| Message ID | 20240625121512.3877754-1-shengyong@oppo.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | [f2fs-dev,v2] f2fs: only fragment segment in the same section | expand |
On 2024/6/25 20:15, 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> Reviewed-by: Chao Yu <chao@kernel.org> Thanks,
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
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;
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(-)