On Wed, Jan 03, 2024 at 11:20:50PM -0800, Darrick J. Wong wrote: > > Sure, I just suspect the commit message is wrong and it's not about > > mapping the page into the kernel address space but something else. > > Yeah, I only did A/B testing of before and after this patch, so it's > quite plausible that it's the lookup that's slowing us down. Can we re-rerun the test once the pending xfile changes are in? I'd be kinda surprised if the fairly simply xarray lookup for the page is so expensive. If it is the patch is a good bandaid for that, I'd just like to ensure it actually is still needed.
