[f2fs-dev,v3] f2fs: only fragment segment in the same section

Commit Message

Sheng Yong July 10, 2024, 1:26 a.m. UTC

When new_curseg() is allocating a new segment, if mode=fragment:xxx is
switched on in large section scenario, __get_next_segno() will select
the next segno randomly in the range of [0, maxsegno] in order to
fragment segments.

If the candidate segno is free, get_new_segment() will use it directly
as the new segment.

However, if the section of the candidate is not empty, and some other
segments have already been used, and have a different type (e.g NODE)
with the candidate (e.g DATA), GC will complain inconsistent segment
type later.

This could be reproduced by the following steps:

  dd if=/dev/zero of=test.img bs=1M count=10240
  mkfs.f2fs -s 128 test.img
  mount -t f2fs test.img /mnt -o mode=fragment:block
  echo 1 > /sys/fs/f2fs/loop0/max_fragment_chunk
  echo 512 > /sys/fs/f2fs/loop0/max_fragment_hole
  dd if=/dev/zero of=/mnt/testfile bs=4K count=100
  umount /mnt

  F2FS-fs (loop0): Inconsistent segment (4377) type [0, 1] in SSA and SIT

In order to allow simulating segment fragmentation in large section
scenario, this patch reduces the candidate range:
 * if curseg is the last segment in the section, return curseg->segno
   to make get_new_segment() itself find the next free segment.
 * if curseg is in the middle of the section, select candicate randomly
   in the range of [curseg + 1, last_seg_in_the_same_section] to keep
   type consistent.

Reviewed-by: Chao Yu <[e-mail]>
Signed-off-by: Sheng Yong <[e-mail]>
---
v3: adjust `if (__is_large_section)' check
v2: update commit msg
---
 fs/f2fs/segment.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

Comments

[e-mail] July 15, 2024, 2:40 p.m. UTC | #1

Hello:

This patch was applied to jaegeuk/f2fs.git (dev)
by Jaegeuk Kim <[e-mail]>:

On Wed, 10 Jul 2024 09:26:59 +0800 you wrote:
> When new_curseg() is allocating a new segment, if mode=fragment:xxx is
> switched on in large section scenario, __get_next_segno() will select
> the next segno randomly in the range of [0, maxsegno] in order to
> fragment segments.
> 
> If the candidate segno is free, get_new_segment() will use it directly
> as the new segment.
> 
> [...]

Here is the summary with links:
  - [f2fs-dev,v3] f2fs: only fragment segment in the same section
    https://git.kernel.org/jaegeuk/f2fs/c/e3a19972a49f

You are awesome, thank you!

Patch

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index a0ce3d080f80..161aed632278 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2784,11 +2784,19 @@  static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 	unsigned short seg_type = curseg->seg_type;
 
 	sanity_check_seg_type(sbi, seg_type);
-	if (f2fs_need_rand_seg(sbi))
-		return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi));
+	if (__is_large_section(sbi)) {
+		if (f2fs_need_rand_seg(sbi)) {
+			unsigned int hint = GET_SEC_FROM_SEG(sbi, curseg->segno);
 
-	if (__is_large_section(sbi))
+			if (GET_SEC_FROM_SEG(sbi, curseg->segno + 1) != hint)
+				return curseg->segno;
+			return get_random_u32_inclusive(curseg->segno + 1,
+					GET_SEG_FROM_SEC(sbi, hint + 1) - 1);
+		}
 		return curseg->segno;
+	} else if (f2fs_need_rand_seg(sbi)) {
+		return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi));
+	}
 
 	/* inmem log may not locate on any segment after mount */
 	if (!curseg->inited)