stevenzwu commented on issue #7393: URL: https://github.com/apache/iceberg/issues/7393#issuecomment-1520391187
> I think if you re-implement the serialization interface of the record, can you give me a sample and I can test it in my scenario to see how much improvement there is. so the 4x slowdown is measured by throughput (not CPU overhead). Unless you are seeing 4x CPU overhead, this will likely not solve your problem. We haven't finished the MVP version with a custom range partitioner. How did you actually shuffle the records leveraging the data statistics? Were the traffic relatively evenly distributed to writer tasks? -- 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]
