Re: [PATCH 1/1] mm: vmscan: Reduce throttling due to a failure to make progress
From: Mike Galbraith <hidden>
Date: 2021-11-30 18:00:27
Also in:
linux-fsdevel, lkml, regressions
On Tue, 2021-11-30 at 17:27 +0000, Mel Gorman wrote:
Obviously a fairly different experience and most likely due to the underlying storage.
I bet a virtual nickle this is the sore spot. --- mm/vmscan.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c@@ -3360,7 +3360,17 @@ static void shrink_node(pg_data_t *pgdat if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) +#if 0 reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); +#else + /* + * wait_iff_congested() used to live here and was + * _apparently_ a misspelled cond_resched()????? + * In any case, we are most definitely NOT starting + * any IO in reclaim_throttle(), so why bother? + */ + cond_resched(); +#endif if (should_continue_reclaim(pgdat, sc->nr_reclaimed -
nr_reclaimed, sc))