Received-SPF: pass (google.com: domain of linux-kernel+bounces-47653-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: "Huang, Ying" <ying.huang@intel.com>
To: Chris Li <chrisl@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
  linux-kernel@vger.kernel.org,  linux-mm@kvack.org,  Wei =?utf-8?Q?Xu?=
 =?utf-8?Q?=EF=BF=BC?=
 <weixugc@google.com>,  Yu =?utf-8?Q?Zhao=EF=BF=BC?= <yuzhao@google.com>,
  Greg Thelen
 <gthelen@google.com>,  Chun-Tse Shao <ctshao@google.com>,  Suren
 =?utf-8?Q?Baghdasaryan=EF=BF=BC?= <surenb@google.com>,  Yosry =?utf-8?Q?A?=
 =?utf-8?Q?hmed=EF=BF=BC?= <yosryahmed@google.com>,
  Brain Geffon <bgeffon@google.com>,  Minchan Kim <minchan@kernel.org>,
  Michal Hocko <mhocko@suse.com>,  Mel Gorman
 <mgorman@techsingularity.net>,  Nhat Pham <nphamcs@gmail.com>,  Johannes
 Weiner <hannes@cmpxchg.org>,  Kairui Song <kasong@tencent.com>,  Zhongkun
 He <hezhongkun.hzk@bytedance.com>,  Kemeng Shi
 <shikemeng@huaweicloud.com>,  Barry Song <v-songbaohua@oppo.com>
Subject: Re: [PATCH v2] mm: swap: async free swap slot cache entries
In-Reply-To: <20240131-async-free-v2-1-525f03e07184@kernel.org> (Chris Li's
	message of "Wed, 31 Jan 2024 17:17:31 -0800")
References: <20240131-async-free-v2-1-525f03e07184@kernel.org>
Date: Thu, 01 Feb 2024 13:33:07 +0800
Message-ID: <87sf2ceoks.fsf@yhuang6-desk2.ccr.corp.intel.com>
User-Agent: Gnus/5.13 (Gnus v5.13)
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable

Chris Li <chrisl@kernel.org> writes:

> We discovered that 1% swap page fault is 100us+ while 50% of
> the swap fault is under 20us.
>
> Further investigation show that a large portion of the time
> spent in the free_swap_slots() function for the long tail case.
>
> The percpu cache of swap slots is freed in a batch of 64 entries
> inside free_swap_slots(). These cache entries are accumulated
> from previous page faults, which may not be related to the current
> process.
>
> Doing the batch free in the page fault handler causes longer
> tail latencies and penalizes the current process.
>
> Move free_swap_slots() outside of the swapin page fault handler into an
> async work queue to avoid such long tail latencies.
>
> The batch free of swap slots is typically at 100us level. Such a

Running ~100us operation in an asynchronous task appears overkill for me
too.

Can you try to move some operations out of swapcache_free_entries() to
check whether that can resolve your issue?

--
Best Regards,
Huang, Ying

> short time will not have a significant impact on the CPU accounting.
> Notice that the previous swap slot batching behavior already performs
> a delayed=C2=A0batch free. It=C2=A0waits for the entries=C2=A0accumulated=
 to 64.
> Adding the async scheduling time does not change the original
> free timing significantly.
>
> Testing:
>
> Chun-Tse did some benchmark in chromebook, showing that
> zram_wait_metrics improve about 15% with 80% and 95% confidence.
>
> I recently ran some experiments on about 1000 Google production
> machines. It shows swapin latency drops in the long tail
> 100us - 500us bucket dramatically.
>
> platform	(100-500us)	 	(0-100us)
> A		1.12% -> 0.36%		98.47% -> 99.22%
> B		0.65% -> 0.15%		98.96% -> 99.46%
> C		0.61% -> 0.23%		98.96% -> 99.38%
>
> Signed-off-by: Chris Li <chrisl@kernel.org>
> To: Andrew Morton <akpm@linux-foundation.org>
> Cc: linux-kernel@vger.kernel.org
> Cc: linux-mm@kvack.org
> Cc: Wei Xu=EF=BF=BC<weixugc@google.com>
> Cc: Yu Zhao=EF=BF=BC<yuzhao@google.com>
> Cc: Greg Thelen <gthelen@google.com>
> Cc: Chun-Tse Shao <ctshao@google.com>
> Cc: Suren Baghdasaryan=EF=BF=BC<surenb@google.com>
> Cc: Yosry Ahmed=EF=BF=BC <yosryahmed@google.com>
> Cc: Brain Geffon <bgeffon@google.com>
> Cc: Minchan Kim <minchan@kernel.org>
> Cc: Michal Hocko <mhocko@suse.com>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Huang Ying <ying.huang@intel.com>
> Cc: Nhat Pham <nphamcs@gmail.com>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: Kairui Song <kasong@tencent.com>
> Cc: Zhongkun He <hezhongkun.hzk@bytedance.com>
> Cc: Kemeng Shi <shikemeng@huaweicloud.com>
> Cc: Barry Song <v-songbaohua@oppo.com>
>
> remove create_work queue
>
> remove another work queue usage
>
> ---
> Changes in v2:
> - Add description of the impact of time changing suggest by Ying.
> - Remove create_workqueue() and use schedule_work()
> - Link to v1: https://lore.kernel.org/r/20231221-async-free-v1-1-94b27799=
2cb0@kernel.org
> ---
>  include/linux/swap_slots.h |  1 +
>  mm/swap_slots.c            | 29 +++++++++++++++++++++--------
>  2 files changed, 22 insertions(+), 8 deletions(-)
>
> diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h
> index 15adfb8c813a..67bc8fa30d63 100644
> --- a/include/linux/swap_slots.h
> +++ b/include/linux/swap_slots.h
> @@ -19,6 +19,7 @@ struct swap_slots_cache {
>  	spinlock_t	free_lock;  /* protects slots_ret, n_ret */
>  	swp_entry_t	*slots_ret;
>  	int		n_ret;
> +	struct work_struct async_free;
>  };
>=20=20
>  void disable_swap_slots_cache_lock(void);
> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
> index 0bec1f705f8e..71d344564e55 100644
> --- a/mm/swap_slots.c
> +++ b/mm/swap_slots.c
> @@ -44,6 +44,7 @@ static DEFINE_MUTEX(swap_slots_cache_mutex);
>  static DEFINE_MUTEX(swap_slots_cache_enable_mutex);
>=20=20
>  static void __drain_swap_slots_cache(unsigned int type);
> +static void swapcache_async_free_entries(struct work_struct *data);
>=20=20
>  #define use_swap_slot_cache (swap_slot_cache_active && swap_slot_cache_e=
nabled)
>  #define SLOTS_CACHE 0x1
> @@ -149,6 +150,7 @@ static int alloc_swap_slot_cache(unsigned int cpu)
>  		spin_lock_init(&cache->free_lock);
>  		cache->lock_initialized =3D true;
>  	}
> +	INIT_WORK(&cache->async_free, swapcache_async_free_entries);
>  	cache->nr =3D 0;
>  	cache->cur =3D 0;
>  	cache->n_ret =3D 0;
> @@ -269,6 +271,20 @@ static int refill_swap_slots_cache(struct swap_slots=
_cache *cache)
>  	return cache->nr;
>  }
>=20=20
> +static void swapcache_async_free_entries(struct work_struct *data)
> +{
> +	struct swap_slots_cache *cache;
> +
> +	cache =3D container_of(data, struct swap_slots_cache, async_free);
> +	spin_lock_irq(&cache->free_lock);
> +	/* Swap slots cache may be deactivated before acquiring lock */
> +	if (cache->slots_ret) {
> +		swapcache_free_entries(cache->slots_ret, cache->n_ret);
> +		cache->n_ret =3D 0;
> +	}
> +	spin_unlock_irq(&cache->free_lock);
> +}
> +
>  void free_swap_slot(swp_entry_t entry)
>  {
>  	struct swap_slots_cache *cache;
> @@ -282,17 +298,14 @@ void free_swap_slot(swp_entry_t entry)
>  			goto direct_free;
>  		}
>  		if (cache->n_ret >=3D SWAP_SLOTS_CACHE_SIZE) {
> -			/*
> -			 * Return slots to global pool.
> -			 * The current swap_map value is SWAP_HAS_CACHE.
> -			 * Set it to 0 to indicate it is available for
> -			 * allocation in global pool
> -			 */
> -			swapcache_free_entries(cache->slots_ret, cache->n_ret);
> -			cache->n_ret =3D 0;
> +			spin_unlock_irq(&cache->free_lock);
> +			schedule_work(&cache->async_free);
> +			goto direct_free;
>  		}
>  		cache->slots_ret[cache->n_ret++] =3D entry;
>  		spin_unlock_irq(&cache->free_lock);
> +		if (cache->n_ret >=3D SWAP_SLOTS_CACHE_SIZE)
> +			schedule_work(&cache->async_free);
>  	} else {
>  direct_free:
>  		swapcache_free_entries(&entry, 1);
>
> ---
> base-commit: eacce8189e28717da6f44ee492b7404c636ae0de
> change-id: 20231216-async-free-bef392015432
>
> Best regards,