1 Documentation for /proc/sys/fs/* kernel version 2.2.10
2 (c) 1998, 1999, Rik van Riel <riel@nl.linux.org>
4 For general info and legal blurb, please look in README.
6 ==============================================================
8 This file contains documentation for the sysctl files in
9 /proc/sys/fs/ and is valid for Linux kernel version 2.2.
11 The files in this directory can be used to tune and monitor
12 miscellaneous and general things in the operation of the Linux
13 kernel. Since some of the files _can_ be used to screw up your
14 system, it is advisable to read both documentation and source
15 before actually making adjustments.
17 Currently, these files are in /proc/sys/fs:
31 Documentation for the files in /proc/sys/fs/binfmt_misc is
32 in Documentation/binfmt_misc.txt.
34 ==============================================================
38 From linux/fs/dentry.c:
39 --------------------------------------------------------------
43 int age_limit; /* age in seconds */
44 int want_pages; /* pages requested by system */
46 } dentry_stat = {0, 0, 45, 0,};
47 --------------------------------------------------------------
49 Dentries are dynamically allocated and deallocated, and
50 nr_dentry seems to be 0 all the time. Hence it's safe to
51 assume that only nr_unused, age_limit and want_pages are
52 used. Nr_unused seems to be exactly what its name says.
53 Age_limit is the age in seconds after which dcache entries
54 can be reclaimed when memory is short and want_pages is
55 nonzero when shrink_dcache_pages() has been called and the
56 dcache isn't pruned yet.
58 ==============================================================
62 The file dquot-max shows the maximum number of cached disk
65 The file dquot-nr shows the number of allocated disk quota
66 entries and the number of free disk quota entries.
68 If the number of free cached disk quotas is very low and
69 you have some awesome number of simultaneous system users,
70 you might want to raise the limit.
72 ==============================================================
76 The kernel allocates file handles dynamically, but as yet it
77 doesn't free them again.
79 The value in file-max denotes the maximum number of file-
80 handles that the Linux kernel will allocate. When you get lots
81 of error messages about running out of file handles, you might
82 want to increase this limit.
84 The three values in file-nr denote the number of allocated
85 file handles, the number of unused file handles and the maximum
86 number of file handles. When the allocated file handles come
87 close to the maximum, but the number of unused file handles is
88 significantly greater than 0, you've encountered a peak in your
89 usage of file handles and you don't need to increase the maximum.
91 ==============================================================
93 inode-max, inode-nr & inode-state:
95 As with file handles, the kernel allocates the inode structures
96 dynamically, but can't free them yet.
98 The value in inode-max denotes the maximum number of inode
99 handlers. This value should be 3-4 times larger than the value
100 in file-max, since stdin, stdout and network sockets also
101 need an inode struct to handle them. When you regularly run
102 out of inodes, you need to increase this value.
104 The file inode-nr contains the first two items from
105 inode-state, so we'll skip to that file...
107 Inode-state contains three actual numbers and four dummies.
108 The actual numbers are, in order of appearance, nr_inodes,
109 nr_free_inodes and preshrink.
111 Nr_inodes stands for the number of inodes the system has
112 allocated, this can be slightly more than inode-max because
113 Linux allocates them one pageful at a time.
115 Nr_free_inodes represents the number of free inodes (?) and
116 preshrink is nonzero when the nr_inodes > inode-max and the
117 system needs to prune the inode list instead of allocating
120 ==============================================================
122 overflowgid & overflowuid:
124 Some filesystems only support 16-bit UIDs and GIDs, although in Linux
125 UIDs and GIDs are 32 bits. When one of these filesystems is mounted
126 with writes enabled, any UID or GID that would exceed 65535 is translated
127 to a fixed value before being written to disk.
129 These sysctls allow you to change the value of the fixed UID and GID.
130 The default is 65534.
132 ==============================================================
134 super-max & super-nr:
136 These numbers control the maximum number of superblocks, and
137 thus the maximum number of mounted filesystems the kernel
138 can have. You only need to increase super-max if you need to
139 mount more filesystems than the current value in super-max
142 ==============================================================
146 aio-nr shows the current system-wide number of asynchronous io
147 requests. aio-max-nr allows you to change the maximum value
150 ==============================================================