When considering a bunch of data writes with very frequent fsync calls, we
are able to think the following performance regression.
N: Node IO, D: Data IO, IO scheduler: cfq
Issue pending IOs
D1 D2 D3 D4
D1 D2 D3 D4 N1
D2 D3 D4 N1 N2
N1 D3 D4 N2 D1
--> N1 can be selected by cfq becase of the same priority of N and D.
Then D3 and D4 would be delayed, resuling in performance degradation.
So, when processing the fsync call, it'd better give higher priority to data IOs
than node IOs by assigning WRITE and WRITE_SYNC respectively.
This patch improves the random wirte performance with frequent fsync calls by up
to 10%.
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@xxxxxxxxxxx>
---
fs/f2fs/f2fs.h | 4 ++--
fs/f2fs/file.c | 2 +-
fs/f2fs/node.c | 7 ++++++-
fs/f2fs/segment.c | 8 ++------
4 files changed, 11 insertions(+), 10 deletions(-)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 07a7ae0..b69f190 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1118,8 +1118,8 @@ int npages_for_summary_flush(struct f2fs_sb_info *);
void allocate_new_segments(struct f2fs_sb_info *);
struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
void write_meta_page(struct f2fs_sb_info *, struct page *);
-void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int,
- block_t, block_t *);
+void write_node_page(struct f2fs_sb_info *, struct page *,
+ struct f2fs_io_info *, unsigned int, block_t, block_t *);
void write_data_page(struct page *, struct dnode_of_data *, block_t *,
struct f2fs_io_info *);
void rewrite_data_page(struct page *, block_t, struct f2fs_io_info *);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index c77ad4d..14511b0 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -115,7 +115,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
int ret = 0;
bool need_cp = false;
struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
+ .sync_mode = WB_SYNC_NONE,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 0230326..b8c9301 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1194,6 +1194,10 @@ static int f2fs_write_node_page(struct page *page,
nid_t nid;
block_t new_addr;
struct node_info ni;
+ struct f2fs_io_info fio = {
+ .type = NODE,
+ .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC: WRITE,
+ };
if (unlikely(sbi->por_doing))
goto redirty_out;
@@ -1218,7 +1222,7 @@ static int f2fs_write_node_page(struct page *page,
mutex_lock(&sbi->node_write);
set_page_writeback(page);
- write_node_page(sbi, page, nid, ni.blk_addr, &new_addr);
+ write_node_page(sbi, page, &fio, nid, ni.blk_addr, &new_addr);
set_node_addr(sbi, &ni, new_addr);
dec_page_count(sbi, F2FS_DIRTY_NODES);
mutex_unlock(&sbi->node_write);
@@ -1253,6 +1257,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
/* if mounting is failed, skip writing node pages */
wbc->nr_to_write = 3 * max_hw_blocks(sbi);
+ wbc->sync_mode = WB_SYNC_NONE;
sync_node_pages(sbi, 0, wbc);
wbc->nr_to_write = nr_to_write - (3 * max_hw_blocks(sbi) -
wbc->nr_to_write);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 555ae76..5f84639 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -924,16 +924,12 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
}
void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
+ struct f2fs_io_info *fio,
unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr)
{
struct f2fs_summary sum;
- struct f2fs_io_info fio = {
- .type = NODE,
- .rw = WRITE_SYNC,
- };
-
set_summary(&sum, nid, 0, 0);
- do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, &fio);
+ do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, fio);
}
void write_data_page(struct page *page, struct dnode_of_data *dn,
--
1.8.4.474.g128a96c
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
