From: Chao Yu <yuchao0@huawei.com>
To: <jaegeuk@kernel.org>
Cc: <linux-f2fs-devel@lists.sourceforge.net>,
<linux-kernel@vger.kernel.org>, <chao@kernel.org>,
Chao Yu <yuchao0@huawei.com>
Subject: [PATCH v5] f2fs: allow out-place-update for direct IO in LFS mode
Date: Thu, 27 Sep 2018 18:34:52 +0800 [thread overview]
Message-ID: <20180927103452.40623-1-yuchao0@huawei.com> (raw)
Normally, DIO uses in-pllace-update, but in LFS mode, f2fs doesn't
allow triggering any in-place-update writes, so we fallback direct
write to buffered write, result in bad performance of large size
write.
This patch adds to support triggering out-place-update for direct IO
to enhance its performance.
Note that it needs to exclude direct read IO during direct write,
since new data writing to new block address will no be valid until
write finished.
storage: zram
time xfs_io -f -d /mnt/f2fs/file -c "pwrite 0 1073741824" -c "fsync"
Before:
real 0m13.061s
user 0m0.327s
sys 0m12.486s
After:
real 0m6.448s
user 0m0.228s
sys 0m6.212s
Signed-off-by: Chao Yu <yuchao0@huawei.com>
---
v5:
- use F2FS_GET_BLOCK_DIO instead of F2FS_GET_BLOCK_DEFAULT.
fs/f2fs/data.c | 44 +++++++++++++++++++++++++++++++++++---------
fs/f2fs/f2fs.h | 45 +++++++++++++++++++++++++++++++++++++++++----
fs/f2fs/file.c | 3 ++-
3 files changed, 78 insertions(+), 14 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index e98ea9a84782..652919552758 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -893,7 +893,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
dn->data_blkaddr = datablock_addr(dn->inode,
dn->node_page, dn->ofs_in_node);
- if (dn->data_blkaddr == NEW_ADDR)
+ if (dn->data_blkaddr != NULL_ADDR)
goto alloc;
if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
@@ -947,7 +947,7 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
if (direct_io) {
map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint);
- flag = f2fs_force_buffered_io(inode, WRITE) ?
+ flag = f2fs_force_buffered_io(inode, iocb, from) ?
F2FS_GET_BLOCK_PRE_AIO :
F2FS_GET_BLOCK_PRE_DIO;
goto map_blocks;
@@ -1066,7 +1066,15 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
goto sync_out;
}
- if (!is_valid_data_blkaddr(sbi, blkaddr)) {
+ if (is_valid_data_blkaddr(sbi, blkaddr)) {
+ /* use out-place-update for driect IO under LFS mode */
+ if (test_opt(sbi, LFS) && create &&
+ flag == F2FS_GET_BLOCK_DIO) {
+ err = __allocate_data_block(&dn, map->m_seg_type);
+ if (!err)
+ set_inode_flag(inode, FI_APPEND_WRITE);
+ }
+ } else {
if (create) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
@@ -2492,36 +2500,53 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
size_t count = iov_iter_count(iter);
loff_t offset = iocb->ki_pos;
int rw = iov_iter_rw(iter);
int err;
enum rw_hint hint = iocb->ki_hint;
int whint_mode = F2FS_OPTION(sbi).whint_mode;
+ bool do_opu;
err = check_direct_IO(inode, iter, offset);
if (err)
return err < 0 ? err : 0;
- if (f2fs_force_buffered_io(inode, rw))
+ if (f2fs_force_buffered_io(inode, iocb, iter))
return 0;
+ do_opu = allow_outplace_dio(inode, iocb, iter);
+
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
if (rw == WRITE && whint_mode == WHINT_MODE_OFF)
iocb->ki_hint = WRITE_LIFE_NOT_SET;
- if (!down_read_trylock(&F2FS_I(inode)->i_gc_rwsem[rw])) {
- if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!down_read_trylock(&fi->i_gc_rwsem[rw])) {
+ iocb->ki_hint = hint;
+ err = -EAGAIN;
+ goto out;
+ }
+ if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) {
+ up_read(&fi->i_gc_rwsem[rw]);
iocb->ki_hint = hint;
err = -EAGAIN;
goto out;
}
- down_read(&F2FS_I(inode)->i_gc_rwsem[rw]);
+ } else {
+ down_read(&fi->i_gc_rwsem[rw]);
+ if (do_opu)
+ down_read(&fi->i_gc_rwsem[READ]);
}
err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
- up_read(&F2FS_I(inode)->i_gc_rwsem[rw]);
+
+ if (do_opu)
+ up_read(&fi->i_gc_rwsem[READ]);
+
+ up_read(&fi->i_gc_rwsem[rw]);
if (rw == WRITE) {
if (whint_mode == WHINT_MODE_OFF)
@@ -2529,7 +2554,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (err > 0) {
f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
err);
- set_inode_flag(inode, FI_UPDATE_WRITE);
+ if (!do_opu)
+ set_inode_flag(inode, FI_UPDATE_WRITE);
} else if (err < 0) {
f2fs_write_failed(mapping, offset + count);
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 6b6871093406..675ff5df13bb 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -8,6 +8,7 @@
#ifndef _LINUX_F2FS_H
#define _LINUX_F2FS_H
+#include <linux/uio.h>
#include <linux/types.h>
#include <linux/page-flags.h>
#include <linux/buffer_head.h>
@@ -3488,11 +3489,47 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
#endif
}
-static inline bool f2fs_force_buffered_io(struct inode *inode, int rw)
+static inline int block_unaligned_IO(struct inode *inode,
+ struct kiocb *iocb, struct iov_iter *iter)
{
- return (f2fs_post_read_required(inode) ||
- (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
- F2FS_I_SB(inode)->s_ndevs);
+ unsigned int i_blkbits = READ_ONCE(inode->i_blkbits);
+ unsigned int blocksize_mask = (1 << i_blkbits) - 1;
+ loff_t offset = iocb->ki_pos;
+ unsigned long align = offset | iov_iter_alignment(iter);
+
+ return align & blocksize_mask;
+}
+
+static inline int allow_outplace_dio(struct inode *inode,
+ struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int rw = iov_iter_rw(iter);
+
+ return (test_opt(sbi, LFS) && (rw == WRITE) &&
+ !block_unaligned_IO(inode, iocb, iter));
+}
+
+static inline bool f2fs_force_buffered_io(struct inode *inode,
+ struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int rw = iov_iter_rw(iter);
+
+ if (f2fs_post_read_required(inode))
+ return true;
+ if (sbi->s_ndevs)
+ return true;
+ /*
+ * for blkzoned device, fallback direct IO to buffered IO, so
+ * all IOs can be serialized by log-structured write.
+ */
+ if (f2fs_sb_has_blkzoned(sbi->sb))
+ return true;
+ if (test_opt(sbi, LFS) && (rw == WRITE) &&
+ block_unaligned_IO(inode, iocb, iter))
+ return true;
+ return false;
}
#ifdef CONFIG_F2FS_FAULT_INJECTION
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 378684bf1ee6..2a4cad36141c 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -3037,7 +3037,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (!f2fs_overwrite_io(inode, iocb->ki_pos,
iov_iter_count(from)) ||
f2fs_has_inline_data(inode) ||
- f2fs_force_buffered_io(inode, WRITE)) {
+ f2fs_force_buffered_io(inode,
+ iocb, from)) {
clear_inode_flag(inode,
FI_NO_PREALLOC);
inode_unlock(inode);
--
2.18.0.rc1
reply other threads:[~2018-09-27 10:35 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180927103452.40623-1-yuchao0@huawei.com \
--to=yuchao0@huawei.com \
--cc=chao@kernel.org \
--cc=jaegeuk@kernel.org \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).