Commit | Line | Data |
---|---|---|
a48d07af CL |
1 | Page migration |
2 | -------------- | |
3 | ||
4 | Page migration allows the moving of the physical location of pages between | |
5 | nodes in a numa system while the process is running. This means that the | |
6 | virtual addresses that the process sees do not change. However, the | |
7 | system rearranges the physical location of those pages. | |
8 | ||
9 | The main intend of page migration is to reduce the latency of memory access | |
10 | by moving pages near to the processor where the process accessing that memory | |
11 | is running. | |
12 | ||
13 | Page migration allows a process to manually relocate the node on which its | |
14 | pages are located through the MF_MOVE and MF_MOVE_ALL options while setting | |
b4fb3766 | 15 | a new memory policy via mbind(). The pages of process can also be relocated |
a48d07af CL |
16 | from another process using the sys_migrate_pages() function call. The |
17 | migrate_pages function call takes two sets of nodes and moves pages of a | |
18 | process that are located on the from nodes to the destination nodes. | |
b4fb3766 CL |
19 | Page migration functions are provided by the numactl package by Andi Kleen |
20 | (a version later than 0.9.3 is required. Get it from | |
6acb2ece MK |
21 | ftp://oss.sgi.com/www/projects/libnuma/download/). numactl provides libnuma |
22 | which provides an interface similar to other numa functionality for page | |
23 | migration. cat /proc/<pid>/numa_maps allows an easy review of where the | |
24 | pages of a process are located. See also the numa_maps documentation in the | |
25 | proc(5) man page. | |
b4fb3766 CL |
26 | |
27 | Manual migration is useful if for example the scheduler has relocated | |
a48d07af CL |
28 | a process to a processor on a distant node. A batch scheduler or an |
29 | administrator may detect the situation and move the pages of the process | |
742755a1 CL |
30 | nearer to the new processor. The kernel itself does only provide |
31 | manual page migration support. Automatic page migration may be implemented | |
32 | through user space processes that move pages. A special function call | |
33 | "move_pages" allows the moving of individual pages within a process. | |
34 | A NUMA profiler may f.e. obtain a log showing frequent off node | |
35 | accesses and may use the result to move pages to more advantageous | |
36 | locations. | |
a48d07af CL |
37 | |
38 | Larger installations usually partition the system using cpusets into | |
39 | sections of nodes. Paul Jackson has equipped cpusets with the ability to | |
21acb9ca | 40 | move pages when a task is moved to another cpuset (See |
09c3bcce | 41 | Documentation/cgroup-v1/cpusets.txt). |
b4fb3766 CL |
42 | Cpusets allows the automation of process locality. If a task is moved to |
43 | a new cpuset then also all its pages are moved with it so that the | |
44 | performance of the process does not sink dramatically. Also the pages | |
45 | of processes in a cpuset are moved if the allowed memory nodes of a | |
46 | cpuset are changed. | |
a48d07af CL |
47 | |
48 | Page migration allows the preservation of the relative location of pages | |
49 | within a group of nodes for all migration techniques which will preserve a | |
50 | particular memory allocation pattern generated even after migrating a | |
51 | process. This is necessary in order to preserve the memory latencies. | |
52 | Processes will run with similar performance after migration. | |
53 | ||
54 | Page migration occurs in several steps. First a high level | |
b4fb3766 CL |
55 | description for those trying to use migrate_pages() from the kernel |
56 | (for userspace usage see the Andi Kleen's numactl package mentioned above) | |
57 | and then a low level description of how the low level details work. | |
a48d07af | 58 | |
b4fb3766 CL |
59 | A. In kernel use of migrate_pages() |
60 | ----------------------------------- | |
a48d07af CL |
61 | |
62 | 1. Remove pages from the LRU. | |
63 | ||
64 | Lists of pages to be migrated are generated by scanning over | |
65 | pages and moving them into lists. This is done by | |
b4fb3766 | 66 | calling isolate_lru_page(). |
a48d07af | 67 | Calling isolate_lru_page increases the references to the page |
b4fb3766 CL |
68 | so that it cannot vanish while the page migration occurs. |
69 | It also prevents the swapper or other scans to encounter | |
70 | the page. | |
a48d07af | 71 | |
742755a1 CL |
72 | 2. We need to have a function of type new_page_t that can be |
73 | passed to migrate_pages(). This function should figure out | |
74 | how to allocate the correct new page given the old page. | |
a48d07af CL |
75 | |
76 | 3. The migrate_pages() function is called which attempts | |
742755a1 CL |
77 | to do the migration. It will call the function to allocate |
78 | the new page for each page that is considered for | |
79 | moving. | |
a48d07af | 80 | |
b4fb3766 CL |
81 | B. How migrate_pages() works |
82 | ---------------------------- | |
a48d07af | 83 | |
b4fb3766 CL |
84 | migrate_pages() does several passes over its list of pages. A page is moved |
85 | if all references to a page are removable at the time. The page has | |
86 | already been removed from the LRU via isolate_lru_page() and the refcount | |
87 | is increased so that the page cannot be freed while page migration occurs. | |
a48d07af CL |
88 | |
89 | Steps: | |
90 | ||
91 | 1. Lock the page to be migrated | |
92 | ||
93 | 2. Insure that writeback is complete. | |
94 | ||
cf4b769a HD |
95 | 3. Lock the new page that we want to move to. It is locked so that accesses to |
96 | this (not yet uptodate) page immediately lock while the move is in progress. | |
a48d07af | 97 | |
cf4b769a | 98 | 4. All the page table references to the page are converted to migration |
7a14239a HD |
99 | entries. This decreases the mapcount of a page. If the resulting |
100 | mapcount is not zero then we do not migrate the page. All user space | |
101 | processes that attempt to access the page will now wait on the page lock. | |
a48d07af | 102 | |
cf4b769a | 103 | 5. The radix tree lock is taken. This will cause all processes trying |
8d3c138b | 104 | to access the page via the mapping to block on the radix tree spinlock. |
a48d07af | 105 | |
cf4b769a | 106 | 6. The refcount of the page is examined and we back out if references remain |
a48d07af CL |
107 | otherwise we know that we are the only one referencing this page. |
108 | ||
cf4b769a | 109 | 7. The radix tree is checked and if it does not contain the pointer to this |
8d3c138b | 110 | page then we back out because someone else modified the radix tree. |
a48d07af | 111 | |
cf4b769a HD |
112 | 8. The new page is prepped with some settings from the old page so that |
113 | accesses to the new page will discover a page with the correct settings. | |
114 | ||
8d3c138b | 115 | 9. The radix tree is changed to point to the new page. |
a48d07af | 116 | |
8d3c138b CL |
117 | 10. The reference count of the old page is dropped because the radix tree |
118 | reference is gone. A reference to the new page is established because | |
119 | the new page is referenced to by the radix tree. | |
a48d07af | 120 | |
8d3c138b CL |
121 | 11. The radix tree lock is dropped. With that lookups in the mapping |
122 | become possible again. Processes will move from spinning on the tree_lock | |
123 | to sleeping on the locked new page. | |
a48d07af | 124 | |
8d3c138b | 125 | 12. The page contents are copied to the new page. |
a48d07af | 126 | |
8d3c138b | 127 | 13. The remaining page flags are copied to the new page. |
a48d07af | 128 | |
8d3c138b CL |
129 | 14. The old page flags are cleared to indicate that the page does |
130 | not provide any information anymore. | |
a48d07af | 131 | |
8d3c138b | 132 | 15. Queued up writeback on the new page is triggered. |
a48d07af | 133 | |
8d3c138b CL |
134 | 16. If migration entries were page then replace them with real ptes. Doing |
135 | so will enable access for user space processes not already waiting for | |
136 | the page lock. | |
b4fb3766 CL |
137 | |
138 | 19. The page locks are dropped from the old and new page. | |
8d3c138b CL |
139 | Processes waiting on the page lock will redo their page faults |
140 | and will reach the new page. | |
b4fb3766 CL |
141 | |
142 | 20. The new page is moved to the LRU and can be scanned by the swapper | |
143 | etc again. | |
144 | ||
bda807d4 MK |
145 | C. Non-LRU page migration |
146 | ------------------------- | |
147 | ||
148 | Although original migration aimed for reducing the latency of memory access | |
149 | for NUMA, compaction who want to create high-order page is also main customer. | |
150 | ||
151 | Current problem of the implementation is that it is designed to migrate only | |
152 | *LRU* pages. However, there are potential non-lru pages which can be migrated | |
153 | in drivers, for example, zsmalloc, virtio-balloon pages. | |
154 | ||
155 | For virtio-balloon pages, some parts of migration code path have been hooked | |
156 | up and added virtio-balloon specific functions to intercept migration logics. | |
157 | It's too specific to a driver so other drivers who want to make their pages | |
158 | movable would have to add own specific hooks in migration path. | |
159 | ||
160 | To overclome the problem, VM supports non-LRU page migration which provides | |
161 | generic functions for non-LRU movable pages without driver specific hooks | |
162 | migration path. | |
163 | ||
164 | If a driver want to make own pages movable, it should define three functions | |
165 | which are function pointers of struct address_space_operations. | |
166 | ||
167 | 1. bool (*isolate_page) (struct page *page, isolate_mode_t mode); | |
168 | ||
169 | What VM expects on isolate_page function of driver is to return *true* | |
170 | if driver isolates page successfully. On returing true, VM marks the page | |
171 | as PG_isolated so concurrent isolation in several CPUs skip the page | |
172 | for isolation. If a driver cannot isolate the page, it should return *false*. | |
173 | ||
174 | Once page is successfully isolated, VM uses page.lru fields so driver | |
175 | shouldn't expect to preserve values in that fields. | |
176 | ||
177 | 2. int (*migratepage) (struct address_space *mapping, | |
178 | struct page *newpage, struct page *oldpage, enum migrate_mode); | |
179 | ||
180 | After isolation, VM calls migratepage of driver with isolated page. | |
181 | The function of migratepage is to move content of the old page to new page | |
182 | and set up fields of struct page newpage. Keep in mind that you should | |
183 | indicate to the VM the oldpage is no longer movable via __ClearPageMovable() | |
dd4123f3 MK |
184 | under page_lock if you migrated the oldpage successfully and returns |
185 | MIGRATEPAGE_SUCCESS. If driver cannot migrate the page at the moment, driver | |
186 | can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time | |
187 | because VM interprets -EAGAIN as "temporal migration failure". On returning | |
188 | any error except -EAGAIN, VM will give up the page migration without retrying | |
189 | in this time. | |
bda807d4 MK |
190 | |
191 | Driver shouldn't touch page.lru field VM using in the functions. | |
192 | ||
193 | 3. void (*putback_page)(struct page *); | |
194 | ||
195 | If migration fails on isolated page, VM should return the isolated page | |
196 | to the driver so VM calls driver's putback_page with migration failed page. | |
197 | In this function, driver should put the isolated page back to the own data | |
198 | structure. | |
a48d07af | 199 | |
bda807d4 MK |
200 | 4. non-lru movable page flags |
201 | ||
202 | There are two page flags for supporting non-lru movable page. | |
203 | ||
204 | * PG_movable | |
205 | ||
206 | Driver should use the below function to make page movable under page_lock. | |
207 | ||
208 | void __SetPageMovable(struct page *page, struct address_space *mapping) | |
209 | ||
210 | It needs argument of address_space for registering migration family functions | |
211 | which will be called by VM. Exactly speaking, PG_movable is not a real flag of | |
212 | struct page. Rather than, VM reuses page->mapping's lower bits to represent it. | |
213 | ||
214 | #define PAGE_MAPPING_MOVABLE 0x2 | |
215 | page->mapping = page->mapping | PAGE_MAPPING_MOVABLE; | |
216 | ||
217 | so driver shouldn't access page->mapping directly. Instead, driver should | |
218 | use page_mapping which mask off the low two bits of page->mapping under | |
219 | page lock so it can get right struct address_space. | |
220 | ||
221 | For testing of non-lru movable page, VM supports __PageMovable function. | |
222 | However, it doesn't guarantee to identify non-lru movable page because | |
223 | page->mapping field is unified with other variables in struct page. | |
224 | As well, if driver releases the page after isolation by VM, page->mapping | |
225 | doesn't have stable value although it has PAGE_MAPPING_MOVABLE | |
226 | (Look at __ClearPageMovable). But __PageMovable is cheap to catch whether | |
227 | page is LRU or non-lru movable once the page has been isolated. Because | |
228 | LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also | |
229 | good for just peeking to test non-lru movable pages before more expensive | |
230 | checking with lock_page in pfn scanning to select victim. | |
231 | ||
232 | For guaranteeing non-lru movable page, VM provides PageMovable function. | |
233 | Unlike __PageMovable, PageMovable functions validates page->mapping and | |
234 | mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden | |
235 | destroying of page->mapping. | |
236 | ||
237 | Driver using __SetPageMovable should clear the flag via __ClearMovablePage | |
238 | under page_lock before the releasing the page. | |
239 | ||
240 | * PG_isolated | |
241 | ||
242 | To prevent concurrent isolation among several CPUs, VM marks isolated page | |
243 | as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru | |
244 | movable page, it can skip it. Driver doesn't need to manipulate the flag | |
245 | because VM will set/clear it automatically. Keep in mind that if driver | |
246 | sees PG_isolated page, it means the page have been isolated by VM so it | |
247 | shouldn't touch page.lru field. | |
248 | PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag | |
249 | for own purpose. | |
250 | ||
251 | Christoph Lameter, May 8, 2006. | |
252 | Minchan Kim, Mar 28, 2016. |