[dm-devel] [PATCH] DM Snapshot: snapshot-merge target
Jonathan Brassow
jbrassow at redhat.com
Fri Apr 17 19:04:42 UTC 2009
This is just a concept at this stage, I may change the way the
implementation works... but it does work (as far as my light tests
show).
brassow
This patch introduces the "snapshot-merge" target. This target can be
used to merge a snapshot into an origin - amoung other uses. The
constructor table is almost identical to the snapshot target.
snapshot table : <start> <len> snapshot <real-origin> <exstore args>
snapshot-merge table: <start> <len> snapshot-merge <virt-origin> <exstore args>
When you create a device-mapper "snapshot-origin" device, the device you
interface with is the 'virt-origin', while the device it covers is the
'real-origin'.
The benefit of using the 'virt-origin' in the snapshot-merge table is that
doing so will preserve all the other snapshots that were made against the
origin. If you specify the 'real-origin', the other snapshots (the ones
you are not merging) would be corrupted. [There are reasons for using the
underlying 'real' devices, though. More on this later.]
The most common use for this target will be for "rollback" capability. If
you are going to upgrade a machine, you first take a snapshot. If the
upgrade fails, then you "merge" the snapshot deltas back into the origin -
restoring the pre-upgrade state. [In this case, you would be sure to
use the 'virt-origin' in your snapshot-merge table.]
Another use of this target is for quick backups. Imagine the following
method for backup (courtesy of Christophe Varoqui):
- snap lv_src (lv_src_snap0)
- full copy lv_src_snap0 to lv_dst
- while true
- wait n seconds
- snap lv_src (lv_src_snap1)
- use snapshot-merge to copy deltas of lv_src_snap0 to lv_dst
- remove lv_src_snap0
- rename lv_src_snap1 lv_src_snap0
- done
In this case, you would use the lv_dst in place of the 'virt-origin'.
The tricky part in this case is that the origin can be under active
use, and the COW will be changing. I don't have a good answer for this
yet, short of suspending the origin while the merge target is active.
Index: linux-2.6/drivers/md/dm-snap.c
===================================================================
--- linux-2.6.orig/drivers/md/dm-snap.c
+++ linux-2.6/drivers/md/dm-snap.c
@@ -1263,8 +1263,26 @@ static int snapshot_status(struct dm_tar
static int snapshot_message(struct dm_target *ti, unsigned argc, char **argv)
{
int r = 0;
+ chunk_t old, new;
struct dm_snapshare *ss = ti->private;
+ if ((argc == 2) &&
+ !strcmp(argv[0], "lookup")) {
+ if (sscanf(argv[1], "%lu", &old) != 1) {
+ DMERR("Failed to read in old chunk value");
+ return -EINVAL;
+ }
+ r = ss->store->type->lookup_exception(ss->store, old, &new,
+ DM_ES_LOOKUP_EXISTS |
+ DM_ES_LOOKUP_CAN_BLOCK);
+ new = dm_chunk_number(new);
+ if (!r)
+ DMERR("Exception found: %lu -> %lu", old, new);
+ else
+ DMERR("Exception not found: %d", r);
+ return 0;
+ }
+
if (ss->store->type->message)
r = ss->store->type->message(ss->store, argc, argv);
@@ -1517,6 +1535,307 @@ static int origin_status(struct dm_targe
return 0;
}
+/*-----------------------------------------------------------------
+ * Snapshot-merge methods
+ *---------------------------------------------------------------*/
+struct dm_snapshot_merge {
+ struct dm_dev *usable_origin;
+
+ spinlock_t lock;
+
+ chunk_t nr_chunks; /* total number of chunks */
+ chunk_t merge_progress; /* Number of chunks completed */
+ struct bio_list queued_bios; /* Block All I/O until merge complete */
+
+ struct dm_exception_store *store;
+
+ struct work_struct merge_work;
+ struct dm_kcopyd_client *kcopyd_client;
+};
+
+static void merge_callback(int read_err, unsigned long write_err, void *context)
+{
+ struct dm_snapshot_merge *sm = context;
+
+ if (read_err || write_err) {
+ DMERR("Failed merge operation");
+ return;
+ }
+
+ spin_lock(&sm->lock);
+ sm->merge_progress++;
+ spin_unlock(&sm->lock);
+
+ schedule_work(&sm->merge_work);
+}
+
+static void merge_work(struct work_struct *work)
+{
+ int rtn;
+ struct bio *bio;
+ struct bio_list bl;
+ uint32_t flags = DM_ES_LOOKUP_EXISTS | DM_ES_LOOKUP_CAN_BLOCK;
+ chunk_t merge_chunk;
+ struct dm_io_region src, dest;
+ struct dm_snapshot_merge *sm =
+ container_of(work, struct dm_snapshot_merge, merge_work);
+
+ for (; sm->merge_progress < sm->nr_chunks;) {
+ rtn = sm->store->type->lookup_exception(sm->store,
+ sm->merge_progress,
+ &merge_chunk, flags);
+ merge_chunk = dm_chunk_number(merge_chunk);
+ if (!rtn) {
+ if (merge_chunk > sm->nr_chunks)
+ DMERR("merge_chunk out of range");
+ else
+ break;
+ } else
+ BUG_ON(rtn != -ENOENT);
+
+ spin_lock(&sm->lock);
+ /*
+ * You can see that we are reading 'merge_progress' above
+ * without the lock, but this is ok, because only this
+ * function and 'merge_callback' increment 'merge_progress';
+ * and 'merge_callback' is a result of this function.
+ */
+ sm->merge_progress++;
+ spin_unlock(&sm->lock);
+ }
+
+ if (sm->merge_progress < sm->nr_chunks) {
+ src.bdev = sm->store->cow->bdev;
+ src.sector = chunk_to_sector(sm->store, merge_chunk);
+ src.count = sm->store->chunk_size;
+
+ dest.bdev = sm->usable_origin->bdev;
+ dest.sector = chunk_to_sector(sm->store, sm->merge_progress);
+ dest.count = src.count;
+
+ rtn = dm_kcopyd_copy(sm->kcopyd_client, &src, 1, &dest, 0,
+ merge_callback, sm);
+ return;
+ }
+
+ /* Raise the event that the merging is completed */
+ dm_table_event(sm->store->ti->table);
+
+ spin_lock(&sm->lock);
+ bio_list_init(&bl);
+ bio_list_merge(&bl, &sm->queued_bios);
+ bio_list_init(&sm->queued_bios);
+ spin_unlock(&sm->lock);
+
+ /* bios in the list are already remapped and can be sent */
+ while ((bio = bio_list_pop(&bl)))
+ generic_make_request(bio);
+}
+
+/*
+ * snapshot_merge_ctr
+ * @ti
+ * @argc
+ * @argv
+ *
+ * Construct a snapshot mapping. Possible mapping tables include:
+ * <ORIGIN> <exception store args> <feature args>
+ * See 'create_exception_store' for format of <exception store args>.
+ *
+ * IMPORTANT: The 'ORIGIN' argument must be the actual origin that
+ * would be used. This is unlike the 'origin' arguments
+ * used in the origin_ctr or snapshot_ctr functions, which
+ * are really just the "real device" under what the actual
+ * user would consider the origin.
+ *
+ * Returns: 0 on success, -XXX on error
+ */
+static int snapshot_merge_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+ int r;
+ unsigned args_used;
+ char *usable_origin_path;
+ struct dm_snapshot_merge *sm;
+
+ if (argc < 4) {
+ ti->error = "too few arguments";
+ return -EINVAL;
+ }
+
+ usable_origin_path = argv[0];
+ argv++;
+ argc--;
+
+ sm = kzalloc(sizeof(*sm), GFP_KERNEL);
+ if (!sm) {
+ ti->error = "Failed to allocate snapshot memory";
+ return -ENOMEM;
+ }
+
+ spin_lock_init(&sm->lock);
+ INIT_WORK(&sm->merge_work, merge_work);
+ bio_list_init(&sm->queued_bios);
+
+ r = create_exception_store(ti, argc, argv, &args_used, &sm->store);
+ if (r) {
+ ti->error = "Failed to create snapshot exception store";
+ goto bad_exception_store;
+ }
+
+ argv += args_used;
+ argc -= args_used;
+
+ sm->nr_chunks = ti->len / sm->store->chunk_size;
+ DMERR("There are %lu chunks to merge", sm->nr_chunks);
+
+ r = dm_get_device(ti, usable_origin_path, 0, ti->len,
+ FMODE_READ | FMODE_WRITE, /* FMODE_EXCL ? */
+ &sm->usable_origin);
+ if (r) {
+ ti->error = "Cannot get usable_origin device";
+ goto bad_origin;
+ }
+
+ r = dm_kcopyd_client_create(SNAPSHOT_PAGES, &sm->kcopyd_client);
+ if (r) {
+ DMERR("Could not create kcopyd client");
+ goto bad_kcopyd;
+ }
+
+ ti->private = sm;
+ return 0;
+
+bad_kcopyd:
+ dm_put_device(ti, sm->usable_origin);
+bad_origin:
+ dm_exception_store_destroy(sm->store);
+bad_exception_store:
+ kfree(sm);
+
+ return r;
+}
+
+static void snapshot_merge_dtr(struct dm_target *ti)
+{
+ struct dm_snapshot_merge *sm = ti->private;
+
+ dm_kcopyd_client_destroy(sm->kcopyd_client);
+
+ dm_put_device(ti, sm->usable_origin);
+
+ dm_exception_store_destroy(sm->store);
+
+ kfree(sm);
+}
+
+static int snapshot_merge_map(struct dm_target *ti, struct bio *bio,
+ union map_info *map_context)
+{
+ int r = DM_MAPIO_SUBMITTED;
+ struct dm_snapshot_merge *sm = ti->private;
+
+ bio->bi_bdev = sm->usable_origin->bdev;
+
+ spin_lock(&sm->lock);
+
+ if (sm->merge_progress < sm->nr_chunks)
+ bio_list_add(&sm->queued_bios, bio);
+ else
+ r = DM_MAPIO_REMAPPED;
+
+ spin_unlock(&sm->lock);
+
+ return r;
+}
+
+static void snapshot_merge_resume(struct dm_target *ti)
+{
+ int r;
+ struct dm_snapshot_merge *sm = ti->private;
+
+ r = sm->store->type->resume(sm->store);
+ if (r)
+ DMERR("Exception store resume failed");
+
+ /* Start copying work */
+ schedule_work(&sm->merge_work);
+}
+
+static void snapshot_merge_presuspend(struct dm_target *ti)
+{
+ struct dm_snapshot_merge *sm = ti->private;
+
+ /* Wait for copy completion and flush I/O */
+ if (sm->store->type->presuspend)
+ sm->store->type->presuspend(sm->store);
+}
+
+static void snapshot_merge_postsuspend(struct dm_target *ti)
+{
+ struct dm_snapshot_merge *sm = ti->private;
+
+ /*
+ * No need to wait for I/O to finish.
+ * DM super-structure will do that for us.
+ */
+ if (sm->store->type->postsuspend)
+ sm->store->type->postsuspend(sm->store);
+}
+
+static int snapshot_merge_status(struct dm_target *ti, status_type_t type,
+ char *result, unsigned int maxlen)
+{
+ unsigned sz = 0;
+ struct dm_snapshot_merge *sm = ti->private;
+
+ switch (type) {
+ case STATUSTYPE_INFO:
+ spin_lock(&sm->lock);
+
+ /* Report copy progress - similar to mirror sync progress */
+ DMEMIT("%lu/%lu", sm->merge_progress, sm->nr_chunks);
+ spin_unlock(&sm->lock);
+ break;
+ case STATUSTYPE_TABLE:
+ DMEMIT("%s", sm->usable_origin->name);
+ sm->store->type->status(sm->store, type, result + sz,
+ maxlen - sz);
+ break;
+ }
+
+ return 0;
+}
+
+static int snapshot_merge_message(struct dm_target *ti,
+ unsigned argc, char **argv)
+{
+ int r = 0;
+ chunk_t old, new;
+ struct dm_snapshot_merge *sm = ti->private;
+
+ if ((argc == 2) &&
+ !strcmp(argv[0], "lookup")) {
+ if (sscanf(argv[1], "%lu", &old) != 1) {
+ DMERR("Failed to read in old chunk value");
+ return -EINVAL;
+ }
+ r = sm->store->type->lookup_exception(sm->store, old, &new,
+ DM_ES_LOOKUP_EXISTS |
+ DM_ES_LOOKUP_CAN_BLOCK);
+ new = dm_chunk_number(new);
+ if (!r)
+ DMERR("Exception found: %lu -> %lu", old, new);
+ else
+ DMERR("Exception not found: %d", r);
+ return 0;
+ }
+
+ if (sm->store->type->message)
+ r = sm->store->type->message(sm->store, argc, argv);
+
+ return r;
+}
+
static struct target_type origin_target = {
.name = "snapshot-origin",
.version = {1, 6, 0},
@@ -1543,6 +1862,20 @@ static struct target_type snapshot_targe
.message = snapshot_message,
};
+static struct target_type snapshot_merge_target = {
+ .name = "snapshot-merge",
+ .version = {0, 1, 0},
+ .module = THIS_MODULE,
+ .ctr = snapshot_merge_ctr,
+ .dtr = snapshot_merge_dtr,
+ .map = snapshot_merge_map,
+ .resume = snapshot_merge_resume,
+ .presuspend = snapshot_merge_presuspend,
+ .postsuspend = snapshot_merge_postsuspend,
+ .status = snapshot_merge_status,
+ .message = snapshot_merge_message,
+};
+
static int __init dm_snapshot_init(void)
{
int r;
@@ -1553,6 +1886,12 @@ static int __init dm_snapshot_init(void)
return r;
}
+ r = dm_register_target(&snapshot_merge_target);
+ if (r) {
+ DMERR("snapshot-merge target register failed %d", r);
+ goto bad_merge_target;
+ }
+
r = dm_register_target(&snapshot_target);
if (r) {
DMERR("snapshot target register failed %d", r);
@@ -1605,6 +1944,8 @@ bad2:
bad1:
dm_unregister_target(&snapshot_target);
bad0:
+ dm_unregister_target(&snapshot_merge_target);
+bad_merge_target:
dm_exception_store_exit();
return r;
}
@@ -1613,8 +1954,9 @@ static void __exit dm_snapshot_exit(void
{
destroy_workqueue(ksnapd);
- dm_unregister_target(&snapshot_target);
dm_unregister_target(&origin_target);
+ dm_unregister_target(&snapshot_target);
+ dm_unregister_target(&snapshot_merge_target);
exit_origin_hash();
kmem_cache_destroy(pending_cache);
More information about the dm-devel
mailing list