richox opened a new issue, #2491: URL: https://github.com/apache/arrow-datafusion/issues/2491
**Is your feature request related to a problem or challenge? Please describe what you are trying to do.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] (This section helps Arrow developers understand the context and *why* for this feature, in addition to the *what*) currently, sort-merge join creates one temporary record batch for each joined key, which results in many small batches and bad performance. **Describe the solution you'd like** A clear and concise description of what you want to happen. to achieve better performance, we can only store indices of joined pairs and generate a bigger record batch when the number of stored indices reaches the target batch size. **Describe alternatives you've considered** A clear and concise description of any alternative solutions or features you've considered. row format with JIT is hopefully a better solution in the joining scenario. **Additional context** Add any other context or screenshots about the feature request here. fuzzy testing with inner joining 1,000,000 integers: the original implementation: ``` real 0m32.045s user 0m30.868s sys 0m1.136s ``` improved implementation: ``` real 0m3.367s user 0m2.242s sys 0m1.048s ``` -- 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]
