blob: d9c11d25bf02132bebeeceb1b5c2c7e04901d4c7 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001Tmpfs is a file system which keeps all files in virtual memory.
2
3
4Everything in tmpfs is temporary in the sense that no files will be
5created on your hard drive. If you unmount a tmpfs instance,
6everything stored therein is lost.
7
8tmpfs puts everything into the kernel internal caches and grows and
9shrinks to accommodate the files it contains and is able to swap
10unneeded pages out to swap space. It has maximum size limits which can
11be adjusted on the fly via 'mount -o remount ...'
12
13If you compare it to ramfs (which was the template to create tmpfs)
14you gain swapping and limit checking. Another similar thing is the RAM
15disk (/dev/ram*), which simulates a fixed size hard disk in physical
16RAM, where you have to create an ordinary filesystem on top. Ramdisks
17cannot swap and you do not have the possibility to resize them.
18
19Since tmpfs lives completely in the page cache and on swap, all tmpfs
Rodrigo Freire0bc126d2016-01-14 15:21:58 -080020pages will be shown as "Shmem" in /proc/meminfo and "Shared" in
21free(1). Notice that these counters also include shared memory
22(shmem, see ipcs(1)). The most reliable way to get the count is
23using df(1) and du(1).
Linus Torvalds1da177e2005-04-16 15:20:36 -070024
25tmpfs has the following uses:
26
271) There is always a kernel internal mount which you will not see at
28 all. This is used for shared anonymous mappings and SYSV shared
29 memory.
30
31 This mount does not depend on CONFIG_TMPFS. If CONFIG_TMPFS is not
32 set, the user visible part of tmpfs is not build. But the internal
33 mechanisms are always present.
34
352) glibc 2.2 and above expects tmpfs to be mounted at /dev/shm for
36 POSIX shared memory (shm_open, shm_unlink). Adding the following
37 line to /etc/fstab should take care of this:
38
39 tmpfs /dev/shm tmpfs defaults 0 0
40
41 Remember to create the directory that you intend to mount tmpfs on
Adrian Bunkbf6ee0a2006-10-03 22:17:48 +020042 if necessary.
Linus Torvalds1da177e2005-04-16 15:20:36 -070043
44 This mount is _not_ needed for SYSV shared memory. The internal
45 mount is used for that. (In the 2.3 kernel versions it was
46 necessary to mount the predecessor of tmpfs (shm fs) to use SYSV
47 shared memory)
48
493) Some people (including me) find it very convenient to mount it
50 e.g. on /tmp and /var/tmp and have a big swap partition. And now
51 loop mounts of tmpfs files do work, so mkinitrd shipped by most
52 distributions should succeed with a tmpfs /tmp.
53
544) And probably a lot more I do not know about :-)
55
56
57tmpfs has three mount options for sizing:
58
59size: The limit of allocated bytes for this tmpfs instance. The
60 default is half of your physical RAM without swap. If you
61 oversize your tmpfs instances the machine will deadlock
62 since the OOM handler will not be able to free that memory.
Kirill A. Shutemovea1754a2016-04-01 15:29:48 +030063nr_blocks: The same as size, but in blocks of PAGE_SIZE.
Linus Torvalds1da177e2005-04-16 15:20:36 -070064nr_inodes: The maximum number of inodes for this instance. The default
65 is half of the number of your physical RAM pages, or (on a
Paolo Ornati670e9f32006-10-03 22:57:56 +020066 machine with highmem) the number of lowmem RAM pages,
Linus Torvalds1da177e2005-04-16 15:20:36 -070067 whichever is the lower.
68
69These parameters accept a suffix k, m or g for kilo, mega and giga and
70can be changed on remount. The size parameter also accepts a suffix %
71to limit this tmpfs instance to that percentage of your physical RAM:
72the default, when neither size nor nr_blocks is specified, is size=50%
73
Hugh Dickins0edd73b2005-06-21 17:15:04 -070074If nr_blocks=0 (or size=0), blocks will not be limited in that instance;
75if nr_inodes=0, inodes will not be limited. It is generally unwise to
Linus Torvalds1da177e2005-04-16 15:20:36 -070076mount with such options, since it allows any user with write access to
77use up all the memory on the machine; but enhances the scalability of
78that instance in a system with many cpus making intensive use of it.
79
80
Robin Holt7339ff82006-01-14 13:20:48 -080081tmpfs has a mount option to set the NUMA memory allocation policy for
Hugh Dickinsb00dc3a2006-02-21 23:49:47 +000082all files in that instance (if CONFIG_NUMA is enabled) - which can be
83adjusted on the fly via 'mount -o remount ...'
Robin Holt7339ff82006-01-14 13:20:48 -080084
KOSAKI Motohiro55741692010-03-23 13:35:33 -070085mpol=default use the process allocation policy
86 (see set_mempolicy(2))
Hugh Dickinsb00dc3a2006-02-21 23:49:47 +000087mpol=prefer:Node prefers to allocate memory from the given Node
88mpol=bind:NodeList allocates memory only from nodes in NodeList
89mpol=interleave prefers to allocate from each node in turn
90mpol=interleave:NodeList allocates from each node of NodeList in turn
KOSAKI Motohiro55741692010-03-23 13:35:33 -070091mpol=local prefers to allocate memory from the local node
Hugh Dickinsb00dc3a2006-02-21 23:49:47 +000092
93NodeList format is a comma-separated list of decimal numbers and ranges,
94a range being two hyphen-separated decimal numbers, the smallest and
95largest node numbers in the range. For example, mpol=bind:0-3,5,7,9-15
Robin Holt7339ff82006-01-14 13:20:48 -080096
Lee Schermerhorn971ada02010-05-24 14:32:05 -070097A memory policy with a valid NodeList will be saved, as specified, for
98use at file creation time. When a task allocates a file in the file
99system, the mount option memory policy will be applied with a NodeList,
100if any, modified by the calling task's cpuset constraints
101[See Documentation/cgroups/cpusets.txt] and any optional flags, listed
102below. If the resulting NodeLists is the empty set, the effective memory
103policy for the file will revert to "default" policy.
104
David Rientjes65d66fc2008-04-28 02:12:31 -0700105NUMA memory allocation policies have optional flags that can be used in
106conjunction with their modes. These optional flags can be specified
107when tmpfs is mounted by appending them to the mode before the NodeList.
108See Documentation/vm/numa_memory_policy.txt for a list of all available
Lee Schermerhorn971ada02010-05-24 14:32:05 -0700109memory allocation policy mode flags and their effect on memory policy.
David Rientjes65d66fc2008-04-28 02:12:31 -0700110
111 =static is equivalent to MPOL_F_STATIC_NODES
112 =relative is equivalent to MPOL_F_RELATIVE_NODES
113
114For example, mpol=bind=static:NodeList, is the equivalent of an
115allocation policy of MPOL_BIND | MPOL_F_STATIC_NODES.
116
Hugh Dickinsad329b152006-02-24 13:04:26 -0800117Note that trying to mount a tmpfs with an mpol option will fail if the
118running kernel does not support NUMA; and will fail if its nodelist
Hugh Dickinsa2109062007-06-08 13:46:46 -0700119specifies a node which is not online. If your system relies on that
120tmpfs being mounted, but from time to time runs a kernel built without
121NUMA capability (perhaps a safe recovery kernel), or with fewer nodes
122online, then it is advisable to omit the mpol option from automatic
Hugh Dickinsad329b152006-02-24 13:04:26 -0800123mount options. It can be added later, when the tmpfs is already mounted
124on MountPoint, by 'mount -o remount,mpol=Policy:NodeList MountPoint'.
125
Robin Holt7339ff82006-01-14 13:20:48 -0800126
Linus Torvalds1da177e2005-04-16 15:20:36 -0700127To specify the initial root directory you can use the following mount
128options:
129
130mode: The permissions as an octal number
131uid: The user id
132gid: The group id
133
134These options do not have any effect on remount. You can change these
135parameters with chmod(1), chown(1) and chgrp(1) on a mounted filesystem.
136
137
138So 'mount -t tmpfs -o size=10G,nr_inodes=10k,mode=700 tmpfs /mytmpfs'
139will give you tmpfs instance on /mytmpfs which can allocate 10GB
140RAM/SWAP in 10240 inodes and it is only accessible by root.
141
142
143Author:
144 Christoph Rohland <cr@sap.com>, 1.12.01
145Updated:
Hugh Dickins98f32602009-05-21 20:33:58 +0100146 Hugh Dickins, 4 June 2007
KOSAKI Motohiro55741692010-03-23 13:35:33 -0700147Updated:
148 KOSAKI Motohiro, 16 Mar 2010