kernel test robot reported the regression of fio.write_iops[1] with [2]. Since lru_add_drain is called frequently, invalidate bh_lrus there could increase bh_lrus cache miss ratio, which needs more IO in the end. This patch moves the bh_lrus invalidation from the hot path( e.g., zap_page_range, pagevec_release) to cold path(i.e., lru_add_drain_all, lru_cache_disable). [1] https://lore.kernel.org/lkml/20210520083144.GD14190@xsang-OptiPlex-9020/ [2] 8cc621d2f45d, mm: fs: invalidate BH LRU during page migration Cc: "Xing, Zhengjun" <zhengjun.xing@xxxxxxxxx> Reported-by: kernel test robot <oliver.sang@xxxxxxxxx> Reviewed-by: Chris Goldsworthy <cgoldswo@xxxxxxxxxxxxxx> Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx> --- * from v1 - https://lore.kernel.org/lkml/YK0oQ76zX0uVZCwQ@xxxxxxxxxx/ * add Reviewed-by - cgoldswo mm/swap.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/mm/swap.c b/mm/swap.c index 1958d5feb148..3e25d99a9dbb 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -642,7 +642,6 @@ void lru_add_drain_cpu(int cpu) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); activate_page_drain(cpu); - invalidate_bh_lrus_cpu(cpu); } /** @@ -725,6 +724,17 @@ void lru_add_drain(void) local_unlock(&lru_pvecs.lock); } +static void lru_add_and_bh_lrus_drain(void) +{ + int cpu; + + local_lock(&lru_pvecs.lock); + cpu = smp_processor_id(); + lru_add_drain_cpu(cpu); + local_unlock(&lru_pvecs.lock); + invalidate_bh_lrus_cpu(cpu); +} + void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); @@ -739,7 +749,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { - lru_add_drain(); + lru_add_and_bh_lrus_drain(); } /* @@ -880,7 +890,7 @@ void lru_cache_disable(void) */ __lru_add_drain_all(true); #else - lru_add_drain(); + lru_add_and_bh_lrus_drain(); #endif } -- 2.31.1.818.g46aad6cb9e-goog
