Re: [PATCH] mm, page_alloc: simplify hot/cold page handling in rmqueue_bulk()

[Mel Gorman]

On Wed, Oct 18, 2017 at 09:35:28AM +0200, Vlastimil Babka wrote:
> The rmqueue_bulk() function fills an empty pcplist with pages from the free
> list. It tries to preserve increasing order by pfn to the caller, because it
> leads to better performance with some I/O controllers, as explained in
> e084b2d95e48 ("page-allocator: preserve PFN ordering when __GFP_COLD is set").
> For callers requesting cold pages, which are obtained from the tail of
> pcplists, it means the pcplist has to be filled in reverse order from the free
> lists (the hot/cold property only applies when pages are recycled on the
> pcplists, not when refilled from free lists).
> 
> The related comment in rmqueue_bulk() wasn't clear to me without reading the
> log of the commit mentioned above, so try to clarify it.
> 
> The code for filling the pcplists in order determined by the cold flag also
> seems unnecessarily hard to follow. It's sufficient to either use list_add()
> or list_add_tail(), but the current code also updates the list head pointer
> in each step to the last added page, which then counterintuitively requires
> to switch the usage of list_add() and list_add_tail() to achieve the desired
> order, with no apparent benefit. This patch simplifies the code.
> 
> Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>

The "cold" treatment is dubious because almost everything that frees
considers the page "hot" which limits the usefulness of hot/cold in the
allocator. While I do not see a problem with your patch as such, please
take a look at "mm: Remove __GFP_COLD" in particular. The last 4 patches
in that series make a number of observations on how "cold" is treated in
the allocator.

-- 
Mel Gorman
SUSE Labs