1Page migration
2--------------
3
4Page migration allows the moving of the physical location of pages between
5nodes in a numa system while the process is running. This means that the
6virtual addresses that the process sees do not change. However, the
7system rearranges the physical location of those pages.
8
9The main intend of page migration is to reduce the latency of memory access
10by moving pages near to the processor where the process accessing that memory
11is running.
12
13Page migration allows a process to manually relocate the node on which its
14pages are located through the MF_MOVE and MF_MOVE_ALL options while setting
15a new memory policy via mbind(). The pages of process can also be relocated
16from another process using the sys_migrate_pages() function call. The
17migrate_pages function call takes two sets of nodes and moves pages of a
18process that are located on the from nodes to the destination nodes.
19Page migration functions are provided by the numactl package by Andi Kleen
20(a version later than 0.9.3 is required. Get it from
21ftp://oss.sgi.com/www/projects/libnuma/download/). numactl provides libnuma
22which provides an interface similar to other numa functionality for page
23migration.  cat /proc/<pid>/numa_maps allows an easy review of where the
24pages of a process are located. See also the numa_maps documentation in the
25proc(5) man page.
26
27Manual migration is useful if for example the scheduler has relocated
28a process to a processor on a distant node. A batch scheduler or an
29administrator may detect the situation and move the pages of the process
30nearer to the new processor. The kernel itself does only provide
31manual page migration support. Automatic page migration may be implemented
32through user space processes that move pages. A special function call
33"move_pages" allows the moving of individual pages within a process.
34A NUMA profiler may f.e. obtain a log showing frequent off node
35accesses and may use the result to move pages to more advantageous
36locations.
37
38Larger installations usually partition the system using cpusets into
39sections of nodes. Paul Jackson has equipped cpusets with the ability to
40move pages when a task is moved to another cpuset (See
41Documentation/cgroups/cpusets.txt).
42Cpusets allows the automation of process locality. If a task is moved to
43a new cpuset then also all its pages are moved with it so that the
44performance of the process does not sink dramatically. Also the pages
45of processes in a cpuset are moved if the allowed memory nodes of a
46cpuset are changed.
47
48Page migration allows the preservation of the relative location of pages
49within a group of nodes for all migration techniques which will preserve a
50particular memory allocation pattern generated even after migrating a
51process. This is necessary in order to preserve the memory latencies.
52Processes will run with similar performance after migration.
53
54Page migration occurs in several steps. First a high level
55description for those trying to use migrate_pages() from the kernel
56(for userspace usage see the Andi Kleen's numactl package mentioned above)
57and then a low level description of how the low level details work.
58
59A. In kernel use of migrate_pages()
60-----------------------------------
61
621. 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
722. 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
763. 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
81B. How migrate_pages() works
82----------------------------
83
84migrate_pages() does several passes over its list of pages. A page is moved
85if all references to a page are removable at the time. The page has
86already been removed from the LRU via isolate_lru_page() and the refcount
87is increased so that the page cannot be freed while page migration occurs.
88
89Steps:
90
911. Lock the page to be migrated
92
932. Insure that writeback is complete.
94
953. Prep the new page that we want to move to. It is locked
96   and set to not being uptodate so that all accesses to the new
97   page immediately lock while the move is in progress.
98
994. The new page is prepped with some settings from the old page so that
100   accesses to the new page will discover a page with the correct settings.
101
1025. All the page table references to the page are converted
103   to migration entries or dropped (nonlinear vmas).
104   This decrease the mapcount of a page. If the resulting
105   mapcount is not zero then we do not migrate the page.
106   All user space processes that attempt to access the page
107   will now wait on the page lock.
108
1096. The radix tree lock is taken. This will cause all processes trying
110   to access the page via the mapping to block on the radix tree spinlock.
111
1127. The refcount of the page is examined and we back out if references remain
113   otherwise we know that we are the only one referencing this page.
114
1158. The radix tree is checked and if it does not contain the pointer to this
116   page then we back out because someone else modified the radix tree.
117
1189. The radix tree is changed to point to the new page.
119
12010. The reference count of the old page is dropped because the radix tree
121    reference is gone. A reference to the new page is established because
122    the new page is referenced to by the radix tree.
123
12411. The radix tree lock is dropped. With that lookups in the mapping
125    become possible again. Processes will move from spinning on the tree_lock
126    to sleeping on the locked new page.
127
12812. The page contents are copied to the new page.
129
13013. The remaining page flags are copied to the new page.
131
13214. The old page flags are cleared to indicate that the page does
133    not provide any information anymore.
134
13515. Queued up writeback on the new page is triggered.
136
13716. If migration entries were page then replace them with real ptes. Doing
138    so will enable access for user space processes not already waiting for
139    the page lock.
140
14119. The page locks are dropped from the old and new page.
142    Processes waiting on the page lock will redo their page faults
143    and will reach the new page.
144
14520. The new page is moved to the LRU and can be scanned by the swapper
146    etc again.
147
148Christoph Lameter, May 8, 2006.
149
150