blob: e96a341eb7e425249cd19babb7e1f8f972001fa2 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001Documentation for /proc/sys/vm/* kernel version 2.2.10
2 (c) 1998, 1999, Rik van Riel <riel@nl.linux.org>
3
4For general info and legal blurb, please look in README.
5
6==============================================================
7
8This file contains the documentation for the sysctl files in
9/proc/sys/vm and is valid for Linux kernel version 2.2.
10
11The files in this directory can be used to tune the operation
12of the virtual memory (VM) subsystem of the Linux kernel and
13the writeout of dirty data to disk.
14
15Default values and initialization routines for most of these
16files can be found in mm/swap.c.
17
18Currently, these files are in /proc/sys/vm:
19- overcommit_memory
20- page-cluster
21- dirty_ratio
22- dirty_background_ratio
23- dirty_expire_centisecs
24- dirty_writeback_centisecs
25- max_map_count
26- min_free_kbytes
27- laptop_mode
28- block_dump
Andrew Morton9d0243b2006-01-08 01:00:39 -080029- drop-caches
Christoph Lameter17436602006-01-18 17:42:32 -080030- zone_reclaim_mode
Christoph Lameter96146342006-07-03 00:24:13 -070031- min_unmapped_ratio
Christoph Lameter0ff38492006-09-25 23:31:52 -070032- min_slab_ratio
KAMEZAWA Hiroyukifadd8fb2006-06-23 02:03:13 -070033- panic_on_oom
Linus Torvalds1da177e2005-04-16 15:20:36 -070034
35==============================================================
36
37dirty_ratio, dirty_background_ratio, dirty_expire_centisecs,
38dirty_writeback_centisecs, vfs_cache_pressure, laptop_mode,
Andrew Morton9d0243b2006-01-08 01:00:39 -080039block_dump, swap_token_timeout, drop-caches:
Linus Torvalds1da177e2005-04-16 15:20:36 -070040
41See Documentation/filesystems/proc.txt
42
43==============================================================
44
45overcommit_memory:
46
47This value contains a flag that enables memory overcommitment.
48
49When this flag is 0, the kernel attempts to estimate the amount
50of free memory left when userspace requests more memory.
51
52When this flag is 1, the kernel pretends there is always enough
53memory until it actually runs out.
54
55When this flag is 2, the kernel uses a "never overcommit"
56policy that attempts to prevent any overcommit of memory.
57
58This feature can be very useful because there are a lot of
59programs that malloc() huge amounts of memory "just-in-case"
60and don't use much of it.
61
62The default value is 0.
63
64See Documentation/vm/overcommit-accounting and
65security/commoncap.c::cap_vm_enough_memory() for more information.
66
67==============================================================
68
69overcommit_ratio:
70
71When overcommit_memory is set to 2, the committed address
72space is not permitted to exceed swap plus this percentage
73of physical RAM. See above.
74
75==============================================================
76
77page-cluster:
78
79The Linux VM subsystem avoids excessive disk seeks by reading
80multiple pages on a page fault. The number of pages it reads
81is dependent on the amount of memory in your machine.
82
83The number of pages the kernel reads in at once is equal to
842 ^ page-cluster. Values above 2 ^ 5 don't make much sense
85for swap because we only cluster swap data in 32-page groups.
86
87==============================================================
88
89max_map_count:
90
91This file contains the maximum number of memory map areas a process
92may have. Memory map areas are used as a side-effect of calling
93malloc, directly by mmap and mprotect, and also when loading shared
94libraries.
95
96While most applications need less than a thousand maps, certain
97programs, particularly malloc debuggers, may consume lots of them,
98e.g., up to one or two maps per allocation.
99
100The default value is 65536.
101
102==============================================================
103
104min_free_kbytes:
105
106This is used to force the Linux VM to keep a minimum number
107of kilobytes free. The VM uses this number to compute a pages_min
108value for each lowmem zone in the system. Each lowmem zone gets
109a number of reserved free pages based proportionally on its size.
Rohit Seth8ad4b1f2006-01-08 01:00:40 -0800110
111==============================================================
112
113percpu_pagelist_fraction
114
115This is the fraction of pages at most (high mark pcp->high) in each zone that
116are allocated for each per cpu page list. The min value for this is 8. It
117means that we don't allow more than 1/8th of pages in each zone to be
118allocated in any single per_cpu_pagelist. This entry only changes the value
119of hot per cpu pagelists. User can specify a number like 100 to allocate
1201/100th of each zone to each per cpu page list.
121
122The batch value of each per cpu pagelist is also updated as a result. It is
123set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8)
124
125The initial value is zero. Kernel does not use this value at boot time to set
126the high water marks for each per cpu page list.
Christoph Lameter17436602006-01-18 17:42:32 -0800127
128===============================================================
129
130zone_reclaim_mode:
131
Matt LaPlante5d3f0832006-11-30 05:21:10 +0100132Zone_reclaim_mode allows someone to set more or less aggressive approaches to
Christoph Lameter1b2ffb72006-02-01 03:05:34 -0800133reclaim memory when a zone runs out of memory. If it is set to zero then no
134zone reclaim occurs. Allocations will be satisfied from other zones / nodes
135in the system.
136
137This is value ORed together of
138
1391 = Zone reclaim on
1402 = Zone reclaim writes dirty pages out
1414 = Zone reclaim swaps pages
142
143zone_reclaim_mode is set during bootup to 1 if it is determined that pages
144from remote zones will cause a measurable performance reduction. The
Christoph Lameter17436602006-01-18 17:42:32 -0800145page allocator will then reclaim easily reusable pages (those page
Christoph Lameter1b2ffb72006-02-01 03:05:34 -0800146cache pages that are currently not used) before allocating off node pages.
Christoph Lameter17436602006-01-18 17:42:32 -0800147
Christoph Lameter1b2ffb72006-02-01 03:05:34 -0800148It may be beneficial to switch off zone reclaim if the system is
149used for a file server and all of memory should be used for caching files
150from disk. In that case the caching effect is more important than
151data locality.
Christoph Lameter17436602006-01-18 17:42:32 -0800152
Christoph Lameter1b2ffb72006-02-01 03:05:34 -0800153Allowing zone reclaim to write out pages stops processes that are
154writing large amounts of data from dirtying pages on other nodes. Zone
155reclaim will write out dirty pages if a zone fills up and so effectively
156throttle the process. This may decrease the performance of a single process
157since it cannot use all of system memory to buffer the outgoing writes
158anymore but it preserve the memory on other nodes so that the performance
159of other processes running on other nodes will not be affected.
160
161Allowing regular swap effectively restricts allocations to the local
162node unless explicitly overridden by memory policies or cpuset
163configurations.
164
KAMEZAWA Hiroyukifadd8fb2006-06-23 02:03:13 -0700165=============================================================
166
Christoph Lameter96146342006-07-03 00:24:13 -0700167min_unmapped_ratio:
168
169This is available only on NUMA kernels.
170
Christoph Lameter0ff38492006-09-25 23:31:52 -0700171A percentage of the total pages in each zone. Zone reclaim will only
Christoph Lameter96146342006-07-03 00:24:13 -0700172occur if more than this percentage of pages are file backed and unmapped.
173This is to insure that a minimal amount of local pages is still available for
174file I/O even if the node is overallocated.
175
176The default is 1 percent.
177
178=============================================================
179
Christoph Lameter0ff38492006-09-25 23:31:52 -0700180min_slab_ratio:
181
182This is available only on NUMA kernels.
183
184A percentage of the total pages in each zone. On Zone reclaim
185(fallback from the local zone occurs) slabs will be reclaimed if more
186than this percentage of pages in a zone are reclaimable slab pages.
187This insures that the slab growth stays under control even in NUMA
188systems that rarely perform global reclaim.
189
190The default is 5 percent.
191
192Note that slab reclaim is triggered in a per zone / node fashion.
193The process of reclaiming slab memory is currently not node specific
194and may not be fast.
195
196=============================================================
197
KAMEZAWA Hiroyukifadd8fb2006-06-23 02:03:13 -0700198panic_on_oom
199
200This enables or disables panic on out-of-memory feature. If this is set to 1,
201the kernel panics when out-of-memory happens. If this is set to 0, the kernel
202will kill some rogue process, called oom_killer. Usually, oom_killer can kill
203rogue processes and system will survive. If you want to panic the system
204rather than killing rogue processes, set this to 1.
205
206The default value is 0.
207