mds: send resolve acks after master updates are safely logged

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com>

diff --git a/src/mds/MDCache.cc b/src/mds/MDCache.cc
index 9156e5bb0e0d5daf26ab5cdb959aaa77bfe4d617..5e7a0ee598db8679a988751f183b7282e74e555f 100644 (file)
--- a/src/mds/MDCache.cc
+++ b/src/mds/MDCache.cc
@@ -2181,6 +2181,17 @@ void MDCache::committed_master_slave(metareqid_t r, int from)
     log_master_commit(r);
 }
 
+void MDCache::logged_master_update(metareqid_t reqid)
+{
+  dout(10) << "logged_master_update " << reqid << dendl;
+  assert(uncommitted_masters.count(reqid));
+  uncommitted_masters[reqid].safe = true;
+  if (pending_masters.count(reqid)) {
+    pending_masters.erase(reqid);
+    if (pending_masters.empty())
+      process_delayed_resolve();
+  }
+}
 
 /*
  * The mds could crash after receiving all slaves' commit acknowledgement,
@@ -2768,8 +2779,23 @@ void MDCache::handle_resolve(MMDSResolve *m)
     return;
   }
 
+  discard_delayed_resolve(from);
+
   // ambiguous slave requests?
   if (!m->slave_requests.empty()) {
+    for (vector<metareqid_t>::iterator p = m->slave_requests.begin();
+        p != m->slave_requests.end();
+        ++p) {
+      if (uncommitted_masters.count(*p) && !uncommitted_masters[*p].safe)
+       pending_masters.insert(*p);
+    }
+
+    if (!pending_masters.empty()) {
+      dout(10) << " still have pending updates, delay processing slave resolve" << dendl;
+      delayed_resolve[from] = m;
+      return;
+    }
+
     MMDSResolveAck *ack = new MMDSResolveAck;
     for (vector<metareqid_t>::iterator p = m->slave_requests.begin();
         p != m->slave_requests.end();
@@ -2792,7 +2818,6 @@ void MDCache::handle_resolve(MMDSResolve *m)
 
   if (!resolve_ack_gather.empty() || !need_resolve_rollback.empty()) {
     dout(10) << "delay processing subtree resolve" << dendl;
-    discard_delayed_resolve(from);
     delayed_resolve[from] = m;
     return;
   }
@@ -2887,10 +2912,10 @@ void MDCache::handle_resolve(MMDSResolve *m)
 void MDCache::process_delayed_resolve()
 {
   dout(10) << "process_delayed_resolve" << dendl;
-  for (map<int, MMDSResolve *>::iterator p = delayed_resolve.begin();
-       p != delayed_resolve.end(); ++p)
+  map<int, MMDSResolve*> tmp;
+  tmp.swap(delayed_resolve);
+  for (map<int, MMDSResolve*>::iterator p = tmp.begin(); p != tmp.end(); ++p)
     handle_resolve(p->second);
-  delayed_resolve.clear();
 }
 
 void MDCache::discard_delayed_resolve(int who)

diff --git a/src/mds/MDCache.h b/src/mds/MDCache.h
index 99420429f2303b78676004cb53b850d3a4082c6f..89144de69b785ebe02f5fcd6152db0f5856ca6d6 100644 (file)
--- a/src/mds/MDCache.h
+++ b/src/mds/MDCache.h
@@ -281,14 +281,16 @@ public:
                                snapid_t follows=CEPH_NOSNAP);
 
   // slaves
-  void add_uncommitted_master(metareqid_t reqid, LogSegment *ls, set<int> &slaves) {
+  void add_uncommitted_master(metareqid_t reqid, LogSegment *ls, set<int> &slaves, bool safe=false) {
     uncommitted_masters[reqid].ls = ls;
     uncommitted_masters[reqid].slaves = slaves;
+    uncommitted_masters[reqid].safe = safe;
   }
   void wait_for_uncommitted_master(metareqid_t reqid, Context *c) {
     uncommitted_masters[reqid].waiters.push_back(c);
   }
   void log_master_commit(metareqid_t reqid);
+  void logged_master_update(metareqid_t reqid);
   void _logged_master_commit(metareqid_t reqid, LogSegment *ls, list<Context*> &waiters);
   void committed_master_slave(metareqid_t r, int from);
   void finish_committed_masters();
@@ -320,9 +322,12 @@ protected:
     set<int> slaves;
     LogSegment *ls;
     list<Context*> waiters;
+    bool safe;
   };
   map<metareqid_t, umaster>                 uncommitted_masters;         // master: req -> slave set
 
+  set<metareqid_t>             pending_masters;
+
   //map<metareqid_t, bool>     ambiguous_slave_updates;         // for log trimming.
   //map<metareqid_t, Context*> waiting_for_slave_update_commit;
   friend class ESlaveUpdate;

diff --git a/src/mds/Server.cc b/src/mds/Server.cc
index 9e0ad7aff9e3c79f437997a7a7cf02f8f2441f37..159dc23eced0a50189585842650bd04d8b4f03f7 100644 (file)
--- a/src/mds/Server.cc
+++ b/src/mds/Server.cc
@@ -4501,6 +4501,9 @@ void Server::_link_remote_finish(MDRequest *mdr, bool inc,
 
   assert(g_conf->mds_kill_link_at != 3);
 
+  if (!mdr->more()->witnessed.empty())
+    mdcache->logged_master_update(mdr->reqid);
+
   if (inc) {
     // link the new dentry
     dn->pop_projected_linkage();
@@ -5111,6 +5114,9 @@ void Server::_unlink_local_finish(MDRequest *mdr,
 {
   dout(10) << "_unlink_local_finish " << *dn << dendl;
 
+  if (!mdr->more()->witnessed.empty())
+    mdcache->logged_master_update(mdr->reqid);
+
   // unlink main dentry
   dn->get_dir()->unlink_inode(dn);
   dn->pop_projected_linkage();
@@ -5919,6 +5925,9 @@ void Server::_rename_finish(MDRequest *mdr, CDentry *srcdn, CDentry *destdn, CDe
 {
   dout(10) << "_rename_finish " << *mdr << dendl;
 
+  if (!mdr->more()->witnessed.empty())
+    mdcache->logged_master_update(mdr->reqid);
+
   // apply
   _rename_apply(mdr, srcdn, destdn, straydn);
 

diff --git a/src/mds/journal.cc b/src/mds/journal.cc
index 75a733b10a7250dd09f27a081783af623cf14a9a..b8139e3a05b9e2fed33f12906cce9f122b10e6a5 100644 (file)
--- a/src/mds/journal.cc
+++ b/src/mds/journal.cc
@@ -1885,7 +1885,7 @@ void EUpdate::replay(MDS *mds)
     dout(10) << "EUpdate.replay " << reqid << " had slaves, expecting a matching ECommitted" << dendl;
     _segment->uncommitted_masters.insert(reqid);
     set<int> slaves;
-    mds->mdcache->add_uncommitted_master(reqid, _segment, slaves);
+    mds->mdcache->add_uncommitted_master(reqid, _segment, slaves, true);
   }
   
   if (client_map.length()) {