f2fs: introduce periodic iostat io latency traces

Whenever we notice some sluggish issues on our machines, we are always
curious about how well all types of I/O in the f2fs filesystem are
handled. But, it's hard to get this kind of real data. First of all,
we need to reproduce the issue while turning on the profiling tool like
blktrace, but the issue doesn't happen again easily. Second, with the
intervention of any tools, the overall timing of the issue will be
slightly changed and it sometimes makes us hard to figure it out.

So, I added the feature printing out IO latency statistics tracepoint
events, which are minimal things to understand filesystem's I/O related
behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs
node on, we can get this statistics info in a periodic way and it
would cause the least overhead.

[samples]
 f2fs_ckpt-254:1-507     [003] ....  2842.439683: f2fs_iostat_latency:
dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count],
rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4],
wr_sync_data [164/16/3331], wr_sync_node [152/3/648],
wr_sync_meta [160/2/4243], wr_async_data [24/13/15],
wr_async_node [0/0/0], wr_async_meta [0/0/0]

 f2fs_ckpt-254:1-507     [002] ....  2845.450514: f2fs_iostat_latency:
dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count],
rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1],
wr_sync_data [120/12/2285], wr_sync_node [88/5/428],
wr_sync_meta [52/6/2990], wr_async_data [4/1/3],
wr_async_node [0/0/0], wr_async_meta [0/0/0]

Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 15 insertions, 4 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index fd16c4fc4507..5e4120b92f59 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -271,7 +271,10 @@ static void f2fs_post_read_work(struct work_struct *work)
 static void f2fs_read_end_io(struct bio *bio)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio));
-	struct bio_post_read_ctx *ctx = bio->bi_private;
+	struct bio_post_read_ctx *ctx;
+
+	iostat_update_and_unbind_ctx(bio, 0);
+	ctx = bio->bi_private;
 
 	if (time_to_inject(sbi, FAULT_READ_IO)) {
 		f2fs_show_injection_info(sbi, FAULT_READ_IO);
@@ -293,10 +296,13 @@ static void f2fs_read_end_io(struct bio *bio)
 
 static void f2fs_write_end_io(struct bio *bio)
 {
-	struct f2fs_sb_info *sbi = bio->bi_private;
+	struct f2fs_sb_info *sbi;
 	struct bio_vec *bvec;
 	struct bvec_iter_all iter_all;
 
+	iostat_update_and_unbind_ctx(bio, 1);
+	sbi = bio->bi_private;
+
 	if (time_to_inject(sbi, FAULT_WRITE_IO)) {
 		f2fs_show_injection_info(sbi, FAULT_WRITE_IO);
 		bio->bi_status = BLK_STS_IOERR;
@@ -400,6 +406,8 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
 		bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi,
 						fio->type, fio->temp);
 	}
+	iostat_alloc_and_bind_ctx(sbi, bio, NULL);
+
 	if (fio->io_wbc)
 		wbc_init_bio(fio->io_wbc, bio);
 
@@ -481,6 +489,8 @@ submit_io:
 		trace_f2fs_submit_read_bio(sbi->sb, type, bio);
 	else
 		trace_f2fs_submit_write_bio(sbi->sb, type, bio);
+
+	iostat_update_submit_ctx(bio, type);
 	submit_bio(bio);
 }
 
@@ -972,7 +982,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
-	struct bio_post_read_ctx *ctx;
+	struct bio_post_read_ctx *ctx = NULL;
 	unsigned int post_read_steps = 0;
 
 	bio = bio_alloc_bioset(for_write ? GFP_NOIO : GFP_KERNEL,
@@ -1008,6 +1018,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 		ctx->fs_blkaddr = blkaddr;
 		bio->bi_private = ctx;
 	}
+	iostat_alloc_and_bind_ctx(sbi, bio, ctx);
 
 	return bio;
 }
@@ -2253,7 +2264,7 @@ submit_and_realloc:
 		if (bio_add_page(bio, page, blocksize, 0) < blocksize)
 			goto submit_and_realloc;
 
-		ctx = bio->bi_private;
+		ctx = get_post_read_ctx(bio);
 		ctx->enabled_steps |= STEP_DECOMPRESS;
 		refcount_inc(&dic->refcnt);