f2fs: don't wait writeback for datas during checkpoint
PATCH v2 1/1 f2fs: don't wait writeback for datas during checkpoint
Normally, while committing checkpoint, we will wait on all pages to be writebacked no matter the page is data or metadata, so in scenario where there are lots of data IO being submitted with metadata, we may suffer long latency for waiting writeback during checkpoint.
Indeed, we only care about persistence for pages with metadata, but not pages with data, as file system consistent are only related to metadate, so in order to avoid encountering long latency in above scenario, let's recognize and reference metadata in submitted IOs, wait writeback only for metadatas.
--- fs/f2fs/checkpoint.c | 2 +- fs/f2fs/data.c | 36 ++++++++++++++++++++++++++++++++---- fs/f2fs/debug.c | 7 ++++--- fs/f2fs/f2fs.h | 8 +++++--- 4 files changed, 42 insertions(+), 11 deletions(-)
fs/f2fs/checkpoint.c +1 -1
@@ -1003,7 +1003,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)for (;;) {prepare_to_wait (&sbi->cp_wait, &wait,TASK_UNINTERRUPTIBLE ); -if (!atomic_read (&sbi->nr_wb_bios)) +if (!get_pages (sbi,F2FS_WB_META ))break ;io_schedule_timeout (5 *HZ );
fs/f2fs/data.c +32 -4
@@ -29,6 +29,26 @@#include "trace.h" #include <trace/events/f2fs.h> +static bool f2fs_is_meta_data (struct page *page) +{ +struct address_space *mapping = page->mapping; +struct f2fs_sb_info *sbi; +struct inode *inode; + +/* it is bounce page of encrypted regular inode */ +if (!mapping) +return false; + + inode = mapping->host; + sbi =F2FS_I_SB (inode); + +if ((inode->i_ino ==F2FS_META_INO (sbi) && + page->index <MAIN_BLKADDR (sbi)) || + inode->i_ino ==F2FS_NODE_INO (sbi) || +S_ISDIR (inode->i_mode)) +return true; +return false; +}static void f2fs_read_end_io (struct bio *bio) {struct bio_vec *bvec;
@@ -73,6 +93,7 @@ static void f2fs_write_end_io(struct bio *bio)bio_for_each_segment_all (bvec, bio, i) {struct page *page = bvec->bv_page; +bool is_meta =f2fs_is_meta_data (page);fscrypt_pullback_bio_page (&page, true);
@@ -80,9 +101,10 @@ static void f2fs_write_end_io(struct bio *bio)mapping_set_error (page->mapping, -EIO );f2fs_stop_checkpoint (sbi, true); } +dec_page_count (sbi, is_meta ?F2FS_WB_META :F2FS_WB_DATA );end_page_writeback (page); } -if (atomic_dec_and_test (&sbi->nr_wb_bios) && +if (!get_pages (sbi,F2FS_WB_META ) &&wq_has_sleeper (&sbi->cp_wait))wake_up (&sbi->cp_wait);
@@ -111,7 +133,6 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type) {if (!is_read_io (bio_op (bio))) { -atomic_inc (&sbi->nr_wb_bios);if (f2fs_sb_mounted_blkzoned (sbi->sb) && current->plug && (type ==DATA || type ==NODE ))blk_finish_plug (current->plug);
@@ -272,6 +293,15 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)verify_block_addr (sbi, fio->old_blkaddr);verify_block_addr (sbi, fio->new_blkaddr); + bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; + +if (!is_read) { +bool is_meta; + + is_meta =f2fs_is_meta_data (bio_page); +inc_page_count (sbi, is_meta ?F2FS_WB_META :F2FS_WB_DATA ); + } +down_write (&io->io_rwsem); if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
@@ -284,8 +314,6 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio) io->fio = *fio; } - bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; -if (bio_add_page (io->bio, bio_page,PAGE_SIZE ,0 ) <PAGE_SIZE ) {__submit_merged_bio (io);
fs/f2fs/debug.c +4 -3
@@ -50,7 +50,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->ndirty_files = sbi->ndirty_inode[FILE_INODE ]; si->ndirty_all = sbi->ndirty_inode[DIRTY_META ]; si->inmem_pages =get_pages (sbi,F2FS_INMEM_PAGES ); - si->wb_bios =atomic_read (&sbi->nr_wb_bios); + si->nr_wb_meta =get_pages (sbi,F2FS_WB_META ); + si->nr_wb_data =get_pages (sbi,F2FS_WB_DATA ); si->total_count = (int )sbi->user_block_count / sbi->blocks_per_seg; si->rsvd_segs =reserved_segments (sbi); si->overp_segs =overprovision_segments (sbi);
@@ -313,8 +314,8 @@ static int stat_show(struct seq_file *s, void *v)seq_printf (s," - Inner Struct Count: tree: %d(%d), node: %d\n" , si->ext_tree, si->zombie_tree, si->ext_node);seq_puts (s,"\nBalancing F2FS Async:\n" ); -seq_printf (s," - inmem: %4d, wb_bios: %4d\n" , - si->inmem_pages, si->wb_bios); +seq_printf (s," - inmem: %4d, wb_meta: %4d, wb_data: %4d\n" , + si->inmem_pages, si->nr_wb_meta, si->nr_wb_data);seq_printf (s," - nodes: %4d in %4d\n" , si->ndirty_node, si->node_pages); seq_printf(s, " - dents: %4d in dirs:%4d (%4d)\n",
fs/f2fs/f2fs.h +5 -3
@@ -682,6 +682,8 @@ enum count_type {F2FS_DIRTY_META ,F2FS_INMEM_PAGES ,F2FS_DIRTY_IMETA , +F2FS_WB_META , +F2FS_WB_DATA , NR_COUNT_TYPE, };
@@ -849,7 +851,6 @@ struct f2fs_sb_info {block_t discard_blks;/* discard command candidats */ block_t last_valid_block_count;/* for recovery */ u32 s_next_generation;/* for NFS support */ -atomic_t nr_wb_bios;/* # of writeback bios */ /* # of pages, see count_type */ atomic_t nr_pages[NR_COUNT_TYPE ];
@@ -1263,7 +1264,8 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) {atomic_inc (&sbi->nr_pages[count_type]); -if (count_type ==F2FS_DIRTY_DATA || count_type ==F2FS_INMEM_PAGES ) +if (count_type ==F2FS_DIRTY_DATA || count_type ==F2FS_INMEM_PAGES || + count_type ==F2FS_WB_META || count_type ==F2FS_WB_DATA )return ;set_sbi_flag (sbi,SBI_IS_DIRTY );
@@ -2219,7 +2221,7 @@ struct f2fs_stat_info {unsigned int ndirty_dirs, ndirty_files, ndirty_all;int nats, dirty_nats, sits, dirty_sits, free_nids, alloc_nids;int total_count, utilization; -int bg_gc, wb_bios; +int bg_gc, nr_wb_meta, nr_wb_data;int inline_xattr, inline_inode, inline_dir, orphans;unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;unsigned int bimodal, avg_vblocks;
Signature · 1 line
2.8.2.311.gee88674
Jaegeuk Kim
maintainerHi Chao,
Quoted 10 lines · Chao Yu
Normally, while committing checkpoint, we will wait on all pages to be writebacked no matter the page is data or metadata, so in scenario where there are lots of data IO being submitted with metadata, we may suffer long latency for waiting writeback during checkpoint.
Indeed, we only care about persistence for pages with metadata, but not pages with data, as file system consistent are only related to metadate, so in order to avoid encountering long latency in above scenario, let's recognize and reference metadata in submitted IOs, wait writeback only for metadatas.
Hmm, another concern comes, which is related to GCed data like below scenario.
1. Write data X
2. Sync
3. Move data X by GC
4. Checkpoint
5. Power-cut
In this case, we should guarantee data X which was migrated by GC during #3. If we don't care about end_io in #4 Checkpoint, we can lose the data after #5 Power-cut.
Any idea?
Thanks,
Quoted 173 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/checkpoint.c | 2 +- fs/f2fs/data.c | 36 ++++++++++++++++++++++++++++++++---- fs/f2fs/debug.c | 7 ++++--- fs/f2fs/f2fs.h | 8 +++++--- 4 files changed, 42 insertions(+), 11 deletions(-)fs/f2fs/checkpoint.c +1
-1@@ -1003,7 +1003,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)for (;;) {prepare_to_wait (&sbi->cp_wait, &wait,TASK_UNINTERRUPTIBLE ); -if (!atomic_read (&sbi->nr_wb_bios)) +if (!get_pages (sbi,F2FS_WB_META ))break ;io_schedule_timeout (5 *HZ );fs/f2fs/data.c +32
-4@@ -29,6 +29,26 @@#include "trace.h" #include <trace/events/f2fs.h> +static bool f2fs_is_meta_data (struct page *page) +{ +struct address_space *mapping = page->mapping; +struct f2fs_sb_info *sbi; +struct inode *inode; + +/* it is bounce page of encrypted regular inode */ +if (!mapping) +return false; + + inode = mapping->host; + sbi =F2FS_I_SB (inode); + +if ((inode->i_ino ==F2FS_META_INO (sbi) && + page->index <MAIN_BLKADDR (sbi)) || + inode->i_ino ==F2FS_NODE_INO (sbi) || +S_ISDIR (inode->i_mode)) +return true; +return false; +}static void f2fs_read_end_io (struct bio *bio) {struct bio_vec *bvec;@@ -73,6 +93,7 @@ static void f2fs_write_end_io(struct bio *bio)bio_for_each_segment_all (bvec, bio, i) {struct page *page = bvec->bv_page; +bool is_meta =f2fs_is_meta_data (page);fscrypt_pullback_bio_page (&page, true);@@ -80,9 +101,10 @@ static void f2fs_write_end_io(struct bio *bio)mapping_set_error (page->mapping, -EIO );f2fs_stop_checkpoint (sbi, true); } +dec_page_count (sbi, is_meta ?F2FS_WB_META :F2FS_WB_DATA );end_page_writeback (page); } -if (atomic_dec_and_test (&sbi->nr_wb_bios) && +if (!get_pages (sbi,F2FS_WB_META ) &&wq_has_sleeper (&sbi->cp_wait))wake_up (&sbi->cp_wait);@@ -111,7 +133,6 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type) {if (!is_read_io (bio_op (bio))) { -atomic_inc (&sbi->nr_wb_bios);if (f2fs_sb_mounted_blkzoned (sbi->sb) && current->plug && (type ==DATA || type ==NODE ))blk_finish_plug (current->plug);@@ -272,6 +293,15 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)verify_block_addr (sbi, fio->old_blkaddr);verify_block_addr (sbi, fio->new_blkaddr); + bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; + +if (!is_read) { +bool is_meta; + + is_meta =f2fs_is_meta_data (bio_page); +inc_page_count (sbi, is_meta ?F2FS_WB_META :F2FS_WB_DATA ); + } +down_write (&io->io_rwsem); if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||@@ -284,8 +314,6 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio) io->fio = *fio; } - bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; -if (bio_add_page (io->bio, bio_page,PAGE_SIZE ,0 ) <PAGE_SIZE ) {__submit_merged_bio (io);fs/f2fs/debug.c +4
-3@@ -50,7 +50,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->ndirty_files = sbi->ndirty_inode[FILE_INODE ]; si->ndirty_all = sbi->ndirty_inode[DIRTY_META ]; si->inmem_pages =get_pages (sbi,F2FS_INMEM_PAGES ); - si->wb_bios =atomic_read (&sbi->nr_wb_bios); + si->nr_wb_meta =get_pages (sbi,F2FS_WB_META ); + si->nr_wb_data =get_pages (sbi,F2FS_WB_DATA ); si->total_count = (int )sbi->user_block_count / sbi->blocks_per_seg; si->rsvd_segs =reserved_segments (sbi); si->overp_segs =overprovision_segments (sbi);@@ -313,8 +314,8 @@ static int stat_show(struct seq_file *s, void *v)seq_printf (s," - Inner Struct Count: tree: %d(%d), node: %d\n" , si->ext_tree, si->zombie_tree, si->ext_node);seq_puts (s,"\nBalancing F2FS Async:\n" ); -seq_printf (s," - inmem: %4d, wb_bios: %4d\n" , - si->inmem_pages, si->wb_bios); +seq_printf (s," - inmem: %4d, wb_meta: %4d, wb_data: %4d\n" , + si->inmem_pages, si->nr_wb_meta, si->nr_wb_data);seq_printf (s," - nodes: %4d in %4d\n" , si->ndirty_node, si->node_pages); seq_printf(s, " - dents: %4d in dirs:%4d (%4d)\n",fs/f2fs/f2fs.h +5
-3@@ -682,6 +682,8 @@ enum count_type {F2FS_DIRTY_META ,F2FS_INMEM_PAGES ,F2FS_DIRTY_IMETA , +F2FS_WB_META , +F2FS_WB_DATA , NR_COUNT_TYPE, };@@ -849,7 +851,6 @@ struct f2fs_sb_info {block_t discard_blks;/* discard command candidats */ block_t last_valid_block_count;/* for recovery */ u32 s_next_generation;/* for NFS support */ -atomic_t nr_wb_bios;/* # of writeback bios */ /* # of pages, see count_type */ atomic_t nr_pages[NR_COUNT_TYPE ];@@ -1263,7 +1264,8 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) {atomic_inc (&sbi->nr_pages[count_type]); -if (count_type ==F2FS_DIRTY_DATA || count_type ==F2FS_INMEM_PAGES ) +if (count_type ==F2FS_DIRTY_DATA || count_type ==F2FS_INMEM_PAGES || + count_type ==F2FS_WB_META || count_type ==F2FS_WB_DATA )return ;set_sbi_flag (sbi,SBI_IS_DIRTY );@@ -2219,7 +2221,7 @@ struct f2fs_stat_info {unsigned int ndirty_dirs, ndirty_files, ndirty_all;int nats, dirty_nats, sits, dirty_sits, free_nids, alloc_nids;int total_count, utilization; -int bg_gc, wb_bios; +int bg_gc, nr_wb_meta, nr_wb_data;int inline_xattr, inline_inode, inline_dir, orphans;unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;unsigned int bimodal, avg_vblocks;Signature · 1 line
2.8.2.311.gee88674
Hi Jaegeuk,
Quoted 22 lines · Jaegeuk Kim
Hi Chao,
Quoted 10 lines · Chao Yu
Normally, while committing checkpoint, we will wait on all pages to be writebacked no matter the page is data or metadata, so in scenario where there are lots of data IO being submitted with metadata, we may suffer long latency for waiting writeback during checkpoint.
Indeed, we only care about persistence for pages with metadata, but not pages with data, as file system consistent are only related to metadate, so in order to avoid encountering long latency in above scenario, let's recognize and reference metadata in submitted IOs, wait writeback only for metadatas.
Hmm, another concern comes, which is related to GCed data like below scenario.
1. Write data X
2. Sync
3. Move data X by GC
4. Checkpoint
5. Power-cut
Quoted 5 lines
In this case, we should guarantee data X which was migrated by GC during #3. If we don't care about
end_ioin #4 Checkpoint, we can lose the data after #5 Power-cut.Any idea?
Yes, good catch. :)
What about tagging these GCed page as cold data through set_cold_data, and clear the tag in end_io, then we can keep reference count and wait on writeback for them?
Thanks,
Quoted 179 lines
Thanks,
Quoted 173 lines
Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/checkpoint.c | 2 +- fs/f2fs/data.c | 36 ++++++++++++++++++++++++++++++++---- fs/f2fs/debug.c | 7 ++++--- fs/f2fs/f2fs.h | 8 +++++--- 4 files changed, 42 insertions(+), 11 deletions(-)fs/f2fs/checkpoint.c +1
-1@@ -1003,7 +1003,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)for (;;) {prepare_to_wait (&sbi->cp_wait, &wait,TASK_UNINTERRUPTIBLE ); -if (!atomic_read (&sbi->nr_wb_bios)) +if (!get_pages (sbi,F2FS_WB_META ))break ;io_schedule_timeout (5 *HZ );fs/f2fs/data.c +32
-4@@ -29,6 +29,26 @@#include "trace.h" #include <trace/events/f2fs.h> +static bool f2fs_is_meta_data (struct page *page) +{ +struct address_space *mapping = page->mapping; +struct f2fs_sb_info *sbi; +struct inode *inode; + +/* it is bounce page of encrypted regular inode */ +if (!mapping) +return false; + + inode = mapping->host; + sbi =F2FS_I_SB (inode); + +if ((inode->i_ino ==F2FS_META_INO (sbi) && + page->index <MAIN_BLKADDR (sbi)) || + inode->i_ino ==F2FS_NODE_INO (sbi) || +S_ISDIR (inode->i_mode)) +return true; +return false; +}static void f2fs_read_end_io (struct bio *bio) {struct bio_vec *bvec;@@ -73,6 +93,7 @@ static void f2fs_write_end_io(struct bio *bio)bio_for_each_segment_all (bvec, bio, i) {struct page *page = bvec->bv_page; +bool is_meta =f2fs_is_meta_data (page);fscrypt_pullback_bio_page (&page, true);@@ -80,9 +101,10 @@ static void f2fs_write_end_io(struct bio *bio)mapping_set_error (page->mapping, -EIO );f2fs_stop_checkpoint (sbi, true); } +dec_page_count (sbi, is_meta ?F2FS_WB_META :F2FS_WB_DATA );end_page_writeback (page); } -if (atomic_dec_and_test (&sbi->nr_wb_bios) && +if (!get_pages (sbi,F2FS_WB_META ) &&wq_has_sleeper (&sbi->cp_wait))wake_up (&sbi->cp_wait);@@ -111,7 +133,6 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type) {if (!is_read_io (bio_op (bio))) { -atomic_inc (&sbi->nr_wb_bios);if (f2fs_sb_mounted_blkzoned (sbi->sb) && current->plug && (type ==DATA || type ==NODE ))blk_finish_plug (current->plug);@@ -272,6 +293,15 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)verify_block_addr (sbi, fio->old_blkaddr);verify_block_addr (sbi, fio->new_blkaddr); + bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; + +if (!is_read) { +bool is_meta; + + is_meta =f2fs_is_meta_data (bio_page); +inc_page_count (sbi, is_meta ?F2FS_WB_META :F2FS_WB_DATA ); + } +down_write (&io->io_rwsem); if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||@@ -284,8 +314,6 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio) io->fio = *fio; } - bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; -if (bio_add_page (io->bio, bio_page,PAGE_SIZE ,0 ) <PAGE_SIZE ) {__submit_merged_bio (io);fs/f2fs/debug.c +4
-3@@ -50,7 +50,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->ndirty_files = sbi->ndirty_inode[FILE_INODE ]; si->ndirty_all = sbi->ndirty_inode[DIRTY_META ]; si->inmem_pages =get_pages (sbi,F2FS_INMEM_PAGES ); - si->wb_bios =atomic_read (&sbi->nr_wb_bios); + si->nr_wb_meta =get_pages (sbi,F2FS_WB_META ); + si->nr_wb_data =get_pages (sbi,F2FS_WB_DATA ); si->total_count = (int )sbi->user_block_count / sbi->blocks_per_seg; si->rsvd_segs =reserved_segments (sbi); si->overp_segs =overprovision_segments (sbi);@@ -313,8 +314,8 @@ static int stat_show(struct seq_file *s, void *v)seq_printf (s," - Inner Struct Count: tree: %d(%d), node: %d\n" , si->ext_tree, si->zombie_tree, si->ext_node);seq_puts (s,"\nBalancing F2FS Async:\n" ); -seq_printf (s," - inmem: %4d, wb_bios: %4d\n" , - si->inmem_pages, si->wb_bios); +seq_printf (s," - inmem: %4d, wb_meta: %4d, wb_data: %4d\n" , + si->inmem_pages, si->nr_wb_meta, si->nr_wb_data);seq_printf (s," - nodes: %4d in %4d\n" , si->ndirty_node, si->node_pages); seq_printf(s, " - dents: %4d in dirs:%4d (%4d)\n",fs/f2fs/f2fs.h +5
-3@@ -682,6 +682,8 @@ enum count_type {F2FS_DIRTY_META ,F2FS_INMEM_PAGES ,F2FS_DIRTY_IMETA , +F2FS_WB_META , +F2FS_WB_DATA , NR_COUNT_TYPE, };@@ -849,7 +851,6 @@ struct f2fs_sb_info {block_t discard_blks;/* discard command candidats */ block_t last_valid_block_count;/* for recovery */ u32 s_next_generation;/* for NFS support */ -atomic_t nr_wb_bios;/* # of writeback bios */ /* # of pages, see count_type */ atomic_t nr_pages[NR_COUNT_TYPE ];@@ -1263,7 +1264,8 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) {atomic_inc (&sbi->nr_pages[count_type]); -if (count_type ==F2FS_DIRTY_DATA || count_type ==F2FS_INMEM_PAGES ) +if (count_type ==F2FS_DIRTY_DATA || count_type ==F2FS_INMEM_PAGES || + count_type ==F2FS_WB_META || count_type ==F2FS_WB_DATA )return ;set_sbi_flag (sbi,SBI_IS_DIRTY );@@ -2219,7 +2221,7 @@ struct f2fs_stat_info {unsigned int ndirty_dirs, ndirty_files, ndirty_all;int nats, dirty_nats, sits, dirty_sits, free_nids, alloc_nids;int total_count, utilization; -int bg_gc, wb_bios; +int bg_gc, nr_wb_meta, nr_wb_data;int inline_xattr, inline_inode, inline_dir, orphans;unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;unsigned int bimodal, avg_vblocks;Signature · 1 line
2.8.2.311.gee88674.