rdhabalia commented on PR #8719: URL: https://github.com/apache/hadoop/pull/8719#issuecomment-5591921705
On the client-as-bottleneck point: the tool is built for multi-client scale-out — you run several instances against the target replica set and aggregate, so a single client's limits don't cap the measurement. I've also added a client-bottleneck warning: when measured throughput drops below 80% of the requested target, it flags that the client (not the DataNodes) may be the limiter, so the results aren't misread. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
