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 | |
b4fb3766 CL |
40 | move pages when a task is moved to another cpuset (See ../cpusets.txt). |
41 | Cpusets allows the automation of process locality. If a task is moved to | |
42 | a new cpuset then also all its pages are moved with it so that the | |
43 | performance of the process does not sink dramatically. Also the pages | |
44 | of processes in a cpuset are moved if the allowed memory nodes of a | |
45 | cpuset are changed. | |
a48d07af CL |
46 | |
47 | Page migration allows the preservation of the relative location of pages | |
48 | within a group of nodes for all migration techniques which will preserve a | |
49 | particular memory allocation pattern generated even after migrating a | |
50 | process. This is necessary in order to preserve the memory latencies. | |
51 | Processes will run with similar performance after migration. | |
52 | ||
53 | Page migration occurs in several steps. First a high level | |
b4fb3766 CL |
54 | description for those trying to use migrate_pages() from the kernel |
55 | (for userspace usage see the Andi Kleen's numactl package mentioned above) | |
56 | and then a low level description of how the low level details work. | |
a48d07af | 57 | |
b4fb3766 CL |
58 | A. In kernel use of migrate_pages() |
59 | ----------------------------------- | |
a48d07af CL |
60 | |
61 | 1. Remove pages from the LRU. | |
62 | ||
63 | Lists of pages to be migrated are generated by scanning over | |
64 | pages and moving them into lists. This is done by | |
b4fb3766 | 65 | calling isolate_lru_page(). |
a48d07af | 66 | Calling isolate_lru_page increases the references to the page |
b4fb3766 CL |
67 | so that it cannot vanish while the page migration occurs. |
68 | It also prevents the swapper or other scans to encounter | |
69 | the page. | |
a48d07af | 70 | |
742755a1 CL |
71 | 2. We need to have a function of type new_page_t that can be |
72 | passed to migrate_pages(). This function should figure out | |
73 | how to allocate the correct new page given the old page. | |
a48d07af CL |
74 | |
75 | 3. The migrate_pages() function is called which attempts | |
742755a1 CL |
76 | to do the migration. It will call the function to allocate |
77 | the new page for each page that is considered for | |
78 | moving. | |
a48d07af | 79 | |
b4fb3766 CL |
80 | B. How migrate_pages() works |
81 | ---------------------------- | |
a48d07af | 82 | |
b4fb3766 CL |
83 | migrate_pages() does several passes over its list of pages. A page is moved |
84 | if all references to a page are removable at the time. The page has | |
85 | already been removed from the LRU via isolate_lru_page() and the refcount | |
86 | is increased so that the page cannot be freed while page migration occurs. | |
a48d07af CL |
87 | |
88 | Steps: | |
89 | ||
90 | 1. Lock the page to be migrated | |
91 | ||
92 | 2. Insure that writeback is complete. | |
93 | ||
8d3c138b | 94 | 3. Prep the new page that we want to move to. It is locked |
a48d07af | 95 | and set to not being uptodate so that all accesses to the new |
b4fb3766 | 96 | page immediately lock while the move is in progress. |
a48d07af | 97 | |
8d3c138b CL |
98 | 4. The new page is prepped with some settings from the old page so that |
99 | accesses to the new page will discover a page with the correct settings. | |
100 | ||
101 | 5. All the page table references to the page are converted | |
102 | to migration entries or dropped (nonlinear vmas). | |
103 | This decrease the mapcount of a page. If the resulting | |
104 | mapcount is not zero then we do not migrate the page. | |
105 | All user space processes that attempt to access the page | |
106 | will now wait on the page lock. | |
a48d07af | 107 | |
b4fb3766 | 108 | 6. The radix tree lock is taken. This will cause all processes trying |
8d3c138b | 109 | to access the page via the mapping to block on the radix tree spinlock. |
a48d07af CL |
110 | |
111 | 7. The refcount of the page is examined and we back out if references remain | |
112 | otherwise we know that we are the only one referencing this page. | |
113 | ||
114 | 8. The radix tree is checked and if it does not contain the pointer to this | |
8d3c138b | 115 | page then we back out because someone else modified the radix tree. |
a48d07af | 116 | |
8d3c138b | 117 | 9. The radix tree is changed to point to the new page. |
a48d07af | 118 | |
8d3c138b CL |
119 | 10. The reference count of the old page is dropped because the radix tree |
120 | reference is gone. A reference to the new page is established because | |
121 | the new page is referenced to by the radix tree. | |
a48d07af | 122 | |
8d3c138b CL |
123 | 11. The radix tree lock is dropped. With that lookups in the mapping |
124 | become possible again. Processes will move from spinning on the tree_lock | |
125 | to sleeping on the locked new page. | |
a48d07af | 126 | |
8d3c138b | 127 | 12. The page contents are copied to the new page. |
a48d07af | 128 | |
8d3c138b | 129 | 13. The remaining page flags are copied to the new page. |
a48d07af | 130 | |
8d3c138b CL |
131 | 14. The old page flags are cleared to indicate that the page does |
132 | not provide any information anymore. | |
a48d07af | 133 | |
8d3c138b | 134 | 15. Queued up writeback on the new page is triggered. |
a48d07af | 135 | |
8d3c138b CL |
136 | 16. If migration entries were page then replace them with real ptes. Doing |
137 | so will enable access for user space processes not already waiting for | |
138 | the page lock. | |
b4fb3766 CL |
139 | |
140 | 19. The page locks are dropped from the old and new page. | |
8d3c138b CL |
141 | Processes waiting on the page lock will redo their page faults |
142 | and will reach the new page. | |
b4fb3766 CL |
143 | |
144 | 20. The new page is moved to the LRU and can be scanned by the swapper | |
145 | etc again. | |
146 | ||
8d3c138b | 147 | Christoph Lameter, May 8, 2006. |
a48d07af | 148 |