mayankshriv opened a new issue #4099: Latency optimization by avoiding redundant bytes<->string conversions URL: https://github.com/apache/incubator-pinot/issues/4099 Aggregation group by queries tend to be expensive in general. Depending on the data and query, a sizable part of the cpu-time is spent de-serializing Strings from bytes (fwd index) when performing group-by. Most of the query (grouping) can be performed without this conversion, working directly on bytes or wrappers such as ByteString. Creating this issue to evaluate the potential gain, and scope out the work needed.
---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
