Documentation/mm/page_migration.rst

2 Page migration
5 Page migration allows moving the physical location of pages between
13 The main intent of page migration is to reduce the latency of memory accesses
17 Page migration allows a process to manually relocate the node on which its
23 Page migration functions are provided by the numactl package by Andi Kleen
27 migration.  cat ``/proc/<pid>/numa_maps`` allows an easy review of where the
31 Manual migration is useful if for example the scheduler has relocated
35 manual page migration support. Automatic page migration may be implemented
52 Page migration allows the preservation of the relative location of pages
53 within a group of nodes for all migration techniques which will preserve a
56 Processes will run with similar performance after migration.
58 Page migration occurs in several steps. First a high level
72    so that it cannot vanish while the folio migration occurs.
81    to do the migration. It will call the function to allocate
90 is increased so that the folio cannot be freed while folio migration occurs.
101 4. All the page table references to the page are converted to migration
105    or wait for the migration page table entry to be removed.
138 16. If migration entries were inserted into the page table, then replace them
149 Non-LRU page migration
152 Although migration originally aimed for reducing the latency of memory
153 accesses for NUMA, compaction also uses migration to create high-order
162 Monitoring Migration
165 The following events (counters) can be used to monitor page migration.
167 1. PGMIGRATE_SUCCESS: Normal page migration success. Each count means that a
171    For example, migration of a single 2MB THP that has 4KB-size base pages
174 2. PGMIGRATE_FAIL: Normal page migration failure. Same counting rules as for
183    to be split. After splitting, a migration retry was used for its sub-pages.
186 PGMIGRATE_FAIL events. For example, a THP migration failure will cause both