1 .\" Copyright (c) 1983, 1991, 1993
2 .\" The Regents of the University of California. All rights reserved.
4 .\" Redistribution and use in source and binary forms, with or without
5 .\" modification, are permitted provided that the following conditions
7 .\" 1. Redistributions of source code must retain the above copyright
8 .\" notice, this list of conditions and the following disclaimer.
9 .\" 2. Redistributions in binary form must reproduce the above copyright
10 .\" notice, this list of conditions and the following disclaimer in the
11 .\" documentation and/or other materials provided with the distribution.
12 .\" 3. All advertising materials mentioning features or use of this software
13 .\" must display the following acknowledgement:
14 .\" This product includes software developed by the University of
15 .\" California, Berkeley and its contributors.
16 .\" 4. Neither the name of the University nor the names of its contributors
17 .\" may be used to endorse or promote products derived from this software
18 .\" without specific prior written permission.
20 .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
21 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
23 .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
24 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
26 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
28 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
29 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
32 .\" @(#)fs.5 8.2 (Berkeley) 4/19/94
33 .\" $FreeBSD: src/share/man/man5/fs.5,v 1.10.2.4 2001/12/17 11:30:14 ru Exp $
34 .\" $DragonFly: src/share/man/man5/fs.5,v 1.3 2006/05/26 19:39:40 swildner Exp $
42 .Nd format of file system volume
56 declare several structures, defined variables and macros
57 which are used to create and manage the underlying format of
58 file system objects on random access devices (disks).
60 The block size and number of blocks which
61 comprise a file system are parameters of the file system.
67 for a disklabel and for some hardware primary
68 and secondary bootstrapping programs.
70 The actual file system begins at sector
76 The following structure describes the super-block and is
81 * Super block for an FFS file system.
84 int32_t fs_firstfield; /* historic file system linked list, */
85 int32_t fs_unused_1; /* used for incore super blocks */
86 ufs_daddr_t fs_sblkno; /* addr of super-block in filesys */
87 ufs_daddr_t fs_cblkno; /* offset of cyl-block in filesys */
88 ufs_daddr_t fs_iblkno; /* offset of inode-blocks in filesys */
89 ufs_daddr_t fs_dblkno; /* offset of first data after cg */
90 int32_t fs_cgoffset; /* cylinder group offset in cylinder */
91 int32_t fs_cgmask; /* used to calc mod fs_ntrak */
92 time_t fs_time; /* last time written */
93 int32_t fs_size; /* number of blocks in fs */
94 int32_t fs_dsize; /* number of data blocks in fs */
95 int32_t fs_ncg; /* number of cylinder groups */
96 int32_t fs_bsize; /* size of basic blocks in fs */
97 int32_t fs_fsize; /* size of frag blocks in fs */
98 int32_t fs_frag; /* number of frags in a block in fs */
99 /* these are configuration parameters */
100 int32_t fs_minfree; /* minimum percentage of free blocks */
101 int32_t fs_rotdelay; /* num of ms for optimal next block */
102 int32_t fs_rps; /* disk revolutions per second */
103 /* these fields can be computed from the others */
104 int32_t fs_bmask; /* ``blkoff'' calc of blk offsets */
105 int32_t fs_fmask; /* ``fragoff'' calc of frag offsets */
106 int32_t fs_bshift; /* ``lblkno'' calc of logical blkno */
107 int32_t fs_fshift; /* ``numfrags'' calc number of frags */
108 /* these are configuration parameters */
109 int32_t fs_maxcontig; /* max number of contiguous blks */
110 int32_t fs_maxbpg; /* max number of blks per cyl group */
111 /* these fields can be computed from the others */
112 int32_t fs_fragshift; /* block to frag shift */
113 int32_t fs_fsbtodb; /* fsbtodb and dbtofsb shift constant */
114 int32_t fs_sbsize; /* actual size of super block */
115 int32_t fs_csmask; /* csum block offset */
116 int32_t fs_csshift; /* csum block number */
117 int32_t fs_nindir; /* value of NINDIR */
118 int32_t fs_inopb; /* value of INOPB */
119 int32_t fs_nspf; /* value of NSPF */
120 /* yet another configuration parameter */
121 int32_t fs_optim; /* optimization preference, see below */
122 /* these fields are derived from the hardware */
123 int32_t fs_npsect; /* # sectors/track including spares */
124 int32_t fs_interleave; /* hardware sector interleave */
125 int32_t fs_trackskew; /* sector 0 skew, per track */
126 /* fs_id takes the space of the unused fs_headswitch and fs_trkseek fields */
127 int32_t fs_id[2]; /* unique filesystem id*/
128 /* sizes determined by number of cylinder groups and their sizes */
129 ufs_daddr_t fs_csaddr; /* blk addr of cyl grp summary area */
130 int32_t fs_cssize; /* size of cyl grp summary area */
131 int32_t fs_cgsize; /* cylinder group size */
132 /* these fields are derived from the hardware */
133 int32_t fs_ntrak; /* tracks per cylinder */
134 int32_t fs_nsect; /* sectors per track */
135 int32_t fs_spc; /* sectors per cylinder */
136 /* this comes from the disk driver partitioning */
137 int32_t fs_ncyl; /* cylinders in file system */
138 /* these fields can be computed from the others */
139 int32_t fs_cpg; /* cylinders per group */
140 int32_t fs_ipg; /* inodes per group */
141 int32_t fs_fpg; /* blocks per group * fs_frag */
142 /* this data must be re-computed after crashes */
143 struct csum fs_cstotal;/* cylinder summary information */
144 /* these fields are cleared at mount time */
145 int8_t fs_fmod; /* super block modified flag */
146 int8_t fs_clean; /* file system is clean flag */
147 int8_t fs_ronly; /* mounted read-only flag */
148 int8_t fs_flags; /* currently unused flag */
149 u_char fs_fsmnt[MAXMNTLEN]; /* name mounted on */
150 /* these fields retain the current block allocation info */
151 int32_t fs_cgrotor; /* last cg searched */
152 struct csum *fs_csp[MAXCSBUFS];/* list of fs_cs info buffers */
153 int32_t *fs_maxcluster;/* max cluster in each cyl group */
154 int32_t fs_cpc; /* cyl per cycle in postbl */
155 int16_t fs_opostbl[16][8]; /* old rotation block list head */
156 int32_t fs_sparecon[50]; /* reserved for future constants */
157 int32_t fs_contigsumsize; /* size of cluster summary array */
158 int32_t fs_maxsymlinklen;/* max length of an internal symlink */
159 int32_t fs_inodefmt; /* format of on-disk inodes */
160 u_int64_t fs_maxfilesize;/* maximum representable file size */
161 int64_t fs_qbmask; /* ~fs_bmask for use with 64-bit size */
162 int64_t fs_qfmask; /* ~fs_fmask for use with 64-bit size */
163 int32_t fs_state; /* validate fs_clean field */
164 int32_t fs_postblformat;/* format of positional layout tables */
165 int32_t fs_nrpos; /* number of rotational positions */
166 int32_t fs_postbloff; /* (u_int16) rotation block list head */
167 int32_t fs_rotbloff; /* (u_int8) blocks for each rotation */
168 int32_t fs_magic; /* magic number */
169 u_int8_t fs_space[1]; /* list of blocks for each rotation */
170 /* actually longer */
174 * Filesystem identification
176 #define FS_MAGIC 0x011954 /* the fast filesystem magic number */
177 #define FS_OKAY 0x7c269d38 /* superblock checksum */
178 #define FS_42INODEFMT -1 /* 4.2BSD inode format */
179 #define FS_44INODEFMT 2 /* 4.4BSD inode format */
181 * Preference for optimization.
183 #define FS_OPTTIME 0 /* minimize allocation time */
184 #define FS_OPTSPACE 1 /* minimize disk fragmentation */
187 * Rotational layout table format types
189 #define FS_42POSTBLFMT -1 /* 4.2BSD rotational table format */
190 #define FS_DYNAMICPOSTBLFMT 1 /* dynamic rotational table format */
193 Each disk drive contains some number of file systems.
194 A file system consists of a number of cylinder groups.
195 Each cylinder group has inodes and data.
197 A file system is described by its super-block, which in turn
198 describes the cylinder groups. The super-block is critical
199 data and is replicated in each cylinder group to protect against
200 catastrophic loss. This is done at file system creation
201 time and the critical
202 super-block data does not change, so the copies need not be
203 referenced further unless disaster strikes.
205 Addresses stored in inodes are capable of addressing fragments
206 of `blocks'. File system blocks of at most size
209 be optionally broken into 2, 4, or 8 pieces, each of which is
210 addressable; these pieces may be
217 Large files consist of exclusively large data blocks. To avoid
218 undue wasted disk space, the last data block of a small file is
219 allocated as only as many fragments of a large block as are
220 necessary. The file system format retains only a single pointer
221 to such a fragment, which is a piece of a single large block that
222 has been divided. The size of such a fragment is determinable from
223 information in the inode, using the
224 .Fn blksize fs ip lbn
227 The file system records space availability at the fragment level;
228 to determine block availability, aligned fragments are examined.
230 The root inode is the root of the file system.
231 Inode 0 can't be used for normal purposes and
232 historically bad blocks were linked to inode 1,
233 thus the root inode is 2 (inode 1 is no longer used for
234 this purpose, however numerous dump tapes make this
235 assumption, so we are stuck with it).
239 element gives the minimum acceptable percentage of file system
240 blocks that may be free.
241 If the freelist drops below this level
242 only the super-user may continue to allocate blocks.
246 may be set to 0 if no reserve of free blocks is deemed necessary,
247 however severe performance degradations will be observed if the
248 file system is run at greater than 90% full; thus the default
253 Empirically the best trade-off between block fragmentation and
254 overall disk utilization at a loading of 90% comes with a
255 fragmentation of 8, thus the default fragment size is an eighth
260 specifies whether the file system should try to minimize the time spent
261 allocating blocks, or if it should attempt to minimize the space
262 fragmentation on the disk.
263 If the value of fs_minfree (see above) is less than 10%,
264 then the file system defaults to optimizing for space to avoid
265 running out of full sized blocks.
266 If the value of minfree is greater than or equal to 10%,
267 fragmentation is unlikely to be problematical, and
268 the file system defaults to optimizing for time.
270 .Em Cylinder group related limits :
271 Each cylinder keeps track of the availability of blocks at different
272 rotational positions, so that sequential blocks can be laid out
273 with minimum rotational latency.
274 With the default of 8 distinguished
275 rotational positions, the resolution of the
276 summary information is 2ms for a typical 3600 rpm drive.
280 gives the minimum number of milliseconds to initiate
281 another disk transfer on the same cylinder.
282 It is used in determining the rotationally optimal
283 layout for disk blocks within a file;
284 the default value for
288 Each file system has a statically allocated number of inodes.
289 An inode is allocated for each
292 The inode allocation strategy is extremely conservative.
295 is the smallest allowable block size.
299 it is possible to create files of size
300 2^32 with only two levels of indirection.
302 must be big enough to hold a cylinder group block,
305 must keep its size within
307 Note that super-blocks are never more than size
310 The path name on which the file system is mounted is maintained in
313 defines the amount of space allocated in
314 the super-block for this name.
315 The limit on the amount of summary information per file system
318 For a 4096 byte block size, it is currently parameterized for a
319 maximum of two million cylinders.
321 Per cylinder group information is summarized in blocks allocated
322 from the first cylinder group's data blocks.
323 These blocks are read in from
327 in addition to the super-block.
330 .Fn sizeof "struct csum"
331 must be a power of two in order for
337 .Em "Super-block for a file system" :
338 The size of the rotational layout tables
339 is limited by the fact that the super-block is of size
341 The size of these tables is
343 proportional to the block
344 size of the file system.
345 The size of the tables is
346 increased when sector sizes are not powers of two,
347 as this increases the number of cylinders
348 included before the rotational pattern repeats
350 The size of the rotational layout
351 tables is derived from the number of bytes remaining in
354 The number of blocks of data per cylinder group
355 is limited because cylinder groups are at most one block.
356 The inode and free block tables
357 must fit into a single block after deducting space for
358 the cylinder group structure
363 The inode is the focus of all file activity in the
366 There is a unique inode allocated
367 for each active file,
368 each current directory, each mounted-on file,
369 text file, and the root.
370 An inode is `named' by its device/i-number pair.
371 For further information, see the include file
372 .In vfs/ufs/inode.h .
374 A super-block structure named filsys appeared in
376 The file system described in this manual appeared