Re: [PATCH 8/8] Per-container pages reclamation

[Balbir Singh <balbir@linux.vnet.ibm.com>]

Pavel Emelianov wrote:
> Balbir Singh wrote:
>> Pavel Emelianov wrote:
>>> Implement try_to_free_pages_in_container() to free the
>>> pages in container that has run out of memory.
>>>
>>> The scan_control->isolate_pages() function isolates the
>>> container pages only.
>>>
>> Pavel,
>>
>> I've just started playing around with these patches, I preferred
>> the approach of v1. Please see below
>>
>>> +static unsigned long isolate_container_pages(unsigned long nr_to_scan,
>>> +        struct list_head *src, struct list_head *dst,
>>> +        unsigned long *scanned, struct zone *zone)
>>> +{
>>> +    unsigned long nr_taken = 0;
>>> +    struct page *page;
>>> +    struct page_container *pc;
>>> +    unsigned long scan;
>>> +    LIST_HEAD(pc_list);
>>> +
>>> +    for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
>>> +        pc = list_entry(src->prev, struct page_container, list);
>>> +        page = pc->page;
>>> +        if (page_zone(page) != zone)
>>> +            continue;
>> shrink_zone() will walk all pages looking for pages belonging to this
> 
> No. shrink_zone() will walk container pages looking for pages in the desired zone.
> Scann through the full zone is done on global memory shortage.
> 

Yes, I see that now. But for each zone in the system, we walk through the
containers list - right?

I have some more fixes, improvements that I want to send across.
I'll start sending them out to you as I test and verify them.


>> container and this slows down the reclaim quite a bit. Although we've
>> reused code, we've ended up walking the entire list of the zone to
>> find pages belonging to a particular container, this was the same
>> problem I had with my RSS controller patches.
>>
>>> +
>>> +        list_move(&pc->list, &pc_list);
>>> +
>>
> 


-- 
	Warm Regards,
	Balbir Singh
	Linux Technology Center
	IBM, ISTL