Re: [PATCH v15 4/7] mm: Introduce Reported pages

[Alexander Duyck <alexander.h.duyck@linux.intel.com>]

On Mon, 2019-12-16 at 06:44 -0500, Nitesh Narayan Lal wrote:
> On 12/5/19 11:22 AM, Alexander Duyck wrote:
> > From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
> > 
> > In order to pave the way for free page reporting in virtualized
> > environments we will need a way to get pages out of the free lists and
> > identify those pages after they have been returned. To accomplish this,
> > this patch adds the concept of a Reported Buddy, which is essentially
> > meant to just be the Uptodate flag used in conjunction with the Buddy
> > page type.
> > 
> > To prevent the reported pages from leaking outside of the buddy lists I
> > added a check to clear the PageReported bit in the del_page_from_free_list
> > function. As a result any reported page that is split, merged, or
> > allocated will have the flag cleared prior to the PageBuddy value being
> > cleared.
> > 
> > The process for reporting pages is fairly simple. Once we free a page that
> > meets the minimum order for page reporting we will schedule a worker thread
> > to start 2s or more in the future. That worker thread will begin working
> > from the lowest supported page reporting order up to MAX_ORDER - 1 pulling
> > unreported pages from the free list and storing them in the scatterlist.
> > 
> > When processing each individual free list it is necessary for the worker
> > thread to release the zone lock when it needs to stop and report the full
> > scatterlist of pages. To reduce the work of the next iteration the worker
> > thread will rotate the free list so that the first unreported page in the
> > free list becomes the first entry in the list.
> 
> [...]
> 
> > k);
> > +
> > +	return err;
> > +}
> > +
> > +static int
> > +page_reporting_process_zone(struct page_reporting_dev_info *prdev,
> > +			    struct scatterlist *sgl, struct zone *zone)
> > +{
> > +	unsigned int order, mt, leftover, offset = PAGE_REPORTING_CAPACITY;
> > +	unsigned long watermark;
> > +	int err = 0;
> > +
> > +	/* Generate minimum watermark to be able to guarantee progress */
> > +	watermark = low_wmark_pages(zone) +
> > +		    (PAGE_REPORTING_CAPACITY << PAGE_REPORTING_MIN_ORDER);
> > +
> > +	/*
> > +	 * Cancel request if insufficient free memory or if we failed
> > +	 * to allocate page reporting statistics for the zone.
> > +	 */
> > +	if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
> > +		return err;
> > +
> 
> Will it not make more sense to check the low watermark condition before every
> reporting request generated for a bunch of 32 isolated pages?
> or will that be too costly?

My thought is to wait until we are actually processing the request. That
way we are only performing this check once every 2 seconds instead of
every time we are thinking about requesting page reporting.

Keep in mind I removed the reported_pages tracking statistics so we now
are requesting as soon as we free any page. So if we moved the check tot
he request itself it would mean that a low memory condition would result
in us repeatedly checking the low water mark and failing the test.