2020-02-17 19:12:26 +03:00
.. SPDX-License-Identifier: GPL-2.0
=====
Tmpfs
=====
2020-12-15 06:06:17 +03:00
Tmpfs is a file system which keeps all of its files in virtual memory.
2005-04-17 02:20:36 +04:00
Everything in tmpfs is temporary in the sense that no files will be
created on your hard drive. If you unmount a tmpfs instance,
everything stored therein is lost.
tmpfs puts everything into the kernel internal caches and grows and
shrinks to accommodate the files it contains and is able to swap
2023-03-10 02:05:45 +03:00
unneeded pages out to swap space, if swap was enabled for the tmpfs
mount. tmpfs also supports THP.
2023-03-10 02:05:44 +03:00
tmpfs extends ramfs with a few userspace configurable options listed and
explained further below, some of which can be reconfigured dynamically on the
fly using a remount ('mount -o remount ...') of the filesystem. A tmpfs
filesystem can be resized but it cannot be resized to a size below its current
usage. tmpfs also supports POSIX ACLs, and extended attributes for the
trusted.* and security.* namespaces. ramfs does not use swap and you cannot
modify any parameter for a ramfs filesystem. The size limit of a ramfs
filesystem is how much memory you have available, and so care must be taken if
used so to not run out of memory.
An alternative to tmpfs and ramfs is to use brd to create RAM disks
(/dev/ram*), which allows you to simulate a block device disk in physical RAM.
To write data you would just then need to create an regular filesystem on top
this ramdisk. As with ramfs, brd ramdisks cannot swap. brd ramdisks are also
configured in size at initialization and you cannot dynamically resize them.
Contrary to brd ramdisks, tmpfs has its own filesystem, it does not rely on the
block layer at all.
2005-04-17 02:20:36 +04:00
2023-03-10 02:05:45 +03:00
Since tmpfs lives completely in the page cache and optionally on swap,
all tmpfs pages will be shown as "Shmem" in /proc/meminfo and "Shared" in
2016-01-15 02:21:58 +03:00
free(1). Notice that these counters also include shared memory
(shmem, see ipcs(1)). The most reliable way to get the count is
using df(1) and du(1).
2005-04-17 02:20:36 +04:00
tmpfs has the following uses:
1) There is always a kernel internal mount which you will not see at
all. This is used for shared anonymous mappings and SYSV shared
2020-02-17 19:12:26 +03:00
memory.
2005-04-17 02:20:36 +04:00
This mount does not depend on CONFIG_TMPFS. If CONFIG_TMPFS is not
2020-12-15 06:06:17 +03:00
set, the user visible part of tmpfs is not built. But the internal
2005-04-17 02:20:36 +04:00
mechanisms are always present.
2) glibc 2.2 and above expects tmpfs to be mounted at /dev/shm for
POSIX shared memory (shm_open, shm_unlink). Adding the following
2020-02-17 19:12:26 +03:00
line to /etc/fstab should take care of this::
2005-04-17 02:20:36 +04:00
tmpfs /dev/shm tmpfs defaults 0 0
Remember to create the directory that you intend to mount tmpfs on
2006-10-04 00:17:48 +04:00
if necessary.
2005-04-17 02:20:36 +04:00
This mount is _not_ needed for SYSV shared memory. The internal
mount is used for that. (In the 2.3 kernel versions it was
necessary to mount the predecessor of tmpfs (shm fs) to use SYSV
2020-12-15 06:06:17 +03:00
shared memory.)
2005-04-17 02:20:36 +04:00
3) Some people (including me) find it very convenient to mount it
e.g. on /tmp and /var/tmp and have a big swap partition. And now
loop mounts of tmpfs files do work, so mkinitrd shipped by most
distributions should succeed with a tmpfs /tmp.
4) And probably a lot more I do not know about :-)
tmpfs has three mount options for sizing:
2020-02-17 19:12:26 +03:00
========= ============================================================
size The limit of allocated bytes for this tmpfs instance. The
2005-04-17 02:20:36 +04:00
default is half of your physical RAM without swap. If you
oversize your tmpfs instances the machine will deadlock
since the OOM handler will not be able to free that memory.
2020-02-17 19:12:26 +03:00
nr_blocks The same as size, but in blocks of PAGE_SIZE.
nr_inodes The maximum number of inodes for this instance. The default
2005-04-17 02:20:36 +04:00
is half of the number of your physical RAM pages, or (on a
2006-10-04 00:57:56 +04:00
machine with highmem) the number of lowmem RAM pages,
2005-04-17 02:20:36 +04:00
whichever is the lower.
2023-03-10 02:05:45 +03:00
noswap Disables swap. Remounts must respect the original settings.
By default swap is enabled.
2020-02-17 19:12:26 +03:00
========= ============================================================
2005-04-17 02:20:36 +04:00
These parameters accept a suffix k, m or g for kilo, mega and giga and
can be changed on remount. The size parameter also accepts a suffix %
to limit this tmpfs instance to that percentage of your physical RAM:
the default, when neither size nor nr_blocks is specified, is size=50%
2005-06-22 04:15:04 +04:00
If nr_blocks=0 (or size=0), blocks will not be limited in that instance;
if nr_inodes=0, inodes will not be limited. It is generally unwise to
2005-04-17 02:20:36 +04:00
mount with such options, since it allows any user with write access to
use up all the memory on the machine; but enhances the scalability of
2020-12-15 06:06:17 +03:00
that instance in a system with many CPUs making intensive use of it.
2005-04-17 02:20:36 +04:00
2023-03-10 02:05:44 +03:00
tmpfs also supports Transparent Huge Pages which requires a kernel
configured with CONFIG_TRANSPARENT_HUGEPAGE and with huge supported for
your system (has_transparent_hugepage(), which is architecture specific).
The mount options for this are:
====== ============================================================
huge=0 never: disables huge pages for the mount
huge=1 always: enables huge pages for the mount
huge=2 within_size: only allocate huge pages if the page will be
fully within i_size, also respect fadvise()/madvise() hints.
huge=3 advise: only allocate huge pages if requested with
fadvise()/madvise()
====== ============================================================
There is a sysfs file which you can also use to control system wide THP
configuration for all tmpfs mounts, the file is:
/sys/kernel/mm/transparent_hugepage/shmem_enabled
This sysfs file is placed on top of THP sysfs directory and so is registered
by THP code. It is however only used to control all tmpfs mounts with one
single knob. Since it controls all tmpfs mounts it should only be used either
for emergency or testing purposes. The values you can set for shmem_enabled are:
== ============================================================
-1 deny: disables huge on shm_mnt and all mounts, for
emergency use
-2 force: enables huge on shm_mnt and all mounts, w/o needing
option, for testing
== ============================================================
2005-04-17 02:20:36 +04:00
2006-01-15 00:20:48 +03:00
tmpfs has a mount option to set the NUMA memory allocation policy for
2006-02-22 02:49:47 +03:00
all files in that instance (if CONFIG_NUMA is enabled) - which can be
adjusted on the fly via 'mount -o remount ...'
2006-01-15 00:20:48 +03:00
2020-02-17 19:12:26 +03:00
======================== ==============================================
2010-03-23 23:35:33 +03:00
mpol=default use the process allocation policy
(see set_mempolicy(2))
2006-02-22 02:49:47 +03:00
mpol=prefer:Node prefers to allocate memory from the given Node
mpol=bind:NodeList allocates memory only from nodes in NodeList
mpol=interleave prefers to allocate from each node in turn
mpol=interleave:NodeList allocates from each node of NodeList in turn
2010-03-23 23:35:33 +03:00
mpol=local prefers to allocate memory from the local node
2020-02-17 19:12:26 +03:00
======================== ==============================================
2006-02-22 02:49:47 +03:00
NodeList format is a comma-separated list of decimal numbers and ranges,
a range being two hyphen-separated decimal numbers, the smallest and
largest node numbers in the range. For example, mpol=bind:0-3,5,7,9-15
2006-01-15 00:20:48 +03:00
2010-05-25 01:32:05 +04:00
A memory policy with a valid NodeList will be saved, as specified, for
use at file creation time. When a task allocates a file in the file
system, the mount option memory policy will be applied with a NodeList,
if any, modified by the calling task's cpuset constraints
2020-02-17 19:12:26 +03:00
[See Documentation/admin-guide/cgroup-v1/cpusets.rst] and any optional flags,
listed below. If the resulting NodeLists is the empty set, the effective
memory policy for the file will revert to "default" policy.
2010-05-25 01:32:05 +04:00
2008-04-28 13:12:31 +04:00
NUMA memory allocation policies have optional flags that can be used in
conjunction with their modes. These optional flags can be specified
when tmpfs is mounted by appending them to the mode before the NodeList.
2018-05-08 10:02:10 +03:00
See Documentation/admin-guide/mm/numa_memory_policy.rst for a list of
all available memory allocation policy mode flags and their effect on
memory policy.
2008-04-28 13:12:31 +04:00
2020-02-17 19:12:26 +03:00
::
2008-04-28 13:12:31 +04:00
=static is equivalent to MPOL_F_STATIC_NODES
=relative is equivalent to MPOL_F_RELATIVE_NODES
For example, mpol=bind=static:NodeList, is the equivalent of an
allocation policy of MPOL_BIND | MPOL_F_STATIC_NODES.
2006-02-25 00:04:26 +03:00
Note that trying to mount a tmpfs with an mpol option will fail if the
running kernel does not support NUMA; and will fail if its nodelist
2007-06-09 00:46:46 +04:00
specifies a node which is not online. If your system relies on that
tmpfs being mounted, but from time to time runs a kernel built without
NUMA capability (perhaps a safe recovery kernel), or with fewer nodes
online, then it is advisable to omit the mpol option from automatic
2006-02-25 00:04:26 +03:00
mount options. It can be added later, when the tmpfs is already mounted
on MountPoint, by 'mount -o remount,mpol=Policy:NodeList MountPoint'.
2006-01-15 00:20:48 +03:00
2005-04-17 02:20:36 +04:00
To specify the initial root directory you can use the following mount
options:
2020-02-17 19:12:26 +03:00
==== ==================================
mode The permissions as an octal number
uid The user id
gid The group id
==== ==================================
2005-04-17 02:20:36 +04:00
These options do not have any effect on remount. You can change these
parameters with chmod(1), chown(1) and chgrp(1) on a mounted filesystem.
2020-08-07 09:20:25 +03:00
tmpfs has a mount option to select whether it will wrap at 32- or 64-bit inode
numbers:
======= ========================
inode64 Use 64-bit inode numbers
inode32 Use 32-bit inode numbers
======= ========================
On a 32-bit kernel, inode32 is implicit, and inode64 is refused at mount time.
On a 64-bit kernel, CONFIG_TMPFS_INODE64 sets the default. inode64 avoids the
possibility of multiple files with the same inode number on a single device;
but risks glibc failing with EOVERFLOW once 33-bit inode numbers are reached -
if a long-lived tmpfs is accessed by 32-bit applications so ancient that
opening a file larger than 2GiB fails with EINVAL.
2005-04-17 02:20:36 +04:00
So 'mount -t tmpfs -o size=10G,nr_inodes=10k,mode=700 tmpfs /mytmpfs'
will give you tmpfs instance on /mytmpfs which can allocate 10GB
RAM/SWAP in 10240 inodes and it is only accessible by root.
2020-02-17 19:12:26 +03:00
:Author:
2005-04-17 02:20:36 +04:00
Christoph Rohland <cr@sap.com>, 1.12.01
2020-02-17 19:12:26 +03:00
:Updated:
2009-05-21 23:33:58 +04:00
Hugh Dickins, 4 June 2007
2020-02-17 19:12:26 +03:00
:Updated:
2010-03-23 23:35:33 +03:00
KOSAKI Motohiro, 16 Mar 2010
2020-08-07 09:20:25 +03:00
:Updated:
Chris Down, 13 July 2020