Let's deprecate an unused io_bits feature to save CPU cycles and memory.
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
option for more randomness.
Please, use these options for your experiments and we strongly
recommend to re-format the filesystem after using these options.
-io_bits=%u Set the bit size of write IO requests. It should be set
- with "mode=lfs".
usrquota Enable plain user disk quota accounting.
grpquota Enable plain group disk quota accounting.
prjquota Enable plain project quota accounting.
struct page *page = bvec->bv_page;
enum count_type type = WB_DATA_TYPE(page, false);
- if (page_private_dummy(page)) {
- clear_page_private_dummy(page);
- unlock_page(page);
- mempool_free(page, sbi->write_io_dummy);
-
- if (unlikely(bio->bi_status))
- f2fs_stop_checkpoint(sbi, true,
- STOP_CP_REASON_WRITE_FAIL);
- continue;
- }
-
fscrypt_finalize_bounce_page(&page);
#ifdef CONFIG_F2FS_FS_COMPRESSION
submit_bio(bio);
}
-static void f2fs_align_write_bio(struct f2fs_sb_info *sbi, struct bio *bio)
-{
- unsigned int start =
- (bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS) % F2FS_IO_SIZE(sbi);
-
- if (start == 0)
- return;
-
- /* fill dummy pages */
- for (; start < F2FS_IO_SIZE(sbi); start++) {
- struct page *page =
- mempool_alloc(sbi->write_io_dummy,
- GFP_NOIO | __GFP_NOFAIL);
- f2fs_bug_on(sbi, !page);
-
- lock_page(page);
-
- zero_user_segment(page, 0, PAGE_SIZE);
- set_page_private_dummy(page);
-
- if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
- f2fs_bug_on(sbi, 1);
- }
-}
-
static void f2fs_submit_write_bio(struct f2fs_sb_info *sbi, struct bio *bio,
enum page_type type)
{
WARN_ON_ONCE(is_read_io(bio_op(bio)));
- if (type == DATA || type == NODE) {
- if (f2fs_lfs_mode(sbi) && current->plug)
- blk_finish_plug(current->plug);
-
- if (F2FS_IO_ALIGNED(sbi)) {
- f2fs_align_write_bio(sbi, bio);
- /*
- * In the NODE case, we lose next block address chain.
- * So, we need to do checkpoint in f2fs_sync_file.
- */
- if (type == NODE)
- set_sbi_flag(sbi, SBI_NEED_CP);
- }
- }
+ if (f2fs_lfs_mode(sbi) && current->plug && PAGE_TYPE_ON_MAIN(type))
+ blk_finish_plug(current->plug);
trace_f2fs_submit_write_bio(sbi->sb, type, bio);
iostat_update_submit_ctx(bio, type);
block_t last_blkaddr,
block_t cur_blkaddr)
{
- if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE)) {
- unsigned int filled_blocks =
- F2FS_BYTES_TO_BLK(bio->bi_iter.bi_size);
- unsigned int io_size = F2FS_IO_SIZE(sbi);
- unsigned int left_vecs = bio->bi_max_vecs - bio->bi_vcnt;
-
- /* IOs in bio is aligned and left space of vectors is not enough */
- if (!(filled_blocks % io_size) && left_vecs < io_size)
- return false;
- }
if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr))
return false;
return io_type_is_mergeable(io, fio);
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
- if (F2FS_IO_ALIGNED(sbi) &&
- (fio->type == DATA || fio->type == NODE) &&
- fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
- dec_page_count(sbi, WB_DATA_TYPE(bio_page,
- fio->compressed_page));
- fio->retry = 1;
- goto skip;
- }
io->bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host,
bio_page->index, fio, GFP_NOIO);
__submit_merged_bio(io);
}
#endif
-skip:
if (fio->in_list)
goto next;
out:
if (fio) {
if (page_private_gcing(fio->page))
return true;
- if (page_private_dummy(fio->page))
- return true;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
return true;
struct f2fs_mount_info {
unsigned int opt;
- int write_io_size_bits; /* Write IO size bits */
block_t root_reserved_blocks; /* root reserved blocks */
kuid_t s_resuid; /* reserved blocks for uid */
kgid_t s_resgid; /* reserved blocks for gid */
* ... Only can be used with META.
*/
#define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type))
+#define PAGE_TYPE_ON_MAIN(type) ((type) == DATA || (type) == NODE)
enum page_type {
DATA = 0,
NODE = 1, /* should not change this */
unsigned int submitted:1; /* indicate IO submission */
unsigned int in_list:1; /* indicate fio is in io_list */
unsigned int is_por:1; /* indicate IO is from recovery or not */
- unsigned int retry:1; /* need to reallocate block address */
unsigned int encrypted:1; /* indicate file is encrypted */
unsigned int post_read:1; /* require post read */
enum iostat_type io_type; /* io type */
* Layout A: lowest bit should be 1
* | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... |
* bit 0 PAGE_PRIVATE_NOT_POINTER
- * bit 1 PAGE_PRIVATE_DUMMY_WRITE
- * bit 2 PAGE_PRIVATE_ONGOING_MIGRATION
- * bit 3 PAGE_PRIVATE_INLINE_INODE
- * bit 4 PAGE_PRIVATE_REF_RESOURCE
- * bit 5- f2fs private data
+ * bit 1 PAGE_PRIVATE_ONGOING_MIGRATION
+ * bit 2 PAGE_PRIVATE_INLINE_INODE
+ * bit 3 PAGE_PRIVATE_REF_RESOURCE
+ * bit 4- f2fs private data
*
* Layout B: lowest bit should be 0
* page.private is a wrapped pointer.
*/
enum {
PAGE_PRIVATE_NOT_POINTER, /* private contains non-pointer data */
- PAGE_PRIVATE_DUMMY_WRITE, /* data page for padding aligned IO */
PAGE_PRIVATE_ONGOING_MIGRATION, /* data page which is on-going migrating */
PAGE_PRIVATE_INLINE_INODE, /* inode page contains inline data */
PAGE_PRIVATE_REF_RESOURCE, /* dirty page has referenced resources */
struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */
/* keep migration IO order for LFS mode */
struct f2fs_rwsem io_order_lock;
- mempool_t *write_io_dummy; /* Dummy pages */
pgoff_t page_eio_ofs[NR_PAGE_TYPE]; /* EIO page offset */
int page_eio_cnt[NR_PAGE_TYPE]; /* EIO count */
if (!__allow_reserved_blocks(sbi, inode, true))
avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
- if (F2FS_IO_ALIGNED(sbi))
- avail_user_block_count -= sbi->blocks_per_seg *
- SM_I(sbi)->additional_reserved_segments;
-
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
if (avail_user_block_count > sbi->unusable_block_count)
avail_user_block_count -= sbi->unusable_block_count;
PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER);
PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION);
-PAGE_PRIVATE_GET_FUNC(dummy, DUMMY_WRITE);
PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE);
PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION);
-PAGE_PRIVATE_SET_FUNC(dummy, DUMMY_WRITE);
PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE);
PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION);
-PAGE_PRIVATE_CLEAR_FUNC(dummy, DUMMY_WRITE);
static inline unsigned long get_page_private_data(struct page *page)
{
if (!__allow_reserved_blocks(sbi, inode, false))
valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
- if (F2FS_IO_ALIGNED(sbi))
- valid_block_count += sbi->blocks_per_seg *
- SM_I(sbi)->additional_reserved_segments;
-
user_block_count = sbi->user_block_count;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
user_block_count -= sbi->unusable_block_count;
*/
if (f2fs_sb_has_blkzoned(sbi) && (rw == WRITE))
return true;
- if (f2fs_lfs_mode(sbi) && rw == WRITE && F2FS_IO_ALIGNED(sbi))
- return true;
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
return true;
.op_flags = 0,
.encrypted_page = NULL,
.in_list = 0,
- .retry = 0,
};
int err;
.op_flags = 0,
.encrypted_page = NULL,
.in_list = 0,
- .retry = 0,
};
struct dnode_of_data dn;
struct f2fs_summary sum;
fio.op_flags = REQ_SYNC;
fio.new_blkaddr = newaddr;
f2fs_submit_page_write(&fio);
- if (fio.retry) {
- err = -EAGAIN;
- if (PageWriteback(fio.encrypted_page))
- end_page_writeback(fio.encrypted_page);
- goto put_page_out;
- }
f2fs_update_iostat(fio.sbi, NULL, FS_GC_DATA_IO, F2FS_BLKSIZE);
f2fs_update_data_blkaddr(&dn, newaddr);
set_inode_flag(inode, FI_APPEND_WRITE);
-put_page_out:
+
f2fs_put_page(fio.encrypted_page, 1);
recover_block:
if (err)
if (fio) {
struct f2fs_bio_info *io;
- if (F2FS_IO_ALIGNED(sbi))
- fio->retry = 0;
-
INIT_LIST_HEAD(&fio->list);
fio->in_list = 1;
io = sbi->write_io[fio->type] + fio->temp;
if (keep_order)
f2fs_down_read(&fio->sbi->io_order_lock);
-reallocate:
+
f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
&fio->new_blkaddr, sum, type, fio);
if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
/* writeout dirty page into bdev */
f2fs_submit_page_write(fio);
- if (fio->retry) {
- fio->old_blkaddr = fio->new_blkaddr;
- goto reallocate;
- }
f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1);
Opt_resgid,
Opt_resuid,
Opt_mode,
- Opt_io_size_bits,
Opt_fault_injection,
Opt_fault_type,
Opt_lazytime,
{Opt_resgid, "resgid=%u"},
{Opt_resuid, "resuid=%u"},
{Opt_mode, "mode=%s"},
- {Opt_io_size_bits, "io_bits=%u"},
{Opt_fault_injection, "fault_injection=%u"},
{Opt_fault_type, "fault_type=%u"},
{Opt_lazytime, "lazytime"},
F2FS_OPTION(sbi).s_resgid));
}
-static inline int adjust_reserved_segment(struct f2fs_sb_info *sbi)
-{
- unsigned int sec_blks = sbi->blocks_per_seg * sbi->segs_per_sec;
- unsigned int avg_vblocks;
- unsigned int wanted_reserved_segments;
- block_t avail_user_block_count;
-
- if (!F2FS_IO_ALIGNED(sbi))
- return 0;
-
- /* average valid block count in section in worst case */
- avg_vblocks = sec_blks / F2FS_IO_SIZE(sbi);
-
- /*
- * we need enough free space when migrating one section in worst case
- */
- wanted_reserved_segments = (F2FS_IO_SIZE(sbi) / avg_vblocks) *
- reserved_segments(sbi);
- wanted_reserved_segments -= reserved_segments(sbi);
-
- avail_user_block_count = sbi->user_block_count -
- sbi->current_reserved_blocks -
- F2FS_OPTION(sbi).root_reserved_blocks;
-
- if (wanted_reserved_segments * sbi->blocks_per_seg >
- avail_user_block_count) {
- f2fs_err(sbi, "IO align feature can't grab additional reserved segment: %u, available segments: %u",
- wanted_reserved_segments,
- avail_user_block_count >> sbi->log_blocks_per_seg);
- return -ENOSPC;
- }
-
- SM_I(sbi)->additional_reserved_segments = wanted_reserved_segments;
-
- f2fs_info(sbi, "IO align feature needs additional reserved segment: %u",
- wanted_reserved_segments);
-
- return 0;
-}
-
static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi)
{
if (!F2FS_OPTION(sbi).unusable_cap_perc)
}
kfree(name);
break;
- case Opt_io_size_bits:
- if (args->from && match_int(args, &arg))
- return -EINVAL;
- if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) {
- f2fs_warn(sbi, "Not support %ld, larger than %d",
- BIT(arg), BIO_MAX_VECS);
- return -EINVAL;
- }
- F2FS_OPTION(sbi).write_io_size_bits = arg;
- break;
#ifdef CONFIG_F2FS_FAULT_INJECTION
case Opt_fault_injection:
if (args->from && match_int(args, &arg))
}
#endif
- if (F2FS_IO_SIZE_BITS(sbi) && !f2fs_lfs_mode(sbi)) {
- f2fs_err(sbi, "Should set mode=lfs with %luKB-sized IO",
- F2FS_IO_SIZE_KB(sbi));
- return -EINVAL;
- }
-
if (test_opt(sbi, INLINE_XATTR_SIZE)) {
int min_size, max_size;
f2fs_destroy_page_array_cache(sbi);
f2fs_destroy_xattr_caches(sbi);
- mempool_destroy(sbi->write_io_dummy);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
kfree(F2FS_OPTION(sbi).s_qf_names[i]);
F2FS_OPTION(sbi).s_resuid),
from_kgid_munged(&init_user_ns,
F2FS_OPTION(sbi).s_resgid));
- if (F2FS_IO_SIZE_BITS(sbi))
- seq_printf(seq, ",io_bits=%u",
- F2FS_OPTION(sbi).write_io_size_bits);
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (test_opt(sbi, FAULT_INJECTION)) {
seq_printf(seq, ",fault_injection=%u",
bool no_read_extent_cache = !test_opt(sbi, READ_EXTENT_CACHE);
bool no_age_extent_cache = !test_opt(sbi, AGE_EXTENT_CACHE);
bool enable_checkpoint = !test_opt(sbi, DISABLE_CHECKPOINT);
- bool no_io_align = !F2FS_IO_ALIGNED(sbi);
bool no_atgc = !test_opt(sbi, ATGC);
bool no_discard = !test_opt(sbi, DISCARD);
bool no_compress_cache = !test_opt(sbi, COMPRESS_CACHE);
goto restore_opts;
}
- if (no_io_align == !!F2FS_IO_ALIGNED(sbi)) {
- err = -EINVAL;
- f2fs_warn(sbi, "switch io_bits option is not allowed");
- goto restore_opts;
- }
-
if (no_compress_cache == !!test_opt(sbi, COMPRESS_CACHE)) {
err = -EINVAL;
f2fs_warn(sbi, "switch compress_cache option is not allowed");
FDEV(i).total_segments,
FDEV(i).start_blk, FDEV(i).end_blk);
}
- f2fs_info(sbi,
- "IO Block Size: %8ld KB", F2FS_IO_SIZE_KB(sbi));
return 0;
}
if (err)
goto free_iostat;
- if (F2FS_IO_ALIGNED(sbi)) {
- sbi->write_io_dummy =
- mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0);
- if (!sbi->write_io_dummy) {
- err = -ENOMEM;
- goto free_percpu;
- }
- }
-
/* init per sbi slab cache */
err = f2fs_init_xattr_caches(sbi);
if (err)
- goto free_io_dummy;
+ goto free_percpu;
err = f2fs_init_page_array_cache(sbi);
if (err)
goto free_xattr_cache;
goto free_nm;
}
- err = adjust_reserved_segment(sbi);
- if (err)
- goto free_nm;
-
/* For write statistics */
sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
f2fs_destroy_page_array_cache(sbi);
free_xattr_cache:
f2fs_destroy_xattr_caches(sbi);
-free_io_dummy:
- mempool_destroy(sbi->write_io_dummy);
free_percpu:
destroy_percpu_info(sbi);
free_iostat:
#define F2FS_ENC_UTF8_12_1 1
-#define F2FS_IO_SIZE(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
-#define F2FS_IO_SIZE_KB(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits + 2) /* KB */
-#define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */
-#define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1)
-#define F2FS_IO_ALIGNED(sbi) (F2FS_IO_SIZE(sbi) > 1)
-
/* This flag is used by node and meta inodes, and by recovery */
#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO)