Contents of /trunk/kernel26-tinyalx/patches-2.6.21-r14/0011-2.6.21-mm-swap_prefetch-35.patch
Parent Directory | Revision Log
Revision 453 -
(show annotations)
(download)
Fri Jan 25 23:34:48 2008 UTC (16 years, 9 months ago) by niro
File size: 30790 byte(s)
Fri Jan 25 23:34:48 2008 UTC (16 years, 9 months ago) by niro
File size: 30790 byte(s)
-tiny-alx 2.6.21-tinyalx-r14
1 | Implement swap prefetching when the vm is relatively idle and there is free |
2 | ram available. The code is based on some preliminary code by Thomas |
3 | Schlichter. |
4 | |
5 | This stores a list of swapped entries in a list ordered most recently used |
6 | and a radix tree. It generates a low priority kernel thread running at |
7 | nice 19 to do the prefetching at a later stage. |
8 | |
9 | Once pages have been added to the swapped list, a timer is started, testing |
10 | for conditions suitable to prefetch swap pages every 5 seconds. Suitable |
11 | conditions are defined as lack of swapping out or in any pages, and no |
12 | watermark tests failing. Significant amounts of dirtied ram and changes in |
13 | free ram representing disk writes or reads also prevent prefetching. |
14 | |
15 | It then checks that we have spare ram looking for at least 3* pages_high |
16 | free per zone and if it succeeds that will prefetch pages from swap into |
17 | the swap cache. The pages are added to the tail of the inactive list to |
18 | preserve LRU ordering. |
19 | |
20 | Pages are prefetched until the list is empty or the vm is seen as busy |
21 | according to the previously described criteria. Node data on numa is |
22 | stored with the entries and an appropriate zonelist based on this is used |
23 | when allocating ram. |
24 | |
25 | The pages are copied to swap cache and kept on backing store. This allows |
26 | pressure on either physical ram or swap to readily find free pages without |
27 | further I/O. |
28 | |
29 | Prefetching can be enabled/disabled via the tunable in |
30 | /proc/sys/vm/swap_prefetch initially set to 1 (enabled). |
31 | |
32 | Enabling laptop_mode disables swap prefetching to prevent unnecessary spin |
33 | ups. |
34 | |
35 | In testing on modern pc hardware this results in wall-clock time activation |
36 | of the firefox browser to speed up 5 fold after a worst case complete |
37 | swap-out of the browser on a static web page. |
38 | |
39 | From: Ingo Molnar <mingo@elte.hu> |
40 | |
41 | Fix potential swap-prefetch deadlock, found by the locking correctness |
42 | validator. |
43 | |
44 | Signed-off-by: Con Kolivas <kernel@kolivas.org> |
45 | Signed-off-by: Ingo Molnar <mingo@elte.hu> |
46 | Signed-off-by: Andrew Morton <akpm@osdl.org> |
47 | |
48 | Documentation/sysctl/vm.txt | 12 |
49 | include/linux/mm_inline.h | 7 |
50 | include/linux/swap-prefetch.h | 55 +++ |
51 | include/linux/swap.h | 2 |
52 | init/Kconfig | 22 + |
53 | kernel/sysctl.c | 11 |
54 | mm/Makefile | 1 |
55 | mm/swap.c | 48 +++ |
56 | mm/swap_prefetch.c | 581 ++++++++++++++++++++++++++++++++++++++++++ |
57 | mm/swap_state.c | 11 |
58 | mm/vmscan.c | 6 |
59 | 11 files changed, 755 insertions(+), 1 deletion(-) |
60 | |
61 | Index: linux-2.6.21-ck2/Documentation/sysctl/vm.txt |
62 | =================================================================== |
63 | --- linux-2.6.21-ck2.orig/Documentation/sysctl/vm.txt 2007-05-14 19:49:19.000000000 +1000 |
64 | +++ linux-2.6.21-ck2/Documentation/sysctl/vm.txt 2007-05-14 19:49:55.000000000 +1000 |
65 | @@ -31,6 +31,7 @@ Currently, these files are in /proc/sys/ |
66 | - min_unmapped_ratio |
67 | - min_slab_ratio |
68 | - panic_on_oom |
69 | +- swap_prefetch |
70 | |
71 | ============================================================== |
72 | |
73 | @@ -205,3 +206,14 @@ rather than killing rogue processes, set |
74 | |
75 | The default value is 0. |
76 | |
77 | +============================================================== |
78 | + |
79 | +swap_prefetch |
80 | + |
81 | +This enables or disables the swap prefetching feature. When the virtual |
82 | +memory subsystem has been extremely idle for at least 5 seconds it will start |
83 | +copying back pages from swap into the swapcache and keep a copy in swap. In |
84 | +practice it can take many minutes before the vm is idle enough. |
85 | + |
86 | +The default value is 1. |
87 | + |
88 | Index: linux-2.6.21-ck2/include/linux/swap.h |
89 | =================================================================== |
90 | --- linux-2.6.21-ck2.orig/include/linux/swap.h 2007-05-14 19:49:19.000000000 +1000 |
91 | +++ linux-2.6.21-ck2/include/linux/swap.h 2007-05-14 19:49:55.000000000 +1000 |
92 | @@ -180,6 +180,7 @@ extern unsigned int nr_free_pagecache_pa |
93 | /* linux/mm/swap.c */ |
94 | extern void FASTCALL(lru_cache_add(struct page *)); |
95 | extern void FASTCALL(lru_cache_add_active(struct page *)); |
96 | +extern void FASTCALL(lru_cache_add_tail(struct page *)); |
97 | extern void FASTCALL(activate_page(struct page *)); |
98 | extern void FASTCALL(mark_page_accessed(struct page *)); |
99 | extern void lru_add_drain(void); |
100 | @@ -237,6 +238,7 @@ extern void free_pages_and_swap_cache(st |
101 | extern struct page * lookup_swap_cache(swp_entry_t); |
102 | extern struct page * read_swap_cache_async(swp_entry_t, struct vm_area_struct *vma, |
103 | unsigned long addr); |
104 | +extern int add_to_swap_cache(struct page *page, swp_entry_t entry); |
105 | /* linux/mm/swapfile.c */ |
106 | extern long total_swap_pages; |
107 | extern unsigned int nr_swapfiles; |
108 | Index: linux-2.6.21-ck2/init/Kconfig |
109 | =================================================================== |
110 | --- linux-2.6.21-ck2.orig/init/Kconfig 2007-05-14 19:49:19.000000000 +1000 |
111 | +++ linux-2.6.21-ck2/init/Kconfig 2007-05-14 19:49:55.000000000 +1000 |
112 | @@ -101,6 +101,28 @@ config SWAP |
113 | used to provide more virtual memory than the actual RAM present |
114 | in your computer. If unsure say Y. |
115 | |
116 | +config SWAP_PREFETCH |
117 | + bool "Support for prefetching swapped memory" |
118 | + depends on SWAP |
119 | + default y |
120 | + ---help--- |
121 | + This option will allow the kernel to prefetch swapped memory pages |
122 | + when idle. The pages will be kept on both swap and in swap_cache |
123 | + thus avoiding the need for further I/O if either ram or swap space |
124 | + is required. |
125 | + |
126 | + What this will do on workstations is slowly bring back applications |
127 | + that have swapped out after memory intensive workloads back into |
128 | + physical ram if you have free ram at a later stage and the machine |
129 | + is relatively idle. This means that when you come back to your |
130 | + computer after leaving it idle for a while, applications will come |
131 | + to life faster. Note that your swap usage will appear to increase |
132 | + but these are cached pages, can be dropped freely by the vm, and it |
133 | + should stabilise around 50% swap usage maximum. |
134 | + |
135 | + Workstations and multiuser workstation servers will most likely want |
136 | + to say Y. |
137 | + |
138 | config SYSVIPC |
139 | bool "System V IPC" |
140 | ---help--- |
141 | Index: linux-2.6.21-ck2/kernel/sysctl.c |
142 | =================================================================== |
143 | --- linux-2.6.21-ck2.orig/kernel/sysctl.c 2007-05-14 19:49:19.000000000 +1000 |
144 | +++ linux-2.6.21-ck2/kernel/sysctl.c 2007-05-14 19:49:55.000000000 +1000 |
145 | @@ -22,6 +22,7 @@ |
146 | #include <linux/mm.h> |
147 | #include <linux/swap.h> |
148 | #include <linux/slab.h> |
149 | +#include <linux/swap-prefetch.h> |
150 | #include <linux/sysctl.h> |
151 | #include <linux/proc_fs.h> |
152 | #include <linux/capability.h> |
153 | @@ -906,6 +907,16 @@ static ctl_table vm_table[] = { |
154 | .extra1 = &zero, |
155 | }, |
156 | #endif |
157 | +#ifdef CONFIG_SWAP_PREFETCH |
158 | + { |
159 | + .ctl_name = CTL_UNNUMBERED, |
160 | + .procname = "swap_prefetch", |
161 | + .data = &swap_prefetch, |
162 | + .maxlen = sizeof(swap_prefetch), |
163 | + .mode = 0644, |
164 | + .proc_handler = &proc_dointvec, |
165 | + }, |
166 | +#endif |
167 | { .ctl_name = 0 } |
168 | }; |
169 | |
170 | Index: linux-2.6.21-ck2/mm/Makefile |
171 | =================================================================== |
172 | --- linux-2.6.21-ck2.orig/mm/Makefile 2007-05-14 19:49:19.000000000 +1000 |
173 | +++ linux-2.6.21-ck2/mm/Makefile 2007-05-14 19:49:55.000000000 +1000 |
174 | @@ -17,6 +17,7 @@ ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy) |
175 | obj-y += bounce.o |
176 | endif |
177 | obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o |
178 | +obj-$(CONFIG_SWAP_PREFETCH) += swap_prefetch.o |
179 | obj-$(CONFIG_HUGETLBFS) += hugetlb.o |
180 | obj-$(CONFIG_NUMA) += mempolicy.o |
181 | obj-$(CONFIG_SPARSEMEM) += sparse.o |
182 | Index: linux-2.6.21-ck2/mm/swap.c |
183 | =================================================================== |
184 | --- linux-2.6.21-ck2.orig/mm/swap.c 2007-05-14 19:49:19.000000000 +1000 |
185 | +++ linux-2.6.21-ck2/mm/swap.c 2007-05-14 19:49:55.000000000 +1000 |
186 | @@ -17,6 +17,7 @@ |
187 | #include <linux/sched.h> |
188 | #include <linux/kernel_stat.h> |
189 | #include <linux/swap.h> |
190 | +#include <linux/swap-prefetch.h> |
191 | #include <linux/mman.h> |
192 | #include <linux/pagemap.h> |
193 | #include <linux/pagevec.h> |
194 | @@ -176,6 +177,7 @@ EXPORT_SYMBOL(mark_page_accessed); |
195 | */ |
196 | static DEFINE_PER_CPU(struct pagevec, lru_add_pvecs) = { 0, }; |
197 | static DEFINE_PER_CPU(struct pagevec, lru_add_active_pvecs) = { 0, }; |
198 | +static DEFINE_PER_CPU(struct pagevec, lru_add_tail_pvecs) = { 0, }; |
199 | |
200 | void fastcall lru_cache_add(struct page *page) |
201 | { |
202 | @@ -197,6 +199,31 @@ void fastcall lru_cache_add_active(struc |
203 | put_cpu_var(lru_add_active_pvecs); |
204 | } |
205 | |
206 | +static void __pagevec_lru_add_tail(struct pagevec *pvec) |
207 | +{ |
208 | + int i; |
209 | + struct zone *zone = NULL; |
210 | + |
211 | + for (i = 0; i < pagevec_count(pvec); i++) { |
212 | + struct page *page = pvec->pages[i]; |
213 | + struct zone *pagezone = page_zone(page); |
214 | + |
215 | + if (pagezone != zone) { |
216 | + if (zone) |
217 | + spin_unlock_irq(&zone->lru_lock); |
218 | + zone = pagezone; |
219 | + spin_lock_irq(&zone->lru_lock); |
220 | + } |
221 | + BUG_ON(PageLRU(page)); |
222 | + SetPageLRU(page); |
223 | + add_page_to_inactive_list_tail(zone, page); |
224 | + } |
225 | + if (zone) |
226 | + spin_unlock_irq(&zone->lru_lock); |
227 | + release_pages(pvec->pages, pvec->nr, pvec->cold); |
228 | + pagevec_reinit(pvec); |
229 | +} |
230 | + |
231 | static void __lru_add_drain(int cpu) |
232 | { |
233 | struct pagevec *pvec = &per_cpu(lru_add_pvecs, cpu); |
234 | @@ -207,6 +234,9 @@ static void __lru_add_drain(int cpu) |
235 | pvec = &per_cpu(lru_add_active_pvecs, cpu); |
236 | if (pagevec_count(pvec)) |
237 | __pagevec_lru_add_active(pvec); |
238 | + pvec = &per_cpu(lru_add_tail_pvecs, cpu); |
239 | + if (pagevec_count(pvec)) |
240 | + __pagevec_lru_add_tail(pvec); |
241 | } |
242 | |
243 | void lru_add_drain(void) |
244 | @@ -403,6 +433,21 @@ void __pagevec_lru_add_active(struct pag |
245 | } |
246 | |
247 | /* |
248 | + * Function used uniquely to put pages back to the lru at the end of the |
249 | + * inactive list to preserve the lru order. Currently only used by swap |
250 | + * prefetch. |
251 | + */ |
252 | +void fastcall lru_cache_add_tail(struct page *page) |
253 | +{ |
254 | + struct pagevec *pvec = &get_cpu_var(lru_add_tail_pvecs); |
255 | + |
256 | + page_cache_get(page); |
257 | + if (!pagevec_add(pvec, page)) |
258 | + __pagevec_lru_add_tail(pvec); |
259 | + put_cpu_var(lru_add_pvecs); |
260 | +} |
261 | + |
262 | +/* |
263 | * Try to drop buffers from the pages in a pagevec |
264 | */ |
265 | void pagevec_strip(struct pagevec *pvec) |
266 | @@ -514,6 +559,9 @@ void __init swap_setup(void) |
267 | * Right now other parts of the system means that we |
268 | * _really_ don't want to cluster much more |
269 | */ |
270 | + |
271 | + prepare_swap_prefetch(); |
272 | + |
273 | #ifdef CONFIG_HOTPLUG_CPU |
274 | hotcpu_notifier(cpu_swap_callback, 0); |
275 | #endif |
276 | Index: linux-2.6.21-ck2/mm/swap_prefetch.c |
277 | =================================================================== |
278 | --- /dev/null 1970-01-01 00:00:00.000000000 +0000 |
279 | +++ linux-2.6.21-ck2/mm/swap_prefetch.c 2007-05-14 19:49:55.000000000 +1000 |
280 | @@ -0,0 +1,581 @@ |
281 | +/* |
282 | + * linux/mm/swap_prefetch.c |
283 | + * |
284 | + * Copyright (C) 2005-2006 Con Kolivas |
285 | + * |
286 | + * Written by Con Kolivas <kernel@kolivas.org> |
287 | + * |
288 | + * This program is free software; you can redistribute it and/or modify |
289 | + * it under the terms of the GNU General Public License version 2 as |
290 | + * published by the Free Software Foundation. |
291 | + */ |
292 | + |
293 | +#include <linux/fs.h> |
294 | +#include <linux/mm.h> |
295 | +#include <linux/swap.h> |
296 | +#include <linux/swap-prefetch.h> |
297 | +#include <linux/ioprio.h> |
298 | +#include <linux/kthread.h> |
299 | +#include <linux/pagemap.h> |
300 | +#include <linux/syscalls.h> |
301 | +#include <linux/writeback.h> |
302 | +#include <linux/vmstat.h> |
303 | +#include <linux/freezer.h> |
304 | + |
305 | +/* |
306 | + * Time to delay prefetching if vm is busy or prefetching unsuccessful. There |
307 | + * needs to be at least this duration of idle time meaning in practice it can |
308 | + * be much longer |
309 | + */ |
310 | +#define PREFETCH_DELAY (HZ * 5) |
311 | + |
312 | +/* sysctl - enable/disable swap prefetching */ |
313 | +int swap_prefetch __read_mostly = 1; |
314 | + |
315 | +struct swapped_root { |
316 | + unsigned long busy; /* vm busy */ |
317 | + spinlock_t lock; /* protects all data */ |
318 | + struct list_head list; /* MRU list of swapped pages */ |
319 | + struct radix_tree_root swap_tree; /* Lookup tree of pages */ |
320 | + unsigned int count; /* Number of entries */ |
321 | + unsigned int maxcount; /* Maximum entries allowed */ |
322 | + struct kmem_cache *cache; /* Of struct swapped_entry */ |
323 | +}; |
324 | + |
325 | +static struct swapped_root swapped = { |
326 | + .lock = SPIN_LOCK_UNLOCKED, |
327 | + .list = LIST_HEAD_INIT(swapped.list), |
328 | + .swap_tree = RADIX_TREE_INIT(GFP_ATOMIC), |
329 | +}; |
330 | + |
331 | +static struct task_struct *kprefetchd_task; |
332 | + |
333 | +/* |
334 | + * We check to see no part of the vm is busy. If it is this will interrupt |
335 | + * trickle_swap and wait another PREFETCH_DELAY. Purposefully racy. |
336 | + */ |
337 | +inline void delay_swap_prefetch(void) |
338 | +{ |
339 | + if (!test_bit(0, &swapped.busy)) |
340 | + __set_bit(0, &swapped.busy); |
341 | +} |
342 | + |
343 | +/* |
344 | + * Drop behind accounting which keeps a list of the most recently used swap |
345 | + * entries. |
346 | + */ |
347 | +void add_to_swapped_list(struct page *page) |
348 | +{ |
349 | + struct swapped_entry *entry; |
350 | + unsigned long index, flags; |
351 | + int wakeup; |
352 | + |
353 | + if (!swap_prefetch) |
354 | + return; |
355 | + |
356 | + wakeup = 0; |
357 | + |
358 | + spin_lock_irqsave(&swapped.lock, flags); |
359 | + if (swapped.count >= swapped.maxcount) { |
360 | + /* |
361 | + * We limit the number of entries to 2/3 of physical ram. |
362 | + * Once the number of entries exceeds this we start removing |
363 | + * the least recently used entries. |
364 | + */ |
365 | + entry = list_entry(swapped.list.next, |
366 | + struct swapped_entry, swapped_list); |
367 | + radix_tree_delete(&swapped.swap_tree, entry->swp_entry.val); |
368 | + list_del(&entry->swapped_list); |
369 | + swapped.count--; |
370 | + } else { |
371 | + entry = kmem_cache_alloc(swapped.cache, GFP_ATOMIC); |
372 | + if (unlikely(!entry)) |
373 | + /* bad, can't allocate more mem */ |
374 | + goto out_locked; |
375 | + } |
376 | + |
377 | + index = page_private(page); |
378 | + entry->swp_entry.val = index; |
379 | + /* |
380 | + * On numa we need to store the node id to ensure that we prefetch to |
381 | + * the same node it came from. |
382 | + */ |
383 | + store_swap_entry_node(entry, page); |
384 | + |
385 | + if (likely(!radix_tree_insert(&swapped.swap_tree, index, entry))) { |
386 | + /* |
387 | + * If this is the first entry, kprefetchd needs to be |
388 | + * (re)started. |
389 | + */ |
390 | + if (!swapped.count) |
391 | + wakeup = 1; |
392 | + list_add(&entry->swapped_list, &swapped.list); |
393 | + swapped.count++; |
394 | + } |
395 | + |
396 | +out_locked: |
397 | + spin_unlock_irqrestore(&swapped.lock, flags); |
398 | + |
399 | + /* Do the wakeup outside the lock to shorten lock hold time. */ |
400 | + if (wakeup) |
401 | + wake_up_process(kprefetchd_task); |
402 | + |
403 | + return; |
404 | +} |
405 | + |
406 | +/* |
407 | + * Removes entries from the swapped_list. The radix tree allows us to quickly |
408 | + * look up the entry from the index without having to iterate over the whole |
409 | + * list. |
410 | + */ |
411 | +void remove_from_swapped_list(const unsigned long index) |
412 | +{ |
413 | + struct swapped_entry *entry; |
414 | + unsigned long flags; |
415 | + |
416 | + if (list_empty(&swapped.list)) |
417 | + return; |
418 | + |
419 | + spin_lock_irqsave(&swapped.lock, flags); |
420 | + entry = radix_tree_delete(&swapped.swap_tree, index); |
421 | + if (likely(entry)) { |
422 | + list_del_init(&entry->swapped_list); |
423 | + swapped.count--; |
424 | + kmem_cache_free(swapped.cache, entry); |
425 | + } |
426 | + spin_unlock_irqrestore(&swapped.lock, flags); |
427 | +} |
428 | + |
429 | +enum trickle_return { |
430 | + TRICKLE_SUCCESS, |
431 | + TRICKLE_FAILED, |
432 | + TRICKLE_DELAY, |
433 | +}; |
434 | + |
435 | +struct node_stats { |
436 | + unsigned long last_free; |
437 | + /* Free ram after a cycle of prefetching */ |
438 | + unsigned long current_free; |
439 | + /* Free ram on this cycle of checking prefetch_suitable */ |
440 | + unsigned long prefetch_watermark; |
441 | + /* Maximum amount we will prefetch to */ |
442 | + unsigned long highfree[MAX_NR_ZONES]; |
443 | + /* The amount of free ram before we start prefetching */ |
444 | + unsigned long lowfree[MAX_NR_ZONES]; |
445 | + /* The amount of free ram where we will stop prefetching */ |
446 | + unsigned long *pointfree[MAX_NR_ZONES]; |
447 | + /* highfree or lowfree depending on whether we've hit a watermark */ |
448 | +}; |
449 | + |
450 | +/* |
451 | + * prefetch_stats stores the free ram data of each node and this is used to |
452 | + * determine if a node is suitable for prefetching into. |
453 | + */ |
454 | +struct prefetch_stats { |
455 | + nodemask_t prefetch_nodes; |
456 | + /* Which nodes are currently suited to prefetching */ |
457 | + unsigned long prefetched_pages; |
458 | + /* Total pages we've prefetched on this wakeup of kprefetchd */ |
459 | + struct node_stats node[MAX_NUMNODES]; |
460 | +}; |
461 | + |
462 | +static struct prefetch_stats sp_stat; |
463 | + |
464 | +/* |
465 | + * This tries to read a swp_entry_t into swap cache for swap prefetching. |
466 | + * If it returns TRICKLE_DELAY we should delay further prefetching. |
467 | + */ |
468 | +static enum trickle_return trickle_swap_cache_async(const swp_entry_t entry, |
469 | + const int node) |
470 | +{ |
471 | + enum trickle_return ret = TRICKLE_FAILED; |
472 | + struct page *page; |
473 | + |
474 | + read_lock_irq(&swapper_space.tree_lock); |
475 | + /* Entry may already exist */ |
476 | + page = radix_tree_lookup(&swapper_space.page_tree, entry.val); |
477 | + read_unlock_irq(&swapper_space.tree_lock); |
478 | + if (page) { |
479 | + remove_from_swapped_list(entry.val); |
480 | + goto out; |
481 | + } |
482 | + |
483 | + /* |
484 | + * Get a new page to read from swap. We have already checked the |
485 | + * watermarks so __alloc_pages will not call on reclaim. |
486 | + */ |
487 | + page = alloc_pages_node(node, GFP_HIGHUSER & ~__GFP_WAIT, 0); |
488 | + if (unlikely(!page)) { |
489 | + ret = TRICKLE_DELAY; |
490 | + goto out; |
491 | + } |
492 | + |
493 | + if (add_to_swap_cache(page, entry)) { |
494 | + /* Failed to add to swap cache */ |
495 | + goto out_release; |
496 | + } |
497 | + |
498 | + /* Add them to the tail of the inactive list to preserve LRU order */ |
499 | + lru_cache_add_tail(page); |
500 | + if (unlikely(swap_readpage(NULL, page))) { |
501 | + ret = TRICKLE_DELAY; |
502 | + goto out_release; |
503 | + } |
504 | + |
505 | + sp_stat.prefetched_pages++; |
506 | + sp_stat.node[node].last_free--; |
507 | + |
508 | + ret = TRICKLE_SUCCESS; |
509 | +out_release: |
510 | + page_cache_release(page); |
511 | +out: |
512 | + return ret; |
513 | +} |
514 | + |
515 | +static void clear_last_prefetch_free(void) |
516 | +{ |
517 | + int node; |
518 | + |
519 | + /* |
520 | + * Reset the nodes suitable for prefetching to all nodes. We could |
521 | + * update the data to take into account memory hotplug if desired.. |
522 | + */ |
523 | + sp_stat.prefetch_nodes = node_online_map; |
524 | + for_each_node_mask(node, sp_stat.prefetch_nodes) { |
525 | + struct node_stats *ns = &sp_stat.node[node]; |
526 | + |
527 | + ns->last_free = 0; |
528 | + } |
529 | +} |
530 | + |
531 | +static void clear_current_prefetch_free(void) |
532 | +{ |
533 | + int node; |
534 | + |
535 | + sp_stat.prefetch_nodes = node_online_map; |
536 | + for_each_node_mask(node, sp_stat.prefetch_nodes) { |
537 | + struct node_stats *ns = &sp_stat.node[node]; |
538 | + |
539 | + ns->current_free = 0; |
540 | + } |
541 | +} |
542 | + |
543 | +/* |
544 | + * This updates the high and low watermarks of amount of free ram in each |
545 | + * node used to start and stop prefetching. We prefetch from pages_high * 4 |
546 | + * down to pages_high * 3. |
547 | + */ |
548 | +static void examine_free_limits(void) |
549 | +{ |
550 | + struct zone *z; |
551 | + |
552 | + for_each_zone(z) { |
553 | + struct node_stats *ns; |
554 | + int idx; |
555 | + |
556 | + if (!populated_zone(z)) |
557 | + continue; |
558 | + |
559 | + ns = &sp_stat.node[z->zone_pgdat->node_id]; |
560 | + idx = zone_idx(z); |
561 | + ns->lowfree[idx] = z->pages_high * 3; |
562 | + ns->highfree[idx] = ns->lowfree[idx] + z->pages_high; |
563 | + |
564 | + if (zone_page_state(z, NR_FREE_PAGES) > ns->highfree[idx]) { |
565 | + /* |
566 | + * We've gotten above the high watermark of free pages |
567 | + * so we can start prefetching till we get to the low |
568 | + * watermark. |
569 | + */ |
570 | + ns->pointfree[idx] = &ns->lowfree[idx]; |
571 | + } |
572 | + } |
573 | +} |
574 | + |
575 | +/* |
576 | + * We want to be absolutely certain it's ok to start prefetching. |
577 | + */ |
578 | +static int prefetch_suitable(void) |
579 | +{ |
580 | + unsigned long limit; |
581 | + struct zone *z; |
582 | + int node, ret = 0, test_pagestate = 0; |
583 | + |
584 | + /* Purposefully racy */ |
585 | + if (test_bit(0, &swapped.busy)) { |
586 | + __clear_bit(0, &swapped.busy); |
587 | + goto out; |
588 | + } |
589 | + |
590 | + /* |
591 | + * get_page_state and above_background_load are expensive so we only |
592 | + * perform them every SWAP_CLUSTER_MAX prefetched_pages. |
593 | + * We test to see if we're above_background_load as disk activity |
594 | + * even at low priority can cause interrupt induced scheduling |
595 | + * latencies. |
596 | + */ |
597 | + if (!(sp_stat.prefetched_pages % SWAP_CLUSTER_MAX)) { |
598 | + if (above_background_load()) |
599 | + goto out; |
600 | + test_pagestate = 1; |
601 | + } |
602 | + |
603 | + clear_current_prefetch_free(); |
604 | + |
605 | + /* |
606 | + * Have some hysteresis between where page reclaiming and prefetching |
607 | + * will occur to prevent ping-ponging between them. |
608 | + */ |
609 | + for_each_zone(z) { |
610 | + struct node_stats *ns; |
611 | + unsigned long free; |
612 | + int idx; |
613 | + |
614 | + if (!populated_zone(z)) |
615 | + continue; |
616 | + |
617 | + node = z->zone_pgdat->node_id; |
618 | + ns = &sp_stat.node[node]; |
619 | + idx = zone_idx(z); |
620 | + |
621 | + free = zone_page_state(z, NR_FREE_PAGES); |
622 | + if (free < *ns->pointfree[idx]) { |
623 | + /* |
624 | + * Free pages have dropped below the low watermark so |
625 | + * we won't start prefetching again till we hit the |
626 | + * high watermark of free pages. |
627 | + */ |
628 | + ns->pointfree[idx] = &ns->highfree[idx]; |
629 | + node_clear(node, sp_stat.prefetch_nodes); |
630 | + continue; |
631 | + } |
632 | + ns->current_free += free; |
633 | + } |
634 | + |
635 | + /* |
636 | + * We iterate over each node testing to see if it is suitable for |
637 | + * prefetching and clear the nodemask if it is not. |
638 | + */ |
639 | + for_each_node_mask(node, sp_stat.prefetch_nodes) { |
640 | + struct node_stats *ns = &sp_stat.node[node]; |
641 | + |
642 | + /* |
643 | + * We check to see that pages are not being allocated |
644 | + * elsewhere at any significant rate implying any |
645 | + * degree of memory pressure (eg during file reads) |
646 | + */ |
647 | + if (ns->last_free) { |
648 | + if (ns->current_free + SWAP_CLUSTER_MAX < |
649 | + ns->last_free) { |
650 | + ns->last_free = ns->current_free; |
651 | + node_clear(node, |
652 | + sp_stat.prefetch_nodes); |
653 | + continue; |
654 | + } |
655 | + } else |
656 | + ns->last_free = ns->current_free; |
657 | + |
658 | + if (!test_pagestate) |
659 | + continue; |
660 | + |
661 | + /* We shouldn't prefetch when we are doing writeback */ |
662 | + if (node_page_state(node, NR_WRITEBACK)) { |
663 | + node_clear(node, sp_stat.prefetch_nodes); |
664 | + continue; |
665 | + } |
666 | + |
667 | + /* |
668 | + * >2/3 of the ram on this node is mapped, slab, swapcache or |
669 | + * dirty, we need to leave some free for pagecache. |
670 | + */ |
671 | + limit = node_page_state(node, NR_FILE_PAGES); |
672 | + limit += node_page_state(node, NR_SLAB_RECLAIMABLE); |
673 | + limit += node_page_state(node, NR_SLAB_UNRECLAIMABLE); |
674 | + limit += node_page_state(node, NR_FILE_DIRTY); |
675 | + limit += node_page_state(node, NR_UNSTABLE_NFS); |
676 | + limit += total_swapcache_pages; |
677 | + if (limit > ns->prefetch_watermark) { |
678 | + node_clear(node, sp_stat.prefetch_nodes); |
679 | + continue; |
680 | + } |
681 | + } |
682 | + |
683 | + if (nodes_empty(sp_stat.prefetch_nodes)) |
684 | + goto out; |
685 | + |
686 | + /* Survived all that? Hooray we can prefetch! */ |
687 | + ret = 1; |
688 | +out: |
689 | + return ret; |
690 | +} |
691 | + |
692 | +/* |
693 | + * Get previous swapped entry when iterating over all entries. swapped.lock |
694 | + * should be held and we should already ensure that entry exists. |
695 | + */ |
696 | +static inline struct swapped_entry *prev_swapped_entry |
697 | + (struct swapped_entry *entry) |
698 | +{ |
699 | + return list_entry(entry->swapped_list.prev->prev, |
700 | + struct swapped_entry, swapped_list); |
701 | +} |
702 | + |
703 | +/* |
704 | + * trickle_swap is the main function that initiates the swap prefetching. It |
705 | + * first checks to see if the busy flag is set, and does not prefetch if it |
706 | + * is, as the flag implied we are low on memory or swapping in currently. |
707 | + * Otherwise it runs until prefetch_suitable fails which occurs when the |
708 | + * vm is busy, we prefetch to the watermark, or the list is empty or we have |
709 | + * iterated over all entries |
710 | + */ |
711 | +static enum trickle_return trickle_swap(void) |
712 | +{ |
713 | + enum trickle_return ret = TRICKLE_DELAY; |
714 | + struct swapped_entry *entry; |
715 | + unsigned long flags; |
716 | + |
717 | + /* |
718 | + * If laptop_mode is enabled don't prefetch to avoid hard drives |
719 | + * doing unnecessary spin-ups |
720 | + */ |
721 | + if (!swap_prefetch || laptop_mode) |
722 | + return ret; |
723 | + |
724 | + examine_free_limits(); |
725 | + entry = NULL; |
726 | + |
727 | + for ( ; ; ) { |
728 | + swp_entry_t swp_entry; |
729 | + int node; |
730 | + |
731 | + if (!prefetch_suitable()) |
732 | + break; |
733 | + |
734 | + spin_lock_irqsave(&swapped.lock, flags); |
735 | + if (list_empty(&swapped.list)) { |
736 | + ret = TRICKLE_FAILED; |
737 | + spin_unlock_irqrestore(&swapped.lock, flags); |
738 | + break; |
739 | + } |
740 | + |
741 | + if (!entry) { |
742 | + /* |
743 | + * This sets the entry for the first iteration. It |
744 | + * also is a safeguard against the entry disappearing |
745 | + * while the lock is not held. |
746 | + */ |
747 | + entry = list_entry(swapped.list.prev, |
748 | + struct swapped_entry, swapped_list); |
749 | + } else if (entry->swapped_list.prev == swapped.list.next) { |
750 | + /* |
751 | + * If we have iterated over all entries and there are |
752 | + * still entries that weren't swapped out there may |
753 | + * be a reason we could not swap them back in so |
754 | + * delay attempting further prefetching. |
755 | + */ |
756 | + spin_unlock_irqrestore(&swapped.lock, flags); |
757 | + break; |
758 | + } |
759 | + |
760 | + node = get_swap_entry_node(entry); |
761 | + if (!node_isset(node, sp_stat.prefetch_nodes)) { |
762 | + /* |
763 | + * We found an entry that belongs to a node that is |
764 | + * not suitable for prefetching so skip it. |
765 | + */ |
766 | + entry = prev_swapped_entry(entry); |
767 | + spin_unlock_irqrestore(&swapped.lock, flags); |
768 | + continue; |
769 | + } |
770 | + swp_entry = entry->swp_entry; |
771 | + entry = prev_swapped_entry(entry); |
772 | + spin_unlock_irqrestore(&swapped.lock, flags); |
773 | + |
774 | + if (trickle_swap_cache_async(swp_entry, node) == TRICKLE_DELAY) |
775 | + break; |
776 | + } |
777 | + |
778 | + if (sp_stat.prefetched_pages) { |
779 | + lru_add_drain(); |
780 | + sp_stat.prefetched_pages = 0; |
781 | + } |
782 | + return ret; |
783 | +} |
784 | + |
785 | +static int kprefetchd(void *__unused) |
786 | +{ |
787 | + struct sched_param param = { .sched_priority = 0 }; |
788 | + |
789 | + sched_setscheduler(current, SCHED_BATCH, ¶m); |
790 | + set_user_nice(current, 19); |
791 | + /* Set ioprio to lowest if supported by i/o scheduler */ |
792 | + sys_ioprio_set(IOPRIO_WHO_PROCESS, 0, IOPRIO_CLASS_IDLE); |
793 | + |
794 | + /* kprefetchd has nothing to do until it is woken up the first time */ |
795 | + set_current_state(TASK_INTERRUPTIBLE); |
796 | + schedule(); |
797 | + |
798 | + do { |
799 | + try_to_freeze(); |
800 | + |
801 | + /* |
802 | + * TRICKLE_FAILED implies no entries left - we do not schedule |
803 | + * a wakeup, and further delay the next one. |
804 | + */ |
805 | + if (trickle_swap() == TRICKLE_FAILED) { |
806 | + set_current_state(TASK_INTERRUPTIBLE); |
807 | + schedule(); |
808 | + } |
809 | + clear_last_prefetch_free(); |
810 | + schedule_timeout_interruptible(PREFETCH_DELAY); |
811 | + } while (!kthread_should_stop()); |
812 | + |
813 | + return 0; |
814 | +} |
815 | + |
816 | +/* |
817 | + * Create kmem cache for swapped entries |
818 | + */ |
819 | +void __init prepare_swap_prefetch(void) |
820 | +{ |
821 | + struct zone *zone; |
822 | + |
823 | + swapped.cache = kmem_cache_create("swapped_entry", |
824 | + sizeof(struct swapped_entry), 0, SLAB_PANIC, NULL, NULL); |
825 | + |
826 | + /* |
827 | + * Set max number of entries to 2/3 the size of physical ram as we |
828 | + * only ever prefetch to consume 2/3 of the ram. |
829 | + */ |
830 | + swapped.maxcount = nr_free_pagecache_pages() / 3 * 2; |
831 | + |
832 | + for_each_zone(zone) { |
833 | + unsigned long present; |
834 | + struct node_stats *ns; |
835 | + int idx; |
836 | + |
837 | + present = zone->present_pages; |
838 | + if (!present) |
839 | + continue; |
840 | + |
841 | + ns = &sp_stat.node[zone->zone_pgdat->node_id]; |
842 | + ns->prefetch_watermark += present / 3 * 2; |
843 | + idx = zone_idx(zone); |
844 | + ns->pointfree[idx] = &ns->highfree[idx]; |
845 | + } |
846 | +} |
847 | + |
848 | +static int __init kprefetchd_init(void) |
849 | +{ |
850 | + kprefetchd_task = kthread_run(kprefetchd, NULL, "kprefetchd"); |
851 | + |
852 | + return 0; |
853 | +} |
854 | + |
855 | +static void __exit kprefetchd_exit(void) |
856 | +{ |
857 | + kthread_stop(kprefetchd_task); |
858 | +} |
859 | + |
860 | +module_init(kprefetchd_init); |
861 | +module_exit(kprefetchd_exit); |
862 | Index: linux-2.6.21-ck2/mm/swap_state.c |
863 | =================================================================== |
864 | --- linux-2.6.21-ck2.orig/mm/swap_state.c 2007-05-14 19:49:19.000000000 +1000 |
865 | +++ linux-2.6.21-ck2/mm/swap_state.c 2007-05-14 19:49:55.000000000 +1000 |
866 | @@ -10,6 +10,7 @@ |
867 | #include <linux/mm.h> |
868 | #include <linux/kernel_stat.h> |
869 | #include <linux/swap.h> |
870 | +#include <linux/swap-prefetch.h> |
871 | #include <linux/init.h> |
872 | #include <linux/pagemap.h> |
873 | #include <linux/buffer_head.h> |
874 | @@ -82,6 +83,7 @@ static int __add_to_swap_cache(struct pa |
875 | error = radix_tree_insert(&swapper_space.page_tree, |
876 | entry.val, page); |
877 | if (!error) { |
878 | + remove_from_swapped_list(entry.val); |
879 | page_cache_get(page); |
880 | SetPageLocked(page); |
881 | SetPageSwapCache(page); |
882 | @@ -95,11 +97,12 @@ static int __add_to_swap_cache(struct pa |
883 | return error; |
884 | } |
885 | |
886 | -static int add_to_swap_cache(struct page *page, swp_entry_t entry) |
887 | +int add_to_swap_cache(struct page *page, swp_entry_t entry) |
888 | { |
889 | int error; |
890 | |
891 | if (!swap_duplicate(entry)) { |
892 | + remove_from_swapped_list(entry.val); |
893 | INC_CACHE_INFO(noent_race); |
894 | return -ENOENT; |
895 | } |
896 | @@ -148,6 +151,9 @@ int add_to_swap(struct page * page, gfp_ |
897 | swp_entry_t entry; |
898 | int err; |
899 | |
900 | + /* Swap prefetching is delayed if we're swapping pages */ |
901 | + delay_swap_prefetch(); |
902 | + |
903 | BUG_ON(!PageLocked(page)); |
904 | |
905 | for (;;) { |
906 | @@ -320,6 +326,9 @@ struct page *read_swap_cache_async(swp_e |
907 | struct page *found_page, *new_page = NULL; |
908 | int err; |
909 | |
910 | + /* Swap prefetching is delayed if we're already reading from swap */ |
911 | + delay_swap_prefetch(); |
912 | + |
913 | do { |
914 | /* |
915 | * First check the swap cache. Since this is normally |
916 | Index: linux-2.6.21-ck2/mm/vmscan.c |
917 | =================================================================== |
918 | --- linux-2.6.21-ck2.orig/mm/vmscan.c 2007-05-14 19:49:19.000000000 +1000 |
919 | +++ linux-2.6.21-ck2/mm/vmscan.c 2007-05-14 19:49:55.000000000 +1000 |
920 | @@ -16,6 +16,7 @@ |
921 | #include <linux/slab.h> |
922 | #include <linux/kernel_stat.h> |
923 | #include <linux/swap.h> |
924 | +#include <linux/swap-prefetch.h> |
925 | #include <linux/pagemap.h> |
926 | #include <linux/init.h> |
927 | #include <linux/highmem.h> |
928 | @@ -424,6 +425,7 @@ int remove_mapping(struct address_space |
929 | |
930 | if (PageSwapCache(page)) { |
931 | swp_entry_t swap = { .val = page_private(page) }; |
932 | + add_to_swapped_list(page); |
933 | __delete_from_swap_cache(page); |
934 | write_unlock_irq(&mapping->tree_lock); |
935 | swap_free(swap); |
936 | @@ -1032,6 +1034,8 @@ unsigned long try_to_free_pages(struct z |
937 | .swappiness = vm_swappiness, |
938 | }; |
939 | |
940 | + delay_swap_prefetch(); |
941 | + |
942 | count_vm_event(ALLOCSTALL); |
943 | |
944 | for (i = 0; zones[i] != NULL; i++) { |
945 | @@ -1381,6 +1385,8 @@ static unsigned long shrink_all_zones(un |
946 | struct zone *zone; |
947 | unsigned long nr_to_scan, ret = 0; |
948 | |
949 | + delay_swap_prefetch(); |
950 | + |
951 | for_each_zone(zone) { |
952 | |
953 | if (!populated_zone(zone)) |
954 | Index: linux-2.6.21-ck2/include/linux/mm_inline.h |
955 | =================================================================== |
956 | --- linux-2.6.21-ck2.orig/include/linux/mm_inline.h 2007-05-14 19:49:19.000000000 +1000 |
957 | +++ linux-2.6.21-ck2/include/linux/mm_inline.h 2007-05-14 19:49:55.000000000 +1000 |
958 | @@ -13,6 +13,13 @@ add_page_to_inactive_list(struct zone *z |
959 | } |
960 | |
961 | static inline void |
962 | +add_page_to_inactive_list_tail(struct zone *zone, struct page *page) |
963 | +{ |
964 | + list_add_tail(&page->lru, &zone->inactive_list); |
965 | + __inc_zone_state(zone, NR_INACTIVE); |
966 | +} |
967 | + |
968 | +static inline void |
969 | del_page_from_active_list(struct zone *zone, struct page *page) |
970 | { |
971 | list_del(&page->lru); |
972 | Index: linux-2.6.21-ck2/include/linux/swap-prefetch.h |
973 | =================================================================== |
974 | --- /dev/null 1970-01-01 00:00:00.000000000 +0000 |
975 | +++ linux-2.6.21-ck2/include/linux/swap-prefetch.h 2007-05-14 19:49:55.000000000 +1000 |
976 | @@ -0,0 +1,55 @@ |
977 | +#ifndef SWAP_PREFETCH_H_INCLUDED |
978 | +#define SWAP_PREFETCH_H_INCLUDED |
979 | + |
980 | +#ifdef CONFIG_SWAP_PREFETCH |
981 | +/* mm/swap_prefetch.c */ |
982 | +extern int swap_prefetch; |
983 | +struct swapped_entry { |
984 | + swp_entry_t swp_entry; /* The actual swap entry */ |
985 | + struct list_head swapped_list; /* Linked list of entries */ |
986 | +#if MAX_NUMNODES > 1 |
987 | + int node; /* Node id */ |
988 | +#endif |
989 | +} __attribute__((packed)); |
990 | + |
991 | +static inline void store_swap_entry_node(struct swapped_entry *entry, |
992 | + struct page *page) |
993 | +{ |
994 | +#if MAX_NUMNODES > 1 |
995 | + entry->node = page_to_nid(page); |
996 | +#endif |
997 | +} |
998 | + |
999 | +static inline int get_swap_entry_node(struct swapped_entry *entry) |
1000 | +{ |
1001 | +#if MAX_NUMNODES > 1 |
1002 | + return entry->node; |
1003 | +#else |
1004 | + return 0; |
1005 | +#endif |
1006 | +} |
1007 | + |
1008 | +extern void add_to_swapped_list(struct page *page); |
1009 | +extern void remove_from_swapped_list(const unsigned long index); |
1010 | +extern void delay_swap_prefetch(void); |
1011 | +extern void prepare_swap_prefetch(void); |
1012 | + |
1013 | +#else /* CONFIG_SWAP_PREFETCH */ |
1014 | +static inline void add_to_swapped_list(struct page *__unused) |
1015 | +{ |
1016 | +} |
1017 | + |
1018 | +static inline void prepare_swap_prefetch(void) |
1019 | +{ |
1020 | +} |
1021 | + |
1022 | +static inline void remove_from_swapped_list(const unsigned long __unused) |
1023 | +{ |
1024 | +} |
1025 | + |
1026 | +static inline void delay_swap_prefetch(void) |
1027 | +{ |
1028 | +} |
1029 | +#endif /* CONFIG_SWAP_PREFETCH */ |
1030 | + |
1031 | +#endif /* SWAP_PREFETCH_H_INCLUDED */ |