linux-f2fs-devel.lists.sourceforge.net archive mirror
 help / color / mirror / Atom feed
From: Jaegeuk Kim <jaegeuk@kernel.org>
To: Sheng Yong <shengyong@oppo.com>
Cc: daehojeong@google.com, linux-kernel@vger.kernel.org,
	linux-f2fs-devel@lists.sourceforge.net
Subject: Re: [f2fs-dev] [PATCH v2] f2fs: only fragment segment in the same section
Date: Tue, 9 Jul 2024 21:37:51 +0000	[thread overview]
Message-ID: <Zo2tr92oxPEuKBFm@google.com> (raw)
In-Reply-To: <20240625121512.3877754-1-shengyong@oppo.com>

On 06/25, Sheng Yong 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.
> 
> 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 secion, select candicate randomly in
>    the range of [curseg + 1, last_seg_in_the_same_section] to keep type
>    consistent.
> 
> Signed-off-by: Sheng Yong <shengyong@oppo.com>
> ---
> v2: update commit msg
> ---
>  fs/f2fs/segment.c | 15 +++++++++++++--
>  1 file changed, 13 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> index a0ce3d080f80a..55d474f5c2103 100644
> --- a/fs/f2fs/segment.c
> +++ b/fs/f2fs/segment.c
> @@ -2782,10 +2782,21 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
>  {
>  	struct curseg_info *curseg = CURSEG_I(sbi, type);
>  	unsigned short seg_type = curseg->seg_type;
> +	unsigned int hint;
>  
>  	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 (f2fs_need_rand_seg(sbi)) {
> +		if (__is_large_section(sbi)) {
> +			hint = GET_SEC_FROM_SEG(sbi, curseg->segno);
> +			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);
> +		} else {
> +			return get_random_u32_below(MAIN_SECS(sbi) *
> +						SEGS_PER_SEC(sbi));
> +		}
> +	}
>  
>  	if (__is_large_section(sbi))
>  		return curseg->segno;

	if (__is_large_section(sbi)) {
		if (f2fs_need_rand_seg(sbi)) {
			unsigned int hint = GET_SEC_FROM_SEG(sbi, curseg->segno);
			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));
	}

> -- 
> 2.40.1


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

      parent reply	other threads:[~2024-07-09 21:38 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-25  7:58 [f2fs-dev] [PATCH] f2fs: only fragment segment in the same section Sheng Yong via Linux-f2fs-devel
2024-06-25 12:15 ` [f2fs-dev] [PATCH v2] " Sheng Yong via Linux-f2fs-devel
2024-06-25 14:12   ` Chao Yu
2024-07-09 21:37   ` Jaegeuk Kim [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=Zo2tr92oxPEuKBFm@google.com \
    --to=jaegeuk@kernel.org \
    --cc=daehojeong@google.com \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=shengyong@oppo.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).