aboutsummaryrefslogtreecommitdiff
path: root/drivers/block/drbd/drbd_main.c
diff options
context:
space:
mode:
authorLars Ellenberg <lars.ellenberg@linbit.com>2013-03-19 18:16:44 +0100
committerJens Axboe <axboe@kernel.dk>2013-03-22 18:13:59 -0600
commit3a4d4eb3cb03fbc66696fc8cd472701d56f3aee7 (patch)
tree06a5d9a18bb35f23e68c3cca745f28b3f409e41c /drivers/block/drbd/drbd_main.c
parentae8bf312e97d554b6aa32e7b2ceb993812ad0835 (diff)
downloadvexpress-lsk-3a4d4eb3cb03fbc66696fc8cd472701d56f3aee7.tar.gz
drbd: prepare for new striped layout of activity log
Introduce two new on-disk meta data fields: al_stripes and al_stripe_size_4k The intended use case is activity log on RAID 0 or similar. Logically consecutive transactions will advance their on-disk position by al_stripe_size_4k 4kB (transaction sized) blocks. Right now, these are still asserted to be the backward compatible values al_stripes = 1, al_stripe_size_4k = 8 (which amounts to 32kB). Also introduce a caching member for meta_dev_idx in the in-core structure: even though it is initially passed in in the rcu-protected disk_conf structure, it cannot change without a detach/attach cycle. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'drivers/block/drbd/drbd_main.c')
-rw-r--r--drivers/block/drbd/drbd_main.c77
1 files changed, 69 insertions, 8 deletions
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 76faeab40c8..7a2e07b45ec 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2850,7 +2850,11 @@ struct meta_data_on_disk {
u32 bm_bytes_per_bit; /* BM_BLOCK_SIZE */
u32 la_peer_max_bio_size; /* last peer max_bio_size */
- u8 reserved_u8[4096 - (7*8 + 8*4)];
+ /* see al_tr_number_to_on_disk_sector() */
+ u32 al_stripes;
+ u32 al_stripe_size_4k;
+
+ u8 reserved_u8[4096 - (7*8 + 10*4)];
} __packed;
/**
@@ -2898,7 +2902,10 @@ void drbd_md_sync(struct drbd_conf *mdev)
buffer->bm_offset = cpu_to_be32(mdev->ldev->md.bm_offset);
buffer->la_peer_max_bio_size = cpu_to_be32(mdev->peer_max_bio_size);
- D_ASSERT(drbd_md_ss__(mdev, mdev->ldev) == mdev->ldev->md.md_offset);
+ buffer->al_stripes = cpu_to_be32(mdev->ldev->md.al_stripes);
+ buffer->al_stripe_size_4k = cpu_to_be32(mdev->ldev->md.al_stripe_size_4k);
+
+ D_ASSERT(drbd_md_ss(mdev->ldev) == mdev->ldev->md.md_offset);
sector = mdev->ldev->md.md_offset;
if (drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
@@ -2916,13 +2923,60 @@ out:
put_ldev(mdev);
}
+static int check_activity_log_stripe_size(struct drbd_conf *mdev,
+ struct meta_data_on_disk *on_disk,
+ struct drbd_md *in_core)
+{
+ u32 al_stripes = be32_to_cpu(on_disk->al_stripes);
+ u32 al_stripe_size_4k = be32_to_cpu(on_disk->al_stripe_size_4k);
+ u64 al_size_4k;
+
+ /* both not set: default to old fixed size activity log */
+ if (al_stripes == 0 && al_stripe_size_4k == 0) {
+ al_stripes = 1;
+ al_stripe_size_4k = MD_32kB_SECT/8;
+ }
+
+ /* some paranoia plausibility checks */
+
+ /* we need both values to be set */
+ if (al_stripes == 0 || al_stripe_size_4k == 0)
+ goto err;
+
+ al_size_4k = (u64)al_stripes * al_stripe_size_4k;
+
+ /* Upper limit of activity log area, to avoid potential overflow
+ * problems in al_tr_number_to_on_disk_sector(). As right now, more
+ * than 72 * 4k blocks total only increases the amount of history,
+ * limiting this arbitrarily to 16 GB is not a real limitation ;-) */
+ if (al_size_4k > (16 * 1024 * 1024/4))
+ goto err;
+
+ /* Lower limit: we need at least 8 transaction slots (32kB)
+ * to not break existing setups */
+ if (al_size_4k < MD_32kB_SECT/8)
+ goto err;
+
+ in_core->al_stripe_size_4k = al_stripe_size_4k;
+ in_core->al_stripes = al_stripes;
+ in_core->al_size_4k = al_size_4k;
+
+ return 0;
+err:
+ dev_err(DEV, "invalid activity log striping: al_stripes=%u, al_stripe_size_4k=%u\n",
+ al_stripes, al_stripe_size_4k);
+ return -EINVAL;
+}
+
/**
* drbd_md_read() - Reads in the meta data super block
* @mdev: DRBD device.
* @bdev: Device from which the meta data should be read in.
*
- * Return 0 (NO_ERROR) on success, and an enum drbd_ret_code in case
+ * Return NO_ERROR on success, and an enum drbd_ret_code in case
* something goes wrong.
+ *
+ * Called exactly once during drbd_adm_attach()
*/
int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
{
@@ -2937,6 +2991,10 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
if (!buffer)
goto out;
+ /* First, figure out where our meta data superblock is located. */
+ bdev->md.meta_dev_idx = bdev->disk_conf->meta_dev_idx;
+ bdev->md.md_offset = drbd_md_ss(bdev);
+
if (drbd_md_sync_page_io(mdev, bdev, bdev->md.md_offset, READ)) {
/* NOTE: can't do normal error processing here as this is
called BEFORE disk is attached */
@@ -2954,40 +3012,43 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
rv = ERR_MD_UNCLEAN;
goto err;
}
+
+ rv = ERR_MD_INVALID;
if (magic != DRBD_MD_MAGIC_08) {
if (magic == DRBD_MD_MAGIC_07)
dev_err(DEV, "Found old (0.7) meta data magic. Did you \"drbdadm create-md\"?\n");
else
dev_err(DEV, "Meta data magic not found. Did you \"drbdadm create-md\"?\n");
- rv = ERR_MD_INVALID;
goto err;
}
+
+ if (check_activity_log_stripe_size(mdev, buffer, &bdev->md))
+ goto err;
+
if (be32_to_cpu(buffer->al_offset) != bdev->md.al_offset) {
dev_err(DEV, "unexpected al_offset: %d (expected %d)\n",
be32_to_cpu(buffer->al_offset), bdev->md.al_offset);
- rv = ERR_MD_INVALID;
goto err;
}
if (be32_to_cpu(buffer->bm_offset) != bdev->md.bm_offset) {
dev_err(DEV, "unexpected bm_offset: %d (expected %d)\n",
be32_to_cpu(buffer->bm_offset), bdev->md.bm_offset);
- rv = ERR_MD_INVALID;
goto err;
}
if (be32_to_cpu(buffer->md_size_sect) != bdev->md.md_size_sect) {
dev_err(DEV, "unexpected md_size: %u (expected %u)\n",
be32_to_cpu(buffer->md_size_sect), bdev->md.md_size_sect);
- rv = ERR_MD_INVALID;
goto err;
}
if (be32_to_cpu(buffer->bm_bytes_per_bit) != BM_BLOCK_SIZE) {
dev_err(DEV, "unexpected bm_bytes_per_bit: %u (expected %u)\n",
be32_to_cpu(buffer->bm_bytes_per_bit), BM_BLOCK_SIZE);
- rv = ERR_MD_INVALID;
goto err;
}
+ rv = NO_ERROR;
+
bdev->md.la_size_sect = be64_to_cpu(buffer->la_size);
for (i = UI_CURRENT; i < UI_SIZE; i++)
bdev->md.uuid[i] = be64_to_cpu(buffer->uuid[i]);