dm thin: relax hard limit on the maximum size of a metadata device

The thin metadata format can only make use of a device that is <=
THIN_METADATA_MAX_SECTORS (currently 15.9375 GB).  Therefore, there is no
practical benefit to using a larger device.

However, it may be that other factors impose a certain granularity for
the space that is allocated to a device (E.g. lvm2 can impose a coarse
granularity through the use of large, >= 1 GB, physical extents).

Rather than reject a larger metadata device, during thin-pool device
construction, switch to allowing it but issue a warning if a device
larger than THIN_METADATA_MAX_SECTORS_WARNING (16 GB) is
provided.  Any space over 15.9375 GB will not be used.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index da50347c00538ec63e761054aa7f50f87159dc9a..a119fbdd0604402122c1a2991ab63c7af81d5273 100644 (file)
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -75,10 +75,12 @@ less sharing than average you'll need a larger-than-average metadata device.
 
 As a guide, we suggest you calculate the number of bytes to use in the
 metadata device as 48 * $data_dev_size / $data_block_size but round it up
-to 2MB if the answer is smaller.  The largest size supported is 16GB.
+to 2MB if the answer is smaller.  If you're creating large numbers of
+snapshots which are recording large amounts of change, you may find you
+need to increase this.
 
-If you're creating large numbers of snapshots which are recording large
-amounts of change, you may need find you need to increase this.
+The largest size supported is 16GB: If the device is larger,
+a warning will be issued and the excess space will not be used.
 
 Reloading a pool table
 ----------------------

diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index a680c761341f14caa0702320c9e0dcb53e89fabe..737d38865b693fb0288306477587f4e0d52f6cfa 100644 (file)
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -713,6 +713,9 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
        if (r)
                goto bad;
 
+       if (bdev_size > THIN_METADATA_MAX_SECTORS)
+               bdev_size = THIN_METADATA_MAX_SECTORS;
+
        disk_super = dm_block_data(sblock);
        disk_super->magic = cpu_to_le64(THIN_SUPERBLOCK_MAGIC);
        disk_super->version = cpu_to_le32(THIN_VERSION);

diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 859c16896877795732ad89df1b854bd2242d019b..ed4725e67c96fbae52f1ce48c28d79f0a02075a4 100644 (file)
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -11,6 +11,19 @@
 
 #define THIN_METADATA_BLOCK_SIZE 4096
 
+/*
+ * The metadata device is currently limited in size.
+ *
+ * We have one block of index, which can hold 255 index entries.  Each
+ * index entry contains allocation info about 16k metadata blocks.
+ */
+#define THIN_METADATA_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
+
+/*
+ * A metadata device larger than 16GB triggers a warning.
+ */
+#define THIN_METADATA_MAX_SECTORS_WARNING (16 * (1024 * 1024 * 1024 >> SECTOR_SHIFT))
+
 /*----------------------------------------------------------------*/
 
 struct dm_pool_metadata;

diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index bcb143396fe004b609392610ab5df5fa3d9b9748..2378ee88b1e829923b612ab70fca661d6b030ac7 100644 (file)
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -32,16 +32,6 @@
 #define DATA_DEV_BLOCK_SIZE_MIN_SECTORS (64 * 1024 >> SECTOR_SHIFT)
 #define DATA_DEV_BLOCK_SIZE_MAX_SECTORS (1024 * 1024 * 1024 >> SECTOR_SHIFT)
 
-/*
- * The metadata device is currently limited in size.  The limitation is
- * checked lower down in dm-space-map-metadata, but we also check it here
- * so we can fail early.
- *
- * We have one block of index, which can hold 255 index entries.  Each
- * index entry contains allocation info about 16k metadata blocks.
- */
-#define METADATA_DEV_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
-
 /*
  * Device id is restricted to 24 bits.
  */
@@ -1736,6 +1726,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
        dm_block_t low_water_blocks;
        struct dm_dev *metadata_dev;
        sector_t metadata_dev_size;
+       char b[BDEVNAME_SIZE];
 
        /*
         * FIXME Remove validation from scope of lock.
@@ -1757,11 +1748,9 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
        }
 
        metadata_dev_size = i_size_read(metadata_dev->bdev->bd_inode) >> SECTOR_SHIFT;
-       if (metadata_dev_size > METADATA_DEV_MAX_SECTORS) {
-               ti->error = "Metadata device is too large";
-               r = -EINVAL;
-               goto out_metadata;
-       }
+       if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING)
+               DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.",
+                      bdevname(metadata_dev->bdev, b), THIN_METADATA_MAX_SECTORS);
 
        r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev);
        if (r) {