mds: send resolve messages after all MDS reach resolve stage

Current code sends resolve messages when resolving MDS set changes.
There is no need to send resolve messages when some MDS leave the
resolve stage. Sending message while some MDS are replaying is also
not very useful.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

4 files changed, 20 insertions, 8 deletions

diff --git a/src/mds/MDCache.cc b/src/mds/MDCache.cc
index c6166521952..cd24fc2f3a2 100644
--- a/src/mds/MDCache.cc
+++ b/src/mds/MDCache.cc
@@ -2740,6 +2740,10 @@ void MDCache::handle_resolve(MMDSResolve *m)
   int from = m->get_source().num();
 
   if (mds->get_state() < MDSMap::STATE_RESOLVE) {
+    if (mds->get_want_state() == CEPH_MDS_STATE_RESOLVE) {
+      mds->wait_for_resolve(new C_MDS_RetryMessage(mds, m));
+      return;
+    }
     // wait until we reach the resolve stage!
     m->put();
     return;
diff --git a/src/mds/MDS.cc b/src/mds/MDS.cc
index bd4bed91585..4153417ad11 100644
--- a/src/mds/MDS.cc
+++ b/src/mds/MDS.cc
@@ -974,14 +974,12 @@ void MDS::handle_mds_map(MMDSMap *m)
   // RESOLVE
   // is someone else newly resolving?
   if (is_resolve() || is_rejoin() || is_clientreplay() || is_active() || is_stopping()) {
-    set<int> oldresolve, resolve;
-    oldmap->get_mds_set(oldresolve, MDSMap::STATE_RESOLVE);
-    mdsmap->get_mds_set(resolve, MDSMap::STATE_RESOLVE);
-    if (oldresolve != resolve) {
-      dout(10) << " resolve set is " << resolve << ", was " << oldresolve << dendl;
+    if (!oldmap->is_resolving() && mdsmap->is_resolving()) {
+      set<int> oldresolve, resolve;
+      mdsmap->get_mds_set(resolve, MDSMap::STATE_RESOLVE);
+      dout(10) << " resolve set is " << resolve << dendl;
       calc_recovery_set();
-      if (!mdsmap->is_any_failed())
-	mdcache->send_resolves();
+      mdcache->send_resolves();
     }
   }
   
@@ -1410,6 +1408,7 @@ void MDS::resolve_start()
   reopen_log();
 
   mdcache->resolve_start();
+  finish_contexts(g_ceph_context, waiting_for_resolve);
 }
 void MDS::resolve_done()
 {
diff --git a/src/mds/MDS.h b/src/mds/MDS.h
index a90587e3aa2..f61ad8ddac5 100644
--- a/src/mds/MDS.h
+++ b/src/mds/MDS.h
@@ -196,7 +196,7 @@ class MDS : public Dispatcher {
   int state;         // my confirmed state
   int want_state;    // the state i want
 
-  list<Context*> waiting_for_active, waiting_for_replay, waiting_for_reconnect;
+  list<Context*> waiting_for_active, waiting_for_replay, waiting_for_reconnect, waiting_for_resolve;
   list<Context*> replay_queue;
   map<int, list<Context*> > waiting_for_active_peer;
   list<Message*> waiting_for_nolaggy;
@@ -219,6 +219,9 @@ class MDS : public Dispatcher {
   void wait_for_reconnect(Context *c) {
     waiting_for_reconnect.push_back(c);
   }
+  void wait_for_resolve(Context *c) {
+    waiting_for_resolve.push_back(c);
+  }
   void wait_for_mdsmap(epoch_t e, Context *c) {
     waiting_for_mdsmap[e].push_back(c);
   }
diff --git a/src/mds/MDSMap.h b/src/mds/MDSMap.h
index 3a83ed88b08..47c2c52d23d 100644
--- a/src/mds/MDSMap.h
+++ b/src/mds/MDSMap.h
@@ -449,6 +449,12 @@ public:
   bool is_any_failed() {
     return failed.size();
   }
+  bool is_resolving() {
+    return
+      get_num_mds(STATE_RESOLVE) > 0 &&
+      get_num_mds(STATE_REPLAY) == 0 &&
+      failed.empty();
+  }
   bool is_rejoining() {  
     // nodes are rejoining cache state
     return