mkfs.f2fs: Introduce configurable reserved sections

Overview
========

This option allows zoned block device users to configure GC reserved and
overprovision area manually according to their demands on performance of
sustained write latency and WAF.

Problem
=======

The overprovision segments that mkfs generates are mostly occupied by GC
reserved. This degrades WAF performance.

Experiment
==========

The following experiment evaluated the application of configurable reserved.
The experimental environment is as follows.

  System info
    - 4.2Ghz, 8 core CPU
    - 64GiB Memory
  Device info
    - a conventional null_blk with 448MiB capacity(meta area) and
    - a sequential null_blk with 953 zones of 64MiB
  Format
    - as-is (find out ovp ratio): mkfs.f2fs <conv null_blk> -c <seq null_blk> -m
        Info: Overprovision ratio = 3.700%
        Info: Overprovision segments = 1152 (GC reserved = 1088)
    - config rsvd: mkfs.f2fs <conv null_blk> -c <seq null_blk> -m -Z 8 -o 2.965
        Info: Overprovision ratio = 2.965%
        Info: Overprovision segments = 1152 (GC reserved = 256)
  Mount
    - mount <conv null_blk> <mount point>
  Fio script
    - fio --rw=randwrite --bs=4k --ba=4k --filesize=58630m --norandommap --overwrite=1 --name=job1 --filename=<mount point>/sustain --time_based --runtime=2h
  WAF calculation
    - (IOs on conv. null_blk + IOs on seq. null_blk) / random write IOs

Conclusion
==========

In the experiment, it can be shown that reducing the reserved segments
decreases WAF to 10% (from 222 to 23) although it triggers checkpoint more
frequently during gc. With direct IO, the WAF of as-is gets much higher.
In other words, a user can configure more reserved segments for lower GC
latency or allocate less reserved segments for lower WAF on the same number
of OP segments.

Signed-off-by: Yonggil Song <yonggil.song@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

5 files changed, 84 insertions, 9 deletions

diff --git a/include/f2fs_fs.h b/include/f2fs_fs.h
index f890634..6948814 100644
--- a/include/f2fs_fs.h
+++ b/include/f2fs_fs.h
@@ -375,6 +375,10 @@ static inline uint64_t bswap_64(uint64_t val)
 
 #define LPF "lost+found"
 
+/* one for gc buffer, the other for node */
+#define MIN_RSVD_SECS	(NR_CURSEG_TYPE + 2U)
+#define CONFIG_RSVD_DEFAULT_OP_RATIO	3.0
+
 enum f2fs_config_func {
 	MKFS,
 	FSCK,
@@ -460,6 +464,7 @@ typedef struct {
 #define ALIGN_UP(addrs, size)	ALIGN_DOWN(((addrs) + (size) - 1), (size))
 
 struct f2fs_configuration {
+	uint32_t conf_reserved_sections;
 	uint32_t reserved_segments;
 	uint32_t new_reserved_segments;
 	int sparse_mode;
@@ -1618,6 +1623,20 @@ extern uint32_t f2fs_get_usable_segments(struct f2fs_super_block *sb);
 #define ZONE_ALIGN(blks)	SIZE_ALIGN(blks, c.blks_per_seg * \
 					c.segs_per_zone)
 
+static inline double get_reserved(struct f2fs_super_block *sb, double ovp)
+{
+	double reserved;
+	uint32_t usable_main_segs = f2fs_get_usable_segments(sb);
+	uint32_t segs_per_sec = round_up(usable_main_segs, get_sb(section_count));
+
+	if (c.conf_reserved_sections)
+		reserved = c.conf_reserved_sections * segs_per_sec;
+	else
+		reserved = (100 / ovp + 1 + NR_CURSEG_TYPE) * segs_per_sec;
+
+	return reserved;
+}
+
 static inline double get_best_overprovision(struct f2fs_super_block *sb)
 {
 	double reserved, ovp, candidate, end, diff, space;
@@ -1635,8 +1654,7 @@ static inline double get_best_overprovision(struct f2fs_super_block *sb)
 	}
 
 	for (; candidate <= end; candidate += diff) {
-		reserved = (100 / candidate + 1 + NR_CURSEG_TYPE) *
-				round_up(usable_main_segs, get_sb(section_count));
+		reserved = get_reserved(sb, candidate);
 		ovp = (usable_main_segs - reserved) * candidate / 100;
 		if (ovp < 0)
 			continue;
diff --git a/lib/libf2fs.c b/lib/libf2fs.c
index 93b0604..6b879f9 100644
--- a/lib/libf2fs.c
+++ b/lib/libf2fs.c
@@ -1066,6 +1066,24 @@ int get_device_info(int i)
 				dev->nr_rnd_zones);
 		MSG(0, "      %zu blocks per zone\n",
 				dev->zone_blocks);
+
+		if (c.conf_reserved_sections) {
+			if (c.conf_reserved_sections < MIN_RSVD_SECS) {
+				MSG(0, "      Too small sections are reserved(%u secs)\n",
+				    c.conf_reserved_sections);
+				c.conf_reserved_sections = MIN_RSVD_SECS;
+				MSG(0, "      It is operated as a minimum reserved sections(%u secs)\n",
+				    c.conf_reserved_sections);
+			} else {
+				MSG(0, "      %u sections are reserved\n",
+				c.conf_reserved_sections);
+			}
+			if (!c.overprovision) {
+				c.overprovision = CONFIG_RSVD_DEFAULT_OP_RATIO;
+				MSG(0, "      Overprovision ratio is set to default(%.1lf%%)\n",
+				    c.overprovision);
+			}
+		}
 	}
 #endif
 	/* adjust wanted_total_sectors */
diff --git a/man/mkfs.f2fs.8 b/man/mkfs.f2fs.8
index a6249f6..474c401 100644
--- a/man/mkfs.f2fs.8
+++ b/man/mkfs.f2fs.8
@@ -92,6 +92,10 @@ mkfs.f2fs \- create an F2FS file system
 [
 .B \-V
 ]
+[
+.B \-Z
+.I #-of-reserved-sections
+]
 .I device
 .I [sectors]
 .SH DESCRIPTION
@@ -265,6 +269,14 @@ Number of sectors. Default is determined by device size.
 .BI \-V
 Print the version number and exit.
 .TP
+.BI \-Z " #-of-reserved-sections"
+Specify the number of GC reserved sections for zoned device. If specified
+to non-zero, reserved segments count is set to the larger size between 8
+sections and the input value. If specified to zero, the best number will be
+assigned automatically according to the partition size.
+If overprovision-ratio-percentage is not specified, it will set to default
+3.0%. Without '-m' option, the filesystem doesn't support the feature.
+.TP
 .BI \-h,\ \-\-help
 Print usage and exit.
 .SH AUTHOR
diff --git a/mkfs/f2fs_format.c b/mkfs/f2fs_format.c
index f4a49ac..d3bb622 100644
--- a/mkfs/f2fs_format.c
+++ b/mkfs/f2fs_format.c
@@ -483,9 +483,7 @@ static int f2fs_prepare_super_block(void)
 	if (c.overprovision == 0)
 		c.overprovision = get_best_overprovision(sb);
 
-	c.reserved_segments =
-			(100 / c.overprovision + 1 + NR_CURSEG_TYPE) *
-			round_up(f2fs_get_usable_segments(sb), get_sb(section_count));
+	c.reserved_segments = get_reserved(sb, c.overprovision);
 
 	if (c.feature & cpu_to_le32(F2FS_FEATURE_RO)) {
 		c.overprovision = 0;
@@ -765,11 +763,31 @@ static int f2fs_write_check_point_pack(void)
 			get_cp(rsvd_segment_count)) *
 			c.overprovision / 100);
 
-	if (get_cp(overprov_segment_count) < get_cp(rsvd_segment_count))
+	if (!(c.conf_reserved_sections) &&
+	    get_cp(overprov_segment_count) < get_cp(rsvd_segment_count))
 		set_cp(overprov_segment_count, get_cp(rsvd_segment_count));
 
-	set_cp(overprov_segment_count, get_cp(overprov_segment_count) +
-			2 * get_sb(segs_per_sec));
+	/*
+	 * If conf_reserved_sections has a non zero value, overprov_segment_count
+	 * is set to overprov_segment_count + rsvd_segment_count.
+	 */
+	if (c.conf_reserved_sections) {
+		/*
+		 * Overprovision segments must be bigger than two sections.
+		 * In non configurable reserved section case, overprovision
+		 * segments are always bigger than two sections.
+		 */
+		if (get_cp(overprov_segment_count) < 2 * get_sb(segs_per_sec)) {
+			MSG(0, "\tError: Not enough overprovision segments (%u)\n",
+			    get_cp(overprov_segment_count));
+			goto free_cp_payload;
+		}
+		set_cp(overprov_segment_count, get_cp(overprov_segment_count) +
+				get_cp(rsvd_segment_count));
+	 } else {
+		set_cp(overprov_segment_count, get_cp(overprov_segment_count) +
+				2 * get_sb(segs_per_sec));
+	 }
 
 	if (f2fs_get_usable_segments(sb) <= get_cp(overprov_segment_count)) {
 		MSG(0, "\tError: Not enough segments to create F2FS Volume\n");
diff --git a/mkfs/f2fs_format_main.c b/mkfs/f2fs_format_main.c
index f50971c..07995b3 100644
--- a/mkfs/f2fs_format_main.c
+++ b/mkfs/f2fs_format_main.c
@@ -75,6 +75,7 @@ static void mkfs_usage()
 	MSG(0, "  -w wanted sector size\n");
 	MSG(0, "  -z # of sections per zone [default:1]\n");
 	MSG(0, "  -V print the version number and exit\n");
+	MSG(0, "  -Z # of reserved sections [default:auto]\n");
 	MSG(0, "sectors: number of sectors [default: determined by device size]\n");
 	exit(1);
 }
@@ -176,7 +177,7 @@ static void add_default_options(void)
 
 static void f2fs_parse_options(int argc, char *argv[])
 {
-	static const char *option_string = "qa:c:C:d:e:E:g:hil:mo:O:rR:s:S:z:t:T:U:Vfw:";
+	static const char *option_string = "qa:c:C:d:e:E:g:hil:mo:O:rR:s:S:z:t:T:U:Vfw:Z:";
 	static const struct option long_opts[] = {
 		{ .name = "help", .has_arg = 0, .flag = NULL, .val = 'h' },
 		{ .name = NULL, .has_arg = 0, .flag = NULL, .val = 0 }
@@ -295,6 +296,9 @@ static void f2fs_parse_options(int argc, char *argv[])
 			}
 			c.feature |= cpu_to_le32(F2FS_FEATURE_CASEFOLD);
 			break;
+		case 'Z':
+			c.conf_reserved_sections = atoi(optarg);
+			break;
 		default:
 			MSG(0, "\tError: Unknown option %c\n",option);
 			mkfs_usage();
@@ -490,6 +494,11 @@ int main(int argc, char *argv[])
 		goto err_format;
 	}
 
+	if (c.conf_reserved_sections && !c.zoned_mode) {
+		MSG(0, "\tError: Reserved area can't be specified on non zoned device\n");
+		goto err_format;
+	}
+
 	if (f2fs_format_device() < 0)
 		goto err_format;