[Qemu-devel] [PATCH 24/32] mirror: introduce mirror job

[Kevin Wolf <kwolf@redhat.com>]

From: Paolo Bonzini <pbonzini@redhat.com>

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.  This can be used for several
purposes, including storage migration, continuous replication, and
observation of the guest I/O in an external program.  It is also a
first step in replacing the inefficient block migration code that is
part of QEMU.

The job is possibly 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.

In other words, the BLOCK_JOB_CANCELLED event means that the target
may _not_ be consistent with a past state of the source; the
BLOCK_JOB_COMPLETED event means that the target is consistent with
a past state of the source.  (Note that it could already happen
that management lost the race against QEMU and got a completion
event instead of cancellation).

It is not yet possible to complete the job and switch over to the target
disk.  The next patches will fix this and add many refinements to the
basic idea introduced here.  These include improved error management,
some tunable knobs and performance optimizations.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block/Makefile.objs |    1 +
 block/mirror.c      |  235 +++++++++++++++++++++++++++++++++++++++++++++++++++
 block_int.h         |   20 +++++
 qapi-schema.json    |   17 ++++
 trace-events        |    7 ++
 5 files changed, 280 insertions(+), 0 deletions(-)
 create mode 100644 block/mirror.c

diff --git a/block/Makefile.objs b/block/Makefile.objs
index 554f429..806e526 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -12,3 +12,4 @@ block-obj-$(CONFIG_GLUSTERFS) += gluster.o
 
 common-obj-y += stream.o
 common-obj-y += commit.o
+common-obj-y += mirror.o
diff --git a/block/mirror.c b/block/mirror.c
new file mode 100644
index 0000000..b353798
--- /dev/null
+++ b/block/mirror.c
@@ -0,0 +1,235 @@
+/*
+ * 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;
+    uint8_t *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);
+    bdrv_reset_dirty(source, s->sector_num, nb_sectors);
+
+    /* Copy the dirty cluster.  */
+    iov.iov_base = s->buf;
+    iov.iov_len  = nb_sectors * 512;
+    qemu_iovec_init_external(&qiov, &iov, 1);
+
+    trace_mirror_one_iteration(s, s->sector_num, nb_sectors);
+    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_NONE) {
+        /* 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) {
+                goto immediate_exit;
+            }
+
+            assert(n > 0);
+            if (ret == 1) {
+                bdrv_set_dirty(bs, sector_num, n);
+                sector_num = next;
+            } else {
+                sector_num += n;
+            }
+        }
+    }
+
+    s->sector_num = -1;
+    for (;;) {
+        uint64_t delay_ns;
+        int64_t cnt;
+        bool should_complete;
+
+        cnt = bdrv_get_dirty_count(bs);
+        if (cnt != 0) {
+            ret = mirror_iteration(s);
+            if (ret < 0) {
+                goto immediate_exit;
+            }
+            cnt = bdrv_get_dirty_count(bs);
+        }
+
+        should_complete = false;
+        if (cnt == 0) {
+            trace_mirror_before_flush(s);
+            ret = bdrv_flush(s->target);
+            if (ret < 0) {
+                goto immediate_exit;
+            }
+
+            /* 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.  This way, block-job-cancel will leave
+             * the target in a consistent state.
+             */
+            synced = true;
+            s->common.offset = end * BDRV_SECTOR_SIZE;
+            should_complete = block_job_is_cancelled(&s->common);
+            cnt = bdrv_get_dirty_count(bs);
+        }
+
+        if (cnt == 0 && 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.
+             */
+            trace_mirror_before_drain(s, cnt);
+            bdrv_drain_all();
+            cnt = bdrv_get_dirty_count(bs);
+        }
+
+        ret = 0;
+        trace_mirror_before_sleep(s, cnt, synced);
+        if (!synced) {
+            /* 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;
+            }
+        } else if (!should_complete) {
+            delay_ns = (cnt == 0 ? SLICE_TIME : 0);
+            block_job_sleep_ns(&s->common, rt_clock, delay_ns);
+        } else 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;
+        }
+    }
+
+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);
+    bdrv_set_enable_write_cache(s->target, 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);
+}
diff --git a/block_int.h b/block_int.h
index f4bae04..aaa46a8 100644
--- a/block_int.h
+++ b/block_int.h
@@ -331,4 +331,24 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
                  BlockdevOnError on_error, 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 cancelled 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 */
diff --git a/qapi-schema.json b/qapi-schema.json
index 37bbeca..8c4b7c8 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -1166,6 +1166,23 @@
   '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: 1.3
+##
+{ 'enum': 'MirrorSyncMode',
+  'data': ['top', 'full', 'none'] }
+
+##
 # @BlockJobInfo:
 #
 # Information about a long-running block device operation.
diff --git a/trace-events b/trace-events
index 9ab8e27..09b5d55 100644
--- a/trace-events
+++ b/trace-events
@@ -77,6 +77,13 @@ stream_start(void *bs, void *base, void *s, void *co, void *opaque) "bs %p base
 commit_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"
 commit_start(void *bs, void *base, void *top, void *s, void *co, void *opaque) "bs %p base %p top %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_before_flush(void *s) "s %p"
+mirror_before_drain(void *s, int64_t cnt) "s %p dirty count %"PRId64
+mirror_before_sleep(void *s, int64_t cnt, int synced) "s %p dirty count %"PRId64" synced %d"
+mirror_one_iteration(void *s, int64_t sector_num, int nb_sectors) "s %p sector_num %"PRId64" nb_sectors %d"
+
 # blockdev.c
 qmp_block_job_cancel(void *job) "job %p"
 qmp_block_job_pause(void *job) "job %p"
-- 
1.7.6.5