I read a kubenetes engineering post that seemed to have the some conflicting info and preformance testing to show. Specifically with point number 3

https://kubernetes.io/blog/2025/08/19/tuning-linux-swap-for-kubernetes-a-deep-dive/

The blog above shows that swapiness should be 0 on workloads sensitive to high I/o latency. Whereas the misconceptions says turning off swap to reduce I/o trashing just shifts the problem elsewhere. I dont have the technical knowledge to know who's right in this situation.