admin-guide/mm/hugetlbpage.rst

2 HugeTLB Pages
28 persistent hugetlb pages in the kernel's huge page pool.  It also displays
30 and surplus huge pages in the pool of huge pages of default size.
46 	is the size of the pool of huge pages.
48 	is the number of huge pages in the pool that are not yet
51 	is short for "reserved," and is the number of huge pages for
53         but no allocation has yet been made.  Reserved huge pages
55         huge page from the pool of huge pages at fault time.
57 	is short for "surplus," and is the number of huge pages in
59         maximum number of surplus huge pages is controlled by
61 	Note: When the feature of freeing unused vmemmap pages associated
62 	with each hugetlb page is enabled, the number of surplus huge pages
64 	pages when the system is under memory pressure.
69         pages of all sizes.
70         If huge pages of different sizes are in use, this number
80 pages in the kernel's huge page pool.  "Persistent" huge pages will be
82 privileges can dynamically allocate more or free some persistent huge pages
85 Note: When the feature of freeing unused vmemmap pages associated with each
86 hugetlb page is enabled, we can fail to free the huge pages triggered by
89 Pages that are used as huge pages are reserved inside the kernel and cannot
90 be used for other purposes.  Huge pages cannot be swapped out under
93 Once a number of huge pages have been pre-allocated to the kernel huge page
95 or shared memory system calls to use the huge pages.  See the discussion of
96 :ref:`Using Huge Pages <using_huge_pages>`, below.
98 The administrator can allocate persistent huge pages on the kernel boot
100 number of huge pages requested.  This is the most reliable method of
101 allocating huge pages as memory has not yet become fragmented.
103 Some platforms support multiple huge page sizes.  To allocate huge pages
104 of a specific size, one must precede the huge pages boot command parameters
113 	parameter to preallocate a number of huge pages of the specified
123 	Specify the number of huge pages to preallocate.  This typically
126 	implicitly specifies the number of huge pages of default size to
127 	allocate.  If the number of huge pages of default size is implicitly
130 	node format.  The node format specifies the number of huge pages
137 	will result in 256 2M huge pages being allocated and a warning message
153 	specific number of huge pages of default size.  The number of default
154 	sized huge pages to preallocate can also be implicitly specified as
162 	will all result in 256 2M huge pages being allocated.  Valid default
169 indicates the current number of pre-allocated huge pages of the default size.
171 default sized persistent huge pages::
175 This command will try to adjust the number of default sized huge pages in the
176 huge page pool to 20, allocating or freeing huge pages, as required.
183 silently skipped when allocating persistent huge pages.  See the
186 with the allocation and freeing of persistent huge pages.
190 allocation attempt.  If the kernel is unable to allocate huge pages from
192 allocating extra pages on other nodes with sufficient available contiguous
196 init files.  This will enable the kernel to allocate huge pages early in
197 the boot process when the possibility of getting physical contiguous pages
198 is still very high.  Administrators can verify the number of huge pages
200 distribution of huge pages in a NUMA system, use::
205 huge pages can grow, if more huge pages than ``/proc/sys/vm/nr_hugepages`` are
208 number of "surplus" huge pages from the kernel's normal page pool, when the
209 persistent huge page pool is exhausted. As these surplus huge pages become
213 surplus pages will first be promoted to persistent huge pages.  Then, additional
214 huge pages will be allocated, if necessary and if possible, to fulfill
217 The administrator may shrink the pool of persistent huge pages for
219 smaller value.  The kernel will attempt to balance the freeing of huge pages
221 Any free huge pages on the selected nodes will be freed back to the kernel's
225 it becomes less than the number of huge pages in use will convert the balance
226 of the in-use huge pages to surplus huge pages.  This will occur even if
227 the number of surplus pages would exceed the overcommit value.  As long as
229 increased sufficiently, or the surplus huge pages go out of use and are freed--
230 no more surplus huge pages will be allowed to be allocated.
247 pages may exist::
259 smaller huge pages.  For example, the x86 architecture supports both
260 1GB and 2MB huge pages sizes.  A 1GB huge page can be split into 512
261 2MB huge pages.  Demote interfaces are not available for the smallest
265         is the size of demoted pages.  When a page is demoted a corresponding
266         number of huge pages of demote_size will be created.  By default,
270         pages size are allowed.
273         is used to demote a number of huge pages.  A user with root privileges
275         requested number of huge pages.  To determine how many pages were
287 Whether huge pages are allocated and freed via the ``/proc`` interface or
289 NUMA nodes from which huge pages are allocated or freed are controlled by the
294 The recommended method to allocate or free huge pages to/from the kernel
305 specified in <node-list>, depending on whether number of persistent huge pages
306 is initially less than or greater than 20, respectively.  No huge pages will be
315    persistent huge pages will be distributed across the node or nodes
321    possibly, allocation of persistent huge pages on nodes not allowed by
344    subset of the system nodes to allocate huge pages outside the cpuset
348    of huge pages over all on-lines nodes with memory.
367 of free and surplus [overcommitted] huge pages, respectively, on the parent
370 The ``nr_hugepages`` attribute returns the total number of huge pages on the
372 pages on the parent node will be adjusted to the specified value, if sufficient
375 Note that the number of overcommit and reserve pages remain global quantities,
388 Using Huge Pages
391 If the user applications are going to request huge pages using mmap system
400 ``/mnt/huge``.  Any file created on ``/mnt/huge`` uses huge pages.
414 The ``size`` option sets the maximum value of memory (huge pages) allowed
419 The ``min_size`` option sets the minimum value of memory (huge pages) allowed
422 At mount time, the number of huge pages specified by ``min_size`` are reserved
424 If there are not enough free huge pages available, the mount will fail.
425 As huge pages are allocated to the filesystem and freed, the reserve count
426 is adjusted so that the sum of allocated and reserved huge pages is always
456 Syscalls that operate on memory backed by hugetlb pages only have their lengths
458 errno set to EINVAL or exclude hugetlb pages that extend beyond the length if