On Tue, Jul 30, 2024 at 5:49 PM Takero Funaki <flintglass@xxxxxxxxx> wrote:
>
> This patch fixes an issue where the zswap global shrinker stopped
> iterating through the memcg tree.
>
> The problem was that shrink_worker() would restart iterating memcg tree
> from the tree root, considering an offline memcg as a failure, and abort
> shrinking after encountering the same offline memcg 16 times even if
> there is only one offline memcg. After this change, an offline memcg in
> the tree is no longer considered a failure. This allows the shrinker to
> continue shrinking the other online memcgs regardless of whether an
> offline memcg exists, gives higher zswap writeback activity.
>
> To avoid holding refcount of offline memcg encountered during the memcg
> tree walking, shrink_worker() must continue iterating to release the
> offline memcg to ensure the next memcg stored in the cursor is online.
>
> The offline memcg cleaner has also been changed to avoid the same issue.
> When the next memcg of the offlined memcg is also offline, the refcount
> stored in the iteration cursor was held until the next shrink_worker()
> run. The cleaner must release the offline memcg recursively.
>
> Fixes: a65b0e7607cc ("zswap: make shrinking memcg-aware")
> Acked-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
> Reviewed-by: Chengming Zhou <chengming.zhou@xxxxxxxxx>
> Reviewed-by: Nhat Pham <nphamcs@xxxxxxxxx>
> Signed-off-by: Takero Funaki <flintglass@xxxxxxxxx>
> ---
> mm/zswap.c | 68 +++++++++++++++++++++++++++++++++++-------------------
> 1 file changed, 44 insertions(+), 24 deletions(-)
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index adeaf9c97fde..3c16a1192252 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -765,12 +765,25 @@ void zswap_folio_swapin(struct folio *folio)
> }
> }
>
> +/*
> + * This function should be called when a memcg is being offlined.
> + *
> + * Since the global shrinker shrink_worker() may hold a reference
> + * of the memcg, we must check and release the reference in
> + * zswap_next_shrink.
> + *
> + * shrink_worker() must handle the case where this function releases
> + * the reference of memcg being shrunk.
> + */
> void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg)
> {
> /* lock out zswap shrinker walking memcg tree */
> spin_lock(&zswap_shrink_lock);
> - if (zswap_next_shrink == memcg)
> - zswap_next_shrink = mem_cgroup_iter(NULL, zswap_next_shrink, NULL);
> + if (zswap_next_shrink == memcg) {
> + do {
> + zswap_next_shrink = mem_cgroup_iter(NULL, zswap_next_shrink, NULL);
> + } while (zswap_next_shrink && !mem_cgroup_online(zswap_next_shrink));
> + }
> spin_unlock(&zswap_shrink_lock);
> }
>
> @@ -1304,43 +1317,50 @@ static void shrink_worker(struct work_struct *w)
> /* Reclaim down to the accept threshold */
> thr = zswap_accept_thr_pages();
>
> - /* global reclaim will select cgroup in a round-robin fashion. */
> + /*
> + * Global reclaim will select cgroup in a round-robin fashion.
> + *
> + * We save iteration cursor memcg into zswap_next_shrink,
> + * which can be modified by the offline memcg cleaner
> + * zswap_memcg_offline_cleanup().
> + *
> + * Since the offline cleaner is called only once, we cannot leave an
> + * offline memcg reference in zswap_next_shrink.
> + * We can rely on the cleaner only if we get online memcg under lock.
> + *
> + * If we get an offline memcg, we cannot determine if the cleaner has
> + * already been called or will be called later. We must put back the
> + * reference before returning from this function. Otherwise, the
> + * offline memcg left in zswap_next_shrink will hold the reference
> + * until the next run of shrink_worker().
> + */
> do {
> spin_lock(&zswap_shrink_lock);
> - zswap_next_shrink = mem_cgroup_iter(NULL, zswap_next_shrink, NULL);
> - memcg = zswap_next_shrink;
>
> /*
> - * We need to retry if we have gone through a full round trip, or if we
> - * got an offline memcg (or else we risk undoing the effect of the
> - * zswap memcg offlining cleanup callback). This is not catastrophic
> - * per se, but it will keep the now offlined memcg hostage for a while.
> - *
> + * Start shrinking from the next memcg after zswap_next_shrink.
> + * When the offline cleaner has already advanced the cursor,
> + * advancing the cursor here overlooks one memcg, but this
> + * should be negligibly rare.
> + */
> + do {
> + memcg = mem_cgroup_iter(NULL, zswap_next_shrink, NULL);
> + zswap_next_shrink = memcg;
> + } while (memcg && !mem_cgroup_tryget_online(memcg));
I took a look at refactoring the loop to a helper, but it's probably
not going to be any clearer because this loop has a tryget, and the
loop in zswap_memcg_offline_cleanup() only has an online check. Using
a tryget in the offline cleanup version would be wasteful and we'll
put the ref right away.
Instead, I think we should just move the spin_lock/unlock() closer to
the loop to make the critical section more obvious, and unify the
comments above and below into a single block.
Andrew, could you please fold in the following diff (unless Takero objects):
diff --git a/mm/zswap.c b/mm/zswap.c
index babf0abbcc765..df620eacd1d11 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1364,24 +1364,22 @@ static void shrink_worker(struct work_struct *w)
* until the next run of shrink_worker().
*/
do {
- spin_lock(&zswap_shrink_lock);
-
/*
* Start shrinking from the next memcg after zswap_next_shrink.
* When the offline cleaner has already advanced the cursor,
* advancing the cursor here overlooks one memcg, but this
* should be negligibly rare.
+ *
+ * If we get an online memcg, keep the extra reference in case
+ * the original one obtained by mem_cgroup_iter() is dropped by
+ * zswap_memcg_offline_cleanup() while we are shrinking the
+ * memcg.
*/
+ spin_lock(&zswap_shrink_lock);
do {
memcg = mem_cgroup_iter(NULL, zswap_next_shrink, NULL);
zswap_next_shrink = memcg;
} while (memcg && !mem_cgroup_tryget_online(memcg));
- /*
- * Note that if we got an online memcg, we will keep the extra
- * reference in case the original reference obtained
by mem_cgroup_iter
- * is dropped by the zswap memcg offlining callback,
ensuring that the
- * memcg is not killed when we are reclaiming.
- */
spin_unlock(&zswap_shrink_lock);
if (!memcg) {
> + /*
> * Note that if we got an online memcg, we will keep the extra
> * reference in case the original reference obtained by mem_cgroup_iter
> * is dropped by the zswap memcg offlining callback, ensuring that the
> * memcg is not killed when we are reclaiming.
> */
> - if (!memcg) {
> - spin_unlock(&zswap_shrink_lock);
> - if (++failures == MAX_RECLAIM_RETRIES)
> - break;
> -
> - goto resched;
> - }
> -
> - if (!mem_cgroup_tryget_online(memcg)) {
> - /* drop the reference from mem_cgroup_iter() */
> - mem_cgroup_iter_break(NULL, memcg);
> - zswap_next_shrink = NULL;
> - spin_unlock(&zswap_shrink_lock);
> + spin_unlock(&zswap_shrink_lock);
>
> + if (!memcg) {
> if (++failures == MAX_RECLAIM_RETRIES)
> break;
>
> goto resched;
> }
> - spin_unlock(&zswap_shrink_lock);
>
> ret = shrink_memcg(memcg);
> /* drop the extra reference */
> --
> 2.43.0
>
