ext4: use ext4_get_block_write in buffer write
Allocate uninitialized extent before ext4 buffer write and
convert the extent to initialized after io completes.
The purpose is to make sure an extent can only be marked
initialized after it has been written with new data so
we can safely drop the i_mutex lock in ext4 DIO read without
exposing stale data. This helps to improve multi-thread DIO
read performance on high-speed disks.
Skip the nobh and data=journal mount cases to make things simple for now.
Signed-off-by: Jiaying Zhang <[email protected]>
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index de3d767..5900385 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -134,6 +134,7 @@ struct mpage_da_data {
int retval;
};
#define EXT4_IO_UNWRITTEN 0x1
+#define EXT4_IO_WRITTEN 0x2
typedef struct ext4_io_end {
struct list_head list; /* per-file finished AIO list */
struct inode *inode; /* file being written to */
@@ -373,7 +374,7 @@ struct ext4_new_group_data {
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
- EXT4_GET_BLOCKS_IO_CREATE_EXT)
+ EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
/*
* Flags used by ext4_free_blocks
@@ -757,6 +758,7 @@ struct ext4_inode_info {
#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
+#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */
@@ -1768,6 +1770,9 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
+/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
+#define BH_Uninit (BH_JBDPrivateStart + 1)
+BUFFER_FNS(Uninit, uninit)
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 1da5c32..2123143 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1603,7 +1603,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
BUG_ON(path[depth].p_hdr == NULL);
/* try to insert block into found extent and return */
- if (ex && (flag != EXT4_GET_BLOCKS_PRE_IO)
+ if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
&& ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
ext4_ext_is_uninitialized(newext),
@@ -1724,7 +1724,7 @@ has_space:
merge:
/* try to merge extents to the right */
- if (flag != EXT4_GET_BLOCKS_PRE_IO)
+ if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
ext4_ext_try_to_merge(inode, path, nearex);
/* try to merge extents to the left */
@@ -3060,7 +3060,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
ext4_ext_show_leaf(inode, path);
/* get_block() before submit the IO, split the extent */
- if (flags == EXT4_GET_BLOCKS_PRE_IO) {
+ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
ret = ext4_split_unwritten_extents(handle,
inode, path, iblock,
max_blocks, flags);
@@ -3073,10 +3073,12 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
io->flag = EXT4_IO_UNWRITTEN;
else
EXT4_I(inode)->i_state |= EXT4_STATE_DIO_UNWRITTEN;
+ if (test_opt(inode->i_sb, DIOREAD_NOLOCK))
+ set_buffer_uninit(bh_result);
goto out;
}
/* IO end_io complete, convert the filled extent to written */
- if (flags == EXT4_GET_BLOCKS_CONVERT) {
+ if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
ret = ext4_convert_unwritten_extents_endio(handle, inode,
path);
if (ret >= 0)
@@ -3322,21 +3324,21 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
ext4_ext_mark_uninitialized(&newex);
/*
- * io_end structure was created for every async
- * direct IO write to the middle of the file.
- * To avoid unecessary convertion for every aio dio rewrite
- * to the mid of file, here we flag the IO that is really
- * need the convertion.
+ * io_end structure was created for every IO write to an
+ * uninitialized extent. To avoid unecessary convertion,
+ * here we flag the IO that really needs the convertion.
* For non asycn direct IO case, flag the inode state
* that we need to perform convertion when IO is done.
*/
- if (flags == EXT4_GET_BLOCKS_PRE_IO) {
+ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
if (io)
io->flag = EXT4_IO_UNWRITTEN;
else
EXT4_I(inode)->i_state |=
EXT4_STATE_DIO_UNWRITTEN;;
}
+ if (test_opt(inode->i_sb, DIOREAD_NOLOCK))
+ set_buffer_uninit(bh_result);
}
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err) {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b2d047b..f601059 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1504,6 +1504,8 @@ static void ext4_truncate_failed_write(struct inode *inode)
ext4_truncate(inode);
}
+static int ext4_get_block_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create);
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
@@ -1545,8 +1547,12 @@ retry:
}
*pagep = page;
- ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- ext4_get_block);
+ if (test_opt(inode->i_sb, DIOREAD_NOLOCK) && S_ISREG(inode->i_mode))
+ ret = block_write_begin(file, mapping, pos, len, flags, pagep,
+ fsdata, ext4_get_block_write);
+ else
+ ret = block_write_begin(file, mapping, pos, len, flags, pagep,
+ fsdata, ext4_get_block);
if (!ret && ext4_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
@@ -2065,6 +2071,8 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
} else if (buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
+ if (buffer_uninit(exbh))
+ set_buffer_uninit(bh);
cur_logical++;
pblock++;
} while ((bh = bh->b_this_page) != head);
@@ -2195,6 +2203,9 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
new.b_state = 0;
get_blocks_flags = (EXT4_GET_BLOCKS_CREATE |
EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+ if (test_opt(mpd->inode->i_sb, DIOREAD_NOLOCK) &&
+ S_ISREG(mpd->inode->i_mode))
+ get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (mpd->b_state & (1 << BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE;
blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks,
@@ -2609,6 +2620,9 @@ out:
return ret;
}
+static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
+static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
+
/*
* Note that we don't need to start a transaction unless we're journaling data
* because we should have holes filled from ext4_page_mkwrite(). We even don't
@@ -2656,7 +2670,7 @@ static int ext4_writepage(struct page *page,
int ret = 0;
loff_t size;
unsigned int len;
- struct buffer_head *page_bufs;
+ struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
trace_ext4_writepage(inode, page);
@@ -2732,7 +2746,11 @@ static int ext4_writepage(struct page *page,
if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
ret = nobh_writepage(page, noalloc_get_block_write, wbc);
- else
+ else if (page_bufs && buffer_uninit(page_bufs)) {
+ ext4_set_bh_endio(page_bufs, inode);
+ ret = block_write_full_page_endio(page, noalloc_get_block_write,
+ wbc, ext4_end_io_buffer_write);
+ } else
ret = block_write_full_page(page, noalloc_get_block_write,
wbc);
@@ -3424,10 +3442,11 @@ out:
static int ext4_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
- handle_t *handle = NULL;
+ handle_t *handle = ext4_journal_current_handle();
int ret = 0;
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
int dio_credits;
+ int started = 0;
ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n",
inode->i_ino, create);
@@ -3438,21 +3457,26 @@ static int ext4_get_block_write(struct inode *inode, sector_t iblock,
*/
create = EXT4_GET_BLOCKS_IO_CREATE_EXT;
- if (max_blocks > DIO_MAX_BLOCKS)
- max_blocks = DIO_MAX_BLOCKS;
- dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
- handle = ext4_journal_start(inode, dio_credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
+ if (!handle) {
+ if (max_blocks > DIO_MAX_BLOCKS)
+ max_blocks = DIO_MAX_BLOCKS;
+ dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
+ handle = ext4_journal_start(inode, dio_credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ started = 1;
}
+
ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
create);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
}
- ext4_journal_stop(handle);
+ if (started)
+ ext4_journal_stop(handle);
out:
return ret;
}
@@ -3506,12 +3530,10 @@ static int ext4_end_io_nolock(ext4_io_end_t *io)
if (list_empty(&io->list))
return ret;
- if (io->flag != EXT4_IO_UNWRITTEN)
+ if (io->flag != EXT4_IO_WRITTEN)
return ret;
- if (offset + size <= i_size_read(inode))
- ret = ext4_convert_unwritten_extents(inode, offset, size);
-
+ ret = ext4_convert_unwritten_extents(inode, offset, size);
if (ret < 0) {
printk(KERN_EMERG "%s: failed to convert unwritten"
"extents to written extents, error is %d"
@@ -3559,7 +3581,7 @@ static void ext4_end_io_work(struct work_struct *work)
*/
int flush_completed_IO(struct inode *inode)
{
- ext4_io_end_t *io;
+ ext4_io_end_t *io, *tmp;
int ret = 0;
int ret2 = 0;
@@ -3567,9 +3589,10 @@ int flush_completed_IO(struct inode *inode)
return ret;
dump_completed_IO(inode);
- while (!list_empty(&EXT4_I(inode)->i_completed_io_list)){
- io = list_entry(EXT4_I(inode)->i_completed_io_list.next,
- ext4_io_end_t, list);
+ list_for_each_entry_safe(io, tmp,
+ &EXT4_I(inode)->i_completed_io_list, list) {
+ if (io->flag == EXT4_IO_UNWRITTEN)
+ continue;
/*
* Calling ext4_end_io_nolock() to convert completed
* IO to written.
@@ -3637,6 +3660,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
io_end->offset = offset;
io_end->size = size;
+ io_end->flag = EXT4_IO_WRITTEN;
wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
/* queue the work to convert unwritten extents to written */
@@ -3648,6 +3672,46 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
iocb->private = NULL;
}
+static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
+{
+ ext4_io_end_t *io_end = bh->b_private;
+ struct workqueue_struct *wq;
+
+ if (!io_end)
+ goto out;
+ io_end->flag = EXT4_IO_WRITTEN;
+ wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
+ /* queue the work to convert unwritten extents to written */
+ queue_work(wq, &io_end->work);
+out:
+ bh->b_private = NULL;
+ bh->b_end_io = NULL;
+ clear_buffer_uninit(bh);
+ end_buffer_async_write(bh, uptodate);
+}
+
+static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode)
+{
+ ext4_io_end_t *io_end;
+ struct page *page = bh->b_page;
+ loff_t offset = (sector_t)page->index << PAGE_CACHE_SHIFT;
+ size_t size = bh->b_size;
+
+ io_end = ext4_init_io_end(inode);
+ if (!io_end)
+ return -ENOMEM;
+ io_end->offset = offset;
+ io_end->size = size;
+ io_end->flag = EXT4_IO_UNWRITTEN;
+ /* Add the io_end to per-inode completed io list*/
+ list_add_tail(&io_end->list,
+ &EXT4_I(io_end->inode)->i_completed_io_list);
+
+ bh->b_private = io_end;
+ bh->b_end_io = ext4_end_io_buffer_write;
+ return 0;
+}
+
/*
* For ext4 extent files, ext4 will do direct-io write to holes,
* preallocated extents, and those write extend the file, no need to
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8254bf0..dccdd41 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -922,6 +922,9 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
if (test_opt(sb, NOLOAD))
seq_puts(seq, ",norecovery");
+ if (test_opt(sb, DIOREAD_NOLOCK))
+ seq_puts(seq, ",dioread_nolock");
+
ext4_show_quota_options(seq, sb);
return 0;
@@ -1103,6 +1106,7 @@ enum {
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
+ Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard,
};
@@ -1170,6 +1174,8 @@ static const match_table_t tokens = {
{Opt_auto_da_alloc, "auto_da_alloc=%u"},
{Opt_auto_da_alloc, "auto_da_alloc"},
{Opt_noauto_da_alloc, "noauto_da_alloc"},
+ {Opt_dioread_nolock, "dioread_nolock"},
+ {Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
{Opt_err, NULL},
@@ -1603,6 +1609,12 @@ set_qf_format:
case Opt_nodiscard:
clear_opt(sbi->s_mount_opt, DISCARD);
break;
+ case Opt_dioread_nolock:
+ set_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ break;
+ case Opt_dioread_lock:
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ break;
default:
ext4_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" "
@@ -2763,7 +2775,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
"suppressed and not mounted read-only");
- goto failed_mount4;
+ goto failed_mount_wq;
} else {
clear_opt(sbi->s_mount_opt, DATA_FLAGS);
set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
@@ -2776,7 +2788,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
- goto failed_mount4;
+ goto failed_mount_wq;
}
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
@@ -2815,7 +2827,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
ext4_msg(sb, KERN_ERR, "Journal does not support "
"requested data journaling mode");
- goto failed_mount4;
+ goto failed_mount_wq;
}
default:
break;
@@ -2823,13 +2835,17 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
no_journal:
-
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
"its supported only with writeback mode");
clear_opt(sbi->s_mount_opt, NOBH);
}
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_WARNING, "dioread_nolock option is "
+ "not supported with nobh mode");
+ goto failed_mount_wq;
+ }
}
EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
if (!EXT4_SB(sb)->dio_unwritten_wq) {
@@ -2894,6 +2910,12 @@ no_journal:
"requested data journaling mode");
clear_opt(sbi->s_mount_opt, DELALLOC);
}
+ if (test_opt(sb, DIOREAD_NOLOCK) &&
+ (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
+ ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock option - "
+ "requested data journaling mode");
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ }
err = ext4_setup_system_zone(sb);
if (err) {