统计内存外碎片事件

参考

• https://blog.csdn.net/qq_43573047/article/details/140734352
• https://zhuanlan.zhihu.com/p/479922331

在内存分配的时候，当指定的迁移类型的内存不足时，会向其他迁移类型借，内核通过下面的数组定义了迁移类型的借用顺序：

/*
 * This array describes the order lists are fallen back to when
 * the free lists for the desirable migrate type are depleted
 *
 * The other migratetypes do not have fallbacks.
 */
static int fallbacks[MIGRATE_TYPES][3] = {
	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_TYPES },
	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES },
	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_TYPES },
};

这部分的代码如下：

/*
 * Try finding a free buddy page on the fallback list and put it on the free
 * list of requested migratetype, possibly along with other pages from the same
 * block, depending on fragmentation avoidance heuristics. Returns true if
 * fallback was found so that __rmqueue_smallest() can grab it.
 *
 * The use of signed ints for order and current_order is a deliberate
 * deviation from the rest of this file, to make the for loop
 * condition simpler.
 */
static __always_inline bool
__rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
						unsigned int alloc_flags)
{
	struct free_area *area;
	int current_order;
	int min_order = order;
	struct page *page;
	int fallback_mt;
	bool can_steal;

	/*
	 * Do not steal pages from freelists belonging to other pageblocks
	 * i.e. orders < pageblock_order. If there are no local zones free,
	 * the zonelists will be reiterated without ALLOC_NOFRAGMENT.
	 */
	if (order < pageblock_order && alloc_flags & ALLOC_NOFRAGMENT)
		min_order = pageblock_order;

	/*
	 * Find the largest available free page in the other list. This roughly
	 * approximates finding the pageblock with the most free pages, which
	 * would be too costly to do exactly.
	 */
	for (current_order = MAX_ORDER - 1; current_order >= min_order;
				--current_order) {
		area = &(zone->free_area[current_order]);
	    // 如果可以借用，那么会返回目标迁移类型
		fallback_mt = find_suitable_fallback(area, current_order,
				start_migratetype, false, &can_steal);
		if (fallback_mt == -1)
			continue;

		/*
		 * We cannot steal all free pages from the pageblock and the
		 * requested migratetype is movable. In that case it's better to
		 * steal and split the smallest available page instead of the
		 * largest available page, because even if the next movable
		 * allocation falls back into a different pageblock than this
		 * one, it won't cause permanent fragmentation.
		 */
		if (!can_steal && start_migratetype == MIGRATE_MOVABLE
					&& current_order > order)
			goto find_smallest;

		goto do_steal;
	}

	return false;

find_smallest:
	for (current_order = order; current_order < MAX_ORDER;
							current_order++) {
		area = &(zone->free_area[current_order]);
		fallback_mt = find_suitable_fallback(area, current_order,
				start_migratetype, false, &can_steal);
		if (fallback_mt != -1)
			break;
	}

	/*
	 * This should not happen - we already found a suitable fallback
	 * when looking for the largest page.
	 */
	VM_BUG_ON(current_order == MAX_ORDER);

do_steal:
    // 从目标迁移类型申请内存
	page = get_page_from_free_area(area, fallback_mt);

    // 修改内存的迁移类型
	steal_suitable_fallback(zone, page, alloc_flags, start_migratetype,
								can_steal);

	// 记录trace
	trace_mm_page_alloc_extfrag(page, order, current_order,
		start_migratetype, fallback_mt);

	return true;
}

上面将借用成功的信息通过trace输出了出来，这样我们就可以在上层利用各种监控机制统计。

这个trace_event的路径是：/sys/kernel/tracing/events/kmem/mm_page_alloc_extfrag

定义如下：include\trace\events\kmem.h

TRACE_EVENT(mm_page_alloc_extfrag,

	TP_PROTO(struct page *page,
		int alloc_order, int fallback_order,
		int alloc_migratetype, int fallback_migratetype),

	TP_ARGS(page,
		alloc_order, fallback_order,
		alloc_migratetype, fallback_migratetype),

	TP_STRUCT__entry(
		__field(	unsigned long,	pfn			)
		__field(	int,		alloc_order		)
		__field(	int,		fallback_order		)
		__field(	int,		alloc_migratetype	)
		__field(	int,		fallback_migratetype	)
		__field(	int,		change_ownership	)
	),

	TP_fast_assign(
		__entry->pfn			= page_to_pfn(page);
		__entry->alloc_order		= alloc_order;
		__entry->fallback_order		= fallback_order;
		__entry->alloc_migratetype	= alloc_migratetype;
		__entry->fallback_migratetype	= fallback_migratetype;
		__entry->change_ownership	= (alloc_migratetype ==
					get_pageblock_migratetype(page));
	),

	TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
		pfn_to_page(__entry->pfn),
		__entry->pfn,
		__entry->alloc_order,
		__entry->fallback_order,
		pageblock_order,
		__entry->alloc_migratetype,
		__entry->fallback_migratetype,
		__entry->fallback_order < pageblock_order,
		__entry->change_ownership)
);

完。