admin-guide/sysctl/vm.rst

13 ------------------------------------------------------------------------------
27 - admin_reserve_kbytes
28 - compact_memory
29 - compaction_proactiveness
30 - compact_unevictable_allowed
31 - defrag_mode
32 - dirty_background_bytes
33 - dirty_background_ratio
34 - dirty_bytes
35 - dirty_expire_centisecs
36 - dirty_ratio
37 - dirtytime_expire_seconds
38 - dirty_writeback_centisecs
39 - drop_caches
40 - enable_soft_offline
41 - extfrag_threshold
42 - highmem_is_dirtyable
43 - hugetlb_shm_group
44 - laptop_mode
45 - legacy_va_layout
46 - lowmem_reserve_ratio
47 - max_map_count
48 - mem_profiling         (only if CONFIG_MEM_ALLOC_PROFILING=y)
49 - memory_failure_early_kill
50 - memory_failure_recovery
51 - min_free_kbytes
52 - min_slab_ratio
53 - min_unmapped_ratio
54 - mmap_min_addr
55 - mmap_rnd_bits
56 - mmap_rnd_compat_bits
57 - nr_hugepages
58 - nr_hugepages_mempolicy
59 - nr_overcommit_hugepages
60 - nr_trim_pages         (only if CONFIG_MMU=n)
61 - numa_zonelist_order
62 - oom_dump_tasks
63 - oom_kill_allocating_task
64 - overcommit_kbytes
65 - overcommit_memory
66 - overcommit_ratio
67 - page-cluster
68 - page_lock_unfairness
69 - panic_on_oom
70 - percpu_pagelist_high_fraction
71 - stat_interval
72 - stat_refresh
73 - numa_stat
74 - swappiness
75 - unprivileged_userfaultfd
76 - user_reserve_kbytes
77 - vfs_cache_pressure
78 - watermark_boost_factor
79 - watermark_scale_factor
80 - zone_reclaim_mode
128 Note that compaction has a non-trivial system-wide impact as pages
153 and maintain the ability to produce huge pages / higher-order pages.
156 once it occurred, can be long-lasting or even permanent.
202 of a second.  Data which has been dirty in-memory for longer than this
257 This is a non-destructive operation and will not free any dirty objects.
282 Correctable memory errors are very common on servers. Soft-offline is kernel's
285 For different types of page, soft-offline has different behaviors / costs.
287 - For a raw error page, soft-offline migrates the in-use page's content to
290 - For a page that is part of a transparent hugepage, soft-offline splits the
295 - For a page that is part of a HugeTLB hugepage, soft-offline first migrates
312 - Request to soft offline pages from RAS Correctable Errors Collector.
314 - On ARM, the request to soft offline pages from GHES driver.
316 - On PARISC, the request to soft offline pages from Page Deallocation Table.
322 reclaim to satisfy a high-order allocation. The extfrag/extfrag_index file in
325 of memory, values towards 1000 imply failures are due to fragmentation and -1
346 storage more effectively. Note this also comes with a risk of pre-mature
363 controlled by this knob are discussed in Documentation/admin-guide/laptops/laptop-mode.rst.
369 If non-zero, this sysctl disables the new 32-bit mmap layout - the kernel
407 in /proc/zoneinfo like the following. (This is an example of x86-64 box).
437     zone[i]->protection[j]
457 The minimum value is 1 (1/1 -> 100%). The value less than 1 completely
465 may have. Memory map areas are used as a side-effect of calling
499 no other up-to-date copy of the data it will kill to prevent any data
559 The process of reclaiming slab memory is currently not node specific
573 against all file-backed unmapped pages including swapcache pages and tmpfs
625 See Documentation/admin-guide/mm/hugetlbpage.rst
668 Change the size of the hugepage pool at run-time on a specific
671 See Documentation/admin-guide/mm/hugetlbpage.rst
680 See Documentation/admin-guide/mm/hugetlbpage.rst
688 This value adjusts the excess page trimming behaviour of power-of-2 aligned
697 See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
711 In non-NUMA case, a zonelist for GFP_KERNEL is ordered as following.
712 ZONE_NORMAL -> ZONE_DMA
719   (A) Node(0) ZONE_NORMAL -> Node(0) ZONE_DMA -> Node(1) ZONE_NORMAL
720   (B) Node(0) ZONE_NORMAL -> Node(1) ZONE_NORMAL -> Node(0) ZONE_DMA.
722 Type(A) offers the best locality for processes on Node(0), but ZONE_DMA
724 out-of-memory(OOM) of ZONE_DMA because ZONE_DMA is tend to be small.
726 Type(B) cannot offer the best locality but is more robust against OOM of
739 On 32-bit, the Normal zone needs to be preserved for allocations accessible
742 On 64-bit, devices that require DMA32/DMA are relatively rare, so "node"
752 Enables a system-wide task dump (excluding kernel threads) to be produced
753 when the kernel performs an OOM-killing and includes such information as
765 If this is set to non-zero, this information is shown whenever the
766 OOM killer actually kills a memory-hogging task.
774 This enables or disables killing the OOM-triggering task in
775 out-of-memory situations.
779 selects a rogue memory-hogging task that frees up a large amount of
782 If this is set to non-zero, the OOM killer simply kills the task that
783 triggered the out-of-memory condition.  This avoids the expensive
819 programs that malloc() huge amounts of memory "just-in-case"
824 See Documentation/mm/overcommit-accounting.rst and
836 page-cluster
839 page-cluster controls the number of pages up to which consecutive pages
843 but consecutive on swap space - that means they were swapped out together.
845 It is a logarithmic value - setting it to zero means "1 page", setting
851 swap-intensive.
869 This enables or disables panic on out-of-memory feature.
875 If this is set to 1, the kernel panics when out-of-memory happens.
878 may be killed by oom-killer. No panic occurs in this case.
883 above-mentioned. Even oom happens under memory cgroup, the whole
899 per-cpu page lists. It is an upper boundary that is divided depending
902 on per-cpu page lists. This entry only changes the value of hot per-cpu
904 each zone between per-cpu lists.
906 The batch value of each per-cpu page list remains the same regardless of
909 The initial value is zero. Kernel uses this value to set the high pcp->high
925 Any read or write (by root only) flushes all the per-cpu vm statistics
929 As a side-effect, it also checks for negative totals (elsewhere reported
958 cache and swap-backed pages equally; lower values signify more
963 experimentation and will also be workload-dependent.
967 For in-memory swap, like zram or zswap, as well as hybrid setups that
974 file-backed pages is less than the high watermark in a zone.
994 Documentation/admin-guide/mm/userfaultfd.rst.
1025 lead to out-of-memory conditions. Increasing vfs_cache_pressure beyond 100
1041 increase the success rate of future high-order allocations such as SLUB
1050 worth of pages will be reclaimed (e.g.  2MB on 64-bit x86). A boost factor
1091 data locality.