Commit 4d3aed70 authored by Daniel Rosenberg's avatar Daniel Rosenberg Committed by Jaegeuk Kim
Browse files

f2fs: Add option to limit required GC for checkpoint=disable 



This extends the checkpoint option to allow checkpoint=disable:%u[%]
This allows you to specify what how much of the disk you are willing
to lose access to while mounting with checkpoint=disable. If the amount
lost would be higher, the mount will return -EAGAIN. This can be given
as a percent of total space, or in blocks.

Currently, we need to run garbage collection until the amount of holes
is smaller than the OVP space. With the new option, f2fs can mark
space as unusable up front instead of requiring garbage collection until
the number of holes is small enough.

Signed-off-by: default avatarDaniel Rosenberg <drosen@google.com>
Reviewed-by: default avatarChao Yu <yuchao0@huawei.com>
Signed-off-by: default avatarJaegeuk Kim <jaegeuk@kernel.org>
parent a4c3ecaa

Documentation/ABI/testing/sysfs-fs-f2fs

+8 −0
Original line number Diff line number Diff line
@@ -243,3 +243,11 @@ Description: 
		 - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list

		 - [h] means add/del hot file extension

		 - [c] means add/del cold file extension



What:		/sys/fs/f2fs/<disk>/unusable

Date		April 2019

Contact:	"Daniel Rosenberg" <drosen@google.com>

Description:

		If checkpoint=disable, it displays the number of blocks that are unusable.

                If checkpoint=enable it displays the enumber of blocks that would be unusable

                if checkpoint=disable were to be set.

Documentation/filesystems/f2fs.txt

+18 −1
Original line number Diff line number Diff line
@@ -214,11 +214,22 @@ fsync_mode=%s Control the policy of fsync. Currently supports "posix", 
                       non-atomic files likewise "nobarrier" mount option.

test_dummy_encryption  Enable dummy encryption, which provides a fake fscrypt

                       context. The fake fscrypt context is used by xfstests.

checkpoint=%s          Set to "disable" to turn off checkpointing. Set to "enable"

checkpoint=%s[:%u[%]]     Set to "disable" to turn off checkpointing. Set to "enable"

                       to reenable checkpointing. Is enabled by default. While

                       disabled, any unmounting or unexpected shutdowns will cause

                       the filesystem contents to appear as they did when the

                       filesystem was mounted with that option.

                       While mounting with checkpoint=disabled, the filesystem must

                       run garbage collection to ensure that all available space can

                       be used. If this takes too much time, the mount may return

                       EAGAIN. You may optionally add a value to indicate how much

                       of the disk you would be willing to temporarily give up to

                       avoid additional garbage collection. This can be given as a

                       number of blocks, or as a percent. For instance, mounting

                       with checkpoint=disable:100% would always succeed, but it may

                       hide up to all remaining free space. The actual space that

                       would be unusable can be viewed at /sys/fs/f2fs/<disk>/unusable

                       This space is reclaimed once checkpoint=enable.



================================================================================

DEBUGFS ENTRIES
@@ -396,6 +407,12 @@ Files in /sys/fs/f2fs/<devname> 


 current_reserved_blocks      This shows # of blocks currently reserved.



 unusable                     If checkpoint=disable, this shows the number of

                              blocks that are unusable.

                              If checkpoint=enable it shows the number of blocks

                              that would be unusable if checkpoint=disable were

                              to be set.



================================================================================

USAGE

================================================================================

fs/f2fs/f2fs.h

+5 −1
Original line number Diff line number Diff line
@@ -136,6 +136,9 @@ struct f2fs_mount_info { 
	int alloc_mode;			/* segment allocation policy */

	int fsync_mode;			/* fsync policy */

	bool test_dummy_encryption;	/* test dummy encryption */

	block_t unusable_cap;		/* Amount of space allowed to be

					 * unusable when disabling checkpoint

					 */

};



#define F2FS_FEATURE_ENCRYPT		0x0001
@@ -3085,7 +3088,8 @@ bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi); 
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,

					struct cp_control *cpc);

void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);

int f2fs_disable_cp_again(struct f2fs_sb_info *sbi);

block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);

int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);

void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);

int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);

void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);

fs/f2fs/segment.c

+14 −3
Original line number Diff line number Diff line
@@ -873,13 +873,14 @@ void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi) 
	mutex_unlock(&dirty_i->seglist_lock);

}



int f2fs_disable_cp_again(struct f2fs_sb_info *sbi)

block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi)

{

	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);

	int ovp_hole_segs =

		(overprovision_segments(sbi) - reserved_segments(sbi));

	block_t ovp_holes = ovp_hole_segs << sbi->log_blocks_per_seg;

	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);

	block_t holes[2] = {0, 0};	/* DATA and NODE */

	block_t unusable;

	struct seg_entry *se;

	unsigned int segno;
@@ -893,7 +894,17 @@ int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) 
	}

	mutex_unlock(&dirty_i->seglist_lock);



	if (holes[DATA] > ovp_holes || holes[NODE] > ovp_holes)

	unusable = holes[DATA] > holes[NODE] ? holes[DATA] : holes[NODE];

	if (unusable > ovp_holes)

		return unusable - ovp_holes;

	return 0;

}



int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable)

{

	int ovp_hole_segs =

		(overprovision_segments(sbi) - reserved_segments(sbi));

	if (unusable > F2FS_OPTION(sbi).unusable_cap)

		return -EAGAIN;

	if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) &&

		dirty_segments(sbi) > ovp_hole_segs)

fs/f2fs/super.c

+38 −21
Original line number Diff line number Diff line
@@ -136,7 +136,10 @@ enum { 
	Opt_alloc,

	Opt_fsync,

	Opt_test_dummy_encryption,

	Opt_checkpoint,

	Opt_checkpoint_disable,

	Opt_checkpoint_disable_cap,

	Opt_checkpoint_disable_cap_perc,

	Opt_checkpoint_enable,

	Opt_err,

};
@@ -195,7 +198,10 @@ static match_table_t f2fs_tokens = { 
	{Opt_alloc, "alloc_mode=%s"},

	{Opt_fsync, "fsync_mode=%s"},

	{Opt_test_dummy_encryption, "test_dummy_encryption"},

	{Opt_checkpoint, "checkpoint=%s"},

	{Opt_checkpoint_disable, "checkpoint=disable"},

	{Opt_checkpoint_disable_cap, "checkpoint=disable:%u"},

	{Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"},

	{Opt_checkpoint_enable, "checkpoint=enable"},

	{Opt_err, NULL},

};
@@ -772,22 +778,30 @@ static int parse_options(struct super_block *sb, char *options) 
					"Test dummy encryption mount option ignored");

#endif

			break;

		case Opt_checkpoint:

			name = match_strdup(&args[0]);

			if (!name)

				return -ENOMEM;



			if (strlen(name) == 6 &&

					!strncmp(name, "enable", 6)) {

				clear_opt(sbi, DISABLE_CHECKPOINT);

			} else if (strlen(name) == 7 &&

					!strncmp(name, "disable", 7)) {

		case Opt_checkpoint_disable_cap_perc:

			if (args->from && match_int(args, &arg))

				return -EINVAL;

			if (arg < 0 || arg > 100)

				return -EINVAL;

			if (arg == 100)

				F2FS_OPTION(sbi).unusable_cap =

					sbi->user_block_count;

			else

				F2FS_OPTION(sbi).unusable_cap =

					(sbi->user_block_count / 100) *	arg;

			set_opt(sbi, DISABLE_CHECKPOINT);

			} else {

				kvfree(name);

			break;

		case Opt_checkpoint_disable_cap:

			if (args->from && match_int(args, &arg))

				return -EINVAL;

			}

			kvfree(name);

			F2FS_OPTION(sbi).unusable_cap = arg;

			set_opt(sbi, DISABLE_CHECKPOINT);

			break;

		case Opt_checkpoint_disable:

			set_opt(sbi, DISABLE_CHECKPOINT);

			break;

		case Opt_checkpoint_enable:

			clear_opt(sbi, DISABLE_CHECKPOINT);

			break;

		default:

			f2fs_msg(sb, KERN_ERR,
@@ -1412,8 +1426,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) 
		seq_printf(seq, ",alloc_mode=%s", "reuse");



	if (test_opt(sbi, DISABLE_CHECKPOINT))

		seq_puts(seq, ",checkpoint=disable");



		seq_printf(seq, ",checkpoint=disable:%u",

				F2FS_OPTION(sbi).unusable_cap);

	if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX)

		seq_printf(seq, ",fsync_mode=%s", "posix");

	else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
@@ -1442,6 +1456,7 @@ static void default_options(struct f2fs_sb_info *sbi) 
	set_opt(sbi, EXTENT_CACHE);

	set_opt(sbi, NOHEAP);

	clear_opt(sbi, DISABLE_CHECKPOINT);

	F2FS_OPTION(sbi).unusable_cap = 0;

	sbi->sb->s_flags |= SB_LAZYTIME;

	set_opt(sbi, FLUSH_MERGE);

	set_opt(sbi, DISCARD);
@@ -1470,6 +1485,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) 
	struct cp_control cpc;

	int err = 0;

	int ret;

	block_t unusable;



	if (s_flags & SB_RDONLY) {

		f2fs_msg(sbi->sb, KERN_ERR,
@@ -1497,7 +1513,8 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) 
		goto restore_flag;

	}



	if (f2fs_disable_cp_again(sbi)) {

	unusable = f2fs_get_unusable_blocks(sbi);

	if (f2fs_disable_cp_again(sbi, unusable)) {

		err = -EAGAIN;

		goto restore_flag;

	}
@@ -1510,7 +1527,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) 
		goto out_unlock;



	spin_lock(&sbi->stat_lock);

	sbi->unusable_block_count = 0;

	sbi->unusable_block_count = unusable;

	spin_unlock(&sbi->stat_lock);



out_unlock:

CRA Git | Maintained and supported by SUSTech CRA and CCSE