diff mbox

[RFC,6/7] replication: Implement block replication for shared disk case

Message ID 1476971860-20860-7-git-send-email-zhang.zhanghailiang@huawei.com
State New
Headers show

Commit Message

Zhanghailiang Oct. 20, 2016, 1:57 p.m. UTC
Just as the scenario of non-shared disk block replication,
we are going to implement block replication from many basic
blocks that are already in QEMU.
The architecture is:

         virtio-blk                     ||                               .----------
             /                          ||                               | Secondary
            /                           ||                               '----------
           /                            ||                                 virtio-blk
          /                             ||                                      |
          |                             ||                               replication(5)
          |                    NBD  -------->   NBD   (2)                       |
          |                  client     ||    server ---> hidden disk <-- active disk(4)
          |                     ^       ||                      |
          |              replication(1) ||                      |
          |                     |       ||                      |
          |   +-----------------'       ||                      |
         (3)  |drive-backup sync=none   ||                      |
--------. |   +-----------------+       ||                      |
Primary | |                     |       ||           backing    |
--------' |                     |       ||                      |
          V                     |                               |
       +-------------------------------------------+            |
       |               shared disk                 | <----------+
       +-------------------------------------------+

    1) Primary writes will read original data and forward it to Secondary
       QEMU.
    2) The hidden-disk is created automatically. It buffers the original content
       that is modified by the primary VM. It should also be an empty disk, and
       the driver supports bdrv_make_empty() and backing file.
    3) Primary write requests will be written to Shared disk.
    4) Secondary write requests will be buffered in the active disk and it
       will overwrite the existing sector content in the buffer.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
---
 block/replication.c | 45 ++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 38 insertions(+), 7 deletions(-)
diff mbox

Patch

diff --git a/block/replication.c b/block/replication.c
index 39c616d..e66b1ca 100644
--- a/block/replication.c
+++ b/block/replication.c
@@ -221,7 +221,7 @@  static coroutine_fn int replication_co_readv(BlockDriverState *bs,
                                              QEMUIOVector *qiov)
 {
     BDRVReplicationState *s = bs->opaque;
-    BdrvChild *child = s->secondary_disk;
+    BdrvChild *child = s->is_shared_disk ? s->primary_disk : s->secondary_disk;
     BlockJob *job = NULL;
     CowRequest req;
     int ret;
@@ -398,8 +398,12 @@  static void backup_job_completed(void *opaque, int ret)
         /* The backup job is cancelled unexpectedly */
         s->error = -EIO;
     }
-
-    backup_job_cleanup(s);
+    if (s->mode == REPLICATION_MODE_PRIMARY) {
+        s->replication_state = BLOCK_REPLICATION_DONE;
+        s->error = 0;
+    } else {
+        backup_job_cleanup(s);
+    }
 }
 
 static bool check_top_bs(BlockDriverState *top_bs, BlockDriverState *bs)
@@ -450,6 +454,15 @@  static void replication_start(ReplicationState *rs, ReplicationMode mode,
 
     switch (s->mode) {
     case REPLICATION_MODE_PRIMARY:
+        if (s->is_shared_disk) {
+            backup_start("replication-backup", s->primary_disk->bs, bs, 0,
+                MIRROR_SYNC_MODE_NONE, NULL, false, BLOCKDEV_ON_ERROR_REPORT,
+                BLOCKDEV_ON_ERROR_REPORT, backup_job_completed,
+                s, NULL, &local_err);
+            if (local_err) {
+                error_propagate(errp, local_err);
+            }
+        }
         break;
     case REPLICATION_MODE_SECONDARY:
         s->active_disk = bs->file;
@@ -468,7 +481,8 @@  static void replication_start(ReplicationState *rs, ReplicationMode mode,
         }
 
         s->secondary_disk = s->hidden_disk->bs->backing;
-        if (!s->secondary_disk->bs || !bdrv_has_blk(s->secondary_disk->bs)) {
+        if (!s->secondary_disk->bs ||
+            (!s->is_shared_disk && !bdrv_has_blk(s->secondary_disk->bs))) {
             error_setg(errp, "The secondary disk doesn't have block backend");
             aio_context_release(aio_context);
             return;
@@ -560,11 +574,24 @@  static void replication_do_checkpoint(ReplicationState *rs, Error **errp)
 
     switch (s->mode) {
     case REPLICATION_MODE_PRIMARY:
+        if (s->is_shared_disk) {
+            if (!s->primary_disk->bs->job) {
+                error_setg(errp, "Primary backup job was cancelled"
+                           " unexpectedly");
+                break;
+            }
+
+            backup_do_checkpoint(s->primary_disk->bs->job, &local_err);
+            if (local_err) {
+                error_propagate(errp, local_err);
+            }
+        }
         break;
     case REPLICATION_MODE_SECONDARY:
         if (!s->is_shared_disk) {
             if (!s->secondary_disk->bs->job) {
-                error_setg(errp, "Backup job was cancelled unexpectedly");
+                error_setg(errp, "Secondary backup job was cancelled"
+                           " unexpectedly");
                 break;
             }
             backup_do_checkpoint(s->secondary_disk->bs->job, &local_err);
@@ -643,8 +670,12 @@  static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
 
     switch (s->mode) {
     case REPLICATION_MODE_PRIMARY:
-        s->replication_state = BLOCK_REPLICATION_DONE;
-        s->error = 0;
+        if (s->is_shared_disk && s->primary_disk->bs->job) {
+            block_job_cancel(s->primary_disk->bs->job);
+        } else {
+            s->replication_state = BLOCK_REPLICATION_DONE;
+            s->error = 0;
+        }
         break;
     case REPLICATION_MODE_SECONDARY:
         /*