Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <1554343303-11880-1-git-send-email-huangzhaoyang@gmail.com>
In-Reply-To: <1554343303-11880-1-git-send-email-huangzhaoyang@gmail.com>
From:   Suren Baghdasaryan <surenb@google.com>
Date:   Sat, 6 Apr 2019 17:43:26 -0700
Message-ID: <CAJuCfpEWG19-7HYjasmRXZV0Q+AnFNPB--qtAXSDCk97k7DRVg@mail.gmail.com>
Subject: Re: [PATCH] mm:workingset use real time to judge activity of the file page
To:     Zhaoyang Huang <huangzhaoyang@gmail.com>
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        Pavel Tatashin <pasha.tatashin@oracle.com>,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>,
        David Rientjes <rientjes@google.com>,
        Roman Gushchin <guro@fb.com>, Jeff Layton <jlayton@redhat.com>,
        Matthew Wilcox <mawilcox@microsoft.com>,
        linux-mm <linux-mm@kvack.org>,
        LKML <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Apr 3, 2019 at 7:03 PM Zhaoyang Huang <huangzhaoyang@gmail.com> wrote:
>
> From: Zhaoyang Huang <Zhaoyang Huang@unisoc.com>
>
> In previous implementation, the number of refault pages is used
> for judging the refault period of each page, which is not precised.
> We introduce the timestamp into the workingset's entry to measure
> the file page's activity.
>
> The patch is tested on an Android system, which can be described as
> comparing the launch time of an application between a huge memory
> consumption. The result is launch time decrease 50% and the page fault
> during the test decrease 80%.
>
> Signed-off-by: Zhaoyang Huang <huangzhaoyang@gmail.com>
> ---
>  include/linux/mmzone.h |  2 ++
>  mm/workingset.c        | 24 +++++++++++++++++-------
>  2 files changed, 19 insertions(+), 7 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 32699b2..c38ba0a 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -240,6 +240,8 @@ struct lruvec {
>         atomic_long_t                   inactive_age;
>         /* Refaults at the time of last reclaim cycle */
>         unsigned long                   refaults;
> +       atomic_long_t                   refaults_ratio;
> +       atomic_long_t                   prev_fault;
>  #ifdef CONFIG_MEMCG
>         struct pglist_data *pgdat;
>  #endif
> diff --git a/mm/workingset.c b/mm/workingset.c
> index 40ee02c..6361853 100644
> --- a/mm/workingset.c
> +++ b/mm/workingset.c
> @@ -159,7 +159,7 @@
>                          NODES_SHIFT +  \
>                          MEM_CGROUP_ID_SHIFT)
>  #define EVICTION_MASK  (~0UL >> EVICTION_SHIFT)
> -
> +#define EVICTION_JIFFIES (BITS_PER_LONG >> 3)
>  /*
>   * Eviction timestamps need to be able to cover the full range of
>   * actionable refaults. However, bits are tight in the radix tree
> @@ -175,18 +175,22 @@ static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
>         eviction >>= bucket_order;
>         eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
>         eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
> +       eviction = (eviction << EVICTION_JIFFIES) | (jiffies >> EVICTION_JIFFIES);
>         eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
>
>         return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
>  }
>
>  static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
> -                         unsigned long *evictionp)
> +                         unsigned long *evictionp, unsigned long *prev_jiffp)
>  {
>         unsigned long entry = (unsigned long)shadow;
>         int memcgid, nid;
> +       unsigned long prev_jiff;
>
>         entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
> +       entry >>= EVICTION_JIFFIES;
> +       prev_jiff = (entry & ((1UL << EVICTION_JIFFIES) - 1)) << EVICTION_JIFFIES;
>         nid = entry & ((1UL << NODES_SHIFT) - 1);
>         entry >>= NODES_SHIFT;
>         memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
> @@ -195,6 +199,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
>         *memcgidp = memcgid;
>         *pgdat = NODE_DATA(nid);
>         *evictionp = entry << bucket_order;
> +       *prev_jiffp = prev_jiff;
>  }
>
>  /**
> @@ -242,8 +247,12 @@ bool workingset_refault(void *shadow)
>         unsigned long refault;
>         struct pglist_data *pgdat;
>         int memcgid;
> +       unsigned long refault_ratio;
> +       unsigned long prev_jiff;
> +       unsigned long avg_refault_time;
> +       unsigned long refault_time;
>
> -       unpack_shadow(shadow, &memcgid, &pgdat, &eviction);
> +       unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &prev_jiff);
>
>         rcu_read_lock();
>         /*
> @@ -288,10 +297,11 @@ bool workingset_refault(void *shadow)
>          * list is not a problem.
>          */
>         refault_distance = (refault - eviction) & EVICTION_MASK;
> -
>         inc_lruvec_state(lruvec, WORKINGSET_REFAULT);
> -
> -       if (refault_distance <= active_file) {
> +       lruvec->refaults_ratio = atomic_long_read(&lruvec->inactive_age) / jiffies;

I also wonder how many times the division above yields a 0...

> +       refault_time = jiffies - prev_jiff;
> +       avg_refault_time = refault_distance / lruvec->refaults_ratio;

and then used here as a denominator.

> +       if (refault_time <= avg_refault_time) {
>                 inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
>                 rcu_read_unlock();
>                 return true;
> @@ -521,7 +531,7 @@ static int __init workingset_init(void)
>          * some more pages at runtime, so keep working with up to
>          * double the initial memory by using totalram_pages as-is.
>          */
> -       timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT;
> +       timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT - EVICTION_JIFFIES;
>         max_order = fls_long(totalram_pages - 1);
>         if (max_order > timestamp_bits)
>                 bucket_order = max_order - timestamp_bits;
> --
> 1.9.1
>