On Thu, Nov 2, 2023 at 4:42 PM Nhat Pham <nphamcs@xxxxxxxxx> wrote:
>
> During our experiment with zswap, we sometimes observe swap IOs due to
> occasional zswap store failures and writebacks-to-swap. These swapping
> IOs prevent many users who cannot tolerate swapping from adopting zswap
> to save memory and improve performance where possible.
>
> This patch adds the option to disable this behavior entirely: do not
> writeback to backing swapping device when a zswap store attempt fail,
> and do not write pages in the zswap pool back to the backing swap
> device (both when the pool is full, and when the new zswap shrinker is
> called).
>
> This new behavior can be opted-in/out on a per-cgroup basis via a new
> cgroup file. By default, writebacks to swap device is enabled, which is
> the previous behavior.
>
> Note that this is subtly different from setting memory.swap.max to 0, as
> it still allows for pages to be stored in the zswap pool (which itself
> consumes swap space in its current form).
>
> Suggested-by: Johannes Weiner <hannes@xxxxxxxxxxx>
> Signed-off-by: Nhat Pham <nphamcs@xxxxxxxxx>
> ---
> Documentation/admin-guide/cgroup-v2.rst | 11 +++++++
> Documentation/admin-guide/mm/zswap.rst | 6 ++++
> include/linux/memcontrol.h | 12 ++++++++
> include/linux/zswap.h | 6 ++++
> mm/memcontrol.c | 38 +++++++++++++++++++++++++
> mm/page_io.c | 6 ++++
> mm/shmem.c | 3 +-
> mm/zswap.c | 14 +++++++++
> 8 files changed, 94 insertions(+), 2 deletions(-)
>
> diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
> index 606b2e0eac4b..18c4171392ea 100644
> --- a/Documentation/admin-guide/cgroup-v2.rst
> +++ b/Documentation/admin-guide/cgroup-v2.rst
> @@ -1672,6 +1672,17 @@ PAGE_SIZE multiple when read back.
> limit, it will refuse to take any more stores before existing
> entries fault back in or are written out to disk.
>
> + memory.zswap.writeback
> + A read-write single value file which exists on non-root
> + cgroups. The default value is "1".
> +
> + When this is set to 0, all swapping attempts to swapping devices
> + are disabled. This included both zswap writebacks, and swapping due
> + to zswap store failure.
> +
> + Note that this is subtly different from setting memory.swap.max to
> + 0, as it still allows for pages to be written to the zswap pool.
> +
> memory.pressure
> A read-only nested-keyed file.
>
> diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst
> index 522ae22ccb84..b987e58edb70 100644
> --- a/Documentation/admin-guide/mm/zswap.rst
> +++ b/Documentation/admin-guide/mm/zswap.rst
> @@ -153,6 +153,12 @@ attribute, e. g.::
>
> Setting this parameter to 100 will disable the hysteresis.
>
> +Some users cannot tolerate the swapping that comes with zswap store failures
> +and zswap writebacks. Swapping can be disabled entirely (without disabling
> +zswap itself) on a cgroup-basis as follows:
> +
> + echo 0 > /sys/fs/cgroup/<cgroup-name>/memory.zswap.writeback
> +
> When there is a sizable amount of cold memory residing in the zswap pool, it
> can be advantageous to proactively write these cold pages to swap and reclaim
> the memory for other use cases. By default, the zswap shrinker is disabled.
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 95f6c9e60ed1..e51eafdf2a15 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -219,6 +219,12 @@ struct mem_cgroup {
>
> #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
> unsigned long zswap_max;
> +
> + /*
> + * Prevent pages from this memcg from being written back from zswap to
> + * swap, and from being swapped out on zswap store failures.
> + */
> + bool zswap_writeback;
> #endif
>
> unsigned long soft_limit;
> @@ -1931,6 +1937,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
> bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
> void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
> void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size);
> +bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg);
> #else
> static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
> {
> @@ -1944,6 +1951,11 @@ static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
> size_t size)
> {
> }
> +static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
> +{
> + /* if zswap is disabled, do not block pages going to the swapping device */
> + return true;
> +}
> #endif
>
> #endif /* _LINUX_MEMCONTROL_H */
> diff --git a/include/linux/zswap.h b/include/linux/zswap.h
> index cbd373ba88d2..b4997e27a74b 100644
> --- a/include/linux/zswap.h
> +++ b/include/linux/zswap.h
> @@ -35,6 +35,7 @@ void zswap_swapoff(int type);
> void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
> void zswap_lruvec_state_init(struct lruvec *lruvec);
> void zswap_lruvec_swapin(struct page *page);
> +bool is_zswap_enabled(void);
> #else
>
> struct zswap_lruvec_state {};
> @@ -55,6 +56,11 @@ static inline void zswap_swapoff(int type) {}
> static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}
> static inline void zswap_lruvec_init(struct lruvec *lruvec) {}
> static inline void zswap_lruvec_swapin(struct page *page) {}
> +
> +static inline bool is_zswap_enabled(void)
> +{
> + return false;
> +}
> #endif
>
> #endif /* _LINUX_ZSWAP_H */
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index e43b5aba8efc..8a6aadcc103c 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -5545,6 +5545,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
> WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
> #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
> memcg->zswap_max = PAGE_COUNTER_MAX;
> + WRITE_ONCE(memcg->zswap_writeback, true);
Generally LGTM, just one question.
Would it be more convenient if the initial value is inherited from the
parent (the root starts with true)?
I can see this being useful if we want to set it to false on the
entire machine or one a parent cgroup, we can set it before creating
any children instead of setting it to 0 every time we create a new
cgroup.
