linux/fs/nilfs2/file.c

156 lines
3.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0+
/*
* NILFS regular file handling primitives including fsync().
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
* Written by Amagai Yoshiji and Ryusuke Konishi.
*/
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/writeback.h>
#include "nilfs.h"
#include "segment.h"
int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
/*
* Called from fsync() system call
* This is the only entry point that can catch write and synch
* timing for both data blocks and intermediate blocks.
*
* This function should be implemented when the writeback function
* will be implemented.
*/
struct the_nilfs *nilfs;
struct inode *inode = file->f_mapping->host;
nilfs2: avoid duplicate segment construction for fsync() This patch removes filemap_write_and_wait_range() from nilfs_sync_file(), because it triggers a data segment construction by calling nilfs_writepages() with WB_SYNC_ALL. A data segment construction does not remove the inode from the i_dirty list and it does not clear the NILFS_I_DIRTY flag. Therefore nilfs_inode_dirty() still returns true, which leads to an unnecessary duplicate segment construction in nilfs_sync_file(). A call to filemap_write_and_wait_range() is not needed, because NILFS2 does not rely on the generic writeback mechanisms. Instead it implements its own mechanism to collect all dirty pages and write them into segments. It is more efficient to initiate the segment construction directly in nilfs_sync_file() without the detour over filemap_write_and_wait_range(). Additionally the lock of i_mutex is not needed, because all code blocks that are protected by i_mutex are also protected by a NILFS transaction: Function i_mutex nilfs_transaction ------------------------------------------------------ nilfs_ioctl_setflags: yes yes nilfs_fiemap: yes no nilfs_write_begin: yes yes nilfs_write_end: yes yes nilfs_lookup: yes no nilfs_create: yes yes nilfs_link: yes yes nilfs_mknod: yes yes nilfs_symlink: yes yes nilfs_mkdir: yes yes nilfs_unlink: yes yes nilfs_rmdir: yes yes nilfs_rename: yes yes nilfs_setattr: yes yes For nilfs_lookup() i_mutex is held for the parent directory, to protect it from modification. The segment construction does not modify directory inodes, so no lock is needed. nilfs_fiemap() reads the block layout on the disk, by using nilfs_bmap_lookup_contig(). This is already protected by bmap->b_sem. Signed-off-by: Andreas Rohner <andreas.rohner@gmx.net> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-10 23:54:29 +00:00
int err = 0;
if (nilfs_inode_dirty(inode)) {
if (datasync)
err = nilfs_construct_dsync_segment(inode->i_sb, inode,
nilfs2: avoid duplicate segment construction for fsync() This patch removes filemap_write_and_wait_range() from nilfs_sync_file(), because it triggers a data segment construction by calling nilfs_writepages() with WB_SYNC_ALL. A data segment construction does not remove the inode from the i_dirty list and it does not clear the NILFS_I_DIRTY flag. Therefore nilfs_inode_dirty() still returns true, which leads to an unnecessary duplicate segment construction in nilfs_sync_file(). A call to filemap_write_and_wait_range() is not needed, because NILFS2 does not rely on the generic writeback mechanisms. Instead it implements its own mechanism to collect all dirty pages and write them into segments. It is more efficient to initiate the segment construction directly in nilfs_sync_file() without the detour over filemap_write_and_wait_range(). Additionally the lock of i_mutex is not needed, because all code blocks that are protected by i_mutex are also protected by a NILFS transaction: Function i_mutex nilfs_transaction ------------------------------------------------------ nilfs_ioctl_setflags: yes yes nilfs_fiemap: yes no nilfs_write_begin: yes yes nilfs_write_end: yes yes nilfs_lookup: yes no nilfs_create: yes yes nilfs_link: yes yes nilfs_mknod: yes yes nilfs_symlink: yes yes nilfs_mkdir: yes yes nilfs_unlink: yes yes nilfs_rmdir: yes yes nilfs_rename: yes yes nilfs_setattr: yes yes For nilfs_lookup() i_mutex is held for the parent directory, to protect it from modification. The segment construction does not modify directory inodes, so no lock is needed. nilfs_fiemap() reads the block layout on the disk, by using nilfs_bmap_lookup_contig(). This is already protected by bmap->b_sem. Signed-off-by: Andreas Rohner <andreas.rohner@gmx.net> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-10 23:54:29 +00:00
start, end);
else
err = nilfs_construct_segment(inode->i_sb);
}
nilfs = inode->i_sb->s_fs_info;
if (!err)
err = nilfs_flush_device(nilfs);
return err;
}
static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct nilfs_transaction_info ti;
int ret = 0;
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
return VM_FAULT_SIGBUS; /* -ENOSPC */
sb_start_pagefault(inode->i_sb);
lock_page(page);
if (page->mapping != inode->i_mapping ||
page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
unlock_page(page);
ret = -EFAULT; /* make the VM retry the fault */
goto out;
}
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto mapped;
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
int fully_mapped = 1;
bh = head = page_buffers(page);
do {
if (!buffer_mapped(bh)) {
fully_mapped = 0;
break;
}
} while (bh = bh->b_this_page, bh != head);
if (fully_mapped) {
SetPageMappedToDisk(page);
goto mapped;
}
}
unlock_page(page);
/*
* fill hole blocks
*/
ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
/* never returns -ENOMEM, but may return -ENOSPC */
if (unlikely(ret))
goto out;
file_update_time(vma->vm_file);
ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
if (ret) {
nilfs_transaction_abort(inode->i_sb);
goto out;
}
nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
nilfs_transaction_commit(inode->i_sb);
mapped:
mm: only enforce stable page writes if the backing device requires it Create a helper function to check if a backing device requires stable page writes and, if so, performs the necessary wait. Then, make it so that all points in the memory manager that handle making pages writable use the helper function. This should provide stable page write support to most filesystems, while eliminating unnecessary waiting for devices that don't require the feature. Before this patchset, all filesystems would block, regardless of whether or not it was necessary. ext3 would wait, but still generate occasional checksum errors. The network filesystems were left to do their own thing, so they'd wait too. After this patchset, all the disk filesystems except ext3 and btrfs will wait only if the hardware requires it. ext3 (if necessary) snapshots pages instead of blocking, and btrfs provides its own bdi so the mm will never wait. Network filesystems haven't been touched, so either they provide their own stable page guarantees or they don't block at all. The blocking behavior is back to what it was before 3.0 if you don't have a disk requiring stable page writes. Here's the result of using dbench to test latency on ext2: 3.8.0-rc3: Operation Count AvgLat MaxLat ---------------------------------------- WriteX 109347 0.028 59.817 ReadX 347180 0.004 3.391 Flush 15514 29.828 287.283 Throughput 57.429 MB/sec 4 clients 4 procs max_latency=287.290 ms 3.8.0-rc3 + patches: WriteX 105556 0.029 4.273 ReadX 335004 0.005 4.112 Flush 14982 30.540 298.634 Throughput 55.4496 MB/sec 4 clients 4 procs max_latency=298.650 ms As you can see, the maximum write latency drops considerably with this patch enabled. The other filesystems (ext3/ext4/xfs/btrfs) behave similarly, but see the cover letter for those results. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Acked-by: Steven Whitehouse <swhiteho@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 00:42:51 +00:00
wait_for_stable_page(page);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}
static const struct vm_operations_struct nilfs_file_vm_ops = {
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = nilfs_page_mkwrite,
};
static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
file_accessed(file);
vma->vm_ops = &nilfs_file_vm_ops;
return 0;
}
/*
* We have mostly NULL's here: the current defaults are ok for
* the nilfs filesystem.
*/
const struct file_operations nilfs_file_operations = {
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.unlocked_ioctl = nilfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = nilfs_compat_ioctl,
#endif /* CONFIG_COMPAT */
.mmap = nilfs_file_mmap,
.open = generic_file_open,
/* .release = nilfs_release_file, */
.fsync = nilfs_sync_file,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
};
const struct inode_operations nilfs_file_inode_operations = {
.setattr = nilfs_setattr,
.permission = nilfs_permission,
.fiemap = nilfs_fiemap,
.fileattr_get = nilfs_fileattr_get,
.fileattr_set = nilfs_fileattr_set,
};
/* end of file */