btrfs: Add zstd support

Add zstd compression and decompression support to BtrFS. zstd at its
fastest level compresses almost as well as zlib, while offering much
faster compression and decompression, approaching lzo speeds.

I benchmarked btrfs with zstd compression against no compression, lzo
compression, and zlib compression. I benchmarked two scenarios. Copying
a set of files to btrfs, and then reading the files. Copying a tarball
to btrfs, extracting it to btrfs, and then reading the extracted files.
After every operation, I call `sync` and include the sync time.
Between every pair of operations I unmount and remount the filesystem
to avoid caching. The benchmark files can be found in the upstream
zstd source repository under
`contrib/linux-kernel/{btrfs-benchmark.sh,btrfs-extract-benchmark.sh}`
[1] [2].

I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor,
16 GB of RAM, and a SSD.

The first compression benchmark is copying 10 copies of the unzipped
Silesia corpus [3] into a BtrFS filesystem mounted with
`-o compress-force=Method`. The decompression benchmark times how long
it takes to `tar` all 10 copies into `/dev/null`. The compression ratio is
measured by comparing the output of `df` and `du`. See the benchmark file
[1] for details. I benchmarked multiple zstd compression levels, although
the patch uses zstd level 1.

| Method  | Ratio | Compression MB/s | Decompression speed |
|---------|-------|------------------|---------------------|
| None    |  0.99 |              504 |                 686 |
| lzo     |  1.66 |              398 |                 442 |
| zlib    |  2.58 |               65 |                 241 |
| zstd 1  |  2.57 |              260 |                 383 |
| zstd 3  |  2.71 |              174 |                 408 |
| zstd 6  |  2.87 |               70 |                 398 |
| zstd 9  |  2.92 |               43 |                 406 |
| zstd 12 |  2.93 |               21 |                 408 |
| zstd 15 |  3.01 |               11 |                 354 |

The next benchmark first copies `linux-4.11.6.tar` [4] to btrfs. Then it
measures the compression ratio, extracts the tar, and deletes the tar.
Then it measures the compression ratio again, and `tar`s the extracted
files into `/dev/null`. See the benchmark file [2] for details.

| Method | Tar Ratio | Extract Ratio | Copy (s) | Extract (s)| Read (s) |
|--------|-----------|---------------|----------|------------|----------|
| None   |      0.97 |          0.78 |    0.981 |      5.501 |    8.807 |
| lzo    |      2.06 |          1.38 |    1.631 |      8.458 |    8.585 |
| zlib   |      3.40 |          1.86 |    7.750 |     21.544 |   11.744 |
| zstd 1 |      3.57 |          1.85 |    2.579 |     11.479 |    9.389 |

[1] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-benchmark.sh
[2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-extract-benchmark.sh
[3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia
[4] https://cdn.kernel.org/pub/linux/kernel/v4.x/linux-4.11.6.tar.xz

zstd source repository: https://github.com/facebook/zstdSigned-off-by: Nick Terrell <terrelln@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>

fs/btrfs/Kconfig

@@ -6,6 +6,8 @@ config BTRFS_FS
 	select ZLIB_DEFLATE
 	select LZO_COMPRESS
 	select LZO_DECOMPRESS
+	select ZSTD_COMPRESS
+	select ZSTD_DECOMPRESS
 	select RAID6_PQ
 	select XOR_BLOCKS
 	select SRCU

fs/btrfs/Makefile

@@ -6,7 +6,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   transaction.o inode.o file.o tree-defrag.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
-	   export.o tree-log.o free-space-cache.o zlib.o lzo.o \
+	   export.o tree-log.o free-space-cache.o zlib.o lzo.o zstd.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
 	   uuid-tree.o props.o hash.o free-space-tree.o

fs/btrfs/compression.c

@@ -704,6 +704,7 @@ static struct {
 static const struct btrfs_compress_op * const btrfs_compress_op[] = {
 	&btrfs_zlib_compress,
 	&btrfs_lzo_compress,
+	&btrfs_zstd_compress,
 };
 
 void __init btrfs_init_compress(void)

fs/btrfs/compression.h

@@ -99,8 +99,9 @@ enum btrfs_compression_type {
 	BTRFS_COMPRESS_NONE  = 0,
 	BTRFS_COMPRESS_ZLIB  = 1,
 	BTRFS_COMPRESS_LZO   = 2,
-	BTRFS_COMPRESS_TYPES = 2,
-	BTRFS_COMPRESS_LAST  = 3,
+	BTRFS_COMPRESS_ZSTD  = 3,
+	BTRFS_COMPRESS_TYPES = 3,
+	BTRFS_COMPRESS_LAST  = 4,
 };
 
 struct btrfs_compress_op {
@@ -128,5 +129,6 @@ struct btrfs_compress_op {
 
 extern const struct btrfs_compress_op btrfs_zlib_compress;
 extern const struct btrfs_compress_op btrfs_lzo_compress;
+extern const struct btrfs_compress_op btrfs_zstd_compress;
 
 #endif

fs/btrfs/ctree.h

@@ -270,6 +270,7 @@ struct btrfs_super_block {
 	 BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS |		\
 	 BTRFS_FEATURE_INCOMPAT_BIG_METADATA |		\
 	 BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO |		\
+	 BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD |		\
 	 BTRFS_FEATURE_INCOMPAT_RAID56 |		\
 	 BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF |		\
 	 BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA |	\

fs/btrfs/disk-io.c

@@ -2828,6 +2828,8 @@ int open_ctree(struct super_block *sb,
 	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
 	if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
 		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+	else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD)
+		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD;
 
 	if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
 		btrfs_info(fs_info, "has skinny extents");

fs/btrfs/ioctl.c

@@ -327,8 +327,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 
 		if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
 			comp = "lzo";
-		else
+		else if (fs_info->compress_type == BTRFS_COMPRESS_ZLIB)
 			comp = "zlib";
+		else
+			comp = "zstd";
 		ret = btrfs_set_prop(inode, "btrfs.compression",
 				     comp, strlen(comp), 0);
 		if (ret)
@@ -1466,6 +1468,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 
 	if (range->compress_type == BTRFS_COMPRESS_LZO) {
 		btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+	} else if (range->compress_type == BTRFS_COMPRESS_ZSTD) {
+		btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
 	}
 
 	ret = defrag_count;

fs/btrfs/props.c

@@ -390,6 +390,8 @@ static int prop_compression_validate(const char *value, size_t len)
 		return 0;
 	else if (!strncmp("zlib", value, len))
 		return 0;
+	else if (!strncmp("zstd", value, len))
+		return 0;
 
 	return -EINVAL;
 }
@@ -412,6 +414,8 @@ static int prop_compression_apply(struct inode *inode,
 		type = BTRFS_COMPRESS_LZO;
 	else if (!strncmp("zlib", value, len))
 		type = BTRFS_COMPRESS_ZLIB;
+	else if (!strncmp("zstd", value, len))
+		type = BTRFS_COMPRESS_ZSTD;
 	else
 		return -EINVAL;
 
@@ -429,6 +433,8 @@ static const char *prop_compression_extract(struct inode *inode)
 		return "zlib";
 	case BTRFS_COMPRESS_LZO:
 		return "lzo";
+	case BTRFS_COMPRESS_ZSTD:
+		return "zstd";
 	}
 
 	return NULL;

fs/btrfs/super.c

@@ -513,6 +513,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
 				btrfs_set_fs_incompat(info, COMPRESS_LZO);
 				no_compress = 0;
+			} else if (strcmp(args[0].from, "zstd") == 0) {
+				compress_type = "zstd";
+				info->compress_type = BTRFS_COMPRESS_ZSTD;
+				btrfs_set_opt(info->mount_opt, COMPRESS);
+				btrfs_clear_opt(info->mount_opt, NODATACOW);
+				btrfs_clear_opt(info->mount_opt, NODATASUM);
+				btrfs_set_fs_incompat(info, COMPRESS_ZSTD);
+				no_compress = 0;
 			} else if (strncmp(args[0].from, "no", 2) == 0) {
 				compress_type = "no";
 				btrfs_clear_opt(info->mount_opt, COMPRESS);
@@ -1227,8 +1235,10 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 	if (btrfs_test_opt(info, COMPRESS)) {
 		if (info->compress_type == BTRFS_COMPRESS_ZLIB)
 			compress_type = "zlib";
-		else
+		else if (info->compress_type == BTRFS_COMPRESS_LZO)
 			compress_type = "lzo";
+		else
+			compress_type = "zstd";
 		if (btrfs_test_opt(info, FORCE_COMPRESS))
 			seq_printf(seq, ",compress-force=%s", compress_type);
 		else

fs/btrfs/sysfs.c

@@ -200,6 +200,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(mixed_backref, MIXED_BACKREF);
 BTRFS_FEAT_ATTR_INCOMPAT(default_subvol, DEFAULT_SUBVOL);
 BTRFS_FEAT_ATTR_INCOMPAT(mixed_groups, MIXED_GROUPS);
 BTRFS_FEAT_ATTR_INCOMPAT(compress_lzo, COMPRESS_LZO);
+BTRFS_FEAT_ATTR_INCOMPAT(compress_zstd, COMPRESS_ZSTD);
 BTRFS_FEAT_ATTR_INCOMPAT(big_metadata, BIG_METADATA);
 BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF);
 BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
@@ -212,6 +213,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(default_subvol),
 	BTRFS_FEAT_ATTR_PTR(mixed_groups),
 	BTRFS_FEAT_ATTR_PTR(compress_lzo),
+	BTRFS_FEAT_ATTR_PTR(compress_zstd),
 	BTRFS_FEAT_ATTR_PTR(big_metadata),
 	BTRFS_FEAT_ATTR_PTR(extended_iref),
 	BTRFS_FEAT_ATTR_PTR(raid56),

include/uapi/linux/btrfs.h

@@ -255,13 +255,7 @@ struct btrfs_ioctl_fs_info_args {
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
 #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)
 #define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO	(1ULL << 3)
-/*
- * some patches floated around with a second compression method
- * lets save that incompat here for when they do get in
- * Note we don't actually support it, we're just reserving the
- * number
- */
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2	(1ULL << 4)
+#define BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD	(1ULL << 4)
 
 /*
  * older kernels tried to do bigger metadata blocks, but the