@@ -242,6 +242,12 @@ offgrpjquota Turn off group journalled quota.
offprjjquota Turn off project journalled quota.
quota Enable plain user disk quota accounting.
noquota Disable all plain disk quota option.
+whint_mode=%s Control which write hints are passed down to block
+ layer. This supports "off", "user-based", and
+ "fs-based". In "off" mode (default), f2fs does not pass
+ down hints. In "user-based" mode, f2fs tries to pass
+ down hints given by users. And in "fs-based" mode, f2fs
+ passes down hints with its policy.
alloc_mode=%s Adjust block allocation policy, which supports "reuse"
and "default".
fsync_mode=%s Control the policy of fsync. Currently supports "posix",
@@ -776,6 +782,70 @@ In order to identify whether the data in the victim segment are valid or not,
F2FS manages a bitmap. Each bit represents the validity of a block, and the
bitmap is composed of a bit stream covering whole blocks in main area.
+Write-hint Policy
+-----------------
+
+1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET.
+
+2) whint_mode=user-based. F2FS tries to pass down hints given by
+users.
+
+===================== ======================== ===================
+User F2FS Block
+===================== ======================== ===================
+N/A META WRITE_LIFE_NOT_SET
+N/A HOT_NODE "
+N/A WARM_NODE "
+N/A COLD_NODE "
+ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
+extension list " "
+
+-- buffered io
+WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+WRITE_LIFE_NONE " "
+WRITE_LIFE_MEDIUM " "
+WRITE_LIFE_LONG " "
+
+-- direct io
+WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+WRITE_LIFE_NONE " WRITE_LIFE_NONE
+WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
+WRITE_LIFE_LONG " WRITE_LIFE_LONG
+===================== ======================== ===================
+
+3) whint_mode=fs-based. F2FS passes down hints with its policy.
+
+===================== ======================== ===================
+User F2FS Block
+===================== ======================== ===================
+N/A META WRITE_LIFE_MEDIUM;
+N/A HOT_NODE WRITE_LIFE_NOT_SET
+N/A WARM_NODE "
+N/A COLD_NODE WRITE_LIFE_NONE
+ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
+extension list " "
+
+-- buffered io
+WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG
+WRITE_LIFE_NONE " "
+WRITE_LIFE_MEDIUM " "
+WRITE_LIFE_LONG " "
+
+-- direct io
+WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+WRITE_LIFE_NONE " WRITE_LIFE_NONE
+WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
+WRITE_LIFE_LONG " WRITE_LIFE_LONG
+===================== ======================== ===================
+
Fallocate(2) Policy
-------------------
@@ -158,6 +158,7 @@ struct f2fs_mount_info {
int s_jquota_fmt; /* Format of quota to use */
#endif
/* For which write hints are passed down to block layer */
+ int whint_mode;
int alloc_mode; /* segment allocation policy */
int fsync_mode; /* fsync policy */
int fs_mode; /* fs mode: LFS or ADAPTIVE */
@@ -1345,6 +1346,12 @@ enum {
FS_MODE_FRAGMENT_BLK, /* block fragmentation mode */
};
+enum {
+ WHINT_MODE_OFF, /* not pass down write hints */
+ WHINT_MODE_USER, /* try to pass down hints given by users */
+ WHINT_MODE_FS, /* pass down hints with F2FS policy */
+};
+
enum {
ALLOC_MODE_DEFAULT, /* stay default */
ALLOC_MODE_REUSE, /* reuse segments as much as possible */
@@ -3731,6 +3738,8 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
void f2fs_destroy_segment_manager_caches(void);
int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
+enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
+ enum page_type type, enum temp_type temp);
unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
unsigned int segno);
unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
@@ -3290,6 +3290,101 @@ int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
}
}
+/* This returns write hints for each segment type. This hints will be
+ * passed down to block layer. There are mapping tables which depend on
+ * the mount option 'whint_mode'.
+ *
+ * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET.
+ *
+ * 2) whint_mode=user-based. F2FS tries to pass down hints given by users.
+ *
+ * User F2FS Block
+ * ---- ---- -----
+ * META WRITE_LIFE_NOT_SET
+ * HOT_NODE "
+ * WARM_NODE "
+ * COLD_NODE "
+ * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
+ * extension list " "
+ *
+ * -- buffered io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+ * WRITE_LIFE_NONE " "
+ * WRITE_LIFE_MEDIUM " "
+ * WRITE_LIFE_LONG " "
+ *
+ * -- direct io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+ * WRITE_LIFE_NONE " WRITE_LIFE_NONE
+ * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
+ * WRITE_LIFE_LONG " WRITE_LIFE_LONG
+ *
+ * 3) whint_mode=fs-based. F2FS passes down hints with its policy.
+ *
+ * User F2FS Block
+ * ---- ---- -----
+ * META WRITE_LIFE_MEDIUM;
+ * HOT_NODE WRITE_LIFE_NOT_SET
+ * WARM_NODE "
+ * COLD_NODE WRITE_LIFE_NONE
+ * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
+ * extension list " "
+ *
+ * -- buffered io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG
+ * WRITE_LIFE_NONE " "
+ * WRITE_LIFE_MEDIUM " "
+ * WRITE_LIFE_LONG " "
+ *
+ * -- direct io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+ * WRITE_LIFE_NONE " WRITE_LIFE_NONE
+ * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
+ * WRITE_LIFE_LONG " WRITE_LIFE_LONG
+ */
+
+enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
+ enum page_type type, enum temp_type temp)
+{
+ if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) {
+ if (type == DATA) {
+ if (temp == WARM)
+ return WRITE_LIFE_NOT_SET;
+ else if (temp == HOT)
+ return WRITE_LIFE_SHORT;
+ else if (temp == COLD)
+ return WRITE_LIFE_EXTREME;
+ } else {
+ return WRITE_LIFE_NOT_SET;
+ }
+ } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) {
+ if (type == DATA) {
+ if (temp == WARM)
+ return WRITE_LIFE_LONG;
+ else if (temp == HOT)
+ return WRITE_LIFE_SHORT;
+ else if (temp == COLD)
+ return WRITE_LIFE_EXTREME;
+ } else if (type == NODE) {
+ if (temp == WARM || temp == HOT)
+ return WRITE_LIFE_NOT_SET;
+ else if (temp == COLD)
+ return WRITE_LIFE_NONE;
+ } else if (type == META) {
+ return WRITE_LIFE_MEDIUM;
+ }
+ }
+ return WRITE_LIFE_NOT_SET;
+}
+
static int __get_segment_type_2(struct f2fs_io_info *fio)
{
if (fio->type == DATA)
@@ -156,6 +156,7 @@ enum {
Opt_jqfmt_vfsold,
Opt_jqfmt_vfsv0,
Opt_jqfmt_vfsv1,
+ Opt_whint,
Opt_alloc,
Opt_fsync,
Opt_test_dummy_encryption,
@@ -235,6 +236,7 @@ static match_table_t f2fs_tokens = {
{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
{Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
+ {Opt_whint, "whint_mode=%s"},
{Opt_alloc, "alloc_mode=%s"},
{Opt_fsync, "fsync_mode=%s"},
{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
@@ -1026,6 +1028,22 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
f2fs_info(sbi, "quota operations not supported");
break;
#endif
+ case Opt_whint:
+ name = match_strdup(&args[0]);
+ if (!name)
+ return -ENOMEM;
+ if (!strcmp(name, "user-based")) {
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER;
+ } else if (!strcmp(name, "off")) {
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
+ } else if (!strcmp(name, "fs-based")) {
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS;
+ } else {
+ kfree(name);
+ return -EINVAL;
+ }
+ kfree(name);
+ break;
case Opt_alloc:
name = match_strdup(&args[0]);
if (!name)
@@ -1437,6 +1455,12 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
return -EINVAL;
}
+ /* Not pass down write hints if the number of active logs is lesser
+ * than NR_CURSEG_PERSIST_TYPE.
+ */
+ if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE)
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
+
if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) {
f2fs_err(sbi, "Allow to mount readonly mode only");
return -EROFS;
@@ -2108,6 +2132,10 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",prjquota");
#endif
f2fs_show_quota_options(seq, sbi->sb);
+ if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER)
+ seq_printf(seq, ",whint_mode=%s", "user-based");
+ else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS)
+ seq_printf(seq, ",whint_mode=%s", "fs-based");
fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb);
@@ -2177,6 +2205,7 @@ static void default_options(struct f2fs_sb_info *sbi, bool remount)
F2FS_OPTION(sbi).active_logs = NR_CURSEG_PERSIST_TYPE;
F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
if (le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_main) <=
SMALL_VOLUME_SEGMENTS)
F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE;
@@ -2491,7 +2520,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
need_stop_gc = true;
}
- if (*flags & SB_RDONLY) {
+ if (*flags & SB_RDONLY ||
+ F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) {
sync_inodes_sb(sb);
set_sbi_flag(sbi, SBI_IS_DIRTY);
Restore support for the whint_mode mount option by reverting commit 930e2607638d ("f2fs: remove obsolete whint_mode"). Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Chao Yu <chao@kernel.org> Signed-off-by: Bart Van Assche <bvanassche@acm.org> --- Documentation/filesystems/f2fs.rst | 70 ++++++++++++++++++++++ fs/f2fs/f2fs.h | 9 +++ fs/f2fs/segment.c | 95 ++++++++++++++++++++++++++++++ fs/f2fs/super.c | 32 +++++++++- 4 files changed, 205 insertions(+), 1 deletion(-)