A question for the people getting good performance on SQL workloads - are you using it in the default "devil may care" setup, or have you set it up for data consistency with proper writes to multiple nodes? My main concern with hyper converged is that not one vendor mentions this in their material, and it could lead to serious data corruption if a node is lost after confirming writes but before copying those writes to a second controller. This setup is fine for VDI but not for SQL, and I'm told setting up for consistency reduces the performance considerably, which is logical given the extra steps and processing.
I ask because I've never had the kit to do testing on so am very interested if real world performance is great even once the settings are date safe. This being my main reason for sticking with traditional SAN.