@@ -9,4 +9,4 @@ block-obj-$(CONFIG_LIBISCSI) += iscsi.o
block-obj-$(CONFIG_CURL) += curl.o
block-obj-$(CONFIG_RBD) += rbd.o
-common-obj-y += stream.o
+common-obj-y += stream.o mirror.o
new file mode 100644
@@ -0,0 +1,228 @@
+/*
+ * Image mirroring
+ *
+ * Copyright Red Hat, Inc. 2012
+ *
+ * Authors:
+ * Paolo Bonzini <pbonzini@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "trace.h"
+#include "blockjob.h"
+#include "block_int.h"
+#include "qemu/ratelimit.h"
+
+enum {
+ /*
+ * Size of data buffer for populating the image file. This should be large
+ * enough to process multiple clusters in a single call, so that populating
+ * contiguous regions of the image is efficient.
+ */
+ BLOCK_SIZE = 512 * BDRV_SECTORS_PER_DIRTY_CHUNK, /* in bytes */
+};
+
+#define SLICE_TIME 100000000ULL /* ns */
+
+typedef struct MirrorBlockJob {
+ BlockJob common;
+ RateLimit limit;
+ BlockDriverState *target;
+ MirrorSyncMode mode;
+ int64_t sector_num;
+ void *buf;
+} MirrorBlockJob;
+
+static int coroutine_fn mirror_iteration(MirrorBlockJob *s)
+{
+ BlockDriverState *source = s->common.bs;
+ BlockDriverState *target = s->target;
+ QEMUIOVector qiov;
+ int ret, nb_sectors;
+ int64_t end;
+ struct iovec iov;
+
+ end = s->common.len >> BDRV_SECTOR_BITS;
+ s->sector_num = bdrv_get_next_dirty(source, s->sector_num);
+ nb_sectors = MIN(BDRV_SECTORS_PER_DIRTY_CHUNK, end - s->sector_num);
+ trace_mirror_one_iteration(s, s->sector_num);
+ bdrv_reset_dirty(source, s->sector_num, BDRV_SECTORS_PER_DIRTY_CHUNK);
+
+ /* Copy the dirty cluster. */
+ iov.iov_base = s->buf;
+ iov.iov_len = nb_sectors * 512;
+ qemu_iovec_init_external(&qiov, &iov, 1);
+
+ ret = bdrv_co_readv(source, s->sector_num, nb_sectors, &qiov);
+ if (ret < 0) {
+ return ret;
+ }
+ return bdrv_co_writev(target, s->sector_num, nb_sectors, &qiov);
+}
+
+static void coroutine_fn mirror_run(void *opaque)
+{
+ MirrorBlockJob *s = opaque;
+ BlockDriverState *bs = s->common.bs;
+ int64_t sector_num, end;
+ int ret = 0;
+ int n;
+ bool synced = false;
+
+ if (block_job_is_cancelled(&s->common)) {
+ goto immediate_exit;
+ }
+
+ s->common.len = bdrv_getlength(bs);
+ if (s->common.len < 0) {
+ block_job_completed(&s->common, s->common.len);
+ return;
+ }
+
+ end = s->common.len >> BDRV_SECTOR_BITS;
+ s->buf = qemu_blockalign(bs, BLOCK_SIZE);
+
+ if (s->mode == MIRROR_SYNC_MODE_FULL || s->mode == MIRROR_SYNC_MODE_TOP) {
+ /* First part, loop on the sectors and initialize the dirty bitmap. */
+ BlockDriverState *base;
+ base = s->mode == MIRROR_SYNC_MODE_FULL ? NULL : bs->backing_hd;
+ for (sector_num = 0; sector_num < end; ) {
+ int64_t next = (sector_num | (BDRV_SECTORS_PER_DIRTY_CHUNK - 1)) + 1;
+ ret = bdrv_co_is_allocated_above(bs, base,
+ sector_num, next - sector_num, &n);
+
+ if (ret < 0) {
+ break;
+ } else if (ret == 1) {
+ bdrv_set_dirty(bs, sector_num, n);
+ sector_num = next;
+ } else {
+ sector_num += n;
+ }
+ }
+ }
+
+ if (ret < 0) {
+ block_job_completed(&s->common, ret);
+ }
+
+ s->sector_num = -1;
+ for (;;) {
+ uint64_t delay_ns;
+ int64_t cnt;
+ bool should_complete;
+
+ if (bdrv_get_dirty_count(bs) != 0) {
+ ret = mirror_iteration(s);
+ if (ret < 0) {
+ break;
+ }
+ }
+
+ if (bdrv_get_dirty_count(bs) == 0) {
+ /* We're out of the streaming phase. From now on, if the
+ * job is cancelled we will actually complete all pending
+ * I/O and report completion, so that drive-reopen can be
+ * used to pivot to the mirroring target.
+ */
+ synced = true;
+ s->common.offset = end * BDRV_SECTOR_SIZE;
+ }
+
+ should_complete = synced && block_job_is_cancelled(&s->common);
+ if (should_complete) {
+ /* The dirty bitmap is not updated while operations are pending.
+ * If we're about to exit, wait for pending operations before
+ * calling bdrv_get_dirty_count(bs), or we may exit while the
+ * source has dirty data to copy!
+ *
+ * Note that I/O can be submitted by the guest while
+ * mirror_populate runs.
+ */
+ bdrv_drain_all();
+ }
+
+ ret = 0;
+ cnt = bdrv_get_dirty_count(bs);
+ if (synced) {
+ if (!should_complete) {
+ delay_ns = (cnt == 0 ? SLICE_TIME : 0);
+ block_job_sleep_ns(&s->common, rt_clock, delay_ns);
+ continue;
+ }
+
+ if (cnt == 0) {
+ /* The two disks are in sync. Exit and report successful
+ * completion.
+ */
+ assert(QLIST_EMPTY(&bs->tracked_requests));
+ s->common.cancelled = false;
+ break;
+ }
+ } else {
+ /* Publish progress */
+ s->common.offset = end * BDRV_SECTOR_SIZE - cnt * BLOCK_SIZE;
+
+ if (s->common.speed) {
+ delay_ns = ratelimit_calculate_delay(&s->limit, BDRV_SECTORS_PER_DIRTY_CHUNK);
+ } else {
+ delay_ns = 0;
+ }
+
+ /* Note that even when no rate limit is applied we need to yield
+ * with no pending I/O here so that qemu_aio_flush() returns.
+ */
+ block_job_sleep_ns(&s->common, rt_clock, delay_ns);
+ if (block_job_is_cancelled(&s->common)) {
+ break;
+ }
+ }
+ }
+
+immediate_exit:
+ g_free(s->buf);
+ bdrv_set_dirty_tracking(bs, false);
+ bdrv_close(s->target);
+ bdrv_delete(s->target);
+ block_job_completed(&s->common, ret);
+}
+
+static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
+{
+ MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
+
+ if (speed < 0) {
+ error_set(errp, QERR_INVALID_PARAMETER, "speed");
+ return;
+ }
+ ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
+}
+
+static BlockJobType mirror_job_type = {
+ .instance_size = sizeof(MirrorBlockJob),
+ .job_type = "mirror",
+ .set_speed = mirror_set_speed,
+};
+
+void mirror_start(BlockDriverState *bs, BlockDriverState *target,
+ int64_t speed, MirrorSyncMode mode,
+ BlockDriverCompletionFunc *cb,
+ void *opaque, Error **errp)
+{
+ MirrorBlockJob *s;
+
+ s = block_job_create(&mirror_job_type, bs, speed, cb, opaque, errp);
+ if (!s) {
+ return;
+ }
+
+ s->target = target;
+ s->mode = mode;
+ bdrv_set_dirty_tracking(bs, true);
+ s->common.co = qemu_coroutine_create(mirror_run);
+ trace_mirror_start(bs, s, s->common.co, opaque);
+ qemu_coroutine_enter(s->common.co, s);
+}
@@ -306,4 +306,24 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp);
+/**
+ * mirror_start:
+ * @bs: Block device to operate on.
+ * @target: Block device to write to.
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @mode: Whether to collapse all images in the chain to the target.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ * @errp: Error object.
+ *
+ * Start a mirroring operation on @bs. Clusters that are allocated
+ * in @bs will be written to @bs until the job is canceled or
+ * manually completed. At the end of a successful mirroring job,
+ * @bs will be switched to read from @target.
+ */
+void mirror_start(BlockDriverState *bs, BlockDriverState *target,
+ int64_t speed, MirrorSyncMode mode,
+ BlockDriverCompletionFunc *cb,
+ void *opaque, Error **errp);
+
#endif /* BLOCK_INT_H */
@@ -920,6 +920,23 @@
'data': ['report', 'ignore', 'enospc', 'stop'] }
##
+# @MirrorSyncMode:
+#
+# An enumeration of possible behaviors for the initial synchronization
+# phase of storage mirroring.
+#
+# @top: copies data in the topmost image to the destination
+#
+# @full: copies data from all images to the destination
+#
+# @none: only copy data written from now on
+#
+# Since: 1.2
+##
+{ 'enum': 'MirrorSyncMode',
+ 'data': ['top', 'full', 'none'] }
+
+##
# @BlockJobTargetInfo:
#
# Information about the target device for a long-running block device
@@ -75,6 +75,10 @@ bdrv_co_do_copy_on_readv(void *bs, int64_t sector_num, int nb_sectors, int64_t c
stream_one_iteration(void *s, int64_t sector_num, int nb_sectors, int is_allocated) "s %p sector_num %"PRId64" nb_sectors %d is_allocated %d"
stream_start(void *bs, void *base, void *s, void *co, void *opaque) "bs %p base %p s %p co %p opaque %p"
+# block/mirror.c
+mirror_start(void *bs, void *s, void *co, void *opaque) "bs %p s %p co %p opaque %p"
+mirror_one_iteration(void *s, int64_t sector_num) "s %p sector_num %"PRId64
+
# blockdev.c
qmp_block_job_cancel(void *job) "job %p"
qmp_block_job_pause(void *job) "job %p"
This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. The mirror job is never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> --- block/Makefile.objs | 2 +- block/mirror.c | 228 +++++++++++++++++++++++++++++++++++++++++++++++++++ block_int.h | 20 +++++ qapi-schema.json | 17 ++++ trace-events | 4 + 5 files changed, 270 insertions(+), 1 deletion(-) create mode 100644 block/mirror.c