Re: [PATCH v3 04/13] mm, compaction: move pageblock checks up from isolate_migratepages_range()

[Joonsoo Kim]

On Fri, Jun 20, 2014 at 05:49:34PM +0200, Vlastimil Babka wrote:
> isolate_migratepages_range() is the main function of the compaction scanner,
> called either on a single pageblock by isolate_migratepages() during regular
> compaction, or on an arbitrary range by CMA's __alloc_contig_migrate_range().
> It currently perfoms two pageblock-wide compaction suitability checks, and
> because of the CMA callpath, it tracks if it crossed a pageblock boundary in
> order to repeat those checks.
> 
> However, closer inspection shows that those checks are always true for CMA:
> - isolation_suitable() is true because CMA sets cc->ignore_skip_hint to true
> - migrate_async_suitable() check is skipped because CMA uses sync compaction
> 
> We can therefore move the checks to isolate_migratepages(), reducing variables
> and simplifying isolate_migratepages_range(). The update_pageblock_skip()
> function also no longer needs set_unsuitable parameter.
> 
> Furthermore, going back to compact_zone() and compact_finished() when pageblock
> is unsuitable is wasteful - the checks are meant to skip pageblocks quickly.
> The patch therefore also introduces a simple loop into isolate_migratepages()
> so that it does not return immediately on pageblock checks, but keeps going
> until isolate_migratepages_range() gets called once. Similarily to
> isolate_freepages(), the function periodically checks if it needs to reschedule
> or abort async compaction.
> 
> Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
> Cc: Minchan Kim <minchan@xxxxxxxxxx>
> Cc: Mel Gorman <mgorman@xxxxxxx>
> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
> Cc: Michal Nazarewicz <mina86@xxxxxxxxxx>
> Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> Cc: Christoph Lameter <cl@xxxxxxxxx>
> Cc: Rik van Riel <riel@xxxxxxxxxx>
> Cc: David Rientjes <rientjes@xxxxxxxxxx>
> ---
>  mm/compaction.c | 112 +++++++++++++++++++++++++++++---------------------------
>  1 file changed, 59 insertions(+), 53 deletions(-)
> 
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 3064a7f..ebe30c9 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -132,7 +132,7 @@ void reset_isolation_suitable(pg_data_t *pgdat)
>   */
>  static void update_pageblock_skip(struct compact_control *cc,
>  			struct page *page, unsigned long nr_isolated,
> -			bool set_unsuitable, bool migrate_scanner)
> +			bool migrate_scanner)
>  {
>  	struct zone *zone = cc->zone;
>  	unsigned long pfn;
> @@ -146,12 +146,7 @@ static void update_pageblock_skip(struct compact_control *cc,
>  	if (nr_isolated)
>  		return;
>  
> -	/*
> -	 * Only skip pageblocks when all forms of compaction will be known to
> -	 * fail in the near future.
> -	 */
> -	if (set_unsuitable)
> -		set_pageblock_skip(page);
> +	set_pageblock_skip(page);
>  
>  	pfn = page_to_pfn(page);
>  
> @@ -180,7 +175,7 @@ static inline bool isolation_suitable(struct compact_control *cc,
>  
>  static void update_pageblock_skip(struct compact_control *cc,
>  			struct page *page, unsigned long nr_isolated,
> -			bool set_unsuitable, bool migrate_scanner)
> +			bool migrate_scanner)
>  {
>  }
>  #endif /* CONFIG_COMPACTION */
> @@ -345,8 +340,7 @@ isolate_fail:
>  
>  	/* Update the pageblock-skip if the whole pageblock was scanned */
>  	if (blockpfn == end_pfn)
> -		update_pageblock_skip(cc, valid_page, total_isolated, true,
> -				      false);
> +		update_pageblock_skip(cc, valid_page, total_isolated, false);
>  
>  	count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
>  	if (total_isolated)
> @@ -474,14 +468,12 @@ unsigned long
>  isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
>  		unsigned long low_pfn, unsigned long end_pfn, bool unevictable)
>  {
> -	unsigned long last_pageblock_nr = 0, pageblock_nr;
>  	unsigned long nr_scanned = 0, nr_isolated = 0;
>  	struct list_head *migratelist = &cc->migratepages;
>  	struct lruvec *lruvec;
>  	unsigned long flags;
>  	bool locked = false;
>  	struct page *page = NULL, *valid_page = NULL;
> -	bool set_unsuitable = true;
>  	const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ?
>  					ISOLATE_ASYNC_MIGRATE : 0) |
>  				    (unevictable ? ISOLATE_UNEVICTABLE : 0);
> @@ -545,28 +537,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
>  		if (!valid_page)
>  			valid_page = page;
>  
> -		/* If isolation recently failed, do not retry */
> -		pageblock_nr = low_pfn >> pageblock_order;
> -		if (last_pageblock_nr != pageblock_nr) {
> -			int mt;
> -
> -			last_pageblock_nr = pageblock_nr;
> -			if (!isolation_suitable(cc, page))
> -				goto next_pageblock;
> -
> -			/*
> -			 * For async migration, also only scan in MOVABLE
> -			 * blocks. Async migration is optimistic to see if
> -			 * the minimum amount of work satisfies the allocation
> -			 */
> -			mt = get_pageblock_migratetype(page);
> -			if (cc->mode == MIGRATE_ASYNC &&
> -			    !migrate_async_suitable(mt)) {
> -				set_unsuitable = false;
> -				goto next_pageblock;
> -			}
> -		}
> -
>  		/*
>  		 * Skip if free. page_order cannot be used without zone->lock
>  		 * as nothing prevents parallel allocations or buddy merging.
> @@ -668,8 +638,7 @@ next_pageblock:
>  	 * if the whole pageblock was scanned without isolating any page.
>  	 */
>  	if (low_pfn == end_pfn)
> -		update_pageblock_skip(cc, valid_page, nr_isolated,
> -				      set_unsuitable, true);
> +		update_pageblock_skip(cc, valid_page, nr_isolated, true);
>  
>  	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
>  
> @@ -840,34 +809,74 @@ typedef enum {
>  } isolate_migrate_t;
>  
>  /*
> - * Isolate all pages that can be migrated from the block pointed to by
> - * the migrate scanner within compact_control.
> + * Isolate all pages that can be migrated from the first suitable block,
> + * starting at the block pointed to by the migrate scanner pfn within
> + * compact_control.
>   */
>  static isolate_migrate_t isolate_migratepages(struct zone *zone,
>  					struct compact_control *cc)
>  {
>  	unsigned long low_pfn, end_pfn;
> +	struct page *page;
>  
> -	/* Do not scan outside zone boundaries */
> -	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
> +	/* Start at where we last stopped, or beginning of the zone */
> +	low_pfn = cc->migrate_pfn;
>  
>  	/* Only scan within a pageblock boundary */
>  	end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
>  
> -	/* Do not cross the free scanner or scan within a memory hole */
> -	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
> -		cc->migrate_pfn = end_pfn;
> -		return ISOLATE_NONE;
> -	}
> +	/*
> +	 * Iterate over whole pageblocks until we find the first suitable.
> +	 * Do not cross the free scanner.
> +	 */
> +	for (; end_pfn <= cc->free_pfn;
> +			low_pfn = end_pfn, end_pfn += pageblock_nr_pages) {
> +
> +		/*
> +		 * This can potentially iterate a massively long zone with
> +		 * many pageblocks unsuitable, so periodically check if we
> +		 * need to schedule, or even abort async compaction.
> +		 */
> +		if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
> +						&& compact_should_abort(cc))
> +			break;
>  
> -	/* Perform the isolation */
> -	low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn, false);
> -	if (!low_pfn || cc->contended)
> -		return ISOLATE_ABORT;
> +		/* Do not scan within a memory hole */
> +		if (!pfn_valid(low_pfn))
> +			continue;
> +
> +		page = pfn_to_page(low_pfn);
> +		/* If isolation recently failed, do not retry */
> +		if (!isolation_suitable(cc, page))
> +			continue;
>  
> +		/*
> +		 * For async compaction, also only scan in MOVABLE blocks.
> +		 * Async compaction is optimistic to see if the minimum amount
> +		 * of work satisfies the allocation.
> +		 */
> +		if (cc->mode == MIGRATE_ASYNC &&
> +		    !migrate_async_suitable(get_pageblock_migratetype(page)))
> +			continue;
> +
> +		/* Perform the isolation */
> +		low_pfn = isolate_migratepages_range(zone, cc, low_pfn,
> +								end_pfn, false);
> +		if (!low_pfn || cc->contended)
> +			return ISOLATE_ABORT;
> +
> +		/*
> +		 * Either we isolated something and proceed with migration. Or
> +		 * we failed and compact_zone should decide if we should
> +		 * continue or not.
> +		 */
> +		break;
> +	}
> +
> +	/* Record where migration scanner will be restarted */

If we make isolate_migratepages* interface like as isolate_freepages*,
we can get more clean and micro optimized code. Because
isolate_migratepages_range() can handle arbitrary range and this patch
make isolate_migratepages() also handle arbitrary range, there would
be some redundant codes. :)

Thanks.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/