mke2fs support for BLKDISCARD

Try calling the BLKDISCARD ioctl at mkfs time to pre-discard all blocks
on an ssd, or a thinly-provisioned storage device.

No real error checking; if it fails, it fails, and that's ok - it's
just an optimization.  Also, it cannot work in conjunction with
the undo io manager, for obvious reasons.

Optionally disabled with a "-K" (mnemonic: Keep) option.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/misc/mke2fs.8.in b/misc/mke2fs.8.in
index b02905b..45a99f8 100644 (file)
--- a/misc/mke2fs.8.in
+++ b/misc/mke2fs.8.in
@@ -45,6 +45,9 @@ mke2fs \- create an ext2/ext3/ext4 filesystem
 .I journal-options
 ]
 [
+.B \-K
+]
+[
 .B \-N
 .I number-of-inodes
 ]
@@ -366,6 +369,10 @@ and may be no more than 102,400 filesystem blocks.
 @JDEV@.BR size " or " device
 @JDEV@options can be given for a filesystem.
 .TP
+.BI \-K
+Keep, do not attempt to discard blocks at mkfs time (discarding blocks initially
+is useful on solid state devices and sparse / thin-provisioned storage).
+.TP
 .BI \-l " filename"
 Read the bad blocks list from
 .IR filename .

diff --git a/misc/mke2fs.c b/misc/mke2fs.c
index f86d6e7..02cd1b7 100644 (file)
--- a/misc/mke2fs.c
+++ b/misc/mke2fs.c
@@ -79,6 +79,7 @@ int   cflag;
 int    verbose;
 int    quiet;
 int    super_only;
+int    discard = 1;
 int    force;
 int    noaction;
 int    journal_size;
@@ -111,7 +112,7 @@ static void usage(void)
        "\t[-g blocks-per-group] [-L volume-label] "
        "[-M last-mounted-directory]\n\t[-O feature[,...]] "
        "[-r fs-revision] [-E extended-option[,...]]\n"
-       "\t[-T fs-type] [-U UUID] [-jnqvFSV] device [blocks-count]\n"),
+       "\t[-T fs-type] [-U UUID] [-jnqvFKSV] device [blocks-count]\n"),
                program_name);
        exit(1);
 }
@@ -1206,7 +1207,7 @@ static void PRS(int argc, char *argv[])
        }
 
        while ((c = getopt (argc, argv,
-                   "b:cf:g:G:i:jl:m:no:qr:s:t:vE:FI:J:L:M:N:O:R:ST:U:V")) != EOF) {
+                   "b:cf:g:G:i:jl:m:no:qr:s:t:vE:FI:J:KL:M:N:O:R:ST:U:V")) != EOF) {
                switch (c) {
                case 'b':
                        blocksize = strtol(optarg, &tmp, 0);
@@ -1285,6 +1286,9 @@ static void PRS(int argc, char *argv[])
                case 'J':
                        parse_journal_opts(optarg);
                        break;
+               case 'K':
+                       discard = 0;
+                       break;
                case 'j':
                        if (!journal_size)
                                journal_size = -1;
@@ -1906,6 +1910,48 @@ static int mke2fs_setup_tdb(const char *name, io_manager *io_ptr)
        return retval;
 }
 
+#ifdef __linux__
+
+#ifndef BLKDISCARD
+#define BLKDISCARD     _IO(0x12,119)
+#endif
+
+static void mke2fs_discard_blocks(ext2_filsys fs)
+{
+       int fd;
+       int ret;
+       int blocksize;
+       __u64 blocks;
+       __uint64_t range[2];
+
+       blocks = fs->super->s_blocks_count;
+       blocksize = EXT2_BLOCK_SIZE(fs->super);
+       range[0] = 0;
+       range[1] = blocks * blocksize;
+
+       fd = open64(fs->device_name, O_RDONLY);
+
+       /*
+        * We don't care about whether the ioctl succeeds; it's only an
+        * optmization for SSDs or sparse storage.
+        */
+       if (fd > 0) {
+               ret = ioctl(fd, BLKDISCARD, &range);
+               if (verbose) {
+                       printf(_("Calling BLKDISCARD from %llu to %llu "),
+                               range[0], range[1]);
+                       if (ret)
+                               printf(_("failed.\n"));
+                       else
+                               printf(_("succeeded.\n"));
+               }
+               close(fd);
+       }
+}
+#else
+#define mke2fs_discard_blocks(fs)
+#endif
+
 int main (int argc, char *argv[])
 {
        errcode_t       retval = 0;
@@ -1949,6 +1995,11 @@ int main (int argc, char *argv[])
                com_err(device_name, retval, _("while setting up superblock"));
                exit(1);
        }
+
+       /* Can't undo discard ... */
+       if (discard && (io_ptr != undo_io_manager))
+               mke2fs_discard_blocks(fs);
+
        sprintf(tdb_string, "tdb_data_size=%d", fs->blocksize <= 4096 ?
                32768 : fs->blocksize * 8);
        io_channel_set_options(fs->io, tdb_string);