1 .. _numa_memory_policy:
7 What is NUMA Memory Policy?
8 ============================
10 In the Linux kernel, "memory policy" determines from which node the kernel will
11 allocate memory in a NUMA system or in an emulated NUMA system. Linux has
12 supported platforms with Non-Uniform Memory Access architectures since 2.4.?.
13 The current memory policy support was added to Linux 2.6 around May 2004. This
14 document attempts to describe the concepts and APIs of the 2.6 memory policy
17 Memory policies should not be confused with cpusets
18 (``Documentation/admin-guide/cgroup-v1/cpusets.rst``)
19 which is an administrative mechanism for restricting the nodes from which
20 memory may be allocated by a set of processes. Memory policies are a
21 programming interface that a NUMA-aware application can take advantage of. When
22 both cpusets and policies are applied to a task, the restrictions of the cpuset
23 takes priority. See :ref:`Memory Policies and cpusets <mem_pol_and_cpusets>`
24 below for more details.
26 Memory Policy Concepts
27 ======================
29 Scope of Memory Policies
30 ------------------------
32 The Linux kernel supports _scopes_ of memory policy, described here from
33 most general to most specific:
36 this policy is "hard coded" into the kernel. It is the policy
37 that governs all page allocations that aren't controlled by
38 one of the more specific policy scopes discussed below. When
39 the system is "up and running", the system default policy will
40 use "local allocation" described below. However, during boot
41 up, the system default policy will be set to interleave
42 allocations across all nodes with "sufficient" memory, so as
43 not to overload the initial boot node with boot-time
47 this is an optional, per-task policy. When defined for a
48 specific task, this policy controls all page allocations made
49 by or on behalf of the task that aren't controlled by a more
50 specific scope. If a task does not define a task policy, then
51 all page allocations that would have been controlled by the
52 task policy "fall back" to the System Default Policy.
54 The task policy applies to the entire address space of a task. Thus,
55 it is inheritable, and indeed is inherited, across both fork()
56 [clone() w/o the CLONE_VM flag] and exec*(). This allows a parent task
57 to establish the task policy for a child task exec()'d from an
58 executable image that has no awareness of memory policy. See the
59 :ref:`Memory Policy APIs <memory_policy_apis>` section,
60 below, for an overview of the system call
61 that a task may use to set/change its task/process policy.
63 In a multi-threaded task, task policies apply only to the thread
64 [Linux kernel task] that installs the policy and any threads
65 subsequently created by that thread. Any sibling threads existing
66 at the time a new task policy is installed retain their current
69 A task policy applies only to pages allocated after the policy is
70 installed. Any pages already faulted in by the task when the task
71 changes its task policy remain where they were allocated based on
72 the policy at the time they were allocated.
77 A "VMA" or "Virtual Memory Area" refers to a range of a task's
78 virtual address space. A task may define a specific policy for a range
79 of its virtual address space. See the
80 :ref:`Memory Policy APIs <memory_policy_apis>` section,
81 below, for an overview of the mbind() system call used to set a VMA
84 A VMA policy will govern the allocation of pages that back
85 this region of the address space. Any regions of the task's
86 address space that don't have an explicit VMA policy will fall
87 back to the task policy, which may itself fall back to the
88 System Default Policy.
90 VMA policies have a few complicating details:
92 * VMA policy applies ONLY to anonymous pages. These include
93 pages allocated for anonymous segments, such as the task
94 stack and heap, and any regions of the address space
95 mmap()ed with the MAP_ANONYMOUS flag. If a VMA policy is
96 applied to a file mapping, it will be ignored if the mapping
97 used the MAP_SHARED flag. If the file mapping used the
98 MAP_PRIVATE flag, the VMA policy will only be applied when
99 an anonymous page is allocated on an attempt to write to the
100 mapping-- i.e., at Copy-On-Write.
102 * VMA policies are shared between all tasks that share a
103 virtual address space--a.k.a. threads--independent of when
104 the policy is installed; and they are inherited across
105 fork(). However, because VMA policies refer to a specific
106 region of a task's address space, and because the address
107 space is discarded and recreated on exec*(), VMA policies
108 are NOT inheritable across exec(). Thus, only NUMA-aware
109 applications may use VMA policies.
111 * A task may install a new VMA policy on a sub-range of a
112 previously mmap()ed region. When this happens, Linux splits
113 the existing virtual memory area into 2 or 3 VMAs, each with
116 * By default, VMA policy applies only to pages allocated after
117 the policy is installed. Any pages already faulted into the
118 VMA range remain where they were allocated based on the
119 policy at the time they were allocated. However, since
120 2.6.16, Linux supports page migration via the mbind() system
121 call, so that page contents can be moved to match a newly
125 Conceptually, shared policies apply to "memory objects" mapped
126 shared into one or more tasks' distinct address spaces. An
127 application installs shared policies the same way as VMA
128 policies--using the mbind() system call specifying a range of
129 virtual addresses that map the shared object. However, unlike
130 VMA policies, which can be considered to be an attribute of a
131 range of a task's address space, shared policies apply
132 directly to the shared object. Thus, all tasks that attach to
133 the object share the policy, and all pages allocated for the
134 shared object, by any task, will obey the shared policy.
136 As of 2.6.22, only shared memory segments, created by shmget() or
137 mmap(MAP_ANONYMOUS|MAP_SHARED), support shared policy. When shared
138 policy support was added to Linux, the associated data structures were
139 added to hugetlbfs shmem segments. At the time, hugetlbfs did not
140 support allocation at fault time--a.k.a lazy allocation--so hugetlbfs
141 shmem segments were never "hooked up" to the shared policy support.
142 Although hugetlbfs segments now support lazy allocation, their support
143 for shared policy has not been completed.
145 As mentioned above in :ref:`VMA policies <vma_policy>` section,
146 allocations of page cache pages for regular files mmap()ed
147 with MAP_SHARED ignore any VMA policy installed on the virtual
148 address range backed by the shared file mapping. Rather,
149 shared page cache pages, including pages backing private
150 mappings that have not yet been written by the task, follow
151 task policy, if any, else System Default Policy.
153 The shared policy infrastructure supports different policies on subset
154 ranges of the shared object. However, Linux still splits the VMA of
155 the task that installs the policy for each range of distinct policy.
156 Thus, different tasks that attach to a shared memory segment can have
157 different VMA configurations mapping that one shared object. This
158 can be seen by examining the /proc/<pid>/numa_maps of tasks sharing
159 a shared memory region, when one task has installed shared policy on
160 one or more ranges of the region.
162 Components of Memory Policies
163 -----------------------------
165 A NUMA memory policy consists of a "mode", optional mode flags, and
166 an optional set of nodes. The mode determines the behavior of the
167 policy, the optional mode flags determine the behavior of the mode,
168 and the optional set of nodes can be viewed as the arguments to the
171 Internally, memory policies are implemented by a reference counted
172 structure, struct mempolicy. Details of this structure will be
173 discussed in context, below, as required to explain the behavior.
175 NUMA memory policy supports the following 4 behavioral modes:
177 Default Mode--MPOL_DEFAULT
178 This mode is only used in the memory policy APIs. Internally,
179 MPOL_DEFAULT is converted to the NULL memory policy in all
180 policy scopes. Any existing non-default policy will simply be
181 removed when MPOL_DEFAULT is specified. As a result,
182 MPOL_DEFAULT means "fall back to the next most specific policy
185 For example, a NULL or default task policy will fall back to the
186 system default policy. A NULL or default vma policy will fall
187 back to the task policy.
189 When specified in one of the memory policy APIs, the Default mode
190 does not use the optional set of nodes.
192 It is an error for the set of nodes specified for this policy to
196 This mode specifies that memory must come from the set of
197 nodes specified by the policy. Memory will be allocated from
198 the node in the set with sufficient free memory that is
199 closest to the node where the allocation takes place.
202 This mode specifies that the allocation should be attempted
203 from the single node specified in the policy. If that
204 allocation fails, the kernel will search other nodes, in order
205 of increasing distance from the preferred node based on
206 information provided by the platform firmware.
208 Internally, the Preferred policy uses a single node--the
209 preferred_node member of struct mempolicy. When the internal
210 mode flag MPOL_F_LOCAL is set, the preferred_node is ignored
211 and the policy is interpreted as local allocation. "Local"
212 allocation policy can be viewed as a Preferred policy that
213 starts at the node containing the cpu where the allocation
216 It is possible for the user to specify that local allocation
217 is always preferred by passing an empty nodemask with this
218 mode. If an empty nodemask is passed, the policy cannot use
219 the MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags
223 This mode specifies that page allocations be interleaved, on a
224 page granularity, across the nodes specified in the policy.
225 This mode also behaves slightly differently, based on the
226 context where it is used:
228 For allocation of anonymous pages and shared memory pages,
229 Interleave mode indexes the set of nodes specified by the
230 policy using the page offset of the faulting address into the
231 segment [VMA] containing the address modulo the number of
232 nodes specified by the policy. It then attempts to allocate a
233 page, starting at the selected node, as if the node had been
234 specified by a Preferred policy or had been selected by a
235 local allocation. That is, allocation will follow the per
238 For allocation of page cache pages, Interleave mode indexes
239 the set of nodes specified by the policy using a node counter
240 maintained per task. This counter wraps around to the lowest
241 specified node after it reaches the highest specified node.
242 This will tend to spread the pages out over the nodes
243 specified by the policy based on the order in which they are
244 allocated, rather than based on any page offset into an
245 address range or file. During system boot up, the temporary
246 interleaved system default policy works in this mode.
249 This mode specifices that the allocation should be preferrably
250 satisfied from the nodemask specified in the policy. If there is
251 a memory pressure on all nodes in the nodemask, the allocation
252 can fall back to all existing numa nodes. This is effectively
253 MPOL_PREFERRED allowed for a mask rather than a single node.
255 NUMA memory policy supports the following optional mode flags:
258 This flag specifies that the nodemask passed by
259 the user should not be remapped if the task or VMA's set of allowed
260 nodes changes after the memory policy has been defined.
262 Without this flag, any time a mempolicy is rebound because of a
263 change in the set of allowed nodes, the preferred nodemask (Preferred
264 Many), preferred node (Preferred) or nodemask (Bind, Interleave) is
265 remapped to the new set of allowed nodes. This may result in nodes
266 being used that were previously undesired.
268 With this flag, if the user-specified nodes overlap with the
269 nodes allowed by the task's cpuset, then the memory policy is
270 applied to their intersection. If the two sets of nodes do not
271 overlap, the Default policy is used.
273 For example, consider a task that is attached to a cpuset with
274 mems 1-3 that sets an Interleave policy over the same set. If
275 the cpuset's mems change to 3-5, the Interleave will now occur
276 over nodes 3, 4, and 5. With this flag, however, since only node
277 3 is allowed from the user's nodemask, the "interleave" only
278 occurs over that node. If no nodes from the user's nodemask are
279 now allowed, the Default behavior is used.
281 MPOL_F_STATIC_NODES cannot be combined with the
282 MPOL_F_RELATIVE_NODES flag. It also cannot be used for
283 MPOL_PREFERRED policies that were created with an empty nodemask
286 MPOL_F_RELATIVE_NODES
287 This flag specifies that the nodemask passed
288 by the user will be mapped relative to the set of the task or VMA's
289 set of allowed nodes. The kernel stores the user-passed nodemask,
290 and if the allowed nodes changes, then that original nodemask will
291 be remapped relative to the new set of allowed nodes.
293 Without this flag (and without MPOL_F_STATIC_NODES), anytime a
294 mempolicy is rebound because of a change in the set of allowed
295 nodes, the node (Preferred) or nodemask (Bind, Interleave) is
296 remapped to the new set of allowed nodes. That remap may not
297 preserve the relative nature of the user's passed nodemask to its
298 set of allowed nodes upon successive rebinds: a nodemask of
299 1,3,5 may be remapped to 7-9 and then to 1-3 if the set of
300 allowed nodes is restored to its original state.
302 With this flag, the remap is done so that the node numbers from
303 the user's passed nodemask are relative to the set of allowed
304 nodes. In other words, if nodes 0, 2, and 4 are set in the user's
305 nodemask, the policy will be effected over the first (and in the
306 Bind or Interleave case, the third and fifth) nodes in the set of
307 allowed nodes. The nodemask passed by the user represents nodes
308 relative to task or VMA's set of allowed nodes.
310 If the user's nodemask includes nodes that are outside the range
311 of the new set of allowed nodes (for example, node 5 is set in
312 the user's nodemask when the set of allowed nodes is only 0-3),
313 then the remap wraps around to the beginning of the nodemask and,
314 if not already set, sets the node in the mempolicy nodemask.
316 For example, consider a task that is attached to a cpuset with
317 mems 2-5 that sets an Interleave policy over the same set with
318 MPOL_F_RELATIVE_NODES. If the cpuset's mems change to 3-7, the
319 interleave now occurs over nodes 3,5-7. If the cpuset's mems
320 then change to 0,2-3,5, then the interleave occurs over nodes
323 Thanks to the consistent remapping, applications preparing
324 nodemasks to specify memory policies using this flag should
325 disregard their current, actual cpuset imposed memory placement
326 and prepare the nodemask as if they were always located on
327 memory nodes 0 to N-1, where N is the number of memory nodes the
328 policy is intended to manage. Let the kernel then remap to the
329 set of memory nodes allowed by the task's cpuset, as that may
332 MPOL_F_RELATIVE_NODES cannot be combined with the
333 MPOL_F_STATIC_NODES flag. It also cannot be used for
334 MPOL_PREFERRED policies that were created with an empty nodemask
337 Memory Policy Reference Counting
338 ================================
340 To resolve use/free races, struct mempolicy contains an atomic reference
341 count field. Internal interfaces, mpol_get()/mpol_put() increment and
342 decrement this reference count, respectively. mpol_put() will only free
343 the structure back to the mempolicy kmem cache when the reference count
346 When a new memory policy is allocated, its reference count is initialized
347 to '1', representing the reference held by the task that is installing the
348 new policy. When a pointer to a memory policy structure is stored in another
349 structure, another reference is added, as the task's reference will be dropped
350 on completion of the policy installation.
352 During run-time "usage" of the policy, we attempt to minimize atomic operations
353 on the reference count, as this can lead to cache lines bouncing between cpus
354 and NUMA nodes. "Usage" here means one of the following:
356 1) querying of the policy, either by the task itself [using the get_mempolicy()
357 API discussed below] or by another task using the /proc/<pid>/numa_maps
360 2) examination of the policy to determine the policy mode and associated node
361 or node lists, if any, for page allocation. This is considered a "hot
362 path". Note that for MPOL_BIND, the "usage" extends across the entire
363 allocation process, which may sleep during page reclaimation, because the
364 BIND policy nodemask is used, by reference, to filter ineligible nodes.
366 We can avoid taking an extra reference during the usages listed above as
369 1) we never need to get/free the system default policy as this is never
370 changed nor freed, once the system is up and running.
372 2) for querying the policy, we do not need to take an extra reference on the
373 target task's task policy nor vma policies because we always acquire the
374 task's mm's mmap_lock for read during the query. The set_mempolicy() and
375 mbind() APIs [see below] always acquire the mmap_lock for write when
376 installing or replacing task or vma policies. Thus, there is no possibility
377 of a task or thread freeing a policy while another task or thread is
380 3) Page allocation usage of task or vma policy occurs in the fault path where
381 we hold them mmap_lock for read. Again, because replacing the task or vma
382 policy requires that the mmap_lock be held for write, the policy can't be
383 freed out from under us while we're using it for page allocation.
385 4) Shared policies require special consideration. One task can replace a
386 shared memory policy while another task, with a distinct mmap_lock, is
387 querying or allocating a page based on the policy. To resolve this
388 potential race, the shared policy infrastructure adds an extra reference
389 to the shared policy during lookup while holding a spin lock on the shared
390 policy management structure. This requires that we drop this extra
391 reference when we're finished "using" the policy. We must drop the
392 extra reference on shared policies in the same query/allocation paths
393 used for non-shared policies. For this reason, shared policies are marked
394 as such, and the extra reference is dropped "conditionally"--i.e., only
397 Because of this extra reference counting, and because we must lookup
398 shared policies in a tree structure under spinlock, shared policies are
399 more expensive to use in the page allocation path. This is especially
400 true for shared policies on shared memory regions shared by tasks running
401 on different NUMA nodes. This extra overhead can be avoided by always
402 falling back to task or system default policy for shared memory regions,
403 or by prefaulting the entire shared memory region into memory and locking
404 it down. However, this might not be appropriate for all applications.
406 .. _memory_policy_apis:
411 Linux supports 4 system calls for controlling memory policy. These APIS
412 always affect only the calling task, the calling task's address space, or
413 some shared object mapped into the calling task's address space.
416 the headers that define these APIs and the parameter data types for
417 user space applications reside in a package that is not part of the
418 Linux kernel. The kernel system call interfaces, with the 'sys\_'
419 prefix, are defined in <linux/syscalls.h>; the mode and flag
420 definitions are defined in <linux/mempolicy.h>.
422 Set [Task] Memory Policy::
424 long set_mempolicy(int mode, const unsigned long *nmask,
425 unsigned long maxnode);
427 Set's the calling task's "task/process memory policy" to mode
428 specified by the 'mode' argument and the set of nodes defined by
429 'nmask'. 'nmask' points to a bit mask of node ids containing at least
430 'maxnode' ids. Optional mode flags may be passed by combining the
431 'mode' argument with the flag (for example: MPOL_INTERLEAVE |
432 MPOL_F_STATIC_NODES).
434 See the set_mempolicy(2) man page for more details
437 Get [Task] Memory Policy or Related Information::
439 long get_mempolicy(int *mode,
440 const unsigned long *nmask, unsigned long maxnode,
441 void *addr, int flags);
443 Queries the "task/process memory policy" of the calling task, or the
444 policy or location of a specified virtual address, depending on the
447 See the get_mempolicy(2) man page for more details
450 Install VMA/Shared Policy for a Range of Task's Address Space::
452 long mbind(void *start, unsigned long len, int mode,
453 const unsigned long *nmask, unsigned long maxnode,
456 mbind() installs the policy specified by (mode, nmask, maxnodes) as a
457 VMA policy for the range of the calling task's address space specified
458 by the 'start' and 'len' arguments. Additional actions may be
459 requested via the 'flags' argument.
461 See the mbind(2) man page for more details.
463 Set home node for a Range of Task's Address Spacec::
465 long sys_set_mempolicy_home_node(unsigned long start, unsigned long len,
466 unsigned long home_node,
467 unsigned long flags);
469 sys_set_mempolicy_home_node set the home node for a VMA policy present in the
470 task's address range. The system call updates the home node only for the existing
471 mempolicy range. Other address ranges are ignored. A home node is the NUMA node
472 closest to which page allocation will come from. Specifying the home node override
473 the default allocation policy to allocate memory close to the local node for an
477 Memory Policy Command Line Interface
478 ====================================
480 Although not strictly part of the Linux implementation of memory policy,
481 a command line tool, numactl(8), exists that allows one to:
483 + set the task policy for a specified program via set_mempolicy(2), fork(2) and
486 + set the shared policy for a shared memory segment via mbind(2)
488 The numactl(8) tool is packaged with the run-time version of the library
489 containing the memory policy system call wrappers. Some distributions
490 package the headers and compile-time libraries in a separate development
493 .. _mem_pol_and_cpusets:
495 Memory Policies and cpusets
496 ===========================
498 Memory policies work within cpusets as described above. For memory policies
499 that require a node or set of nodes, the nodes are restricted to the set of
500 nodes whose memories are allowed by the cpuset constraints. If the nodemask
501 specified for the policy contains nodes that are not allowed by the cpuset and
502 MPOL_F_RELATIVE_NODES is not used, the intersection of the set of nodes
503 specified for the policy and the set of nodes with memory is used. If the
504 result is the empty set, the policy is considered invalid and cannot be
505 installed. If MPOL_F_RELATIVE_NODES is used, the policy's nodes are mapped
506 onto and folded into the task's set of allowed nodes as previously described.
508 The interaction of memory policies and cpusets can be problematic when tasks
509 in two cpusets share access to a memory region, such as shared memory segments
510 created by shmget() of mmap() with the MAP_ANONYMOUS and MAP_SHARED flags, and
511 any of the tasks install shared policy on the region, only nodes whose
512 memories are allowed in both cpusets may be used in the policies. Obtaining
513 this information requires "stepping outside" the memory policy APIs to use the
514 cpuset information and requires that one know in what cpusets other task might
515 be attaching to the shared region. Furthermore, if the cpusets' allowed
516 memory sets are disjoint, "local" allocation is the only valid policy.