1.\" Copyright (c) 1983, 1991, 1993 2.\" The Regents of the University of California. All rights reserved. 3.\" 4.\" Redistribution and use in source and binary forms, with or without 5.\" modification, are permitted provided that the following conditions 6.\" are met: 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. 19.\" 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 30.\" SUCH DAMAGE. 31.\" 32.\" @(#)fs.5 8.2 (Berkeley) 4/19/94 33.\" 34.Dd April 19, 1994 35.Dt FS 5 36.Os BSD 4.2 37.Sh NAME 38.Nm fs , 39.Nm inode 40.Nd format of file system volume 41.Sh SYNOPSIS 42.Fd #include <sys/types.h> 43.Fd #include <ufs/ffs/fs.h> 44.Fd #include <ufs/ufs/inode.h> 45.Sh DESCRIPTION 46The files 47.Aq Pa fs.h 48and 49.Aq Pa inode.h 50declare several structures, defined variables and macros 51which are used to create and manage the underlying format of 52file system objects on random access devices (disks). 53.Pp 54The block size and number of blocks which 55comprise a file system are parameters of the file system. 56Sectors beginning at 57.Dv BBLOCK 58and continuing for 59.Dv BBSIZE 60are used 61for a disklabel and for some hardware primary 62and secondary bootstrapping programs. 63.Pp 64The actual file system begins at sector 65.Dv SBLOCK 66with the 67.Em super-block 68that is of size 69.Dv SBSIZE . 70The following structure describes the super-block and is 71from the file 72.Aq Pa ufs/ffs/fs.h : 73.Bd -literal 74/* 75 * Super block for an FFS file system. 76 */ 77struct fs { 78 int32_t fs_firstfield; /* historic file system linked list, */ 79 int32_t fs_unused_1; /* used for incore super blocks */ 80 ufs_daddr_t fs_sblkno; /* addr of super-block in filesys */ 81 ufs_daddr_t fs_cblkno; /* offset of cyl-block in filesys */ 82 ufs_daddr_t fs_iblkno; /* offset of inode-blocks in filesys */ 83 ufs_daddr_t fs_dblkno; /* offset of first data after cg */ 84 int32_t fs_cgoffset; /* cylinder group offset in cylinder */ 85 int32_t fs_cgmask; /* used to calc mod fs_ntrak */ 86 time_t fs_time; /* last time written */ 87 int32_t fs_size; /* number of blocks in fs */ 88 int32_t fs_dsize; /* number of data blocks in fs */ 89 int32_t fs_ncg; /* number of cylinder groups */ 90 int32_t fs_bsize; /* size of basic blocks in fs */ 91 int32_t fs_fsize; /* size of frag blocks in fs */ 92 int32_t fs_frag; /* number of frags in a block in fs */ 93/* these are configuration parameters */ 94 int32_t fs_minfree; /* minimum percentage of free blocks */ 95 int32_t fs_rotdelay; /* num of ms for optimal next block */ 96 int32_t fs_rps; /* disk revolutions per second */ 97/* these fields can be computed from the others */ 98 int32_t fs_bmask; /* ``blkoff'' calc of blk offsets */ 99 int32_t fs_fmask; /* ``fragoff'' calc of frag offsets */ 100 int32_t fs_bshift; /* ``lblkno'' calc of logical blkno */ 101 int32_t fs_fshift; /* ``numfrags'' calc number of frags */ 102/* these are configuration parameters */ 103 int32_t fs_maxcontig; /* max number of contiguous blks */ 104 int32_t fs_maxbpg; /* max number of blks per cyl group */ 105/* these fields can be computed from the others */ 106 int32_t fs_fragshift; /* block to frag shift */ 107 int32_t fs_fsbtodb; /* fsbtodb and dbtofsb shift constant */ 108 int32_t fs_sbsize; /* actual size of super block */ 109 int32_t fs_csmask; /* csum block offset */ 110 int32_t fs_csshift; /* csum block number */ 111 int32_t fs_nindir; /* value of NINDIR */ 112 int32_t fs_inopb; /* value of INOPB */ 113 int32_t fs_nspf; /* value of NSPF */ 114/* yet another configuration parameter */ 115 int32_t fs_optim; /* optimization preference, see below */ 116/* these fields are derived from the hardware */ 117 int32_t fs_npsect; /* # sectors/track including spares */ 118 int32_t fs_interleave; /* hardware sector interleave */ 119 int32_t fs_trackskew; /* sector 0 skew, per track */ 120 int32_t fs_headswitch; /* head switch time, usec */ 121 int32_t fs_trkseek; /* track-to-track seek, usec */ 122/* sizes determined by number of cylinder groups and their sizes */ 123 ufs_daddr_t fs_csaddr; /* blk addr of cyl grp summary area */ 124 int32_t fs_cssize; /* size of cyl grp summary area */ 125 int32_t fs_cgsize; /* cylinder group size */ 126/* these fields are derived from the hardware */ 127 int32_t fs_ntrak; /* tracks per cylinder */ 128 int32_t fs_nsect; /* sectors per track */ 129 int32_t fs_spc; /* sectors per cylinder */ 130/* this comes from the disk driver partitioning */ 131 int32_t fs_ncyl; /* cylinders in file system */ 132/* these fields can be computed from the others */ 133 int32_t fs_cpg; /* cylinders per group */ 134 int32_t fs_ipg; /* inodes per group */ 135 int32_t fs_fpg; /* blocks per group * fs_frag */ 136/* this data must be re-computed after crashes */ 137 struct csum fs_cstotal;/* cylinder summary information */ 138/* these fields are cleared at mount time */ 139 int8_t fs_fmod; /* super block modified flag */ 140 int8_t fs_clean; /* file system is clean flag */ 141 int8_t fs_ronly; /* mounted read-only flag */ 142 int8_t fs_flags; /* currently unused flag */ 143 u_char fs_fsmnt[MAXMNTLEN]; /* name mounted on */ 144/* these fields retain the current block allocation info */ 145 int32_t fs_cgrotor; /* last cg searched */ 146 struct csum *fs_csp[MAXCSBUFS];/* list of fs_cs info buffers */ 147 int32_t *fs_maxcluster;/* max cluster in each cyl group */ 148 int32_t fs_cpc; /* cyl per cycle in postbl */ 149 int16_t fs_opostbl[16][8]; /* old rotation block list head */ 150 int32_t fs_sparecon[50]; /* reserved for future constants */ 151 int32_t fs_contigsumsize; /* size of cluster summary array */ 152 int32_t fs_maxsymlinklen;/* max length of an internal symlink */ 153 int32_t fs_inodefmt; /* format of on-disk inodes */ 154 u_int64_t fs_maxfilesize;/* maximum representable file size */ 155 int64_t fs_qbmask; /* ~fs_bmask for use with 64-bit size */ 156 int64_t fs_qfmask; /* ~fs_fmask for use with 64-bit size */ 157 int32_t fs_state; /* validate fs_clean field */ 158 int32_t fs_postblformat;/* format of positional layout tables */ 159 int32_t fs_nrpos; /* number of rotational positions */ 160 int32_t fs_postbloff; /* (u_int16) rotation block list head */ 161 int32_t fs_rotbloff; /* (u_int8) blocks for each rotation */ 162 int32_t fs_magic; /* magic number */ 163 u_int8_t fs_space[1]; /* list of blocks for each rotation */ 164/* actually longer */ 165}; 166 167/* 168 * Filesystem identification 169 */ 170#define FS_MAGIC 0x011954 /* the fast filesystem magic number */ 171#define FS_OKAY 0x7c269d38 /* superblock checksum */ 172#define FS_42INODEFMT -1 /* 4.2BSD inode format */ 173#define FS_44INODEFMT 2 /* 4.4BSD inode format */ 174/* 175 * Preference for optimization. 176 */ 177#define FS_OPTTIME 0 /* minimize allocation time */ 178#define FS_OPTSPACE 1 /* minimize disk fragmentation */ 179 180/* 181 * Rotational layout table format types 182 */ 183#define FS_42POSTBLFMT -1 /* 4.2BSD rotational table format */ 184#define FS_DYNAMICPOSTBLFMT 1 /* dynamic rotational table format */ 185.Ed 186.Pp 187Each disk drive contains some number of file systems. 188A file system consists of a number of cylinder groups. 189Each cylinder group has inodes and data. 190.Pp 191A file system is described by its super-block, which in turn 192describes the cylinder groups. The super-block is critical 193data and is replicated in each cylinder group to protect against 194catastrophic loss. This is done at file system creation 195time and the critical 196super-block data does not change, so the copies need not be 197referenced further unless disaster strikes. 198.Pp 199Addresses stored in inodes are capable of addressing fragments 200of `blocks'. File system blocks of at most size 201.Dv MAXBSIZE 202can 203be optionally broken into 2, 4, or 8 pieces, each of which is 204addressable; these pieces may be 205.Dv DEV_BSIZE , 206or some multiple of 207a 208.Dv DEV_BSIZE 209unit. 210.Pp 211Large files consist of exclusively large data blocks. To avoid 212undue wasted disk space, the last data block of a small file is 213allocated as only as many fragments of a large block as are 214necessary. The file system format retains only a single pointer 215to such a fragment, which is a piece of a single large block that 216has been divided. The size of such a fragment is determinable from 217information in the inode, using the 218.Fn blksize fs ip lbn 219macro. 220.Pp 221The file system records space availability at the fragment level; 222to determine block availability, aligned fragments are examined. 223.Pp 224The root inode is the root of the file system. 225Inode 0 can't be used for normal purposes and 226historically bad blocks were linked to inode 1, 227thus the root inode is 2 (inode 1 is no longer used for 228this purpose, however numerous dump tapes make this 229assumption, so we are stuck with it). 230.Pp 231The 232.Fa fs_minfree 233element gives the minimum acceptable percentage of file system 234blocks that may be free. If the freelist drops below this level 235only the super-user may continue to allocate blocks. 236The 237.Fa fs_minfree 238element 239may be set to 0 if no reserve of free blocks is deemed necessary, 240however severe performance degradations will be observed if the 241file system is run at greater than 90% full; thus the default 242value of 243.Fa fs_minfree 244is 10%. 245.Pp 246Empirically the best trade-off between block fragmentation and 247overall disk utilization at a loading of 90% comes with a 248fragmentation of 8, thus the default fragment size is an eighth 249of the block size. 250.Pp 251The element 252.Fa fs_optim 253specifies whether the file system should try to minimize the time spent 254allocating blocks, or if it should attempt to minimize the space 255fragmentation on the disk. 256If the value of fs_minfree (see above) is less than 10%, 257then the file system defaults to optimizing for space to avoid 258running out of full sized blocks. 259If the value of minfree is greater than or equal to 10%, 260fragmentation is unlikely to be problematical, and 261the file system defaults to optimizing for time. 262.Pp 263.Em Cylinder group related limits : 264Each cylinder keeps track of the availability of blocks at different 265rotational positions, so that sequential blocks can be laid out 266with minimum rotational latency. With the default of 8 distinguished 267rotational positions, the resolution of the 268summary information is 2ms for a typical 3600 rpm drive. 269.Pp 270The element 271.Fa fs_rotdelay 272gives the minimum number of milliseconds to initiate 273another disk transfer on the same cylinder. 274It is used in determining the rotationally optimal 275layout for disk blocks within a file; 276the default value for 277.Fa fs_rotdelay 278is 2ms. 279.Pp 280Each file system has a statically allocated number of inodes. 281An inode is allocated for each 282.Dv NBPI 283bytes of disk space. 284The inode allocation strategy is extremely conservative. 285.Pp 286.Dv MINBSIZE 287is the smallest allowable block size. 288With a 289.Dv MINBSIZE 290of 4096 291it is possible to create files of size 2922^32 with only two levels of indirection. 293.Dv MINBSIZE 294must be big enough to hold a cylinder group block, 295thus changes to 296.Pq Fa struct cg 297must keep its size within 298.Dv MINBSIZE . 299Note that super-blocks are never more than size 300.Dv SBSIZE . 301.Pp 302The path name on which the file system is mounted is maintained in 303.Fa fs_fsmnt . 304.Dv MAXMNTLEN 305defines the amount of space allocated in 306the super-block for this name. 307The limit on the amount of summary information per file system 308is defined by 309.Dv MAXCSBUFS. 310For a 4096 byte block size, it is currently parameterized for a 311maximum of two million cylinders. 312.Pp 313Per cylinder group information is summarized in blocks allocated 314from the first cylinder group's data blocks. 315These blocks are read in from 316.Fa fs_csaddr 317(size 318.Fa fs_cssize ) 319in addition to the super-block. 320.Pp 321.Sy N.B.: 322.Fn sizeof "struct csum" 323must be a power of two in order for 324the 325.Fn fs_cs 326macro to work. 327.Pp 328The 329.Em "Super-block for a file system" : 330The size of the rotational layout tables 331is limited by the fact that the super-block is of size 332.Dv SBSIZE . 333The size of these tables is 334.Em inversely 335proportional to the block 336size of the file system. The size of the tables is 337increased when sector sizes are not powers of two, 338as this increases the number of cylinders 339included before the rotational pattern repeats 340.Pq Fa fs_cpc . 341The size of the rotational layout 342tables is derived from the number of bytes remaining in 343.Pq Fa struct fs . 344.Pp 345The number of blocks of data per cylinder group 346is limited because cylinder groups are at most one block. 347The inode and free block tables 348must fit into a single block after deducting space for 349the cylinder group structure 350.Pq Fa struct cg . 351.Pp 352The 353.Em Inode : 354The inode is the focus of all file activity in the 355.Tn UNIX 356file system. 357There is a unique inode allocated 358for each active file, 359each current directory, each mounted-on file, 360text file, and the root. 361An inode is `named' by its device/i-number pair. 362For further information, see the include file 363.Aq Pa sys/inode.h . 364.Sh HISTORY 365A super-block structure named filsys appeared in 366.At v6 . 367The file system described in this manual appeared 368in 369.Bx 4.2 . 370