monkeyboy123 edited a comment on pull request #32683: URL: https://github.com/apache/spark/pull/32683#issuecomment-990983566
> At present, AQE uses the compressed size to do conditional judgment. In some extreme cases, such as when the compression ratio is relatively high, if smj is converted to shj when enable AQE, it is very likely that the oom issue will happen when building the hash table in shj. @JkSelf I think AQE is Based on metrics dataSize,and dataSize is the actually size, rather than the compressed size. Can you point this why? -- 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]
