Based on kernel version 4.9. Page generated on 2016-12-21 14:37 EST.
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 15 a new memory policy via mbind(). The pages of process can also be relocated 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. 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 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. 26 27 Manual migration is useful if for example the scheduler has relocated 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 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. 37 38 Larger installations usually partition the system using cpusets into 39 sections of nodes. Paul Jackson has equipped cpusets with the ability to 40 move pages when a task is moved to another cpuset (See 41 Documentation/cgroup-v1/cpusets.txt). 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. 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 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. 58 59 A. In kernel use of migrate_pages() 60 ----------------------------------- 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 66 calling isolate_lru_page(). 67 Calling isolate_lru_page increases the references to the page 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. 71 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. 75 76 3. The migrate_pages() function is called which attempts 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. 80 81 B. How migrate_pages() works 82 ---------------------------- 83 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. 88 89 Steps: 90 91 1. Lock the page to be migrated 92 93 2. Insure that writeback is complete. 94 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. 97 98 4. All the page table references to the page are converted to migration 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. 102 103 5. The radix tree lock is taken. This will cause all processes trying 104 to access the page via the mapping to block on the radix tree spinlock. 105 106 6. The refcount of the page is examined and we back out if references remain 107 otherwise we know that we are the only one referencing this page. 108 109 7. The radix tree is checked and if it does not contain the pointer to this 110 page then we back out because someone else modified the radix tree. 111 112 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. 114 115 9. The radix tree is changed to point to the new page. 116 117 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. 120 121 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. 124 125 12. The page contents are copied to the new page. 126 127 13. The remaining page flags are copied to the new page. 128 129 14. The old page flags are cleared to indicate that the page does 130 not provide any information anymore. 131 132 15. Queued up writeback on the new page is triggered. 133 134 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. 137 138 19. The page locks are dropped from the old and new page. 139 Processes waiting on the page lock will redo their page faults 140 and will reach the new page. 141 142 20. The new page is moved to the LRU and can be scanned by the swapper 143 etc again. 144 145 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() 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. 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. 199 200 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.