Group Live Snapshots

This is a QAPI/QMP only command to take a snapshot of a group of devices. This is similar to the blockdev-snapshot-sync command, except blockdev-group-snapshot-sync accepts a list devices, filenames, and formats.

It is attempted to keep the snapshot of the group atomic; if the creation or open of any of the new snapshots fails, then all of the new snapshots are abandoned, and the name of the snapshot image that failed is returned. The failure case should not interrupt any operations.

Rather than use bdrv_close() along with a subsequent bdrv_open() to perform the pivot, the original image is never closed and the new image is placed 'in front' of the original image via manipulation of the BlockDriverState fields. Thus, once the new snapshot image has been successfully created, there are no more failure points before pivoting to the new snapshot.

This allows the group of disks to remain consistent with each other, even across snapshot failures.

Signed-off-by Jeff Cody <[email protected]>

---
 block.c          |   80 ++++++++++++++++++++++++++++++++
 block.h          |    1 +
 block_int.h      |    6 +++
 blockdev.c       |  133 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 qapi-schema.json |   38 +++++++++++++++
 5 files changed, 258 insertions(+), 0 deletions(-)

block.c +48 -0

index 3621d11..393e8bf 100644
@@ -880,6 +880,86 @@ void bdrv_make_anon(BlockDriverState *bs)
     bs->device_name[0] = '\0';
 }
 
+/*
+ * Add new bs contents at the top of an image chain while the chain is
+ * live, while keeping required fields on the top layer.
+ *
+ * This will modify the BlockDriverState fields, and swap contents
+ * between bs_new and bs_top. Both bs_new and bs_top are modified.
+ *
+ * This function does not create any image files.
+ */
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
+{
+    BlockDriverState tmp;
+
+    /* the new bs must not be in bdrv_states */
+    bdrv_make_anon(bs_new);
+
+    tmp = *bs_new;
+
+    /* there are some fields that need to stay on the top layer: */
+
+    /* dev info */
+    tmp.dev_ops           = bs_top->dev_ops;
+    tmp.dev_opaque        = bs_top->dev_opaque;
+    tmp.dev               = bs_top->dev;
+    tmp.buffer_alignment  = bs_top->buffer_alignment;
+    tmp.copy_on_read      = bs_top->copy_on_read;
+
+    /* i/o timing parameters */
+    tmp.slice_time        = bs_top->slice_time;
+    tmp.slice_start       = bs_top->slice_start;
+    tmp.slice_end         = bs_top->slice_end;
+    tmp.io_limits         = bs_top->io_limits;
+    tmp.io_base           = bs_top->io_base;
+    tmp.throttled_reqs    = bs_top->throttled_reqs;
+    tmp.block_timer       = bs_top->block_timer;
+    tmp.io_limits_enabled = bs_top->io_limits_enabled;
+
+    /* geometry */
+    tmp.cyls              = bs_top->cyls;
+    tmp.heads             = bs_top->heads;
+    tmp.secs              = bs_top->secs;
+    tmp.translation       = bs_top->translation;
+
+    /* r/w error */
+    tmp.on_read_error     = bs_top->on_read_error;
+    tmp.on_write_error    = bs_top->on_write_error;
+
+    /* i/o status */

block.c +22 -0

+
+    /* swap contents of the fixed new bs and the current top */
+    *bs_new = *bs_top;
+    *bs_top = tmp;
+
+    /* clear the copied fields in the new backing file */
+    bdrv_detach_dev(bs_new, bs_new->dev);
+
+    qemu_co_queue_init(&bs_new->throttled_reqs);
+    memset(&bs_new->io_base,   0, sizeof(bs_new->io_base));
+    memset(&bs_new->io_limits, 0, sizeof(bs_new->io_limits));
+    bdrv_iostatus_disable(bs_new);
+
+    /* we don't use bdrv_io_limits_disable() for this, because we don't want
+     * to affect or delete the block_timer, as it has been moved to bs_top */
+    bs_new->io_limits_enabled = false;
+    bs_new->block_timer       = NULL;
+    bs_new->slice_time        = 0;
+    bs_new->slice_start       = 0;
+    bs_new->slice_end         = 0;
+}
+
 void bdrv_delete(BlockDriverState *bs)
 {
     assert(!bs->dev);

block.h +1 -0

index cae289b..190a780 100644
@@ -114,6 +114,7 @@ int bdrv_create(BlockDriver *drv, const char* filename,
 int bdrv_create_file(const char* filename, QEMUOptionParameter *options);
 BlockDriverState *bdrv_new(const char *device_name);
 void bdrv_make_anon(BlockDriverState *bs);
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top);
 void bdrv_delete(BlockDriverState *bs);
 int bdrv_parse_cache_flags(const char *mode, int *flags);
 int bdrv_file_open(BlockDriverState **pbs, const char *filename, int flags);

block_int.h +6 -0

index 7be2988..5edc8c1 100644
@@ -219,6 +219,12 @@ struct BlockDriver {
     QLIST_ENTRY(BlockDriver) list;
 };
 
+/*
+ * Note: the function bdrv_append() copies and swaps contents of
+ * BlockDriverStates, so if you add new fields to this struct, please
+ * inspect bdrv_append() to determine if the new fields need to be
+ * copied as well.
+ */
 struct BlockDriverState {
     int64_t total_sectors; /* if we are reading a disk image, give its
                               size in sectors */

blockdev.c +34 -0

index ab9fd21..90cbcc5 100644
@@ -719,6 +719,139 @@ void qmp_blockdev_snapshot_sync(const char *device, const char *snapshot_file,
     }
 }
 
+
+/* New and old BlockDriverState structs for group snapshots */
+typedef struct BlkGroupSnapshotStates {
+    BlockDriverState *old_bs;
+    BlockDriverState *new_bs;
+    QSIMPLEQ_ENTRY(BlkGroupSnapshotStates) entry;
+} BlkGroupSnapshotStates;
+
+/*
+ * 'Atomic' group snapshots.  The snapshots are taken as a set, and if any fail
+ *  then we do not pivot any of the devices in the group, and abandon the
+ *  snapshots
+ */
+void qmp_blockdev_group_snapshot_sync(SnapshotDevList *dev_list,
+                                      Error **errp)
+{
+    int ret = 0;
+    SnapshotDevList *dev_entry = dev_list;
+    SnapshotDev *dev_info = NULL;
+    BlkGroupSnapshotStates *states;
+    BlockDriver *proto_drv;
+    BlockDriver *drv;
+    int flags;
+    const char *format;
+    const char *snapshot_file;
+
+    QSIMPLEQ_HEAD(snap_bdrv_states, BlkGroupSnapshotStates) snap_bdrv_states;
+    QSIMPLEQ_INIT(&snap_bdrv_states);
+
+    /* drain all i/o before any snapshots */
+    bdrv_drain_all();
+
+    /* We don't do anything in this loop that commits us to the snapshot */
+    while (NULL != dev_entry) {