Commit | Line | Data |
---|---|---|
1da177e4 LT |
1 | Documentation for /proc/sys/fs/* kernel version 2.2.10 |
2 | (c) 1998, 1999, Rik van Riel <riel@nl.linux.org> | |
760df93e | 3 | (c) 2009, Shen Feng<shen@cn.fujitsu.com> |
1da177e4 LT |
4 | |
5 | For general info and legal blurb, please look in README. | |
6 | ||
7 | ============================================================== | |
8 | ||
9 | This file contains documentation for the sysctl files in | |
10 | /proc/sys/fs/ and is valid for Linux kernel version 2.2. | |
11 | ||
12 | The files in this directory can be used to tune and monitor | |
13 | miscellaneous and general things in the operation of the Linux | |
14 | kernel. Since some of the files _can_ be used to screw up your | |
15 | system, it is advisable to read both documentation and source | |
16 | before actually making adjustments. | |
17 | ||
760df93e SF |
18 | 1. /proc/sys/fs |
19 | ---------------------------------------------------------- | |
20 | ||
1da177e4 | 21 | Currently, these files are in /proc/sys/fs: |
760df93e SF |
22 | - aio-max-nr |
23 | - aio-nr | |
1da177e4 LT |
24 | - dentry-state |
25 | - dquot-max | |
26 | - dquot-nr | |
27 | - file-max | |
28 | - file-nr | |
29 | - inode-max | |
30 | - inode-nr | |
31 | - inode-state | |
9cfe015a | 32 | - nr_open |
1da177e4 LT |
33 | - overflowuid |
34 | - overflowgid | |
a2e0b563 | 35 | - suid_dumpable |
1da177e4 LT |
36 | - super-max |
37 | - super-nr | |
38 | ||
760df93e SF |
39 | ============================================================== |
40 | ||
41 | aio-nr & aio-max-nr: | |
42 | ||
43 | aio-nr is the running total of the number of events specified on the | |
44 | io_setup system call for all currently active aio contexts. If aio-nr | |
45 | reaches aio-max-nr then io_setup will fail with EAGAIN. Note that | |
46 | raising aio-max-nr does not result in the pre-allocation or re-sizing | |
47 | of any kernel data structures. | |
1da177e4 LT |
48 | |
49 | ============================================================== | |
50 | ||
51 | dentry-state: | |
52 | ||
53 | From linux/fs/dentry.c: | |
54 | -------------------------------------------------------------- | |
55 | struct { | |
56 | int nr_dentry; | |
57 | int nr_unused; | |
58 | int age_limit; /* age in seconds */ | |
59 | int want_pages; /* pages requested by system */ | |
60 | int dummy[2]; | |
61 | } dentry_stat = {0, 0, 45, 0,}; | |
62 | -------------------------------------------------------------- | |
63 | ||
64 | Dentries are dynamically allocated and deallocated, and | |
65 | nr_dentry seems to be 0 all the time. Hence it's safe to | |
66 | assume that only nr_unused, age_limit and want_pages are | |
67 | used. Nr_unused seems to be exactly what its name says. | |
68 | Age_limit is the age in seconds after which dcache entries | |
69 | can be reclaimed when memory is short and want_pages is | |
70 | nonzero when shrink_dcache_pages() has been called and the | |
71 | dcache isn't pruned yet. | |
72 | ||
73 | ============================================================== | |
74 | ||
75 | dquot-max & dquot-nr: | |
76 | ||
77 | The file dquot-max shows the maximum number of cached disk | |
78 | quota entries. | |
79 | ||
80 | The file dquot-nr shows the number of allocated disk quota | |
81 | entries and the number of free disk quota entries. | |
82 | ||
83 | If the number of free cached disk quotas is very low and | |
84 | you have some awesome number of simultaneous system users, | |
85 | you might want to raise the limit. | |
86 | ||
87 | ============================================================== | |
88 | ||
89 | file-max & file-nr: | |
90 | ||
1da177e4 LT |
91 | The value in file-max denotes the maximum number of file- |
92 | handles that the Linux kernel will allocate. When you get lots | |
93 | of error messages about running out of file handles, you might | |
94 | want to increase this limit. | |
95 | ||
ca3b78aa FT |
96 | Historically,the kernel was able to allocate file handles |
97 | dynamically, but not to free them again. The three values in | |
98 | file-nr denote the number of allocated file handles, the number | |
99 | of allocated but unused file handles, and the maximum number of | |
100 | file handles. Linux 2.6 always reports 0 as the number of free | |
101 | file handles -- this is not an error, it just means that the | |
102 | number of allocated file handles exactly matches the number of | |
103 | used file handles. | |
bcadbbd4 XF |
104 | |
105 | Attempts to allocate more file descriptors than file-max are | |
106 | reported with printk, look for "VFS: file-max limit <number> | |
107 | reached". | |
1da177e4 | 108 | ============================================================== |
9cfe015a ED |
109 | |
110 | nr_open: | |
111 | ||
112 | This denotes the maximum number of file-handles a process can | |
113 | allocate. Default value is 1024*1024 (1048576) which should be | |
114 | enough for most machines. Actual limit depends on RLIMIT_NOFILE | |
115 | resource limit. | |
116 | ||
117 | ============================================================== | |
1da177e4 LT |
118 | |
119 | inode-max, inode-nr & inode-state: | |
120 | ||
121 | As with file handles, the kernel allocates the inode structures | |
122 | dynamically, but can't free them yet. | |
123 | ||
124 | The value in inode-max denotes the maximum number of inode | |
125 | handlers. This value should be 3-4 times larger than the value | |
126 | in file-max, since stdin, stdout and network sockets also | |
127 | need an inode struct to handle them. When you regularly run | |
128 | out of inodes, you need to increase this value. | |
129 | ||
130 | The file inode-nr contains the first two items from | |
131 | inode-state, so we'll skip to that file... | |
132 | ||
133 | Inode-state contains three actual numbers and four dummies. | |
134 | The actual numbers are, in order of appearance, nr_inodes, | |
135 | nr_free_inodes and preshrink. | |
136 | ||
137 | Nr_inodes stands for the number of inodes the system has | |
138 | allocated, this can be slightly more than inode-max because | |
139 | Linux allocates them one pageful at a time. | |
140 | ||
141 | Nr_free_inodes represents the number of free inodes (?) and | |
142 | preshrink is nonzero when the nr_inodes > inode-max and the | |
143 | system needs to prune the inode list instead of allocating | |
144 | more. | |
145 | ||
146 | ============================================================== | |
147 | ||
148 | overflowgid & overflowuid: | |
149 | ||
150 | Some filesystems only support 16-bit UIDs and GIDs, although in Linux | |
151 | UIDs and GIDs are 32 bits. When one of these filesystems is mounted | |
152 | with writes enabled, any UID or GID that would exceed 65535 is translated | |
153 | to a fixed value before being written to disk. | |
154 | ||
155 | These sysctls allow you to change the value of the fixed UID and GID. | |
156 | The default is 65534. | |
157 | ||
158 | ============================================================== | |
159 | ||
a2e0b563 AD |
160 | suid_dumpable: |
161 | ||
162 | This value can be used to query and set the core dump mode for setuid | |
163 | or otherwise protected/tainted binaries. The modes are | |
164 | ||
165 | 0 - (default) - traditional behaviour. Any process which has changed | |
166 | privilege levels or is execute only will not be dumped | |
167 | 1 - (debug) - all processes dump core when possible. The core dump is | |
168 | owned by the current user and no security is applied. This is | |
169 | intended for system debugging situations only. Ptrace is unchecked. | |
170 | 2 - (suidsafe) - any binary which normally would not be dumped is dumped | |
171 | readable by root only. This allows the end user to remove | |
172 | such a dump but not access it directly. For security reasons | |
173 | core dumps in this mode will not overwrite one another or | |
5d3f083d | 174 | other files. This mode is appropriate when administrators are |
a2e0b563 AD |
175 | attempting to debug problems in a normal environment. |
176 | ||
177 | ============================================================== | |
178 | ||
1da177e4 LT |
179 | super-max & super-nr: |
180 | ||
181 | These numbers control the maximum number of superblocks, and | |
182 | thus the maximum number of mounted filesystems the kernel | |
183 | can have. You only need to increase super-max if you need to | |
184 | mount more filesystems than the current value in super-max | |
185 | allows you to. | |
186 | ||
187 | ============================================================== | |
188 | ||
189 | aio-nr & aio-max-nr: | |
190 | ||
191 | aio-nr shows the current system-wide number of asynchronous io | |
192 | requests. aio-max-nr allows you to change the maximum value | |
193 | aio-nr can grow to. | |
194 | ||
195 | ============================================================== | |
760df93e SF |
196 | |
197 | ||
198 | 2. /proc/sys/fs/binfmt_misc | |
199 | ---------------------------------------------------------- | |
200 | ||
201 | Documentation for the files in /proc/sys/fs/binfmt_misc is | |
202 | in Documentation/binfmt_misc.txt. | |
203 | ||
204 | ||
205 | 3. /proc/sys/fs/mqueue - POSIX message queues filesystem | |
206 | ---------------------------------------------------------- | |
207 | ||
208 | The "mqueue" filesystem provides the necessary kernel features to enable the | |
209 | creation of a user space library that implements the POSIX message queues | |
210 | API (as noted by the MSG tag in the POSIX 1003.1-2001 version of the System | |
211 | Interfaces specification.) | |
212 | ||
213 | The "mqueue" filesystem contains values for determining/setting the amount of | |
214 | resources used by the file system. | |
215 | ||
216 | /proc/sys/fs/mqueue/queues_max is a read/write file for setting/getting the | |
217 | maximum number of message queues allowed on the system. | |
218 | ||
219 | /proc/sys/fs/mqueue/msg_max is a read/write file for setting/getting the | |
220 | maximum number of messages in a queue value. In fact it is the limiting value | |
221 | for another (user) limit which is set in mq_open invocation. This attribute of | |
222 | a queue must be less or equal then msg_max. | |
223 | ||
224 | /proc/sys/fs/mqueue/msgsize_max is a read/write file for setting/getting the | |
225 | maximum message size value (it is every message queue's attribute set during | |
226 | its creation). | |
227 | ||
228 | ||
229 | 4. /proc/sys/fs/epoll - Configuration options for the epoll interface | |
230 | -------------------------------------------------------- | |
231 | ||
232 | This directory contains configuration options for the epoll(7) interface. | |
233 | ||
760df93e SF |
234 | max_user_watches |
235 | ---------------- | |
236 | ||
237 | Every epoll file descriptor can store a number of files to be monitored | |
238 | for event readiness. Each one of these monitored files constitutes a "watch". | |
239 | This configuration option sets the maximum number of "watches" that are | |
240 | allowed for each user. | |
241 | Each "watch" costs roughly 90 bytes on a 32bit kernel, and roughly 160 bytes | |
242 | on a 64bit one. | |
243 | The current default value for max_user_watches is the 1/32 of the available | |
244 | low memory, divided for the "watch" cost in bytes. | |
245 |