Lines Matching full:pages

13 using huge pages for the backing of virtual memory with huge pages
53 collapses sequences of basic pages into huge pages.
109 pages unless hugepages are immediately available. Clearly if we spend CPU
111 use hugepages later instead of regular pages. This isn't always
125 	allocation failure and directly reclaim pages and compact
132 	to reclaim pages and wake kcompactd to compact memory so that
134 	of khugepaged to then install the THP pages later.
140 	pages and wake kcompactd to compact memory so that THP is
179 You can also control how many pages khugepaged should scan at each
194 The khugepaged progress can be seen in the number of pages collapsed (note
195 that this counter may not be an exact count of the number of pages
197 being replaced by a PMD mapping, or (2) All 4K physical pages replaced by
209 ``max_ptes_none`` specifies how many extra small pages (that are
211 of small pages into one large page::
220 ``max_ptes_swap`` specifies how many pages can be brought in from
221 swap when collapsing a group of pages into a transparent huge page::
227 collapsed, resulting fewer pages being collapsed into
230 ``max_ptes_shared`` specifies how many pages can be shared across multiple
252     Attempt to allocate huge pages every time we need a new page;
255     Do not allocate huge pages;
262     Only allocate huge pages if requested with fadvise()/madvise();
267 ``huge=never`` will not attempt to break up huge pages at all, just stop more
295 The number of anonymous transparent huge pages currently used by the
297 To identify what applications are using anonymous transparent huge pages,
301 The number of file transparent huge pages mapped to userspace is available
303 To identify what applications are mapping file transparent huge pages, it
311 monitor how successfully the system is providing huge pages for use.
319 	a range of pages to collapse into one huge page and has
324 	a huge page and instead falls back to using small pages.
328 	instead falls back to using small pages even though the
333 	of pages that should be collapsed into one huge page but failed
342 	but fails and instead falls back to using small pages.
346 	falls back to using small pages even though the allocation was
355 	pages. This can happen for a variety of reasons but a common
366 	splitting it would free up some memory. Pages on split queue are
382 	huge zero page and falls back to using small pages.
393 As the system ages, allocating huge pages may be expensive as the
413 for huge pages.