Re: [PATCH v3] f2fs: add bio cache for IPU

From: Jaegeuk Kim
Date: Wed Dec 26 2018 - 18:09:31 EST


On 12/24, Chao Yu wrote:
> Jaegeuk,
>
> Will kernel still hang with this v3?

I'll consider this later, since it blocked local tests before.

>
> Thanks,
>
> On 2018/12/19 17:29, Chao Yu wrote:
> > SQLite in Wal mode may trigger sequential IPU write in db-wal file, after
> > commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we
> > lost the chance of merging page in inner managed bio cache, result in
> > submitting more small-sized IO.
> >
> > So let's add temporary bio in writepages() to cache mergeable write IO as
> > much as possible.
> >
> > Test case:
> > 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync"
> > 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync"
> >
> > Before:
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096
> >
> > After:
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536
> > f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096
> >
> > Signed-off-by: Chao Yu <yuchao0@xxxxxxxxxx>
> > ---
> > v3:
> > - introduce f2fs_submit_ipu_bio() to check page Writeback status.
> > fs/f2fs/data.c | 85 ++++++++++++++++++++++++++++++++++++++++++-----
> > fs/f2fs/f2fs.h | 3 ++
> > fs/f2fs/segment.c | 5 ++-
> > 3 files changed, 84 insertions(+), 9 deletions(-)
> >
> > diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> > index cdfe9a7b856e..e5cd3fd9e215 100644
> > --- a/fs/f2fs/data.c
> > +++ b/fs/f2fs/data.c
> > @@ -341,20 +341,20 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
> > io->bio = NULL;
> > }
> >
> > -static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
> > +static bool __has_merged_page(struct bio *bio, struct inode *inode,
> > struct page *page, nid_t ino)
> > {
> > struct bio_vec *bvec;
> > struct page *target;
> > int i;
> >
> > - if (!io->bio)
> > + if (!bio)
> > return false;
> >
> > if (!inode && !page && !ino)
> > return true;
> >
> > - bio_for_each_segment_all(bvec, io->bio, i) {
> > + bio_for_each_segment_all(bvec, bio, i) {
> >
> > if (bvec->bv_page->mapping)
> > target = bvec->bv_page;
> > @@ -405,7 +405,7 @@ static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
> > struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
> >
> > down_read(&io->io_rwsem);
> > - ret = __has_merged_page(io, inode, page, ino);
> > + ret = __has_merged_page(io->bio, inode, page, ino);
> > up_read(&io->io_rwsem);
> > }
> > if (ret)
> > @@ -474,6 +474,59 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
> > return 0;
> > }
> >
> > +int f2fs_merge_page_bio(struct f2fs_io_info *fio)
> > +{
> > + struct bio *bio = *fio->bio;
> > + struct page *page = fio->encrypted_page ?
> > + fio->encrypted_page : fio->page;
> > +
> > + if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
> > + __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
> > + return -EFAULT;
> > +
> > + trace_f2fs_submit_page_bio(page, fio);
> > + f2fs_trace_ios(fio, 0);
> > +
> > + if (bio && (*fio->last_block + 1 != fio->new_blkaddr ||
> > + !__same_bdev(fio->sbi, fio->new_blkaddr, bio))) {
> > + __submit_bio(fio->sbi, bio, fio->type);
> > + bio = NULL;
> > + }
> > +alloc_new:
> > + if (!bio) {
> > + bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc,
> > + BIO_MAX_PAGES, false, fio->type, fio->temp);
> > + *fio->last_block = fio->new_blkaddr;
> > + bio_set_op_attrs(bio, fio->op, fio->op_flags);
> > + }
> > +
> > + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
> > + __submit_bio(fio->sbi, bio, fio->type);
> > + bio = NULL;
> > + goto alloc_new;
> > + }
> > +
> > + if (fio->io_wbc)
> > + wbc_account_io(fio->io_wbc, page, PAGE_SIZE);
> > +
> > + *fio->last_block = fio->new_blkaddr;
> > +
> > + inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page));
> > +
> > + *fio->bio = bio;
> > + return 0;
> > +}
> > +
> > +void f2fs_submit_ipu_bio(struct f2fs_sb_info *sbi, struct bio *bio,
> > + struct page *page)
> > +{
> > + if (!__has_merged_page(bio, NULL, page, 0))
> > + return;
> > +
> > + if (bio)
> > + __submit_bio(sbi, bio, DATA);
> > +}
> > +
> > void f2fs_submit_page_write(struct f2fs_io_info *fio)
> > {
> > struct f2fs_sb_info *sbi = fio->sbi;
> > @@ -1903,6 +1956,8 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
> > }
> >
> > static int __write_data_page(struct page *page, bool *submitted,
> > + struct bio **bio,
> > + sector_t *last_block,
> > struct writeback_control *wbc,
> > enum iostat_type io_type)
> > {
> > @@ -1928,6 +1983,8 @@ static int __write_data_page(struct page *page, bool *submitted,
> > .need_lock = LOCK_RETRY,
> > .io_type = io_type,
> > .io_wbc = wbc,
> > + .bio = bio,
> > + .last_block = last_block,
> > };
> >
> > trace_f2fs_writepage(page, DATA);
> > @@ -2029,6 +2086,10 @@ static int __write_data_page(struct page *page, bool *submitted,
> > f2fs_balance_fs(sbi, need_balance_fs);
> >
> > if (unlikely(f2fs_cp_error(sbi))) {
> > + if (bio && *bio) {
> > + __submit_bio(sbi, *bio, DATA);
> > + *bio = NULL;
> > + }
> > f2fs_submit_merged_write(sbi, DATA);
> > submitted = NULL;
> > }
> > @@ -2055,7 +2116,7 @@ static int __write_data_page(struct page *page, bool *submitted,
> > static int f2fs_write_data_page(struct page *page,
> > struct writeback_control *wbc)
> > {
> > - return __write_data_page(page, NULL, wbc, FS_DATA_IO);
> > + return __write_data_page(page, NULL, NULL, NULL, wbc, FS_DATA_IO);
> > }
> >
> > /*
> > @@ -2071,6 +2132,8 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
> > int done = 0;
> > struct pagevec pvec;
> > struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
> > + struct bio *bio = NULL;
> > + sector_t last_block;
> > int nr_pages;
> > pgoff_t uninitialized_var(writeback_index);
> > pgoff_t index;
> > @@ -2147,17 +2210,20 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
> > }
> >
> > if (PageWriteback(page)) {
> > - if (wbc->sync_mode != WB_SYNC_NONE)
> > + if (wbc->sync_mode != WB_SYNC_NONE) {
> > f2fs_wait_on_page_writeback(page,
> > DATA, true);
> > - else
> > + f2fs_submit_ipu_bio(sbi, bio, page);
> > + } else {
> > goto continue_unlock;
> > + }
> > }
> >
> > if (!clear_page_dirty_for_io(page))
> > goto continue_unlock;
> >
> > - ret = __write_data_page(page, &submitted, wbc, io_type);
> > + ret = __write_data_page(page, &submitted, &bio,
> > + &last_block, wbc, io_type);
> > if (unlikely(ret)) {
> > /*
> > * keep nr_to_write, since vfs uses this to
> > @@ -2206,6 +2272,9 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
> > if (nwritten)
> > f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
> > NULL, 0, DATA);
> > + /* submit cached bio of IPU write */
> > + if (bio)
> > + __submit_bio(sbi, bio, DATA);
> >
> > return ret;
> > }
> > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> > index 9e56c78fe519..eeede26339a8 100644
> > --- a/fs/f2fs/f2fs.h
> > +++ b/fs/f2fs/f2fs.h
> > @@ -1044,6 +1044,8 @@ struct f2fs_io_info {
> > bool retry; /* need to reallocate block address */
> > enum iostat_type io_type; /* io type */
> > struct writeback_control *io_wbc; /* writeback control */
> > + struct bio **bio; /* bio for ipu */
> > + sector_t *last_block; /* last block number in bio */
> > unsigned char version; /* version of the node */
> > };
> >
> > @@ -3105,6 +3107,7 @@ void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
> > nid_t ino, enum page_type type);
> > void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
> > int f2fs_submit_page_bio(struct f2fs_io_info *fio);
> > +int f2fs_merge_page_bio(struct f2fs_io_info *fio);
> > void f2fs_submit_page_write(struct f2fs_io_info *fio);
> > struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
> > block_t blk_addr, struct bio *bio);
> > diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> > index 3241e0619275..a361d61b005e 100644
> > --- a/fs/f2fs/segment.c
> > +++ b/fs/f2fs/segment.c
> > @@ -3163,7 +3163,10 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
> >
> > stat_inc_inplace_blocks(fio->sbi);
> >
> > - err = f2fs_submit_page_bio(fio);
> > + if (fio->bio)
> > + err = f2fs_merge_page_bio(fio);
> > + else
> > + err = f2fs_submit_page_bio(fio);
> > if (!err)
> > update_device_state(fio);
> >
> >