diff options
Diffstat (limited to 'Documentation/filesystems')
| -rw-r--r-- | Documentation/filesystems/00-INDEX | 58 | ||||
| -rw-r--r-- | Documentation/filesystems/9p.txt | 17 | ||||
| -rw-r--r-- | Documentation/filesystems/Locking | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/btrfs.txt | 47 | ||||
| -rw-r--r-- | Documentation/filesystems/f2fs.txt | 24 | ||||
| -rw-r--r-- | Documentation/filesystems/nfs/nfs41-server.txt | 42 | ||||
| -rw-r--r-- | Documentation/filesystems/nilfs2.txt | 56 | ||||
| -rw-r--r-- | Documentation/filesystems/proc.txt | 15 | ||||
| -rw-r--r-- | Documentation/filesystems/sysfs.txt | 6 | ||||
| -rw-r--r-- | Documentation/filesystems/vfs.txt | 12 |
10 files changed, 193 insertions, 86 deletions
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 8042050eb26..632211cbdd5 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -10,24 +10,32 @@ afs.txt - info and examples for the distributed AFS (Andrew File System) fs. affs.txt - info and mount options for the Amiga Fast File System. +autofs4-mount-control.txt + - info on device control operations for autofs4 module. automount-support.txt - information about filesystem automount support. befs.txt - information about the BeOS filesystem for Linux. bfs.txt - info for the SCO UnixWare Boot Filesystem (BFS). +btrfs.txt + - info for the BTRFS filesystem. +caching/ + - directory containing filesystem cache documentation. ceph.txt - - info for the Ceph Distributed File System -cifs.txt - - description of the CIFS filesystem. + - info for the Ceph Distributed File System. +cifs/ + - directory containing CIFS filesystem documentation and example code. coda.txt - description of the CODA filesystem. configfs/ - directory containing configfs documentation and example code. cramfs.txt - info on the cram filesystem for small storage (ROMs etc). -dentry-locking.txt - - info on the RCU-based dcache locking model. +debugfs.txt + - info on the debugfs filesystem. +devpts.txt + - info on the devpts filesystem. directory-locking - info about the locking scheme used for directory operations. dlmfs.txt @@ -35,7 +43,7 @@ dlmfs.txt dnotify.txt - info about directory notification in Linux. dnotify_test.c - - example program for dnotify + - example program for dnotify. ecryptfs.txt - docs on eCryptfs: stacked cryptographic filesystem for Linux. efivarfs.txt @@ -48,12 +56,18 @@ ext3.txt - info, mount options and specifications for the Ext3 filesystem. ext4.txt - info, mount options and specifications for the Ext4 filesystem. -files.txt - - info on file management in the Linux kernel. f2fs.txt - info and mount options for the F2FS filesystem. +fiemap.txt + - info on fiemap ioctl. +files.txt + - info on file management in the Linux kernel. fuse.txt - info on the Filesystem in User SpacE including mount options. +gfs2-glocks.txt + - info on the Global File System 2 - Glock internal locking rules. +gfs2-uevents.txt + - info on the Global File System 2 - uevents. gfs2.txt - info on the Global File System 2. hfs.txt @@ -84,40 +98,58 @@ ntfs.txt - info and mount options for the NTFS filesystem (Windows NT). ocfs2.txt - info and mount options for the OCFS2 clustered filesystem. +omfs.txt + - info on the Optimized MPEG FileSystem. +path-lookup.txt + - info on path walking and name lookup locking. +pohmelfs/ + - directory containing pohmelfs filesystem documentation. porting - various information on filesystem porting. proc.txt - info on Linux's /proc filesystem. +qnx6.txt + - info on the QNX6 filesystem. +quota.txt + - info on Quota subsystem. ramfs-rootfs-initramfs.txt - info on the 'in memory' filesystems ramfs, rootfs and initramfs. -reiser4.txt - - info on the Reiser4 filesystem based on dancing tree algorithms. relay.txt - info on relay, for efficient streaming from kernel to user space. romfs.txt - description of the ROMFS filesystem. seq_file.txt - - how to use the seq_file API + - how to use the seq_file API. sharedsubtree.txt - a description of shared subtrees for namespaces. spufs.txt - info and mount options for the SPU filesystem used on Cell. +squashfs.txt + - info on the squashfs filesystem. sysfs-pci.txt - info on accessing PCI device resources through sysfs. +sysfs-tagging.txt + - info on sysfs tagging to avoid duplicates. sysfs.txt - info on sysfs, a ram-based filesystem for exporting kernel objects. sysv-fs.txt - info on the SystemV/V7/Xenix/Coherent filesystem. tmpfs.txt - info on tmpfs, a filesystem that holds all files in virtual memory. +ubifs.txt + - info on the Unsorted Block Images FileSystem. udf.txt - info and mount options for the UDF filesystem. ufs.txt - info on the ufs filesystem. vfat.txt - - info on using the VFAT filesystem used in Windows NT and Windows 95 + - info on using the VFAT filesystem used in Windows NT and Windows 95. vfs.txt - - overview of the Virtual File System + - overview of the Virtual File System. +xfs-delayed-logging-design.txt + - info on the XFS Delayed Logging Design. +xfs-self-describing-metadata.txt + - info on XFS Self Describing Metadata. xfs.txt - info and mount options for the XFS filesystem. xip.txt diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt index 2c032144284..fec7144e817 100644 --- a/Documentation/filesystems/9p.txt +++ b/Documentation/filesystems/9p.txt @@ -69,10 +69,14 @@ OPTIONS offering several exported file systems. cache=mode specifies a caching policy. By default, no caches are used. + none = default no cache policy, metadata and data + alike are synchronous. loose = no attempts are made at consistency, intended for exclusive, read-only mounts - fscache = use FS-Cache for a persistent, read-only + fscache = use FS-Cache for a persistent, read-only cache backend. + mmap = minimal cache that is only used for read-write + mmap. Northing else is cached, like cache=none debug=n specifies debug level. The debug level is a bitmask. 0x01 = display verbose error messages @@ -147,8 +151,7 @@ on sourceforge (http://sourceforge.net/projects/v9fs). News and other information is maintained on a Wiki. (http://sf.net/apps/mediawiki/v9fs/index.php). -Bug reports may be issued through the kernel.org bugzilla -(http://bugzilla.kernel.org) +Bug reports are best issued via the mailing list. For more information on the Plan 9 Operating System check out http://plan9.bell-labs.com/plan9 @@ -156,11 +159,3 @@ http://plan9.bell-labs.com/plan9 For information on Plan 9 from User Space (Plan 9 applications and libraries ported to Linux/BSD/OSX/etc) check out http://swtch.com/plan9 - -STATUS -====== - -The 2.6 kernel support is working on PPC and x86. - -PLEASE USE THE KERNEL BUGZILLA TO REPORT PROBLEMS. (http://bugzilla.kernel.org) - diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index fe7afe22538..5b0c083d7c0 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -544,7 +544,7 @@ like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which will cause the VM to retry the fault. ->access() is called when get_user_pages() fails in -acces_process_vm(), typically used to debug a process through +access_process_vm(), typically used to debug a process through /proc/pid/mem or ptrace. This function is needed only for VM_IO | VM_PFNMAP VMAs. diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt index 5dd282dda55..d11cc2f8077 100644 --- a/Documentation/filesystems/btrfs.txt +++ b/Documentation/filesystems/btrfs.txt @@ -38,7 +38,7 @@ Mount Options ============= When mounting a btrfs filesystem, the following option are accepted. -Unless otherwise specified, all options default to off. +Options with (*) are default options and will not show in the mount options. alloc_start=<bytes> Debugging option to force all block allocations above a certain @@ -46,10 +46,12 @@ Unless otherwise specified, all options default to off. bytes, optionally with a K, M, or G suffix, case insensitive. Default is 1MB. + noautodefrag(*) autodefrag - Detect small random writes into files and queue them up for the - defrag process. Works best for small files; Not well suited for - large database workloads. + Disable/enable auto defragmentation. + Auto defragmentation detects small random writes into files and queue + them up for the defrag process. Works best for small files; + Not well suited for large database workloads. check_int check_int_data @@ -96,21 +98,26 @@ Unless otherwise specified, all options default to off. can be avoided. Especially useful when trying to mount a multi-device setup as root. May be specified multiple times for multiple devices. + nodiscard(*) discard - Issue frequent commands to let the block device reclaim space freed by - the filesystem. This is useful for SSD devices, thinly provisioned + Disable/enable discard mount option. + Discard issues frequent commands to let the block device reclaim space + freed by the filesystem. + This is useful for SSD devices, thinly provisioned LUNs and virtual machine images, but may have a significant performance impact. (The fstrim command is also available to initiate batch trims from userspace). + noenospc_debug(*) enospc_debug - Debugging option to be more verbose in some ENOSPC conditions. + Disable/enable debugging option to be more verbose in some ENOSPC conditions. fatal_errors=<action> Action to take when encountering a fatal error: "bug" - BUG() on a fatal error. This is the default. "panic" - panic() on a fatal error. + noflushoncommit(*) flushoncommit The 'flushoncommit' mount option forces any data dirtied by a write in a prior transaction to commit as part of the current commit. This makes @@ -134,26 +141,32 @@ Unless otherwise specified, all options default to off. Specify that 1 metadata chunk should be allocated after every <value> data chunks. Off by default. + acl(*) noacl - Disable support for Posix Access Control Lists (ACLs). See the + Enable/disable support for Posix Access Control Lists (ACLs). See the acl(5) manual page for more information about ACLs. + barrier(*) nobarrier - Disables the use of block layer write barriers. Write barriers ensure - that certain IOs make it through the device cache and are on persistent - storage. If used on a device with a volatile (non-battery-backed) - write-back cache, this option will lead to filesystem corruption on a - system crash or power loss. + Enable/disable the use of block layer write barriers. Write barriers + ensure that certain IOs make it through the device cache and are on + persistent storage. If disabled on a device with a volatile + (non-battery-backed) write-back cache, nobarrier option will lead to + filesystem corruption on a system crash or power loss. + datacow(*) nodatacow - Disable data copy-on-write for newly created files. Implies nodatasum, - and disables all compression. + Enable/disable data copy-on-write for newly created files. + Nodatacow implies nodatasum, and disables all compression. + datasum(*) nodatasum - Disable data checksumming for newly created files. + Enable/disable data checksumming for newly created files. + Datasum implies datacow. + treelog(*) notreelog - Disable the tree logging used for fsync and O_SYNC writes. + Enable/disable the tree logging used for fsync and O_SYNC writes. recovery Enable autorecovery attempts if a bad tree root is found at mount time. diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index a3fe811bbdb..b8d284975f0 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -120,6 +120,8 @@ active_logs=%u Support configuring the number of active logs. In the disable_ext_identify Disable the extension list configured by mkfs, so f2fs does not aware of cold files such as media files. inline_xattr Enable the inline xattrs feature. +inline_data Enable the inline data feature: New created small(<~3.4k) + files can be written into inode block. ================================================================================ DEBUGFS ENTRIES @@ -171,6 +173,28 @@ Files in /sys/fs/f2fs/<devname> conduct checkpoint to reclaim the prefree segments to free segments. By default, 100 segments, 200MB. + max_small_discards This parameter controls the number of discard + commands that consist small blocks less than 2MB. + The candidates to be discarded are cached until + checkpoint is triggered, and issued during the + checkpoint. By default, it is disabled with 0. + + ipu_policy This parameter controls the policy of in-place + updates in f2fs. There are five policies: + 0: F2FS_IPU_FORCE, 1: F2FS_IPU_SSR, + 2: F2FS_IPU_UTIL, 3: F2FS_IPU_SSR_UTIL, + 4: F2FS_IPU_DISABLE. + + min_ipu_util This parameter controls the threshold to trigger + in-place-updates. The number indicates percentage + of the filesystem utilization, and used by + F2FS_IPU_UTIL and F2FS_IPU_SSR_UTIL policies. + + max_victim_search This parameter controls the number of trials to + find a victim segment when conducting SSR and + cleaning operations. The default value is 4096 + which covers 8GB block address range. + ================================================================================ USAGE ================================================================================ diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt index 01c2db76979..b930ad08778 100644 --- a/Documentation/filesystems/nfs/nfs41-server.txt +++ b/Documentation/filesystems/nfs/nfs41-server.txt @@ -5,11 +5,11 @@ Server support for minorversion 1 can be controlled using the by reading this file will contain either "+4.1" or "-4.1" correspondingly. -Currently, server support for minorversion 1 is disabled by default. -It can be enabled at run time by writing the string "+4.1" to +Currently, server support for minorversion 1 is enabled by default. +It can be disabled at run time by writing the string "-4.1" to the /proc/fs/nfsd/versions control file. Note that to write this -control file, the nfsd service must be taken down. Use your user-mode -nfs-utils to set this up; see rpc.nfsd(8) +control file, the nfsd service must be taken down. You can use rpc.nfsd +for this; see rpc.nfsd(8). (Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and "-4", respectively. Therefore, code meant to work on both new and old @@ -29,29 +29,6 @@ are still under development out of tree. See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design for more information. -The current implementation is intended for developers only: while it -does support ordinary file operations on clients we have tested against -(including the linux client), it is incomplete in ways which may limit -features unexpectedly, cause known bugs in rare cases, or cause -interoperability problems with future clients. Known issues: - - - gss support is questionable: currently mounts with kerberos - from a linux client are possible, but we aren't really - conformant with the spec (for example, we don't use kerberos - on the backchannel correctly). - - We do not support SSV, which provides security for shared - client-server state (thus preventing unauthorized tampering - with locks and opens, for example). It is mandatory for - servers to support this, though no clients use it yet. - -In addition, some limitations are inherited from the current NFSv4 -implementation: - - - Incomplete delegation enforcement: if a file is renamed or - unlinked by a local process, a client holding a delegation may - continue to indefinitely allow opens of the file under the old - name. - The table below, taken from the NFSv4.1 document, lists the operations that are mandatory to implement (REQ), optional (OPT), and NFSv4.0 operations that are required not to implement (MNI) @@ -169,6 +146,16 @@ NS*| CB_WANTS_CANCELLED | OPT | FDELG, | Section 20.10 | Implementation notes: +SSV: +* The spec claims this is mandatory, but we don't actually know of any + implementations, so we're ignoring it for now. The server returns + NFS4ERR_ENCR_ALG_UNSUPP on EXCHANGE_ID, which should be future-proof. + +GSS on the backchannel: +* Again, theoretically required but not widely implemented (in + particular, the current Linux client doesn't request it). We return + NFS4ERR_ENCR_ALG_UNSUPP on CREATE_SESSION. + DELEGPURGE: * mandatory only for servers that support CLAIM_DELEGATE_PREV and/or CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that @@ -176,7 +163,6 @@ DELEGPURGE: now. EXCHANGE_ID: -* only SP4_NONE state protection supported * implementation ids are ignored CREATE_SESSION: diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt index 873a2ab2e9f..06887d46ccf 100644 --- a/Documentation/filesystems/nilfs2.txt +++ b/Documentation/filesystems/nilfs2.txt @@ -81,6 +81,62 @@ nodiscard(*) The discard/TRIM commands are sent to the underlying block device when blocks are freed. This is useful for SSD devices and sparse/thinly-provisioned LUNs. +Ioctls +====== + +There is some NILFS2 specific functionality which can be accessed by applications +through the system call interfaces. The list of all NILFS2 specific ioctls are +shown in the table below. + +Table of NILFS2 specific ioctls +.............................................................................. + Ioctl Description + NILFS_IOCTL_CHANGE_CPMODE Change mode of given checkpoint between + checkpoint and snapshot state. This ioctl is + used in chcp and mkcp utilities. + + NILFS_IOCTL_DELETE_CHECKPOINT Remove checkpoint from NILFS2 file system. + This ioctl is used in rmcp utility. + + NILFS_IOCTL_GET_CPINFO Return info about requested checkpoints. This + ioctl is used in lscp utility and by + nilfs_cleanerd daemon. + + NILFS_IOCTL_GET_CPSTAT Return checkpoints statistics. This ioctl is + used by lscp, rmcp utilities and by + nilfs_cleanerd daemon. + + NILFS_IOCTL_GET_SUINFO Return segment usage info about requested + segments. This ioctl is used in lssu, + nilfs_resize utilities and by nilfs_cleanerd + daemon. + + NILFS_IOCTL_GET_SUSTAT Return segment usage statistics. This ioctl + is used in lssu, nilfs_resize utilities and + by nilfs_cleanerd daemon. + + NILFS_IOCTL_GET_VINFO Return information on virtual block addresses. + This ioctl is used by nilfs_cleanerd daemon. + + NILFS_IOCTL_GET_BDESCS Return information about descriptors of disk + block numbers. This ioctl is used by + nilfs_cleanerd daemon. + + NILFS_IOCTL_CLEAN_SEGMENTS Do garbage collection operation in the + environment of requested parameters from + userspace. This ioctl is used by + nilfs_cleanerd daemon. + + NILFS_IOCTL_SYNC Make a checkpoint. This ioctl is used in + mkcp utility. + + NILFS_IOCTL_RESIZE Resize NILFS2 volume. This ioctl is used + by nilfs_resize utility. + + NILFS_IOCTL_SET_ALLOC_RANGE Define lower limit of segments in bytes and + upper limit of segments in bytes. This ioctl + is used by nilfs_resize utility. + NILFS2 usage ============ diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 22d89aa3721..f00bee144ad 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -547,7 +547,7 @@ Table 1-5: Kernel info in /proc sys See chapter 2 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) tty Info of tty drivers - uptime System uptime + uptime Wall clock since boot, combined idle time of all cpus version Kernel version video bttv info of video resources (2.4) vmallocinfo Show vmalloced areas @@ -767,6 +767,7 @@ The "Locked" indicates whether the mapping is locked in memory or not. MemTotal: 16344972 kB MemFree: 13634064 kB +MemAvailable: 14836172 kB Buffers: 3656 kB Cached: 1195708 kB SwapCached: 0 kB @@ -799,6 +800,14 @@ AnonHugePages: 49152 kB MemTotal: Total usable ram (i.e. physical ram minus a few reserved bits and the kernel binary code) MemFree: The sum of LowFree+HighFree +MemAvailable: An estimate of how much memory is available for starting new + applications, without swapping. Calculated from MemFree, + SReclaimable, the size of the file LRU lists, and the low + watermarks in each zone. + The estimate takes into account that the system needs some + page cache to function well, and that not all reclaimable + slab will be reclaimable, due to items being in use. The + impact of those factors will vary from system to system. Buffers: Relatively temporary storage for raw disk blocks shouldn't get tremendously large (20MB or so) Cached: in-memory cache for files read from the disk (the @@ -1377,8 +1386,8 @@ may allocate from based on an estimation of its current memory and swap use. For example, if a task is using all allowed memory, its badness score will be 1000. If it is using half of its allowed memory, its score will be 500. -There is an additional factor included in the badness score: root -processes are given 3% extra memory over other tasks. +There is an additional factor included in the badness score: the current memory +and swap usage is discounted by 3% for root processes. The amount of "allowed" memory depends on the context in which the oom killer was called. If it is due to the memory assigned to the allocating task's cpuset diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index a6619b7064b..b35a64b82f9 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.txt @@ -108,12 +108,12 @@ static DEVICE_ATTR(foo, S_IWUSR | S_IRUGO, show_foo, store_foo); is equivalent to doing: static struct device_attribute dev_attr_foo = { - .attr = { + .attr = { .name = "foo", .mode = S_IWUSR | S_IRUGO, - .show = show_foo, - .store = store_foo, }, + .show = show_foo, + .store = store_foo, }; diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index deb48b5fd88..c53784c119c 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -782,7 +782,7 @@ struct file_operations ---------------------- This describes how the VFS can manipulate an open file. As of kernel -3.5, the following members are defined: +3.12, the following members are defined: struct file_operations { struct module *owner; @@ -803,9 +803,6 @@ struct file_operations { int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *); - ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *); - ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *); ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); @@ -814,6 +811,7 @@ struct file_operations { ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int); int (*setlease)(struct file *, long arg, struct file_lock **); long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len); + int (*show_fdinfo)(struct seq_file *m, struct file *f); }; Again, all methods are called without any locks being held, unless @@ -864,12 +862,6 @@ otherwise noted. lock: called by the fcntl(2) system call for F_GETLK, F_SETLK, and F_SETLKW commands - readv: called by the readv(2) system call - - writev: called by the writev(2) system call - - sendfile: called by the sendfile(2) system call - get_unmapped_area: called by the mmap(2) system call check_flags: called by the fcntl(2) system call for F_SETFL command |