On 2021-10-28 17:54:01 [+0200], David Hildenbrand wrote:
> Makes perfect sense to me. I was also wondering how "dangerous"
> MIGRATION (and everything depending on it, like CMA, compaction,
> MEMORY_HOTREMOVE, ...) is for RT recently.
for compatcion there is
6923aa0d8c629 ("mm/compaction: Disable compact_unevictable_allowed on RT")
to honour mlock() otherwise it can end unpleasant. But yeah, any page
migrations outside of the "setup/ init" phase of the RT task are bad.
Sebastian
