rbd-mirror: simplify resync handling within image replayer

Signed-off-by: Jason Dillaman <dillaman@redhat.com>

diff --git a/qa/workunits/rbd/rbd_mirror.sh b/qa/workunits/rbd/rbd_mirror.sh
index 7d59200c1711389e79ddcda7b15a9a949ffd83b5..021cbaf03f740ed5bf58ba0ccc9b0ac3e5a2f03d 100755 (executable)
--- a/qa/workunits/rbd/rbd_mirror.sh
+++ b/qa/workunits/rbd/rbd_mirror.sh
@@ -286,6 +286,7 @@ wait_for_image_replay_started ${CLUSTER1} ${POOL} ${image}
 testlog "TEST: simple image resync"
 request_resync_image ${CLUSTER1} ${POOL} ${image} image_id
 wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'deleted' ${image_id}
+wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'present'
 wait_for_image_replay_started ${CLUSTER1} ${POOL} ${image}
 wait_for_status_in_pool_dir ${CLUSTER1} ${POOL} ${image} 'up+replaying' 'master_position'
 compare_images ${POOL} ${image}
@@ -297,6 +298,7 @@ request_resync_image ${CLUSTER1} ${POOL} ${image} image_id
 admin_daemon ${CLUSTER1} rbd mirror start ${POOL}/${image}
 wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'deleted' ${image_id}
 admin_daemon ${CLUSTER1} rbd mirror start ${POOL}/${image}
+wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'present'
 wait_for_image_replay_started ${CLUSTER1} ${POOL} ${image}
 wait_for_status_in_pool_dir ${CLUSTER1} ${POOL} ${image} 'up+replaying' 'master_position'
 compare_images ${POOL} ${image}
@@ -306,6 +308,7 @@ stop_mirror ${CLUSTER1}
 request_resync_image ${CLUSTER1} ${POOL} ${image} image_id
 start_mirror ${CLUSTER1}
 wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'deleted' ${image_id}
+wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'present'
 wait_for_image_replay_started ${CLUSTER1} ${POOL} ${image}
 wait_for_status_in_pool_dir ${CLUSTER1} ${POOL} ${image} 'up+replaying' 'master_position'
 compare_images ${POOL} ${image}
@@ -327,6 +330,7 @@ wait_for_status_in_pool_dir ${CLUSTER1} ${POOL} ${image} 'up+error' 'disconnecte
 testlog " - replay started after resync requested"
 request_resync_image ${CLUSTER1} ${POOL} ${image} image_id
 wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'deleted' ${image_id}
+wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'present'
 wait_for_image_replay_started ${CLUSTER1} ${POOL} ${image}
 wait_for_replay_complete ${CLUSTER1} ${CLUSTER2} ${POOL} ${image}
 test -n "$(get_mirror_position ${CLUSTER2} ${POOL} ${image})"
@@ -352,6 +356,7 @@ wait_for_status_in_pool_dir ${CLUSTER1} ${POOL} ${image} 'up+error' 'disconnecte
 testlog " - replay started after resync requested"
 request_resync_image ${CLUSTER1} ${POOL} ${image} image_id
 wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'deleted' ${image_id}
+wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'present'
 wait_for_image_replay_started ${CLUSTER1} ${POOL} ${image}
 wait_for_replay_complete ${CLUSTER1} ${CLUSTER2} ${POOL} ${image}
 test -n "$(get_mirror_position ${CLUSTER2} ${POOL} ${image})"
@@ -361,8 +366,10 @@ testlog " - rbd_mirroring_resync_after_disconnect config option"
 set_image_meta ${CLUSTER2} ${POOL} ${image} \
               conf_rbd_mirroring_resync_after_disconnect true
 wait_for_replay_complete ${CLUSTER1} ${CLUSTER2} ${POOL} ${image}
+image_id=$(get_image_id ${CLUSTER1} ${pool} ${image})
 disconnect_image ${CLUSTER2} ${POOL} ${image}
-wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'deleted'
+wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'deleted' ${image_id}
+wait_for_image_present ${CLUSTER1} ${POOL} ${image} 'present'
 wait_for_image_replay_started ${CLUSTER1} ${POOL} ${image}
 wait_for_replay_complete ${CLUSTER1} ${CLUSTER2} ${POOL} ${image}
 test -n "$(get_mirror_position ${CLUSTER2} ${POOL} ${image})"

diff --git a/src/test/rbd_mirror/test_ImageReplayer.cc b/src/test/rbd_mirror/test_ImageReplayer.cc
index 4c9103eb930dbe12ff22eda7dad66e288a1e83bb..57ceeff4740abcb2fa1f8ea12df0f872139dc74e 100644 (file)
--- a/src/test/rbd_mirror/test_ImageReplayer.cc
+++ b/src/test/rbd_mirror/test_ImageReplayer.cc
@@ -947,7 +947,7 @@ TEST_F(TestImageReplayer, Disconnect)
   close_image(ictx);
   C_SaferCond cond2;
   m_replayer->start(&cond2);
-  ASSERT_EQ(-ENOTCONN, cond2.wait());
+  ASSERT_EQ(0, cond2.wait());
   C_SaferCond delete_cond;
   m_image_deleter->wait_for_scheduled_deletion(
     m_local_ioctx.get_id(), m_replayer->get_global_image_id(), &delete_cond);

diff --git a/src/tools/rbd_mirror/ImageReplayer.cc b/src/tools/rbd_mirror/ImageReplayer.cc
index e43cfb939563f798a08202f4a8576a7aee7829b3..5842dd4fb4f0b1ae6235da07d2d6363fab76bf26 100644 (file)
--- a/src/tools/rbd_mirror/ImageReplayer.cc
+++ b/src/tools/rbd_mirror/ImageReplayer.cc
@@ -525,7 +525,8 @@ void ImageReplayer<I>::bootstrap() {
     &m_local_image_ctx, m_local_image_id, m_remote_image.image_id,
     m_global_image_id, m_threads->work_queue, m_threads->timer,
     &m_threads->timer_lock, m_local_mirror_uuid, m_remote_image.mirror_uuid,
-    m_remote_journaler, &m_client_meta, ctx, &m_do_resync, &m_progress_cxt);
+    m_remote_journaler, &m_client_meta, ctx, &m_resync_requested,
+    &m_progress_cxt);
 
   {
     Mutex::Locker locker(m_lock);
@@ -565,6 +566,9 @@ void ImageReplayer<I>::handle_bootstrap(int r) {
     return;
   } else if (on_start_interrupted()) {
     return;
+  } else if (m_resync_requested) {
+    on_start_fail(0, "resync requested");
+    return;
   }
 
   assert(m_local_journal == nullptr);
@@ -583,22 +587,6 @@ void ImageReplayer<I>::handle_bootstrap(int r) {
 
   {
     Mutex::Locker locker(m_lock);
-
-    if (m_do_resync) {
-      Context *on_finish = m_on_start_finish;
-      m_stopping_for_resync = true;
-      FunctionContext *ctx = new FunctionContext([this, on_finish](int r) {
-         if (r < 0) {
-           if (on_finish) {
-             on_finish->complete(r);
-           }
-           return;
-         }
-          resync_image(on_finish);
-        });
-      m_on_start_finish = ctx;
-    }
-
     std::string name = m_local_ioctx.get_pool_name() + "/" +
                        m_local_image_ctx->name;
     if (m_name != name) {
@@ -652,13 +640,18 @@ void ImageReplayer<I>::handle_init_remote_journaler(int r) {
     return;
   }
 
-  if (client.state != cls::journal::CLIENT_STATE_CONNECTED) {
+  derr << "image_id=" << m_local_image_id << ", "
+       << "m_client_meta.image_id=" << m_client_meta.image_id << ", "
+       << "client.state=" << client.state << dendl;
+  if (m_client_meta.image_id == m_local_image_id &&
+      client.state != cls::journal::CLIENT_STATE_CONNECTED) {
     dout(5) << "client flagged disconnected, stopping image replay" << dendl;
     if (m_local_image_ctx->mirroring_resync_after_disconnect) {
-      Mutex::Locker locker(m_lock);
-      m_stopping_for_resync = true;
+      m_resync_requested = true;
+      on_start_fail(-ENOTCONN, "disconnected: automatic resync");
+    } else {
+      on_start_fail(-ENOTCONN, "disconnected");
     }
-    on_start_fail(-ENOTCONN, "disconnected");
     return;
   }
 
@@ -1582,11 +1575,6 @@ void ImageReplayer<I>::shut_down(int r) {
        m_remote_journaler->remove_listener(&m_remote_listener);
         m_remote_journaler->shut_down(ctx);
       });
-    if (m_stopping_for_resync) {
-      ctx = new FunctionContext([this, ctx](int r) {
-          m_remote_journaler->unregister_client(ctx);
-        });
-    }
   }
 
   // stop the replay of remote journal events
@@ -1674,12 +1662,12 @@ void ImageReplayer<I>::handle_shut_down(int r) {
       return;
     }
 
-    if (m_stopping_for_resync) {
+    if (m_resync_requested) {
       m_image_deleter->schedule_image_delete(m_local,
                                              m_local_pool_id,
                                              m_global_image_id,
                                              true);
-      m_stopping_for_resync = false;
+      m_resync_requested = false;
     }
   }
 
@@ -1759,11 +1747,7 @@ template <typename I>
 void ImageReplayer<I>::resync_image(Context *on_finish) {
   dout(20) << dendl;
 
-  {
-    Mutex::Locker l(m_lock);
-    m_stopping_for_resync = true;
-  }
-
+  m_resync_requested = true;
   stop(on_finish);
 }
 

diff --git a/src/tools/rbd_mirror/ImageReplayer.h b/src/tools/rbd_mirror/ImageReplayer.h
index 11ff0b3579498742990ad1b6c494f30d3ead3eda..fe0be00b563ba75f934cf755031314fccad2f7b7 100644 (file)
--- a/src/tools/rbd_mirror/ImageReplayer.h
+++ b/src/tools/rbd_mirror/ImageReplayer.h
@@ -309,7 +309,7 @@ private:
   int m_last_r = 0;
 
   BootstrapProgressContext m_progress_cxt;
-  bool m_do_resync{false};
+  bool m_resync_requested = false;
   image_replayer::EventPreprocessor<ImageCtxT> *m_event_preprocessor = nullptr;
   image_replayer::ReplayStatusFormatter<ImageCtxT> *m_replay_status_formatter =
     nullptr;
@@ -322,7 +322,6 @@ private:
   Journaler* m_remote_journaler = nullptr;
   ::journal::ReplayHandler *m_replay_handler = nullptr;
   librbd::journal::Listener *m_journal_listener;
-  bool m_stopping_for_resync = false;
 
   Context *m_on_start_finish = nullptr;
   Context *m_on_stop_finish = nullptr;