On Sun, Apr 16, 2023 at 8:44 PM Sergey Senozhatsky <senozhatsky@xxxxxxxxxxxx> wrote: > > On (23/04/16 13:27), Yu Zhao wrote: > > > Hi, > > > > > > Did you bisect it down to this series? > > > > Not exactly -- since this series was the only suspect I had, I cherry > > picked it to v6.3-rc6 and verified it is the culprit. > > Can't reproduce it yet. One of the theories is that get_fullness_group() > maybe returns an invalid index, but I don't immediately see how would it > do so. > > Is the problem reproducible? Whenever swapping *multithreaded* heavily. > Do you run some specific test? E.g., tools/testing/selftests/kvm/max_guest_memory_test -c 112 -m 800 -s 800 with 112 CPUs and ~770GB DRAM + 32GB zram.
