2020년 3월 19일 (목) 오전 2:52, Johannes Weiner <hannes@xxxxxxxxxxx>님이 작성:
>
> On Tue, Mar 17, 2020 at 02:41:50PM +0900, js1304@xxxxxxxxx wrote:
> > From: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
> >
> > In current implementation, newly created or swap-in anonymous page
> > is started on active list. Growing active list results in rebalancing
> > active/inactive list so old pages on active list are demoted to inactive
> > list. Hence, the page on active list isn't protected at all.
> >
> > Following is an example of this situation.
> >
> > Assume that 50 hot pages on active list. Numbers denote the number of
> > pages on active/inactive list (active | inactive).
> >
> > 1. 50 hot pages on active list
> > 50(h) | 0
> >
> > 2. workload: 50 newly created (used-once) pages
> > 50(uo) | 50(h)
> >
> > 3. workload: another 50 newly created (used-once) pages
> > 50(uo) | 50(uo), swap-out 50(h)
> >
> > This patch tries to fix this issue.
> > Like as file LRU, newly created or swap-in anonymous pages will be
> > inserted to the inactive list. They are promoted to active list if
> > enough reference happens. This simple modification changes the above
> > example as following.
> >
> > 1. 50 hot pages on active list
> > 50(h) | 0
> >
> > 2. workload: 50 newly created (used-once) pages
> > 50(h) | 50(uo)
> >
> > 3. workload: another 50 newly created (used-once) pages
> > 50(h) | 50(uo), swap-out 50(uo)
> >
> > As you can see, hot pages on active list would be protected.
> >
> > Note that, this implementation has a drawback that the page cannot
> > be promoted and will be swapped-out if re-access interval is greater than
> > the size of inactive list but less than the size of total(active+inactive).
> > To solve this potential issue, following patch will apply workingset
> > detection that is applied to file LRU some day before.
> >
> > Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
>
> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
>
> > -void lru_cache_add_active_or_unevictable(struct page *page,
> > +void lru_cache_add_inactive_or_unevictable(struct page *page,
> > struct vm_area_struct *vma)
> > {
> > + bool evictable;
> > +
> > VM_BUG_ON_PAGE(PageLRU(page), page);
> >
> > - if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
> > - SetPageActive(page);
> > - else if (!TestSetPageMlocked(page)) {
> > + evictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED;
> > + if (!evictable && !TestSetPageMlocked(page)) {
>
> Minor point, but in case there is a v4: `unevictable` instead of
> !evictable would be a bit easier to read, match the function name,
> PageUnevictable etc.
Okay. Looks like v4 is needed so I will change it as you said.
Thanks.
