diff options
Diffstat (limited to 'Documentation/filesystems')
| -rw-r--r-- | Documentation/filesystems/Locking | 43 | ||||
| -rw-r--r-- | Documentation/filesystems/btrfs.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/ext3.txt | 7 | ||||
| -rw-r--r-- | Documentation/filesystems/ext4.txt | 9 | ||||
| -rw-r--r-- | Documentation/filesystems/f2fs.txt | 84 | ||||
| -rw-r--r-- | Documentation/filesystems/jfs.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/nfs/Exporting | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/nfs/pnfs.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/porting | 6 | ||||
| -rw-r--r-- | Documentation/filesystems/proc.txt | 7 | ||||
| -rw-r--r-- | Documentation/filesystems/qnx6.txt | 4 | ||||
| -rw-r--r-- | Documentation/filesystems/relay.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/sysfs-tagging.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/vfat.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/vfs.txt | 73 | ||||
| -rw-r--r-- | Documentation/filesystems/xfs.txt | 317 |
16 files changed, 387 insertions, 177 deletions
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 0706d32a61e6..fe7afe225381 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -11,10 +11,8 @@ be able to use diff(1). prototypes: int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); - int (*d_hash)(const struct dentry *, const struct inode *, - struct qstr *); - int (*d_compare)(const struct dentry *, const struct inode *, - const struct dentry *, const struct inode *, + int (*d_hash)(const struct dentry *, struct qstr *); + int (*d_compare)(const struct dentry *, const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(struct dentry *); void (*d_release)(struct dentry *); @@ -66,6 +64,7 @@ prototypes: int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode, int *opened); + int (*tmpfile) (struct inode *, struct dentry *, umode_t); locking rules: all may block @@ -93,6 +92,7 @@ removexattr: yes fiemap: no update_time: no atomic_open: yes +tmpfile: no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on victim. @@ -189,7 +189,7 @@ prototypes: loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); sector_t (*bmap)(struct address_space *, sector_t); - int (*invalidatepage) (struct page *, unsigned long); + void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, int); void (*freepage)(struct page *); int (*direct_IO)(int, struct kiocb *, const struct iovec *iov, @@ -310,8 +310,8 @@ filesystems and by the swapper. The latter will eventually go away. Please, keep it that way and don't breed new callers. ->invalidatepage() is called when the filesystem must attempt to drop -some or all of the buffers from the page when it is being truncated. It -returns zero on success. If ->invalidatepage is zero, the kernel uses +some or all of the buffers from the page when it is being truncated. It +returns zero on success. If ->invalidatepage is zero, the kernel uses block_invalidatepage() instead. ->releasepage() is called when the kernel is about to try to drop the @@ -344,25 +344,38 @@ prototypes: locking rules: - file_lock_lock may block + inode->i_lock may block fl_copy_lock: yes no fl_release_private: maybe no ----------------------- lock_manager_operations --------------------------- prototypes: int (*lm_compare_owner)(struct file_lock *, struct file_lock *); + unsigned long (*lm_owner_key)(struct file_lock *); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, struct file_lock *, int); void (*lm_break)(struct file_lock *); /* break_lease callback */ int (*lm_change)(struct file_lock **, int); locking rules: - file_lock_lock may block -lm_compare_owner: yes no -lm_notify: yes no -lm_grant: no no -lm_break: yes no -lm_change yes no + + inode->i_lock blocked_lock_lock may block +lm_compare_owner: yes[1] maybe no +lm_owner_key yes[1] yes no +lm_notify: yes yes no +lm_grant: no no no +lm_break: yes no no +lm_change yes no no + +[1]: ->lm_compare_owner and ->lm_owner_key are generally called with +*an* inode->i_lock held. It may not be the i_lock of the inode +associated with either file_lock argument! This is the case with deadlock +detection, since the code has to chase down the owners of locks that may +be entirely unrelated to the one on which the lock is being acquired. +For deadlock detection however, the blocked_lock_lock is also held. The +fact that these locks are held ensures that the file_locks do not +disappear out from under you while doing the comparison or generating an +owner key. --------------------------- buffer_head ----------------------------------- prototypes: @@ -414,7 +427,7 @@ prototypes: ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); - int (*readdir) (struct file *, void *, filldir_t); + int (*iterate) (struct file *, struct dir_context *); unsigned int (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt index b349d57b76ea..9dae59407437 100644 --- a/Documentation/filesystems/btrfs.txt +++ b/Documentation/filesystems/btrfs.txt @@ -87,7 +87,7 @@ Unless otherwise specified, all options default to off. device=<devicepath> Specify a device during mount so that ioctls on the control device - can be avoided. Especialy useful when trying to mount a multi-device + can be avoided. Especially useful when trying to mount a multi-device setup as root. May be specified multiple times for multiple devices. discard diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt index 293855e95000..7ed0d17d6721 100644 --- a/Documentation/filesystems/ext3.txt +++ b/Documentation/filesystems/ext3.txt @@ -26,11 +26,12 @@ journal=inum When a journal already exists, this option is ignored. Otherwise, it specifies the number of the inode which will represent the ext3 file system's journal file. +journal_path=path journal_dev=devnum When the external journal device's major/minor numbers - have changed, this option allows the user to specify + have changed, these options allow the user to specify the new journal location. The journal device is - identified through its new major/minor numbers encoded - in devnum. + identified through either its new major/minor numbers + encoded in devnum, or via a path to the device. norecovery Don't load the journal on mounting. Note that this forces noload mount of inconsistent filesystem, which can lead to diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index f7cbf574a875..919a3293aaa4 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -2,7 +2,7 @@ Ext4 Filesystem =============== -Ext4 is an an advanced level of the ext3 filesystem which incorporates +Ext4 is an advanced level of the ext3 filesystem which incorporates scalability and reliability enhancements for supporting large filesystems (64 bit) in keeping with increasing disk capacities and state-of-the-art feature requirements. @@ -144,11 +144,12 @@ journal_async_commit Commit block can be written to disk without waiting mount the device. This will enable 'journal_checksum' internally. +journal_path=path journal_dev=devnum When the external journal device's major/minor numbers - have changed, this option allows the user to specify + have changed, these options allow the user to specify the new journal location. The journal device is - identified through its new major/minor numbers encoded - in devnum. + identified through either its new major/minor numbers + encoded in devnum, or via a path to the device. norecovery Don't load the journal on mounting. Note that noload if the filesystem was not unmounted cleanly, diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index bd3c56c67380..3cd27bed6349 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -18,8 +18,8 @@ according to its internal geometry or flash memory management scheme, namely FTL F2FS and its tools support various parameters not only for configuring on-disk layout, but also for selecting allocation and cleaning algorithms. -The file system formatting tool, "mkfs.f2fs", is available from the following -git tree: +The following git tree provides the file system formatting tool (mkfs.f2fs), +a consistency checking tool (fsck.f2fs), and a debugging tool (dump.f2fs). >> git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git For reporting bugs and sending patches, please use the following mailing list: @@ -98,8 +98,13 @@ Cleaning Overhead MOUNT OPTIONS ================================================================================ -background_gc_off Turn off cleaning operations, namely garbage collection, - triggered in background when I/O subsystem is idle. +background_gc=%s Turn on/off cleaning operations, namely garbage + collection, triggered in background when I/O subsystem is + idle. If background_gc=on, it will turn on the garbage + collection and if background_gc=off, garbage collection + will be truned off. + Default value for this option is on. So garbage + collection is on by default. disable_roll_forward Disable the roll-forward recovery routine discard Issue discard/TRIM commands when a segment is cleaned. no_heap Disable heap-style segment allocation which finds free @@ -128,6 +133,38 @@ f2fs. Each file shows the whole f2fs information. - current memory footprint consumed by f2fs. ================================================================================ +SYSFS ENTRIES +================================================================================ + +Information about mounted f2f2 file systems can be found in +/sys/fs/f2fs. Each mounted filesystem will have a directory in +/sys/fs/f2fs based on its device name (i.e., /sys/fs/f2fs/sda). +The files in each per-device directory are shown in table below. + +Files in /sys/fs/f2fs/<devname> +(see also Documentation/ABI/testing/sysfs-fs-f2fs) +.............................................................................. + File Content + + gc_max_sleep_time This tuning parameter controls the maximum sleep + time for the garbage collection thread. Time is + in milliseconds. + + gc_min_sleep_time This tuning parameter controls the minimum sleep + time for the garbage collection thread. Time is + in milliseconds. + + gc_no_gc_sleep_time This tuning parameter controls the default sleep + time for the garbage collection thread. Time is + in milliseconds. + + gc_idle This parameter controls the selection of victim + policy for garbage collection. Setting gc_idle = 0 + (default) will disable this option. Setting + gc_idle = 1 will select the Cost Benefit approach + & setting gc_idle = 2 will select the greedy aproach. + +================================================================================ USAGE ================================================================================ @@ -144,8 +181,12 @@ USAGE # mkfs.f2fs -l label /dev/block_device # mount -t f2fs /dev/block_device /mnt/f2fs -Format options --------------- +mkfs.f2fs +--------- +The mkfs.f2fs is for the use of formatting a partition as the f2fs filesystem, +which builds a basic on-disk layout. + +The options consist of: -l [label] : Give a volume label, up to 512 unicode name. -a [0 or 1] : Split start location of each area for heap-based allocation. 1 is set by default, which performs this. @@ -159,6 +200,37 @@ Format options -t [0 or 1] : Disable discard command or not. 1 is set by default, which conducts discard. +fsck.f2fs +--------- +The fsck.f2fs is a tool to check the consistency of an f2fs-formatted +partition, which examines whether the filesystem metadata and user-made data +are cross-referenced correctly or not. +Note that, initial version of the tool does not fix any inconsistency. + +The options consist of: + -d debug level [default:0] + +dump.f2fs +--------- +The dump.f2fs shows the information of specific inode and dumps SSA and SIT to +file. Each file is dump_ssa and dump_sit. + +The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem. +It shows on-disk inode information reconized by a given inode number, and is +able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and +./dump_sit respectively. + +The options consist of: + -d debug level [default:0] + -i inode no (hex) + -s [SIT dump segno from #1~#2 (decimal), for all 0~-1] + -a [SSA dump segno from #1~#2 (decimal), for all 0~-1] + +Examples: +# dump.f2fs -i [ino] /dev/sdx +# dump.f2fs -s 0~-1 /dev/sdx (SIT dump) +# dump.f2fs -a 0~-1 /dev/sdx (SSA dump) + ================================================================================ DESIGN ================================================================================ diff --git a/Documentation/filesystems/jfs.txt b/Documentation/filesystems/jfs.txt index f7433355394a..41fd757997b3 100644 --- a/Documentation/filesystems/jfs.txt +++ b/Documentation/filesystems/jfs.txt @@ -42,7 +42,7 @@ nodiscard(*) block device when blocks are freed. This is useful for SSD devices and sparse/thinly-provisioned LUNs. The FITRIM ioctl command is also available together with the nodiscard option. The value of minlen specifies the minimum blockcount, when - a TRIM command to the block device is considered usefull. + a TRIM command to the block device is considered useful. When no value is given to the discard option, it defaults to 64 blocks, which means 256KiB in JFS. The minlen value of discard overrides the minlen value given diff --git a/Documentation/filesystems/nfs/Exporting b/Documentation/filesystems/nfs/Exporting index 09994c247289..e543b1a619cc 100644 --- a/Documentation/filesystems/nfs/Exporting +++ b/Documentation/filesystems/nfs/Exporting @@ -93,7 +93,7 @@ For a filesystem to be exportable it must: 2/ make sure that d_splice_alias is used rather than d_add when ->lookup finds an inode for a given parent and name. - If inode is NULL, d_splice_alias(inode, dentry) is eqivalent to + If inode is NULL, d_splice_alias(inode, dentry) is equivalent to d_add(dentry, inode), NULL diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt index 52ae07f5f578..adc81a35fe2d 100644 --- a/Documentation/filesystems/nfs/pnfs.txt +++ b/Documentation/filesystems/nfs/pnfs.txt @@ -12,7 +12,7 @@ struct pnfs_layout_hdr ---------------------- The on-the-wire command LAYOUTGET corresponds to struct pnfs_layout_segment, usually referred to by the variable name lseg. -Each nfs_inode may hold a pointer to a cache of of these layout +Each nfs_inode may hold a pointer to a cache of these layout segments in nfsi->layout, of type struct pnfs_layout_hdr. We reference the header for the inode pointing to it, across each diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 4db22f6491e0..206a1bdc7321 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -445,3 +445,9 @@ object doesn't exist. It's remote/distributed ones that might care... [mandatory] FS_REVAL_DOT is gone; if you used to have it, add ->d_weak_revalidate() in your dentry operations instead. +-- +[mandatory] + vfs_readdir() is gone; switch to iterate_dir() instead +-- +[mandatory] + ->readdir() is gone now; switch to ->iterate() diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index fd8d0d594fc7..fcc22c982a25 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -473,7 +473,8 @@ This file is only present if the CONFIG_MMU kernel configuration option is enabled. The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG -bits on both physical and virtual pages associated with a process. +bits on both physical and virtual pages associated with a process, and the +soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details). To clear the bits for all the pages associated with the process > echo 1 > /proc/PID/clear_refs @@ -482,6 +483,10 @@ To clear the bits for the anonymous pages associated with the process To clear the bits for the file mapped pages associated with the process > echo 3 > /proc/PID/clear_refs + +To clear the soft-dirty bit + > echo 4 > /proc/PID/clear_refs + Any other value written to /proc/PID/clear_refs will have no effect. The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags diff --git a/Documentation/filesystems/qnx6.txt b/Documentation/filesystems/qnx6.txt index e59f2f09f56e..408679789136 100644 --- a/Documentation/filesystems/qnx6.txt +++ b/Documentation/filesystems/qnx6.txt @@ -148,8 +148,8 @@ smaller than addressing space in the bitmap. Bitmap system area ------------------ -The bitmap itself is devided into three parts. -First the system area, that is split into two halfs. +The bitmap itself is divided into three parts. +First the system area, that is split into two halves. Then userspace. The requirement for a static, fixed preallocated system area comes from how diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt index 510b722667ac..33e2f3694733 100644 --- a/Documentation/filesystems/relay.txt +++ b/Documentation/filesystems/relay.txt @@ -31,7 +31,7 @@ Semantics Each relay channel has one buffer per CPU, each buffer has one or more sub-buffers. Messages are written to the first sub-buffer until it is -too full to contain a new message, in which case it it is written to +too full to contain a new message, in which case it is written to the next (if available). Messages are never split across sub-buffers. At this point, userspace can be notified so it empties the first sub-buffer, while the kernel continues writing to the next. diff --git a/Documentation/filesystems/sysfs-tagging.txt b/Documentation/filesystems/sysfs-tagging.txt index caaaf1266d8f..eb843e49c5a3 100644 --- a/Documentation/filesystems/sysfs-tagging.txt +++ b/Documentation/filesystems/sysfs-tagging.txt @@ -24,7 +24,7 @@ flag between KOBJ_NS_TYPE_NONE and KOBJ_NS_TYPES, and s_ns will point to the namespace to which it belongs. Each sysfs superblock's sysfs_super_info contains an array void -*ns[KOBJ_NS_TYPES]. When a a task in a tagging namespace +*ns[KOBJ_NS_TYPES]. When a task in a tagging namespace kobj_nstype first mounts sysfs, a new superblock is created. It will be differentiated from other sysfs mounts by having its s_fs_info->ns[kobj_nstype] set to the new namespace. Note that diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt index 4a93e98b290a..aa1f459fa6cf 100644 --- a/Documentation/filesystems/vfat.txt +++ b/Documentation/filesystems/vfat.txt @@ -307,7 +307,7 @@ the following: <proceeding files...> <slot #3, id = 0x43, characters = "h is long"> - <slot #2, id = 0x02, characters = "xtension whic"> + <slot #2, id = 0x02, characters = "xtension which"> <slot #1, id = 0x01, characters = "My Big File.E"> <directory entry, name = "MYBIGFIL.EXT"> diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index bc4b06b3160a..f93a88250a44 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -360,6 +360,8 @@ struct inode_operations { int (*removexattr) (struct dentry *, const char *); void (*update_time)(struct inode *, struct timespec *, int); int (*atomic_open)(struct inode *, struct dentry *, + int (*tmpfile) (struct inode *, struct dentry *, umode_t); +} ____cacheline_aligned; struct file *, unsigned open_flag, umode_t create_mode, int *opened); }; @@ -472,6 +474,9 @@ otherwise noted. component is negative or needs lookup. Cached positive dentries are still handled by f_op->open(). + tmpfile: called in the end of O_TMPFILE open(). Optional, equivalent to + atomically creating, opening and unlinking a file in given directory. + The Address Space Object ======================== @@ -549,12 +554,11 @@ struct address_space_operations ------------------------------- This describes how the VFS can manipulate mapping of a file to page cache in -your filesystem. As of kernel 2.6.22, the following members are defined: +your filesystem. The following members are defined: struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); - int (*sync_page)(struct page *); int (*writepages)(struct address_space *, struct writeback_control *); int (*set_page_dirty)(struct page *page); int (*readpages)(struct file *filp, struct address_space *mapping, @@ -566,7 +570,7 @@ struct address_space_operations { loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); sector_t (*bmap)(struct address_space *, sector_t); - int (*invalidatepage) (struct page *, unsigned long); + void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, int); void (*freepage)(struct page *); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, @@ -576,6 +580,9 @@ struct address_space_operations { /* migrate the contents of a page to the specified target */ int (*migratepage) (struct page *, struct page *); int (*launder_page) (struct page *); + int (*is_partially_uptodate) (struct page *, read_descriptor_t *, + unsigned long); + void (*is_dirty_writeback) (struct page *, bool *, bool *); int (*error_remove_page) (struct mapping *mapping, struct page *page); int (*swap_activate)(struct file *); int (*swap_deactivate)(struct file *); @@ -607,13 +614,6 @@ struct address_space_operations { In this case, the page will be relocated, relocked and if that all succeeds, ->readpage will be called again. - sync_page: called by the VM to notify the backing store to perform all - queued I/O operations for a page. I/O operations for other pages - associated with this address_space object may also be performed. - - This function is optional and is called only for pages with - PG_Writeback set while waiting for the writeback to complete. - writepages: called by the VM to write out pages associated with the address_space object. If wbc->sync_mode is WBC_SYNC_ALL, then the writeback_control will specify a range of pages that must be @@ -685,14 +685,14 @@ struct address_space_operations { invalidatepage: If a page has PagePrivate set, then invalidatepage will be called when part or all of the page is to be removed from the address space. This generally corresponds to either a - truncation or a complete invalidation of the address space - (in the latter case 'offset' will always be 0). - Any private data associated with the page should be updated - to reflect this truncation. If offset is 0, then - the private data should be released, because the page - must be able to be completely discarded. This may be done by - calling the ->releasepage function, but in this case the - release MUST succeed. + truncation, punch hole or a complete invalidation of the address + space (in the latter case 'offset' will always be 0 and 'length' + will be PAGE_CACHE_SIZE). Any private data associated with the page + should be updated to reflect this truncation. If offset is 0 and + length is PAGE_CACHE_SIZE, then the private data should be released, + because the page must be able to be completely discarded. This may + be done by calling the ->releasepage function, but in this case the + release MUST succeed. releasepage: releasepage is called on PagePrivate pages to indicate that the page should be freed if possible. ->releasepage @@ -742,6 +742,20 @@ struct address_space_operations { prevent redirtying the page, it is kept locked during the whole operation. + is_partially_uptodate: Called by the VM when reading a file through the + pagecache when the underlying blocksize != pagesize. If the required + block is up to date then the read can complete without needing the IO + to bring the whole page up to date. + + is_dirty_writeback: Called by the VM when attempting to reclaim a page. + The VM uses dirty and writeback information to determine if it needs + to stall to allow flushers a chance to complete some IO. Ordinarily + it can use PageDirty and PageWriteback but some filesystems have + more complex state (unstable pages in NFS prevent reclaim) or + do not set those flags due to locking problems (jbd). This callback + allows a filesystem to indicate to the VM if a page should be + treated as dirty or writeback for the purposes of stalling. + error_remove_page: normally set to generic_error_remove_page if truncation is ok for this address space. Used for memory failure handling. Setting this implies you deal with pages going away under you, @@ -777,7 +791,7 @@ struct file_operations { ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); - int (*readdir) (struct file *, void *, filldir_t); + int (*iterate) (struct file *, struct dir_context *); unsigned int (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); @@ -815,7 +829,7 @@ otherwise noted. aio_write: called by io_submit(2) and other asynchronous I/O operations - readdir: called when the VFS needs to read the directory contents + iterate: called when the VFS needs to read the directory contents poll: called by the VFS when a process wants to check if there is activity on this file and (optionally) go to sleep until there @@ -901,10 +915,8 @@ defined: struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); - int (*d_hash)(const struct dentry *, const struct inode *, - struct qstr *); - int (*d_compare)(const struct dentry *, const struct inode *, - const struct dentry *, const struct inode *, + int (*d_hash)(const struct dentry *, struct qstr *); + int (*d_compare)(const struct dentry *, const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); void (*d_release)(struct dentry *); @@ -949,25 +961,24 @@ struct dentry_operations { d_hash: called when the VFS adds a dentry to the hash table. The first dentry passed to d_hash is the parent directory that the name is - to be hashed into. The inode is the dentry's inode. + to be hashed into. Same locking and synchronisation rules as d_compare regarding what is safe to dereference etc. d_compare: called to compare a dentry name with a given name. The first dentry is the parent of the dentry to be compared, the second is - the parent's inode, then the dentry and inode (may be NULL) of the - child dentry. len and name string are properties of the dentry to be - compared. qstr is the name to compare it with. + the child dentry. len and name string are properties of the dentry + to be compared. qstr is the name to compare it with. Must be constant and idempotent, and should not take locks if - possible, and should not or store into the dentry or inodes. - Should not dereference pointers outside the dentry or inodes without + possible, and should not or store into the dentry. + Should not dereference pointers outside the dentry without lots of care (eg. d_parent, d_inode, d_name should not be used). However, our vfsmount is pinned, and RCU held, so the dentries and inodes won't disappear, neither will our sb or filesystem module. - ->i_sb and ->d_sb may be used. + ->d_sb may be used. It is a tricky calling convention because it needs to be called under "rcu-walk", ie. without any locks or references on things. diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt index 83577f0232a0..5be51fd888bd 100644 --- a/Documentation/filesystems/xfs.txt +++ b/Documentation/filesystems/xfs.txt @@ -18,6 +18,8 @@ Mount Options ============= When mounting an XFS filesystem, the following options are accepted. +For boolean mount options, the names with the (*) suffix is the +default behaviour. allocsize=size Sets the buffered I/O end-of-file preallocation size when @@ -25,97 +27,128 @@ When mounting an XFS filesystem, the following options are accepted. Valid values for this option are page size (typically 4KiB) through to 1GiB, inclusive, in power-of-2 increments. - attr2/noattr2 - The options enable/disable (default is disabled for backward - compatibility on-disk) an "opportunistic" improvement to be - made in the way inline extended attributes are stored on-disk. - When the new form is used for the first time (by setting or - removing extended attributes) the on-disk superblock feature - bit field will be updated to reflect this format being in use. + The default behaviour is for dynamic end-of-file + preallocation size, which uses a set of heuristics to + optimise the preallocation size based on the current + allocation patterns within the file and the access patterns + to the file. Specifying a fixed allocsize value turns off + the dynamic behaviour. + + attr2 + noattr2 + The options enable/disable an "opportunistic" improvement to + be made in the way inline extended attributes are stored + on-disk. When the new form is used for the first time when + attr2 is selected (either when setting or removing extended + attributes) the on-disk superblock feature bit field will be + updated to reflect this format being in use. + + The default behaviour is determined by the on-disk feature + bit indicating that attr2 behaviour is active. If either + mount option it set, then that becomes the new default used + by the filesystem. CRC enabled filesystems always use the attr2 format, and so will reject the noattr2 mount option if it is set. - barrier - Enables the use of block layer write barriers for writes into - the journal and unwritten extent conversion. This allows for - drive level write caching to be enabled, for devices that - support write barriers. + barrier (*) + nobarrier + Enables/disables the use of block layer write barriers for + writes into the journal and for data integrity operations. + This allows for drive level write caching to be enabled, for + devices that support write barriers. discard - Issue command 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 performance - impact. - - dmapi - Enable the DMAPI (Data Management API) event callouts. - Use with the "mtpt" option. - - grpid/bsdgroups and nogrpid/sysvgroups - These options define what group ID a newly created file gets. - When grpid is set, it takes the group ID of the directory in - which it is created; otherwise (the default) it takes the fsgid - of the current process, unless the directory has the setgid bit - set, in which case it takes the gid from the parent directory, - and also gets the setgid bit set if it is a directory itself. - - ihashsize=value - In memory inode hashes have been removed, so this option has - no function as of August 2007. Option is deprecated. - - ikeep/noikeep - When ikeep is specified, XFS does not delete empty inode clusters - and keeps them around on disk. ikeep is the traditional XFS - behaviour. When noikeep is specified, empty inode clusters - are returned to the free space pool. The default is noikeep for - non-DMAPI mounts, while ikeep is the default when DMAPI is in use. - - inode64 - Indicates that XFS is allowed to create inodes at any location - in the filesystem, including those which will result in inode - numbers occupying more than 32 bits of significance. This is - the default allocation option. Applications which do not handle - inode numbers bigger than 32 bits, should use inode32 option. + nodiscard (*) + Enable/disable the issuing of 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 performance impact. + + Note: It is currently recommended that you use the fstrim + application to discard unused blocks rather than the discard + mount option because the performance impact of this option + is quite severe. + + grpid/bsdgroups + nogrpid/sysvgroups (*) + These options define what group ID a newly created file + gets. When grpid is set, it takes the group ID of the + directory in which it is created; otherwise it takes the + fsgid of the current process, unless the directory has the + setgid bit set, in which case it takes the gid from the + parent directory, and also gets the setgid bit set if it is + a directory itself. + + filestreams + Make the data allocator use the filestreams allocation mode + across the entire filesystem rather than just on directories + configured to use it. + + ikeep + noikeep (*) + When ikeep is specified, XFS does not delete empty inode + clusters and keeps them around on disk. When noikeep is + specified, empty inode clusters are returned to the free + space pool. inode32 - Indicates that XFS is limited to create inodes at locations which - will not result in inode numbers with more than 32 bits of - significance. This is provided for backwards compatibility, since - 64 bits inode numbers might cause problems for some applications - that cannot handle large inode numbers. - - largeio/nolargeio + inode64 (*) + When inode32 is specified, it indicates that XFS limits + inode creation to locations which will not result in inode + numbers with more than 32 bits of significance. + + When inode64 is specified, it indicates that XFS is allowed + to create inodes at any location in the filesystem, + including those which will result in inode numbers occupying + more than 32 bits of significance. + + inode32 is provided for backwards compatibility with older + systems and applications, since 64 bits inode numbers might + cause problems for some applications that cannot handle + large inode numbers. If applications are in use which do + not handle inode numbers bigger than 32 bits, the inode32 + option should be specified. + + + largeio + nolargeio (*) If "nolargeio" is specified, the optimal I/O reported in - st_blksize by stat(2) will be as small as possible to allow user - applications to avoid inefficient read/modify/write I/O. - If "largeio" specified, a filesystem that has a "swidth" specified - will return the "swidth" value (in bytes) in st_blksize. If the - filesystem does not have a "swidth" specified but does specify - an "allocsize" then "allocsize" (in bytes) will be returned - instead. - If neither of these two options are specified, then filesystem - will behave as if "nolargeio" was specified. + st_blksize by stat(2) will be as small as possible to allow + user applications to avoid inefficient read/modify/write + I/O. This is typically the page size of the machine, as + this is the granularity of the page cache. + + If "largeio" specified, a filesystem that was created with a + "swidth" specified will return the "swidth" value (in bytes) + in st_blksize. If the filesystem does not have a "swidth" + specified but does specify an "allocsize" then "allocsize" + (in bytes) will be returned instead. Otherwise the behaviour + is the same as if "nolargeio" was specified. logbufs=value - Set the number of in-memory log buffers. Valid numbers range - from 2-8 inclusive. - The default value is 8 buffers for filesystems with a - blocksize of 64KiB, 4 buffers for filesystems with a blocksize - of 32KiB, 3 buffers for filesystems with a blocksize of 16KiB - and 2 buffers for all other configurations. Increasing the - number of buffers may increase performance on some workloads - at the cost of the memory used for the additional log buffers - and their associated control structures. + Set the number of in-memory log buffers. Valid numbers + range from 2-8 inclusive. + + The default value is 8 buffers. + + If the memory cost of 8 log buffers is too high on small + systems, then it may be reduced at some cost to performance + on metadata intensive workloads. The logbsize option below + controls the size of each buffer and so is also relevant to + this case. logbsize=value - Set the size of each in-memory log buffer. - Size may be specified in bytes, or in kilobytes with a "k" suffix. - Valid sizes for version 1 and version 2 logs are 16384 (16k) and - 32768 (32k). Valid sizes for version 2 logs also include - 65536 (64k), 131072 (128k) and 262144 (256k). - The default value for machines with more than 32MiB of memory - is 32768, machines with less memory use 16384 by default. + Set the size of each in-memory log buffer. The size may be + specified in bytes, or in kilobytes with a "k" suffix. + Valid sizes for version 1 and version 2 logs are 16384 (16k) + and 32768 (32k). Valid sizes for version 2 logs also + include 65536 (64k), 131072 (128k) and 262144 (256k). The + logbsize must be an integer multiple of the log + stripe unit configured at mkfs time. + + The default value for for version 1 logs is 32768, while the + default value for version 2 logs is MAX(32768, log_sunit). logdev=device and rtdev=device Use an external log (metadata journal) and/or real-time device. @@ -124,16 +157,11 @@ When mounting an XFS filesystem, the following options are accepted. optional, and the log section can be separate from the data section or contained within it. - mtpt=mountpoint - Use with the "dmapi" option. The value specified here will be - included in the DMAPI mount event, and should be the path of - the actual mountpoint that is used. - noalign - Data allocations will not be aligned at stripe unit boundaries. - - noatime - Access timestamps are not updated when a file is read. + Data allocations will not be aligned at stripe unit + boundaries. This is only relevant to filesystems created + with non-zero data alignment parameters (sunit, swidth) by + mkfs. norecovery The filesystem will be mounted without running log recovery. @@ -144,8 +172,14 @@ When mounting an XFS filesystem, the following options are accepted. the mount will fail. nouuid - Don't check for double mounted file systems using the file system uuid. - This is useful to mount LVM snapshot volumes. + Don't check for double mounted file systems using the file + system uuid. This is useful to mount LVM snapshot volumes, + and often used in combination with "norecovery" for mounting + read-only snapshots. + + noquota + Forcibly turns off all quota accounting and enforcement + within the filesystem. uquota/usrquota/uqnoenforce/quota User disk quota accounting enabled, and limits (optionally) @@ -160,24 +194,64 @@ When mounting an XFS filesystem, the following options are accepted. enforced. Refer to xfs_quota(8) for further details. sunit=value and swidth=value - Used to specify the stripe unit and width for a RAID device or - a stripe volume. "value" must be specified in 512-byte block - units. - If this option is not specified and the filesystem was made on - a stripe volume or the stripe width or unit were specified for - the RAID device at mkfs time, then the mount system call will - restore the value from the superblock. For filesystems that - are made directly on RAID devices, these options can be used - to override the information in the superblock if the underlying - disk layout changes after the filesystem has been created. - The "swidth" option is required if the "sunit" option has been - specified, and must be a multiple of the "sunit" value. + Used to specify the stripe unit and width for a RAID device + or a stripe volume. "value" must be specified in 512-byte + block units. These options are only relevant to filesystems + that were created with non-zero data alignment parameters. + + The sunit and swidth parameters specified must be compatible + with the existing filesystem alignment characteristics. In + general, that means the only valid changes to sunit are + increasing it by a power-of-2 multiple. Valid swidth values + are any integer multiple of a valid sunit value. + + Typically the only time these mount options are necessary if + after an underlying RAID device has had it's geometry + modified, such as adding a new disk to a RAID5 lun and + reshaping it. swalloc Data allocations will be rounded up to stripe width boundaries when the current end of file is being extended and the file size is larger than the stripe width size. + wsync + When specified, all filesystem namespace operations are + executed synchronously. This ensures that when the namespace + operation (create, unlink, etc) completes, the change to the + namespace is on stable storage. This is useful in HA setups + where failover must not result in clients seeing + inconsistent namespace presentation during or after a + failover event. + + +Deprecated Mount Options +======================== + + delaylog/nodelaylog + Delayed logging is the only logging method that XFS supports + now, so these mount options are now ignored. + + Due for removal in 3.12. + + ihashsize=value + In memory inode hashes have been removed, so this option has + no function as of August 2007. Option is deprecated. + + Due for removal in 3.12. + + irixsgid + This behaviour is now controlled by a sysctl, so the mount + option is ignored. + + Due for removal in 3.12. + + osyncisdsync + osyncisosync + O_SYNC and O_DSYNC are fully supported, so there is no need + for these options any more. + + Due for removal in 3.12. sysctls ======= @@ -189,15 +263,20 @@ The following sysctls are available for the XFS filesystem: in /proc/fs/xfs/stat. It then immediately resets to "0". fs.xfs.xfssyncd_centisecs (Min: 100 Default: 3000 Max: 720000) - The interval at which the xfssyncd thread flushes metadata - out to disk. This thread will flush log activity out, and - do some processing on unlinked inodes. + The interval at which the filesystem flushes metadata + out to disk and runs internal cache cleanup routines. - fs.xfs.xfsbufd_centisecs (Min: 50 Default: 100 Max: 3000) - The interval at which xfsbufd scans the dirty metadata buffers list. + fs.xfs.filestream_centisecs (Min: 1 Default: 3000 Max: 360000) + The interval at which the filesystem ages filestreams cache + references and returns timed-out AGs back to the free stream + pool. - fs.xfs.age_buffer_centisecs (Min: 100 Default: 1500 Max: 720000) - The age at which xfsbufd flushes dirty metadata buffers to disk. + fs.xfs.speculative_prealloc_lifetime + (Units: seconds Min: 1 Default: 300 Max: 86400) + The interval at which the background scanning for inodes + with unused speculative preallocation runs. The scan + removes unused preallocation from clean inodes and releases + the unused space back to the free pool. fs.xfs.error_level (Min: 0 Default: 3 Max: 11) A volume knob for error reporting when internal errors occur. @@ -254,9 +333,31 @@ The following sysctls are available for the XFS filesystem: by the xfs_io(8) chattr command on a directory to be inherited by files in that directory. + fs.xfs.inherit_nodefrag (Min: 0 Default: 1 Max: 1) + Setting this to "1" will cause the "nodefrag" flag set + by the xfs_io(8) chattr command on a directory to be + inherited by files in that directory. + fs.xfs.rotorstep (Min: 1 Default: 1 Max: 256) In "inode32" allocation mode, this option determines how many files the allocator attempts to allocate in the same allocation group before moving to the next allocation group. The intent is to control the rate at which the allocator moves between allocation groups when allocating extents for new files. + +Deprecated Sysctls +================== + + fs.xfs.xfsbufd_centisecs (Min: 50 Default: 100 Max: 3000) + Dirty metadata is now tracked by the log subsystem and + flushing is driven by log space and idling demands. The + xfsbufd no longer exists, so this syctl does nothing. + + Due for removal in 3.14. + + fs.xfs.age_buffer_centisecs (Min: 100 Default: 1500 Max: 720000) + Dirty metadata is now tracked by the log subsystem and + flushing is driven by log space and idling demands. The + xfsbufd no longer exists, so this syctl does nothing. + + Due for removal in 3.14. |