Btrfs-progs: detect if the disk we are formatting is a ssd

Patch rebased because of changes in mkfs.c but otherwise the same
as created by Josef Bacik

SSD's do not gain anything by having metadata DUP turned on.  The underlying
file system that is a part of all SSD's could easily map duplicate metadat
blocks into the same erase block which effectively eliminates the benefit of
duplicating the metadata on disk.  So detect if we are formatting a single
SSD drive and if we are do not use DUP.  Thanks,

Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Gene Czarcinski <gene@czarc.net>

diff --git a/Makefile b/Makefile
index 48949039fd044c0ddbb785437b069acfa5a6ca8e..c7fd97d582f1be404d7839759c074e0c5dd13612 100644 (file)
--- a/Makefile
+++ b/Makefile
@@ -67,7 +67,7 @@ btrfsck: $(objects) btrfsck.o
        $(CC) $(CFLAGS) -o btrfsck btrfsck.o $(objects) $(LDFLAGS) $(LIBS)
 
 mkfs.btrfs: $(objects) mkfs.o
-       $(CC) $(CFLAGS) -o mkfs.btrfs $(objects) mkfs.o $(LDFLAGS) $(LIBS)
+       $(CC) $(CFLAGS) -o mkfs.btrfs $(objects) mkfs.o $(LDFLAGS) $(LIBS) -lblkid
 
 btrfs-debug-tree: $(objects) debug-tree.o
        $(CC) $(CFLAGS) -o btrfs-debug-tree $(objects) debug-tree.o $(LDFLAGS) $(LIBS)

diff --git a/man/mkfs.btrfs.8.in b/man/mkfs.btrfs.8.in
index 72025ed780ced84d4ed41202a191d3c9aac55539..b7bcc1b2374ceb81eed60a92f797ae8b49bfd19c 100644 (file)
--- a/man/mkfs.btrfs.8.in
+++ b/man/mkfs.btrfs.8.in
@@ -47,7 +47,10 @@ Specify a label for the filesystem.
 .TP
 \fB\-m\fR, \fB\-\-metadata \fIprofile\fR
 Specify how metadata must be spanned across the devices specified. Valid
-values are raid0, raid1, raid10 or single.
+values are raid0, raid1, raid10, single or dup.  Single device will have dup
+set by default except in the case of SSDs which will default to single.  This is
+because SSDs can remap blocks internally so duplicate blocks could end up in the
+same erase block which negates the benefits of doing metadata duplication.
 .TP
 \fB\-M\fR, \fB\-\-mixed\fR
 Mix data and metadata chunks together for more efficient space 

diff --git a/mkfs.c b/mkfs.c
index 384f2c6108a15394891d290cca250fb66313e399..36c39145b31fe44a87242683c5f35dc0d9d292b7 100644 (file)
--- a/mkfs.c
+++ b/mkfs.c
@@ -39,6 +39,7 @@
 #include <linux/fs.h>
 #include <ctype.h>
 #include <attr/xattr.h>
+#include <blkid/blkid.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "volumes.h"
@@ -204,7 +205,7 @@ static int create_one_raid_group(struct btrfs_trans_handle *trans,
 static int create_raid_groups(struct btrfs_trans_handle *trans,
                              struct btrfs_root *root, u64 data_profile,
                              int data_profile_opt, u64 metadata_profile,
-                             int metadata_profile_opt, int mixed)
+                             int metadata_profile_opt, int mixed, int ssd)
 {
        u64 num_devices = btrfs_super_num_devices(&root->fs_info->super_copy);
        u64 allowed;
@@ -215,8 +216,12 @@ static int create_raid_groups(struct btrfs_trans_handle *trans,
         * For mixed groups defaults are single/single.
         */
        if (!metadata_profile_opt && !mixed) {
+               if (num_devices == 1 && ssd)
+                       printf("Detected a SSD, turning off metadata "
+                              "duplication.  Mkfs with -m dup if you want to "
+                              "force metadata duplication.\n");
                metadata_profile = (num_devices > 1) ?
-                       BTRFS_BLOCK_GROUP_RAID1 : BTRFS_BLOCK_GROUP_DUP;
+                       BTRFS_BLOCK_GROUP_RAID1 : (ssd) ? 0: BTRFS_BLOCK_GROUP_DUP;
        }
        if (!data_profile_opt && !mixed) {
                data_profile = (num_devices > 1) ?
@@ -1193,6 +1198,54 @@ static int check_leaf_or_node_size(u32 size, u32 sectorsize)
        return 0;
 }
 
+static int is_ssd(const char *file)
+{
+       char *devname;
+       blkid_probe probe;
+       char *dev;
+       char path[PATH_MAX];
+       dev_t disk;
+       int fd;
+       char rotational;
+
+       probe = blkid_new_probe_from_filename(file);
+       if (!probe)
+               return 0;
+
+       /*
+        * We want to use blkid_devno_to_wholedisk() but it's broken for some
+        * reason on F17 at least so we'll do this trickery
+        */
+       disk = blkid_probe_get_wholedisk_devno(probe);
+       if (!disk)
+               return 0;
+
+       devname = blkid_devno_to_devname(disk);
+       if (!devname)
+               return 0;
+
+       dev = strrchr(devname, '/');
+       dev++;
+
+       snprintf(path, PATH_MAX, "/sys/block/%s/queue/rotational", dev);
+
+       free(devname);
+       blkid_free_probe(probe);
+
+       fd = open(path, O_RDONLY);
+       if (fd < 0) {
+               return 0;
+       }
+
+       if (read(fd, &rotational, sizeof(char)) < sizeof(char)) {
+               close(fd);
+               return 0;
+       }
+       close(fd);
+
+       return !atoi((const char *)&rotational);
+}
+
 int main(int ac, char **av)
 {
        char *file;
@@ -1219,6 +1272,7 @@ int main(int ac, char **av)
        int data_profile_opt = 0;
        int metadata_profile_opt = 0;
        int nodiscard = 0;
+       int ssd = 0;
 
        char *source_dir = NULL;
        int source_dir_set = 0;
@@ -1338,6 +1392,9 @@ int main(int ac, char **av)
                        exit(1);
                }
        }
+
+       ssd = is_ssd(file);
+
        if (mixed) {
                if (metadata_profile != data_profile) {
                        fprintf(stderr, "With mixed block groups data and metadata "
@@ -1424,7 +1481,7 @@ raid_groups:
        if (!source_dir_set) {
                ret = create_raid_groups(trans, root, data_profile,
                                 data_profile_opt, metadata_profile,
-                                metadata_profile_opt, mixed);
+                                metadata_profile_opt, mixed, ssd);
                BUG_ON(ret);
        }