Linux内核情景分析的alloc_pages

NUMA结构的alloc_pages

==================== mm/numa.c 43 43 ====================
43  #ifdef CONFIG_DISCONTIGMEM
==================== mm/numa.c 91 128 ====================
91  /*
92   * This can be refined. Currently, tries to do round robin, instead
93   * should do concentratic circle search, starting from current node.
94   */
                             //分配策略,  所需物理块的大小,2的order次方
95  struct page * alloc_pages(int gfp_mask, unsigned long order)
96  {
97 struct page *ret = 0;
98 pg_data_t *start, *temp;
99  #ifndef CONFIG_NUMA
100 unsigned long flags;
101 static pg_data_t *next = 0;
102  #endif
103
104 if (order >= MAX_ORDER)
105 return NULL;
106  #ifdef CONFIG_NUMA//NUMA结构
107 temp = NODE_DATA(numa_node_id());//可以通过宏操作找到cpu的节数据结构队列
108  #else
109 spin_lock_irqsave(&node_lock, flags);
110 if (!next) next = pgdat_list;
111 temp = next;
112 next = next->node_next;
113 spin_unlock_irqrestore(&node_lock, flags);
114  #endif
/*
函数主要操作2个循环,一个从temp到队列末尾,一个从队头到temp,扫描所有节,直到某节点内存分配成功
*/
115 start = temp;
116 while (temp) {
117 if ((ret = alloc_pages_pgdat(temp, gfp_mask, order)))//接下来解析此函数
118 return(ret);
119 temp = temp->node_next;
120 }
121 temp = pgdat_list;
122 while (temp != start) {
123 if ((ret = alloc_pages_pgdat(temp, gfp_mask, order)))
124 return(ret);
125 temp = temp->node_next;
126 }
127 return(0);
128  }

alloc_pages_pgdat试图分配所需页面,是__alloc_pages的封装

85  static struct page * alloc_pages_pgdat(pg_data_t *pgdat, int gfp_mask,
86 unsigned long order)
87  {                      //node_zonelist决定分配策略数组
88     return __alloc_pages(pgdat->node_zonelists + gfp_mask, order);
89  }

与UMA的alloc_pages()相比较,UMA只有一个节点,contig_page_data.UMA与NUMA共同使用__alloc_pages

==================== include/linux/mm.h 343 352 ====================
343  #ifndef CONFIG_DISCONTIGMEM//只有这个无定义,才使用uma的__alloc_pages
344  static inline struct page * alloc_pages(int gfp_mask, unsigned long order)
83
345  {
346 /*
347  * Gets optimized away by the compiler.
348  */
349 if (order >= MAX_ORDER)
350 return NULL;
351 return __alloc_pages(contig_page_data.node_zonelists+(gfp_mask), order);
352  }

查看__alloc_page,

1. 如果只分配一个页面,而且要等待完成分配,又不适用于管理的目的
2. 把direct_reclaim设置为1,表示可以从相应的管理区的不活跃干净页面缓冲队列中回收
3. 84发现空闲页面短缺,唤醒以下2个进程,试图腾出一些页面出来

[alloc_pages()>__alloc_pages()]
270  /*
271   * This is the 'heart' of the zoned buddy allocator:
272   */
273  struct page * __alloc_pages(zonelist_t *zonelist, unsigned long order)
274  {
275 zone_t **zone;
276 int direct_reclaim = 0;
277 unsigned int gfp_mask = zonelist->gfp_mask;//获取具体的分配策略
278 struct page * page;
279
280 /*
281  * Allocations put pressure on the VM subsystem.
282  */
283 memory_pressure++;//表示内存管理所承受的压力,分配++,归还--
284
285 /*
286  * (If anyone calls gfp from interrupts nonatomically then it
287  * will sooner or later tripped up by a schedule().)
288  *
289  * We are falling back to lower-level zones if allocation
290  * in a higher zone fails.
291  */
292
293 /*
294  如果只分配一个页面,而且要等待完成分配,又不适用于管理的目的
把direct_reclaim设置为1,表示可以从相应的管理区的不活跃干净页面缓冲队列中回收
296  */
297 if (order == 0 && (gfp_mask & __GFP_WAIT) &&
298 !(current->flags & PF_MEMALLOC))
299 direct_reclaim = 1;
300
301 /*
302  * If we are about to get low on free pages and we also have
303  * an inactive page shortage, wake up kswapd.
84发现空闲页面短缺,唤醒以下2个进程,试图腾出一些页面出来
304  */
305 if (inactive_shortage() > inactive_target / 2 && free_shortage())
306 wakeup_kswapd(0);
307 /*
308  * If we are about to get low on free pages and cleaning
309  * the inactive_dirty pages would fix the situation,
310  * wake up bdflush.
311  */
312 else if (free_shortage() && nr_inactive_dirty_pages > free_shortage()
313 && nr_inactive_dirty_pages >= freepages.high)
314 wakeup_bdflush(0);
315

继续看__alloc_page代码

//如果管理区的空闲页面大于其最低标准,分配成功直接返回

1. //否则有进程(内核线程kreclaimd)在等待队列睡眠,把它唤醒,用于回收一些页面,备用

==================== mm/page_alloc.c 316 340 ====================
[alloc_pages()>__alloc_pages()]
316  try_again:
317 /*
318  * First, see if we have any zones with lots of free memory.
319  *
320  * We allocate free memory first because it doesn't contain
321  * any data ... DUH!
322  */
323 zone = zonelist->zones;//获取管理区指针
324 for (;;) {
325 zone_t *z = *(zone++);//管理区
326 if (!z)
327 break;
328 if (!z->size)
329 BUG();
330//如果管理区的空闲页面大于其最低标准
331 if (z->free_pages >= z->pages_low) {
332 page = rmqueue(z, order);//分配内存,接下来分析此函数
333 if (page)
334 return page;
335 } 
//否则有进程(内核线程kreclaimd)在等待队列睡眠,把它唤醒,用于回收一些页面,备用
else if (z->free_pages < z->pages_min &&
336 waitqueue_active(&kreclaimd_wait)) {
85
337 wake_up_interruptible(&kreclaimd_wait);
338 }
339 }
340

[alloc_pages()>__alloc_pages()>rmqueue()]
172  static struct page * rmqueue(zone_t *zone, unsigned long order)
173  {
174 free_area_t * area = zone->free_area + order;//获取其数组对应的元素
175 unsigned long curr_order = order;
176 struct list_head *head, *curr;
177 unsigned long flags;
178 struct page *page;
179
180 spin_lock_irqsave(&zone->lock, flags);//相应管理区加锁
181 do {
182 head = &area->free_list;//头
183 curr = memlist_next(head);//头的下一个节点
184
185 if (curr != head) {//不等于空,说明有物理页块
186 unsigned int index;
187//从非空队列中取出第一个结构page元素
188 page = memlist_entry(curr, struct page, list);
189 if (BAD_RANGE(zone,page))
190 BUG();
191 memlist_del(curr);//删除队列中的元素
192 index = (page - mem_map) - zone->offset;//偏移
193 MARK_USED(index, curr_order, area);//将相应位图设置为1
194 zone->free_pages -= 1 << order;
195//分配成功,把大块剩余的部分分解为小块,链入相应的队列
196 page = expand(zone, page, index, order, curr_order, area);
197 spin_unlock_irqrestore(&zone->lock, flags);
198
199 set_page_count(page, 1);
200 if (BAD_RANGE(zone,page))
201 BUG();
202 DEBUG_ADD_PAGE
203 return page;
204 }
205 curr_order++;
206 area++;
86
207 } while (curr_order < MAX_ORDER);
208 spin_unlock_irqrestore(&zone->lock, flags);
209
210 return NULL;
211  }

[alloc_pages()>__alloc_pages()>rmqueue()>expand()]
   /*
    
    low表示所需块大小,high表示实际大小
    */

150  static inline struct page * expand (zone_t *zone, struct page *page,
151  unsigned long index, int low, int high, free_area_t * area)
152  {
153 unsigned long size = 1 << high;
154
155 while (high > low) {
156 if (BAD_RANGE(zone,page))
157 BUG();
158 area--;
159 high--;
160 size >>= 1;//每次减少2的n次方
161 memlist_add_head(&(page)->list, &(area)->free_list);
162 MARK_USED(index, high, area);//标记位图
//处理更低一档的空闲块队列
163 index += size;
164 page += size;
165 }
166 if (BAD_RANGE(zone,page))
167 BUG();
168 return page;
169  }

就这样rmqueue队列一直往上扫描,直到分配成功或者失败,如果失败,则__alloc_pages通过for循环

指向下一个管理区(按照分配策略),直到成功.

要是给定的分配策略中的所有页面管理区都失败,那就只能加大力度再试试.要么降低对页面的水位要求

要么把缓冲在管理区的不活跃干净页面也给考虑进去

[alloc_pages()>__alloc_pages()]
341 /*
342  * Try to allocate a page from a zone with a HIGH
343  * amount of free + inactive_clean pages.
344  *
345  * If there is a lot of activity, inactive_target
346  * will be high and we'll have a good chance of
347  * finding a page using the HIGH limit.
348  */
//先用page_high,如果不行再用page_low
349 page = __alloc_pages_limit(zonelist, order, PAGES_HIGH, direct_reclaim);
350 if (page)
351 return page;
352
353 /*
354  * Then try to allocate a page from a zone with more
355  * than zone->pages_low free + inactive_clean pages.
356  *
357  * When the working set is very large and VM activity
358  * is low, we're most likely to have our allocation
359  * succeed here.
360  */
361 page = __alloc_pages_limit(zonelist, order, PAGES_LOW, direct_reclaim);
362 if (page)
363 return page;
364

[alloc_pages()>__alloc_pages()>__alloc_pages_limit()]
213  #define PAGES_MIN  0
214  #define PAGES_LOW  1
215  #define PAGES_HIGH 2
88
216
217  /*
218   * This function does the dirty work for __alloc_pages
219   * and is separated out to keep the code size smaller.
220   * (suggested by Davem at 1:30 AM, typed by Rik at 6 AM)
221   */
222  static struct page * __alloc_pages_limit(zonelist_t *zonelist,
223 unsigned long order, int limit, int direct_reclaim)
224  {
225 zone_t **zone = zonelist->zones;
226
227 for (;;) {
228 zone_t *z = *(zone++);
229 unsigned long water_mark;
230
231 if (!z)
232 break;
233 if (!z->size)
234 BUG();
235
236 /*
237  * We allocate if the number of free + inactive_clean
238  * pages is above the watermark.
239  */
240 switch (limit) {
241 default:
242 case PAGES_MIN://通过分配策略,改变水位
243 water_mark = z->pages_min;
244 break;
245 case PAGES_LOW:
246 water_mark = z->pages_low;
247 break;
248 case PAGES_HIGH:
249 water_mark = z->pages_high;
250 }
251//如果空闲页面+干净回收页面大于最低水位
252 if (z->free_pages + z->inactive_clean_pages > water_mark) {
253 struct page *page = NULL;
254 /* 如果空闲页面小于最低水位+8,那就回收. */
255 if (direct_reclaim && z->free_pages < z->pages_min + 8)
256 page = reclaim_page(z);//把inactive_clean_list队列回收页面
257 /* If that fails, fall back to rmqueue. */
258 if (!page)
259 page = rmqueue(z, order);
260 if (page)
261 return page;
262 }
263 }
264
89
265 /* Found nothing. */
266 return NULL;
267  }

如果还是不行,那就说明管理区的页面很短缺了

[alloc_pages()>__alloc_pages()]
365 /*
366  * OK, none of the zones on our zonelist has lots
367  * of pages free.
368  *
369  * We wake up kswapd, in the hope that kswapd will
370  * resolve this situation before memory gets tight.
371  *
372  * We also yield the CPU, because that:
373  * - gives kswapd a chance to do something
374  * - slows down allocations, in particular the
375  *   allocations from the fast allocator that's
376  *   causing the problems ...
377  * - ... which minimises the impact the "bad guys"
378  *   have on the rest of the system
379  * - if we don't have __GFP_IO set, kswapd may be
380  *   able to free some memory we can't free ourselves
381  */
382 wakeup_kswapd(0);//唤醒内核线程,想办法换出一些页面
383 if (gfp_mask & __GFP_WAIT) {//要求必须获取页面,分配不到时等待,那就让系统再调用一次(目的为了调度kswapd线程)
//以此获取一些页面
384 __set_current_state(TASK_RUNNING);
385 current->policy |= SCHED_YIELD;
386 schedule();
387 }
388
389 /*
390  * After waking up kswapd, we try to allocate a page
391  * from any zone which isn't critical yet.
392  *
393  * Kswapd should, in most situations, bring the situation
394  * back to normal in no time.
395  */
/*
如果不允许等待,那就用pages_min再调用一次__alloc_pages_limit
*/
396 page = __alloc_pages_limit(zonelist, order, PAGES_MIN, direct_reclaim);
397 if (page)
398 return page;
399

要是再失败,那就看谁在要求分配内存页面.如果是kswaped,本身就是内存分配工作者

是要更好的分配页面,比一般进程更重要,那就PF_memalloc标志位为1,不过我们先看一般进程

即pe_memalloc标志位为0的策略.

==================== mm/page_alloc.c 400 477 ====================
[alloc_pages()>__alloc_pages()]
400 /*
401  * Damn, we didn't succeed.
402  *
403  * This can be due to 2 reasons:
404  * - we're doing a higher-order allocation
405  *   --> move pages to the free list until we succeed
406  * - we're /really/ tight on memory
407  *   --> wait on the kswapd waitqueue until memory is freed
408  */
409 if (!(current->flags & PF_MEMALLOC)) {
410 /*
411  * Are we dealing with a higher order allocation?
412  *
413  * Move pages from the inactive_clean to the free list
414  * in the hope of creating a large, physically contiguous
415  * piece of free memory.
416  */
417 if (order > 0 && (gfp_mask & __GFP_WAIT)) {
418 zone = zonelist->zones;
419 /* First, clean some dirty pages. */
420 current->flags |= PF_MEMALLOC;
421 page_launder(gfp_mask, 1);//把脏页洗干净(页面的定期换出)
422 current->flags &= ~PF_MEMALLOC;
423 for (;;) {
424 zone_t *z = *(zone++);//通过一个for循环把干净页面等待队列的页面回收
425 if (!z)
426 break;
427 if (!z->size)
428 continue;
//是否有干净页面
429 while (z->inactive_clean_pages) {
430 struct page * page;
431 /* Move one page to the free list. */
432 page = reclaim_page(z);//回收干净页面等待队列
433 if (!page)
434 break;
91
435 __free_page(page);//通过__free_page释放页面的同时,把空闲页面拼接成大的页面块
436 /* Try if the allocation succeeds. */
437 page = rmqueue(z, order);//试图再次请求成功
438 if (page)
439 return page;
440 }
441 }
442 }
443 /*
444  * When we arrive here, we are really tight on memory.
445  *
446  * We wake up kswapd and sleep until kswapd wakes us
447  * up again. After that we loop back to the start.
448  *
449  * We have to do this because something else might eat
450  * the memory kswapd frees for us and we need to be
451  * reliable. Note that we don't loop back for higher
452  * order allocations since it is possible that kswapd
453  * simply cannot free a large enough contiguous area
454  * of memory *ever*.
455  */
/*
如果依旧失败,而且必须要求分配到页面,那就等待,进程睡眠
*/
456 if ((gfp_mask & (__GFP_WAIT|__GFP_IO)) == (__GFP_WAIT|__GFP_IO)) {
457 wakeup_kswapd(1);//唤醒kswaped,要求分配页面进程睡眠,等待kswapd完成一轮运行再唤醒需要页面的进程
458 memory_pressure++;
459 if (!order)//如果要求分配的是1个页面,跳到try_again
460 goto try_again;
461 /*
462  * If __GFP_IO isn't set, we can't wait on kswapd because
463  * kswapd just might need some IO locks /we/ are holding ...
464  *
465  * SUBTLE: The scheduling point above makes sure that
466  * kswapd does get the chance to free memory we can't
467  * free ourselves...
468  */
469 } else if (gfp_mask & __GFP_WAIT) {
470 try_to_free_pages(gfp_mask);//另外一种方案...直接调用此函数获取页面(本来就是kswaped函数调用的)
471 memory_pressure++;
472 if (!order)
473 goto try_again;
474 }
475
476 }
477

最后的办法了

 

[alloc_pages()>__alloc_pages()]
478 /*
479  * Final phase: allocate anything we can!
480  *
481  * Higher order allocations, GFP_ATOMIC allocations and
482  * recursive allocations (PF_MEMALLOC) end up here.
483  *
484  * Only recursive allocations can use the very last pages
485  * in the system, otherwise it would be just too easy to
486  * deadlock the system...
487  */
488 zone = zonelist->zones;
489 for (;;) {
490 zone_t *z = *(zone++);
491 struct page * page = NULL;
492 if (!z)
493 break;
494 if (!z->size)
495 BUG();
496
497 /*
498  * SUBTLE: direct_reclaim is only possible if the task
499  * becomes PF_MEMALLOC while looping above. This will
500  * happen when the OOM killer selects this task for
501  * instant execution...
93
502  */
503 if (direct_reclaim) {
504 page = reclaim_page(z);
505 if (page)
506 return page;
507 }
508
509 /* XXX: is pages_min/4 a good amount to reserve for this? */
510 if (z->free_pages < z->pages_min / 4 &&
511 !(current->flags & PF_MEMALLOC))
512 continue;
513 page = rmqueue(z, order);
514 if (page)
515 return page;
516 }
517
518 /* No luck.. */
519 printk(KERN_ERR "__alloc_pages: %lu-order allocation failed.\n", order);
520 return NULL;
521  }

如果这都失败,那就系统一定出现了问题了

节点->页面短缺->调用线程,试图腾出页面->

开始遍历每个管理区->一旦管理区的空闲页面大于最低水位,那就调用rmqueue进行分配,否则把kcreclaimd线程唤醒,回收页面

rmqueue分析->如果失败,换一个管理区(按照分配策略),如果全部失败->降低页面的水位要求,把不活跃干净的页面考虑进来

->调用__alloc_pages_limit->如果空闲页面小于最低水位+8,那就回收干净页面队列(换出,腾出空间)->失败,唤醒内核线程,获取页面

->依旧失败,把脏页面洗干净,换出.获取页面->依旧失败,再次调用线程换取页面,依旧失败->把水位降低到1/4看能否满足分配->

依旧不能,系统出了问题

 

来自为知笔记(Wiz)