| Message ID | 20210625073204.1005986-8-ying.huang@intel.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Migrate Pages in lieu of discard | expand |
On Fri, Jun 25, 2021 at 12:33 AM Huang Ying <ying.huang@intel.com> wrote: > > From: Keith Busch <kbusch@kernel.org> > > Reclaim anonymous pages if a migration path is available now that > demotion provides a non-swap recourse for reclaiming anon pages. > > Note that this check is subtly different from the > anon_should_be_aged() checks. This mechanism checks whether a > specific page in a specific context *can* actually be reclaimed, given > current swap space and cgroup limits > > anon_should_be_aged() is a much simpler and more preliminary check > which just says whether there is a possibility of future reclaim. > > Cc: Keith Busch <kbusch@kernel.org> > Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> > Signed-off-by: "Huang, Ying" <ying.huang@intel.com> > Reviewed-by: Yang Shi <shy828301@gmail.com> > Cc: Michal Hocko <mhocko@suse.com> > Cc: Zi Yan <ziy@nvidia.com> > Cc: Wei Xu <weixugc@google.com> > Cc: David Rientjes <rientjes@google.com> > Cc: Dan Williams <dan.j.williams@intel.com> > Cc: David Hildenbrand <david@redhat.com> > > -- > > Changes since 20210618: > * Consider whether demotion is disabled > > Changes from Dave 202010: > * remove 'total_swap_pages' modification > > Changes from Dave 202006: > * rename reclaim_anon_pages()->can_reclaim_anon_pages() > > Note: Keith's Intel SoB is commented out because he is no > longer at Intel and his @intel.com mail will bounce. > --- > mm/vmscan.c | 37 ++++++++++++++++++++++++++++++++++--- > 1 file changed, 34 insertions(+), 3 deletions(-) > > diff --git a/mm/vmscan.c b/mm/vmscan.c > index 55f6192b2a51..fce43c7970d7 100644 > --- a/mm/vmscan.c > +++ b/mm/vmscan.c > @@ -519,6 +519,36 @@ static long add_nr_deferred(long nr, struct shrinker *shrinker, > return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); > } > > +static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, > + int node_id, > + struct scan_control *sc) > +{ > + if (memcg == NULL) { > + /* > + * For non-memcg reclaim, is there > + * space in any swap device? > + */ > + if (get_nr_swap_pages() > 0) > + return true; > + } else { > + /* Is the memcg below its swap limit? */ > + if (mem_cgroup_get_nr_swap_pages(memcg) > 0) > + return true; > + } > + > + /* > + * The page can not be swapped. > + * > + * Can it be reclaimed from this node via demotion? > + */ > + if ((!sc || !sc->no_demotion) && > + next_demotion_node(node_id) != NUMA_NO_NODE) > + return true; It is better to abstract these checks into a function, e.g. can_demote_anon_pages(), to share with anon_can_be_aged(). > + /* No way to reclaim anon pages */ > + return false; > +} > + > /* > * This misses isolated pages which are not accounted for to save counters. > * As the data only determines if reclaim or compaction continues, it is > @@ -530,7 +560,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone) > > nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + > zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); > - if (get_nr_swap_pages() > 0) > + if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) > nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + > zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); > > @@ -2531,6 +2561,7 @@ enum scan_balance { > static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, > unsigned long *nr) > { > + struct pglist_data *pgdat = lruvec_pgdat(lruvec); > struct mem_cgroup *memcg = lruvec_memcg(lruvec); > unsigned long anon_cost, file_cost, total_cost; > int swappiness = mem_cgroup_swappiness(memcg); > @@ -2541,7 +2572,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, > enum lru_list lru; > > /* If we have no swap space, do not bother scanning anon pages. */ > - if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { > + if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { > scan_balance = SCAN_FILE; > goto out; > } > @@ -2916,7 +2947,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, > */ > pages_for_compaction = compact_gap(sc->order); > inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); > - if (get_nr_swap_pages() > 0) > + if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) > inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); > > return inactive_lru_pages > pages_for_compaction; > -- > 2.30.2 >
Wei Xu <weixugc@google.com> writes: > On Fri, Jun 25, 2021 at 12:33 AM Huang Ying <ying.huang@intel.com> wrote: >> >> From: Keith Busch <kbusch@kernel.org> >> >> Reclaim anonymous pages if a migration path is available now that >> demotion provides a non-swap recourse for reclaiming anon pages. >> >> Note that this check is subtly different from the >> anon_should_be_aged() checks. This mechanism checks whether a >> specific page in a specific context *can* actually be reclaimed, given >> current swap space and cgroup limits >> >> anon_should_be_aged() is a much simpler and more preliminary check >> which just says whether there is a possibility of future reclaim. >> >> Cc: Keith Busch <kbusch@kernel.org> >> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> >> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> >> Reviewed-by: Yang Shi <shy828301@gmail.com> >> Cc: Michal Hocko <mhocko@suse.com> >> Cc: Zi Yan <ziy@nvidia.com> >> Cc: Wei Xu <weixugc@google.com> >> Cc: David Rientjes <rientjes@google.com> >> Cc: Dan Williams <dan.j.williams@intel.com> >> Cc: David Hildenbrand <david@redhat.com> >> >> -- >> >> Changes since 20210618: >> * Consider whether demotion is disabled >> >> Changes from Dave 202010: >> * remove 'total_swap_pages' modification >> >> Changes from Dave 202006: >> * rename reclaim_anon_pages()->can_reclaim_anon_pages() >> >> Note: Keith's Intel SoB is commented out because he is no >> longer at Intel and his @intel.com mail will bounce. >> --- >> mm/vmscan.c | 37 ++++++++++++++++++++++++++++++++++--- >> 1 file changed, 34 insertions(+), 3 deletions(-) >> >> diff --git a/mm/vmscan.c b/mm/vmscan.c >> index 55f6192b2a51..fce43c7970d7 100644 >> --- a/mm/vmscan.c >> +++ b/mm/vmscan.c >> @@ -519,6 +519,36 @@ static long add_nr_deferred(long nr, struct shrinker *shrinker, >> return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); >> } >> >> +static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, >> + int node_id, >> + struct scan_control *sc) >> +{ >> + if (memcg == NULL) { >> + /* >> + * For non-memcg reclaim, is there >> + * space in any swap device? >> + */ >> + if (get_nr_swap_pages() > 0) >> + return true; >> + } else { >> + /* Is the memcg below its swap limit? */ >> + if (mem_cgroup_get_nr_swap_pages(memcg) > 0) >> + return true; >> + } >> + >> + /* >> + * The page can not be swapped. >> + * >> + * Can it be reclaimed from this node via demotion? >> + */ >> + if ((!sc || !sc->no_demotion) && >> + next_demotion_node(node_id) != NUMA_NO_NODE) >> + return true; > > It is better to abstract these checks into a function, e.g. > can_demote_anon_pages(), to share with anon_can_be_aged(). Thanks! This is a really good idea! The function can be used by shrink_page_list() too. So code duplication is reduced greatly! Will do that in the next version. Best Regards, Huang, Ying >> + /* No way to reclaim anon pages */ >> + return false; >> +} >> + >> /* >> * This misses isolated pages which are not accounted for to save counters. >> * As the data only determines if reclaim or compaction continues, it is >> @@ -530,7 +560,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone) >> >> nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + >> zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); >> - if (get_nr_swap_pages() > 0) >> + if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) >> nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + >> zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); >> >> @@ -2531,6 +2561,7 @@ enum scan_balance { >> static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, >> unsigned long *nr) >> { >> + struct pglist_data *pgdat = lruvec_pgdat(lruvec); >> struct mem_cgroup *memcg = lruvec_memcg(lruvec); >> unsigned long anon_cost, file_cost, total_cost; >> int swappiness = mem_cgroup_swappiness(memcg); >> @@ -2541,7 +2572,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, >> enum lru_list lru; >> >> /* If we have no swap space, do not bother scanning anon pages. */ >> - if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { >> + if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { >> scan_balance = SCAN_FILE; >> goto out; >> } >> @@ -2916,7 +2947,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, >> */ >> pages_for_compaction = compact_gap(sc->order); >> inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); >> - if (get_nr_swap_pages() > 0) >> + if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) >> inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); >> >> return inactive_lru_pages > pages_for_compaction; >> -- >> 2.30.2 >>
diff --git a/mm/vmscan.c b/mm/vmscan.c index 55f6192b2a51..fce43c7970d7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -519,6 +519,36 @@ static long add_nr_deferred(long nr, struct shrinker *shrinker, return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); } +static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, + int node_id, + struct scan_control *sc) +{ + if (memcg == NULL) { + /* + * For non-memcg reclaim, is there + * space in any swap device? + */ + if (get_nr_swap_pages() > 0) + return true; + } else { + /* Is the memcg below its swap limit? */ + if (mem_cgroup_get_nr_swap_pages(memcg) > 0) + return true; + } + + /* + * The page can not be swapped. + * + * Can it be reclaimed from this node via demotion? + */ + if ((!sc || !sc->no_demotion) && + next_demotion_node(node_id) != NUMA_NO_NODE) + return true; + + /* No way to reclaim anon pages */ + return false; +} + /* * This misses isolated pages which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is @@ -530,7 +560,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone) nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); - if (get_nr_swap_pages() > 0) + if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); @@ -2531,6 +2561,7 @@ enum scan_balance { static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { + struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; int swappiness = mem_cgroup_swappiness(memcg); @@ -2541,7 +2572,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru; /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { + if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { scan_balance = SCAN_FILE; goto out; } @@ -2916,7 +2947,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); - if (get_nr_swap_pages() > 0) + if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction;