensource commented on pull request #7022: ARROW-8562: [C++] IO: Parameterize I/O Coalescing using S3 metrics

2020-04-24 Thread GitBox
mayuropensource commented on pull request #7022: URL: https://github.com/apache/arrow/pull/7022#issuecomment-619276182 // SOME_S3_DATA_URI should point to a file (over http) that is ~500 MiB. // TTFB_sec is the time-to-first-byte in seconds as measured by curl //

[GitHub] [arrow] mayuropensource commented on pull request #7022: ARROW-8562: [C++] IO: Parameterize I/O Coalescing using S3 metrics

2020-04-24 Thread GitBox
mayuropensource commented on pull request #7022: URL: https://github.com/apache/arrow/pull/7022#issuecomment-619184138 @fsaintjacques, I can try to put together a python script using boto to determine the S3 metrics. Will that work for you?