Currently, F2FS requires the packed_ssa feature to be enabled when
utilizing non-4KB block sizes (e.g., 16KB). This restriction limits
the flexibility of filesystem formatting options.
This patch allows F2FS to support non-4KB block sizes even when the
packed_ssa feature is disabled. It adjusts the SSA calculation logic to
correctly handle summary entries in larger blocks without the packed
layout.
Cc: stable@kernel.org
Fixes: 7ee8bc3942 ("f2fs: revert summary entry count from 2048 to 512 in 16kb block support")
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The check for enough sections in segment.h has the following issues:
1. has_not_enough_free_secs() should return "enough secs" when "free_secs
>= upper_secs", not just structly greater. Conversely, it should only
return "not enough secs" when "free_secs < lower_secs", not when they are
equal. This accounts for the possibility that blocks can fit within
curseg without requiring an additional free section.
2. __get_secs_required() currently separates the needed space to section
and block parts, checking them against free sections and curseg,
respectively. This does not consider the case where curseg cannot hold
the whole block part, but excess free sections beyond the section part
can accommodate some of the block part.
3. has_curseg_enough_space() only checks CURSEG_HOT_DATA for dentry
blocks, but when active_logs=6, they may be placed in WARM and COLD
sections. Also, the current logic does not consider that dentry and data
blocks can be put in the same section when active_logs=2 or 6.
This patch modifies the three functions to address the above issues:
1. Rename has_curseg_enough_space() to get_additional_blocks_required().
Calculate the minimum node, dentry, and data blocks curseg can
accommodate. Then subtract these from the total required blocks of
respective type to determine the worst-case number of blocks that must
be placed in free sections.
2. In __get_secs_required(), get the number of blocks needing new
sections from the new get_additional_blocks_required(). Return the upper
bound of necessary free sections for these blocks. For active_logs=2 or
6, dentry blocks are combined with data blocks.
3. In has_not_enough_free_secs(), get the required sections from
__get_secs_required(), and return “not enough secs” if “free_secs <
required_secs”.
Signed-off-by: Joanne Chang <joannechien@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
w/ LFS mode, in get_left_section_blocks(), we should not account the
blocks which were used before and now are invalided, otherwise those
blocks will be counted as freed one in has_curseg_enough_space(), result
in missing to trigger GC in time.
Cc: stable@kernel.org
Fixes: 249ad438e1 ("f2fs: add a method for calculating the remaining blocks in the current segment in LFS mode.")
Fixes: bf34c93d26 ("f2fs: check curseg space before foreground GC")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The usage of unusable_blocks_per_sec is already wrapped by
CONFIG_BLK_DEV_ZONED, except for its declaration and the definitions of
CAP_BLKS_PER_SEC and CAP_SEGS_PER_SEC. This patch ensures that all code
related to unusable_blocks_per_sec is properly wrapped under the
CONFIG_BLK_DEV_ZONED option.
Signed-off-by: Yongpeng Yang <yangyongpeng@xiaomi.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The recent increase in the number of Segment Summary Area (SSA) entries
from 512 to 2048 was an unintentional change in logic of 16kb block
support. This commit corrects the issue.
To better utilize the space available from the erroneous 2048-entry
calculation, we are implementing a solution to share the currently
unused SSA space with neighboring segments. This enhances overall
SSA utilization without impacting the established 8MB segment size.
Fixes: d7e9a9037d ("f2fs: Support Block Size == Page Size")
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Introduce get_left_section_blocks() for cleanup, no logic changes.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In lfs mode, dirty data needs OPU, we'd better calculate lower_p and
upper_p w/ them during has_not_enough_free_secs(), otherwise we may
encounter out-of-space issue due to we missed to reclaim enough
free section w/ foreground gc.
Fixes: 36abef4e79 ("f2fs: introduce mode=lfs mount option")
Cc: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Commit 1acd73edbb ("f2fs: fix to account dirty data in __get_secs_required()")
missed to calculate upper_p w/ data_secs, fix it.
Fixes: 1acd73edbb ("f2fs: fix to account dirty data in __get_secs_required()")
Cc: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
There are redundant codes in IS_CUR{SEG,SEC}() macros, let's introduce
inline is_cur{seg,sec}() functions, and use a loop in it for cleanup.
Meanwhile, it enhances expansibility, as it doesn't need to change
is_cur{seg,sec}() when we add a new log header.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
when performing buffered writes in a large section,
overhead is incurred due to the iteration through
ckpt_valid_blocks within the section.
when SEGS_PER_SEC is 128, this overhead accounts for 20% within
the f2fs_write_single_data_page routine.
as the size of the section increases, the overhead also grows.
to handle this problem ckpt_valid_blocks is
added within the section entries.
Test
insmod null_blk.ko nr_devices=1 completion_nsec=1 submit_queues=8
hw_queue_depth=64 max_sectors=512 bs=4096 memory_backed=1
make_f2fs /dev/block/nullb0
make_f2fs -s 128 /dev/block/nullb0
fio --bs=512k --size=1536M --rw=write --name=1
--filename=/mnt/test_dir/seq_write
--ioengine=io_uring --iodepth=64 --end_fsync=1
before
SEGS_PER_SEC 1
2556MiB/s
SEGS_PER_SEC 128
2145MiB/s
after
SEGS_PER_SEC 1
2556MiB/s
SEGS_PER_SEC 128
2556MiB/s
Signed-off-by: yohan.joung <yohan.joung@sk.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In LFS mode, the previous segment cannot use invalid blocks,
so the remaining blocks from the next_blkoff of the current segment
to the end of the section are calculated.
Signed-off-by: yohan.joung <yohan.joung@sk.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Grab a folio instead of a page. Also convert seg_info_to_sit_page() to
seg_info_to_sit_folio() and use a folio in f2fs_flush_sit_entries().
Saves a couple of calls to compound_head().
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When selecting a victim using next_victim_seg in a large section, the
selected section might already have been cleared and designated as the
new current section, making it actively in use.
This behavior causes inconsistency between the SIT and SSA.
F2FS-fs (dm-54): Inconsistent segment (70961) type [0, 1] in SSA and SIT
Call trace:
dump_backtrace+0xe8/0x10c
show_stack+0x18/0x28
dump_stack_lvl+0x50/0x6c
dump_stack+0x18/0x28
f2fs_stop_checkpoint+0x1c/0x3c
do_garbage_collect+0x41c/0x271c
f2fs_gc+0x27c/0x828
gc_thread_func+0x290/0x88c
kthread+0x11c/0x164
ret_from_fork+0x10/0x20
issue scenario
segs_per_sec=2
- seg#0 and seg#1 are all dirty
- all valid blocks are removed in seg#1
- gc select this sec and next_victim_seg=seg#0
- migrate seg#0, next_victim_seg=seg#1
- checkpoint -> sec(seg#0, seg#1) becomes free
- allocator assigns sec(seg#0, seg#1) to curseg
- gc tries to migrate seg#1
Fixes: e3080b0120 ("f2fs: support subsectional garbage collection")
Signed-off-by: yohan.joung <yohan.joung@sk.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
additional_reserved_segments was introduced by
commit 300a842937 ("f2fs: fix to reserve space for IO align feature"),
and its initialization was deleted by
commit 87161a2b0a ("f2fs: deprecate io_bits").
Signed-off-by: LongPing Wei <weilongping@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In __get_segment_type(), __get_segment_type_6() may return
CURSEG_COLD_DATA_PINNED or CURSEG_ALL_DATA_ATGC log type, but
following f2fs_get_segment_temp() can only handle persistent
log type, fix it.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When the free segment is used up during CP disable, many write or
ioctl operations will get ENOSPC error codes, even if there are
still many blocks available. We can reproduce it in the following
steps:
dd if=/dev/zero of=f2fs.img bs=1M count=65
mkfs.f2fs -f f2fs.img
mount f2fs.img f2fs_dir -o checkpoint=disable:10%
cd f2fs_dir
i=1 ; while [[ $i -lt 50 ]] ; do (file_name=./2M_file$i ; dd \
if=/dev/random of=$file_name bs=1M count=2); i=$((i+1)); done
sync
i=1 ; while [[ $i -lt 50 ]] ; do (file_name=./2M_file$i ; truncate \
-s 1K $file_name); i=$((i+1)); done
sync
dd if=/dev/zero of=./file bs=1M count=20
In f2fs_need_SSR() function, it is allowed to use SSR to allocate
blocks when CP is disabled, so in f2fs_is_checkpoint_ready function,
can we judge the number of invalid blocks when free segment is not
enough, and return ENOSPC only if the number of invalid blocks is
also not enough.
Signed-off-by: Qi Han <hanqi@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
first_zoned_segno() returns a fixed value, let's cache it in
structure f2fs_sb_info to avoid redundant calculation.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
It will trigger system panic w/ testcase in [1]:
------------[ cut here ]------------
kernel BUG at fs/f2fs/segment.c:2752!
RIP: 0010:new_curseg+0xc81/0x2110
Call Trace:
f2fs_allocate_data_block+0x1c91/0x4540
do_write_page+0x163/0xdf0
f2fs_outplace_write_data+0x1aa/0x340
f2fs_do_write_data_page+0x797/0x2280
f2fs_write_single_data_page+0x16cd/0x2190
f2fs_write_cache_pages+0x994/0x1c80
f2fs_write_data_pages+0x9cc/0xea0
do_writepages+0x194/0x7a0
filemap_fdatawrite_wbc+0x12b/0x1a0
__filemap_fdatawrite_range+0xbb/0xf0
file_write_and_wait_range+0xa1/0x110
f2fs_do_sync_file+0x26f/0x1c50
f2fs_sync_file+0x12b/0x1d0
vfs_fsync_range+0xfa/0x230
do_fsync+0x3d/0x80
__x64_sys_fsync+0x37/0x50
x64_sys_call+0x1e88/0x20d0
do_syscall_64+0x4b/0x110
entry_SYSCALL_64_after_hwframe+0x76/0x7e
The root cause is if checkpoint_disabling and lfs_mode are both on,
it will trigger OPU for all overwritten data, it may cost more free
segment than expected, so f2fs must account those data correctly to
calculate cosumed free segments later, and return ENOSPC earlier to
avoid run out of free segment during block allocation.
[1] https://lore.kernel.org/fstests/20241015025106.3203676-1-chao@kernel.org/
Fixes: 4354994f09 ("f2fs: checkpoint disabling")
Cc: Daniel Rosenberg <drosen@google.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When segs_per_sec is larger than 1, section may contain invalid segments,
mtime should be the average value of each valid blocks,
so introduce f2fs_get_section_mtime to
record the average mtime of all valid blocks in a section.
Signed-off-by: liuderong <liuderong@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We need to introduce a valid block ratio threshold not to trigger
excessive GC for zoned deivces. The initial value of it is 95%. So, F2FS
will stop the thread from intiating GC for sections having valid blocks
exceeding the ratio.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
get_ckpt_valid_blocks() checks valid ckpt blocks in current section.
It counts all vblocks from the first to the last segment in the
large section. However, START_SEGNO() is used to get the first segno
in an SIT block. This patch fixes that to get the correct start segno.
Fixes: 61461fc921 ("f2fs: fix to avoid touching checkpointed data in get_victim()")
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Kundan KumarandChristian Brauner
Daeho JeongandJaegeuk Kim
Joanne ChangandJaegeuk Kim
Chao YuandJaegeuk Kim
Yongpeng YangandJaegeuk Kim
yohan.joungandJaegeuk Kim
Matthew Wilcox (Oracle)andJaegeuk Kim
LongPing WeiandJaegeuk Kim
Qi HanandJaegeuk Kim
liuderongandJaegeuk Kim
Sheng YongandJaegeuk Kim