Re: [PATCH 1/3] mm/swap.c: pre-sort pages in pagevec for pagevec_lru_move_fn

2020-12-01 Thread Alex Shi
在 2020/12/1 下午4:10, Michal Hocko 写道: > On Tue 01-12-20 16:02:13, Alex Shi wrote: >> Pages in pagevec may have different lruvec, so we have to do relock in >> function pagevec_lru_move_fn(), but a relock may cause current cpu wait >> for long time on the same lock for spinlock fairness reason. >>

Re: [PATCH 1/3] mm/swap.c: pre-sort pages in pagevec for pagevec_lru_move_fn

2020-12-01 Thread Michal Hocko
On Tue 01-12-20 16:02:13, Alex Shi wrote: > Pages in pagevec may have different lruvec, so we have to do relock in > function pagevec_lru_move_fn(), but a relock may cause current cpu wait > for long time on the same lock for spinlock fairness reason. > > Before per memcg lru_lock, we have to bear

[PATCH 1/3] mm/swap.c: pre-sort pages in pagevec for pagevec_lru_move_fn

2020-12-01 Thread Alex Shi
Pages in pagevec may have different lruvec, so we have to do relock in function pagevec_lru_move_fn(), but a relock may cause current cpu wait for long time on the same lock for spinlock fairness reason. Before per memcg lru_lock, we have to bear the relock since the spinlock is the only way to se