> > @@ -4355,7 +4355,7 @@ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat,
> > static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
> > unsigned int highest_zoneidx)
> > {
> > - long remaining = 0;
> > + long remaining = ~0;
> > DEFINE_WAIT(wait);
> >
> > if (freezing(current) || kthread_should_stop())
>
> While this does avoid calling prepare_kswapd_sleep() twice if the pgdat
> is balanced on the first try, it then does not restore the vmstat
> thresholds and doesn't call schedul() for kswapd to go to sleep.
I intended not to call prepare_kswapd_sleep() twice when the pgdat is NOT
balanced on the first try:)
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 700434db5735..40784693c840 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -4355,7 +4355,8 @@ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat,
> static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
> unsigned int highest_zoneidx)
> {
> - long remaining = 0;
> + long remaining;
> + bool balanced;
> DEFINE_WAIT(wait);
>
> if (freezing(current) || kthread_should_stop())
> @@ -4370,7 +4371,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o
> * eligible zone balanced that it's also unlikely that compaction will
> * succeed.
> */
> - if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
> + balanced = prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx);
> + if (balanced) {
> /*
> * Compaction records what page blocks it recently failed to
> * isolate pages from and skips them in the future scanning.
> @@ -4387,6 +4389,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o
>
> remaining = schedule_timeout(HZ/10);
>
> + /* Is pgdat balanced after a short sleep? */
> + balanced = prepare_kswapd_sleep(pgdat, reclaim_order,
> + highest_zoneidx);
> +
> /*
> * If woken prematurely then reset kswapd_highest_zoneidx and
> * order. The values will either be from a wakeup request or
> @@ -4406,11 +4412,11 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o
> }
>
> /*
> - * After a short sleep, check if it was a premature sleep. If not, then
> - * go fully to sleep until explicitly woken up.
> + * If balanced to the high watermark, restore vmstat thresholds and
> + * kswapd goes to sleep. If kswapd remains awake, account whether
> + * the low or high watermark was hit quickly.
> */
> - if (!remaining &&
> - prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
> + if (balanced) {
> trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
>
> /*
But, I think what you did is more readable and nice.
Thanks!
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index 700434db5735..1217ecec5bbb 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -4331,7 +4331,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
> > /*
> > * Return the order kswapd stopped reclaiming at as
> > * prepare_kswapd_sleep() takes it into account. If another caller
> > - * entered the allocator slow path while kswapd was awake, order will
> > + * entered the allqocator slow path while kswapd was awake, order will
> > * remain at the higher level.
> > */
> > return sc.order;
>
> This hunk just adds a typo, drop it.
Sorry about that;;
