Earlier this week I've posted the following comment for tomorrow's Yarn meetup. I just realized that most folks may miss that post, thus sending it to the alias.
We've been working on getting Impala running on YARN and wanted to share Llama, a system that mediates between Impala and YARN. Our design and some of the rationale behind it and the code are available at: Docs: http://cloudera.github.io/llama... Code: https://github.com/cloudera/llam... We think our approach will be applicable to similar frameworks - those with low latency requirements that seek to run work in processes outside of the typical container lifecycle. Thanks for taking a look and for any feedback! -Alex, Eli, Henry, Karthik, Sandy, and Tucu
