Re: [v5 PATCH 08/11] mm: vmscan: use per memcg nr_deferred of shrinker

[Yang Shi]

On Fri, Jan 29, 2021 at 6:59 AM Kirill Tkhai <ktkhai@xxxxxxxxxxxxx> wrote:
>
> On 29.01.2021 17:55, Kirill Tkhai wrote:
> > On 28.01.2021 02:33, Yang Shi wrote:
> >> Use per memcg's nr_deferred for memcg aware shrinkers.  The shrinker's nr_deferred
> >> will be used in the following cases:
> >>     1. Non memcg aware shrinkers
> >>     2. !CONFIG_MEMCG
> >>     3. memcg is disabled by boot parameter
> >>
> >> Signed-off-by: Yang Shi <shy828301@xxxxxxxxx>
> >> ---
> >>  mm/vmscan.c | 87 ++++++++++++++++++++++++++++++++++++++++++++---------
> >>  1 file changed, 73 insertions(+), 14 deletions(-)
> >>
> >> diff --git a/mm/vmscan.c b/mm/vmscan.c
> >> index 20be0db291fe..e1f8960f5cf6 100644
> >> --- a/mm/vmscan.c
> >> +++ b/mm/vmscan.c
> >> @@ -205,7 +205,8 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg,
> >>
> >>      for_each_node(nid) {
> >>              old = rcu_dereference_protected(
> >> -                    mem_cgroup_nodeinfo(memcg, nid)->shrinker_info, true);
> >> +                    mem_cgroup_nodeinfo(memcg, nid)->shrinker_info,
> >> +                    lockdep_is_held(&shrinker_rwsem));
> >
> > Won't it better to pack this repeating pattern into helper function, e.g.:
> >
> > static struct shrinker_info memcg_shrinker_info(struct mem_cgroup *memcg, int nid)
> > {
> >       return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info,
> >                                          lockdep_is_held(&shrinker_rwsem));
> > }
> >
> > ?
> >
> > Even shrink_slab_memcg() may want to use it.
>
> Hm, I see you already introduced a helper in [10/11], but it is used in only place.
> Then, we should use it for all places (introduce the helper earlier).

Yes, good point. Will fix in v6.

>
> >>              /* Not yet online memcg */
> >>              if (!old)
> >>                      return 0;
> >> @@ -239,7 +240,8 @@ void free_shrinker_info(struct mem_cgroup *memcg)
> >>
> >>      for_each_node(nid) {
> >>              pn = mem_cgroup_nodeinfo(memcg, nid);
> >> -            info = rcu_dereference_protected(pn->shrinker_info, true);
> >> +            info = rcu_dereference_protected(pn->shrinker_info,
> >> +                                             lockdep_is_held(&shrinker_rwsem));
> >>              if (info)
> >>                      kvfree(info);
> >>              rcu_assign_pointer(pn->shrinker_info, NULL);
> >> @@ -360,6 +362,27 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker)
> >>      up_write(&shrinker_rwsem);
> >>  }
> >>
> >> +static long count_nr_deferred_memcg(int nid, struct shrinker *shrinker,
> >> +                                struct mem_cgroup *memcg)
> >> +{
> >> +    struct shrinker_info *info;
> >> +
> >> +    info = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info,
> >> +                                     lockdep_is_held(&shrinker_rwsem));
> >> +    return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0);
> >> +}
> >> +
> >> +static long set_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
> >> +                              struct mem_cgroup *memcg)
> >> +{
> >> +    struct shrinker_info *info;
> >> +
> >> +    info = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info,
> >> +                                     lockdep_is_held(&shrinker_rwsem));
> >> +
> >> +    return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]);
> >> +}
> >> +
> >>  static bool cgroup_reclaim(struct scan_control *sc)
> >>  {
> >>      return sc->target_mem_cgroup;
> >> @@ -398,6 +421,18 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker)
> >>  {
> >>  }
> >>
> >> +static long count_nr_deferred_memcg(int nid, struct shrinker *shrinker,
> >> +                                struct mem_cgroup *memcg)
> >> +{
> >> +    return 0;
> >> +}
> >> +
> >> +static long set_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
> >> +                              struct mem_cgroup *memcg)
> >> +{
> >> +    return 0;
> >> +}
> >> +
> >>  static bool cgroup_reclaim(struct scan_control *sc)
> >>  {
> >>      return false;
> >> @@ -409,6 +444,39 @@ static bool writeback_throttling_sane(struct scan_control *sc)
> >>  }
> >>  #endif
> >>
> >> +static long count_nr_deferred(struct shrinker *shrinker,
> >> +                          struct shrink_control *sc)
> >> +{
> >> +    int nid = sc->nid;
> >> +
> >> +    if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> >> +            nid = 0;
> >> +
> >> +    if (sc->memcg &&
> >> +        (shrinker->flags & SHRINKER_MEMCG_AWARE))
> >> +            return count_nr_deferred_memcg(nid, shrinker,
> >> +                                           sc->memcg);
> >> +
> >> +    return atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
> >> +}
> >> +
> >> +
> >> +static long set_nr_deferred(long nr, struct shrinker *shrinker,
> >> +                        struct shrink_control *sc)
> >> +{
> >> +    int nid = sc->nid;
> >> +
> >> +    if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> >> +            nid = 0;
> >> +
> >> +    if (sc->memcg &&
> >> +        (shrinker->flags & SHRINKER_MEMCG_AWARE))
> >> +            return set_nr_deferred_memcg(nr, nid, shrinker,
> >> +                                         sc->memcg);
> >> +
> >> +    return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]);
> >> +}
> >> +
> >>  /*
> >>   * This misses isolated pages which are not accounted for to save counters.
> >>   * As the data only determines if reclaim or compaction continues, it is
> >> @@ -545,14 +613,10 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
> >>      long freeable;
> >>      long nr;
> >>      long new_nr;
> >> -    int nid = shrinkctl->nid;
> >>      long batch_size = shrinker->batch ? shrinker->batch
> >>                                        : SHRINK_BATCH;
> >>      long scanned = 0, next_deferred;
> >>
> >> -    if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> >> -            nid = 0;
> >> -
> >>      freeable = shrinker->count_objects(shrinker, shrinkctl);
> >>      if (freeable == 0 || freeable == SHRINK_EMPTY)
> >>              return freeable;
> >> @@ -562,7 +626,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
> >>       * and zero it so that other concurrent shrinker invocations
> >>       * don't also do this scanning work.
> >>       */
> >> -    nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
> >> +    nr = count_nr_deferred(shrinker, shrinkctl);
> >>
> >>      total_scan = nr;
> >>      if (shrinker->seeks) {
> >> @@ -653,14 +717,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
> >>              next_deferred = 0;
> >>      /*
> >>       * move the unused scan count back into the shrinker in a
> >> -     * manner that handles concurrent updates. If we exhausted the
> >> -     * scan, there is no need to do an update.
> >> +     * manner that handles concurrent updates.
> >>       */
> >> -    if (next_deferred > 0)
> >> -            new_nr = atomic_long_add_return(next_deferred,
> >> -                                            &shrinker->nr_deferred[nid]);
> >> -    else
> >> -            new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
> >> +    new_nr = set_nr_deferred(next_deferred, shrinker, shrinkctl);
> >>
> >>      trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan);
> >>      return freed;
> >>
> >
>
>