Documentation/vm/page_migration.rst

4 Page migration
7 Page migration allows moving the physical location of pages between
15 The main intent of page migration is to reduce the latency of memory accesses
19 Page migration allows a process to manually relocate the node on which its
25 Page migration functions are provided by the numactl package by Andi Kleen
29 migration.  cat ``/proc/<pid>/numa_maps`` allows an easy review of where the
33 Manual migration is useful if for example the scheduler has relocated
37 manual page migration support. Automatic page migration may be implemented
54 Page migration allows the preservation of the relative location of pages
55 within a group of nodes for all migration techniques which will preserve a
58 Processes will run with similar performance after migration.
60 Page migration occurs in several steps. First a high level
74    so that it cannot vanish while the page migration occurs.
83    to do the migration. It will call the function to allocate
93 is increased so that the page cannot be freed while page migration occurs.
104 4. All the page table references to the page are converted to migration
108    or wait for the migration page table entry to be removed.
141 16. If migration entries were inserted into the page table, then replace them
152 Non-LRU page migration
155 Although migration originally aimed for reducing the latency of memory accesses
156 for NUMA, compaction also uses migration to create high-order pages.
162 For virtio-balloon pages, some parts of migration code path have been hooked
163 up and added virtio-balloon specific functions to intercept migration logics.
165 movable would have to add their own specific hooks in the migration path.
167 To overcome the problem, VM supports non-LRU page migration which provides
169 in the migration path.
194    can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time
195    because VM interprets -EAGAIN as "temporary migration failure". On returning
196    any error except -EAGAIN, VM will give up the page migration without
203    If migration fails on the isolated page, VM should return the isolated page
218      It needs argument of address_space for registering migration
260 Monitoring Migration
263 The following events (counters) can be used to monitor page migration.
265 1. PGMIGRATE_SUCCESS: Normal page migration success. Each count means that a
268    the number of THP subpages. For example, migration of a single 2MB THP that
272 2. PGMIGRATE_FAIL: Normal page migration failure. Same counting rules as for
281    to be split. After splitting, a migration retry was used for it's sub-pages.
284 PGMIGRATE_FAIL events. For example, a THP migration failure will cause both