rxin edited a comment on pull request #33784: URL: https://github.com/apache/spark/pull/33784#issuecomment-902171436
Caffeine is definitely fairly popular (At Databricks, I actually had a project that used it but eventually removed it due to a timing bug we found; Ben knows what I'm talking about here; the bug was ultimately fixed but we had to remove it due to project deadline). I'm confused here. Did we see perf improvement with Caffeine in any real scenarios? I saw some microbenchmarks in the original JIRA ticket saying there was improvements (and with some commentary from Ben saying the benchmark was not done correctly), but the pull request here claiming no improvement. -- 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]
