resend it via the right mailling list and rewrite the comments by ZY.
On Thu, Apr 4, 2019 at 3:15 PM Michal Hocko <mhocko@xxxxxxxxxx> wrote:
>
> [Fixup email for Pavel and add Johannes]
>
> On Thu 04-04-19 11:30:17, Zhaoyang Huang wrote:
> > From: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
> >
> > In previous implementation, the number of refault pages is used
> > for judging the refault period of each page, which is not precised as
> > eviction of other files will be affect a lot on current cache.
> > We introduce the timestamp into the workingset's entry and refault ratio
> > to measure the file page's activity. It helps to decrease the affection
> > of other files(average refault ratio can reflect the view of whole system
> > 's memory).
> > 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%.
> >
I don't understand what exactly you're saying here, can you please elaborate?
The reason it's using distances instead of absolute time is because
the ordering of the LRU is relative and not based on absolute time.
E.g. if a page is accessed every 500ms, it depends on all other pages
to determine whether this page is at the head or the tail of the LRU.
So when you refault, in order to determine the relative position of
the refaulted page in the LRU, you have to compare it to how fast that
LRU is moving. The absolute refault time, or the average time between
refaults, is not comparable to what's already in memory.
comment by ZY
For current implementation, it is hard to deal with the evaluation of
refault period under the scenario of huge dropping of file pages
within short time, which maybe caused by a high order allocation or
continues single page allocation in KSWAPD. On the contrary, such page
which having a big refault_distance will be deemed as INACTIVE
wrongly, which will be reclaimed earlier than it should be and lead to
page thrashing. So we introduce 'avg_refault_time' & 'refault_ratio'
to judge if the refault is a accumulated thing or caused by a tight
reclaiming. That is to say, a big refault_distance in a long time
would also be inactive as the result of comparing it with ideal
time(avg_refault_time: avg_refault_time = delta_lru_reclaimed_pages/
avg_refault_retio (refault_ratio = lru->inactive_ages / time).
> > Signed-off-by: Zhaoyang Huang <huangzhaoyang@xxxxxxxxx>
> > ---
> > 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;
> > + refault_time = jiffies - prev_jiff;
> > + avg_refault_time = refault_distance / lruvec->refaults_ratio;
> > + 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
>
> --
> Michal Hocko
> SUSE Labs
