Merge remote-tracking branch 'yan/wip-mds'

Reviewed-by: Sage Weil <sage@inktank.com>

7 files changed, 52 insertions, 56 deletions

diff --git a/src/mds/CInode.cc b/src/mds/CInode.cc
index d215d18690f..dd483263b6d 100644
--- a/src/mds/CInode.cc
+++ b/src/mds/CInode.cc
@@ -2733,10 +2733,12 @@ int CInode::encode_inodestat(bufferlist& bl, Session *session,
 
   // do not issue caps if inode differs from readdir snaprealm
   SnapRealm *realm = find_snaprealm();
-  bool no_caps = (realm && dir_realm && realm != dir_realm) ||
+  bool no_caps = session->is_stale() ||
+		 (realm && dir_realm && realm != dir_realm) ||
 		 is_frozen() || state_test(CInode::STATE_EXPORTINGCAPS);
   if (no_caps)
     dout(20) << "encode_inodestat no caps"
+	     << (session->is_stale()?", session stale ":"")
 	     << ((realm && dir_realm && realm != dir_realm)?", snaprealm differs ":"")
 	     << (state_test(CInode::STATE_EXPORTINGCAPS)?", exporting caps":"")
 	     << (is_frozen()?", frozen inode":"") << dendl;
diff --git a/src/mds/Capability.h b/src/mds/Capability.h
index fdecb9090b3..fb6b3dc1f16 100644
--- a/src/mds/Capability.h
+++ b/src/mds/Capability.h
@@ -171,14 +171,16 @@ public:
   }
   void confirm_receipt(ceph_seq_t seq, unsigned caps) {
     if (seq == last_sent) {
-      _pending = caps;
       _revokes.clear();
       _issued = caps;
+      // don't add bits
+      _pending &= caps;
     } else {
       // can i forget any revocations?
-      while (!_revokes.empty() &&
-	     _revokes.front().seq <= seq)
+      while (!_revokes.empty() && _revokes.front().seq < seq)
 	_revokes.pop_front();
+      if (!_revokes.empty() && _revokes.front().seq == seq)
+	_revokes.begin()->before = caps;
       _calc_issued();
     }
     //check_rdcaps_list();
diff --git a/src/mds/Locker.cc b/src/mds/Locker.cc
index 30e014ab785..084d64aeb9c 100644
--- a/src/mds/Locker.cc
+++ b/src/mds/Locker.cc
@@ -543,15 +543,16 @@ void Locker::cancel_locking(Mutation *mut, set<CInode*> *pneed_issue)
   dout(10) << "cancel_locking " << *lock << " on " << *mut << dendl;
 
   if (lock->get_parent()->is_auth()) {
-    if (lock->get_type() != CEPH_LOCK_DN) {
-      bool need_issue = false;
-      if (lock->get_state() == LOCK_PREXLOCK)
-	_finish_xlock(lock, &need_issue);
-      if (lock->is_stable())
-	eval(lock, &need_issue);
-      if (need_issue)
-	pneed_issue->insert(static_cast<CInode *>(lock->get_parent()));
+    bool need_issue = false;
+    if (lock->get_state() == LOCK_PREXLOCK) {
+      _finish_xlock(lock, -1, &need_issue);
+    } else if (lock->get_state() == LOCK_LOCK_XLOCK &&
+	       lock->get_num_xlocks() == 0) {
+      lock->set_state(LOCK_XLOCKDONE);
+      eval_gather(lock, true, &need_issue);
     }
+    if (need_issue)
+      pneed_issue->insert(static_cast<CInode *>(lock->get_parent()));
   }
   mut->finish_locking(lock);
 }
@@ -1458,19 +1459,29 @@ bool Locker::xlock_start(SimpleLock *lock, MDRequest *mut)
   }
 }
 
-void Locker::_finish_xlock(SimpleLock *lock, bool *pneed_issue)
+void Locker::_finish_xlock(SimpleLock *lock, client_t xlocker, bool *pneed_issue)
 {
   assert(!lock->is_stable());
-  if (lock->get_type() != CEPH_LOCK_DN && (static_cast<CInode*>(lock->get_parent())->get_loner()) >= 0)
-    lock->set_state(LOCK_EXCL);
-  else
-    lock->set_state(LOCK_LOCK);
-  if (lock->get_type() == CEPH_LOCK_DN && lock->get_parent()->is_replicated() &&
-      !lock->is_waiter_for(SimpleLock::WAIT_WR))
-    simple_sync(lock, pneed_issue);
-  if (lock->get_cap_shift())
-    *pneed_issue = true;
-  lock->get_parent()->auth_unpin(lock);
+  if (lock->get_num_rdlocks() == 0 &&
+      lock->get_num_wrlocks() == 0 &&
+      lock->get_num_client_lease() == 0 &&
+      lock->get_type() != CEPH_LOCK_DN) {
+    CInode *in = static_cast<CInode*>(lock->get_parent());
+    client_t loner = in->get_target_loner();
+    if (loner >= 0 && (xlocker < 0 || xlocker == loner)) {
+      lock->set_state(LOCK_EXCL);
+      lock->get_parent()->auth_unpin(lock);
+      lock->finish_waiters(SimpleLock::WAIT_STABLE|SimpleLock::WAIT_WR|SimpleLock::WAIT_RD);
+      if (lock->get_cap_shift())
+	*pneed_issue = true;
+      if (lock->get_parent()->is_auth() &&
+	  lock->is_stable())
+	try_eval(lock, pneed_issue);
+      return;
+    }
+  }
+  // the xlocker may have CEPH_CAP_GSHARED, need to revoke it if next state is LOCK_LOCK
+  eval_gather(lock, true, pneed_issue);
 }
 
 void Locker::xlock_finish(SimpleLock *lock, Mutation *mut, bool *pneed_issue)
@@ -1481,6 +1492,8 @@ void Locker::xlock_finish(SimpleLock *lock, Mutation *mut, bool *pneed_issue)
 
   dout(10) << "xlock_finish on " << *lock << " " << *lock->get_parent() << dendl;
 
+  client_t xlocker = lock->get_xlock_by_client();
+
   // drop ref
   lock->put_xlock();
   assert(mut);
@@ -1508,24 +1521,12 @@ void Locker::xlock_finish(SimpleLock *lock, Mutation *mut, bool *pneed_issue)
 			 SimpleLock::WAIT_WR | 
 			 SimpleLock::WAIT_RD, 0); 
   } else {
-    if (lock->get_num_xlocks() == 0 &&
-	lock->get_num_rdlocks() == 0 &&
-	lock->get_num_wrlocks() == 0 &&
-	lock->get_num_client_lease() == 0) {
-      _finish_xlock(lock, &do_issue);
+    if (lock->get_num_xlocks() == 0) {
+      if (lock->get_state() == LOCK_LOCK_XLOCK)
+	lock->set_state(LOCK_XLOCKDONE);
+      _finish_xlock(lock, xlocker, &do_issue);
     }
-
-    // others waiting?
-    lock->finish_waiters(SimpleLock::WAIT_STABLE |
-			 SimpleLock::WAIT_WR | 
-			 SimpleLock::WAIT_RD, 0); 
   }
-    
-  // eval?
-  if (!lock->is_stable())
-    eval_gather(lock, false, &do_issue);
-  else if (lock->get_parent()->is_auth())
-    try_eval(lock, &do_issue);
   
   if (do_issue) {
     CInode *in = static_cast<CInode*>(lock->get_parent());
@@ -3440,7 +3441,6 @@ bool Locker::simple_sync(SimpleLock *lock, bool *need_issue)
 
     switch (lock->get_state()) {
     case LOCK_MIX: lock->set_state(LOCK_MIX_SYNC); break;
-    case LOCK_SCAN:
     case LOCK_LOCK: lock->set_state(LOCK_LOCK_SYNC); break;
     case LOCK_XSYN: lock->set_state(LOCK_XSYN_SYNC); break;
     case LOCK_EXCL: lock->set_state(LOCK_EXCL_SYNC); break;
@@ -3517,7 +3517,6 @@ void Locker::simple_excl(SimpleLock *lock, bool *need_issue)
     in = static_cast<CInode *>(lock->get_parent());
 
   switch (lock->get_state()) {
-  case LOCK_SCAN:
   case LOCK_LOCK: lock->set_state(LOCK_LOCK_EXCL); break;
   case LOCK_SYNC: lock->set_state(LOCK_SYNC_EXCL); break;
   case LOCK_XSYN: lock->set_state(LOCK_XSYN_EXCL); break;
@@ -3576,7 +3575,6 @@ void Locker::simple_lock(SimpleLock *lock, bool *need_issue)
   int old_state = lock->get_state();
 
   switch (lock->get_state()) {
-  case LOCK_SCAN: lock->set_state(LOCK_SCAN_LOCK); break;
   case LOCK_SYNC: lock->set_state(LOCK_SYNC_LOCK); break;
   case LOCK_XSYN:
     file_excl(static_cast<ScatterLock*>(lock), need_issue);
@@ -4162,10 +4160,6 @@ void Locker::file_eval(ScatterLock *lock, bool *need_issue)
   if (lock->get_parent()->is_freezing_or_frozen())
     return;
 
-  // wait for scan
-  if (lock->get_state() == LOCK_SCAN)
-    return;
-
   // excl -> *?
   if (lock->get_state() == LOCK_EXCL) {
     dout(20) << " is excl" << dendl;
@@ -4352,7 +4346,6 @@ void Locker::file_excl(ScatterLock *lock, bool *need_issue)
   switch (lock->get_state()) {
   case LOCK_SYNC: lock->set_state(LOCK_SYNC_EXCL); break;
   case LOCK_MIX: lock->set_state(LOCK_MIX_EXCL); break;
-  case LOCK_SCAN:
   case LOCK_LOCK: lock->set_state(LOCK_LOCK_EXCL); break;
   case LOCK_XSYN: lock->set_state(LOCK_XSYN_EXCL); break;
   default: assert(0);
@@ -4463,12 +4456,12 @@ void Locker::file_recover(ScatterLock *lock)
     issue_caps(in);
     gather++;
   }
-  if (gather) {
-    lock->get_parent()->auth_pin(lock);
-  } else {
-    lock->set_state(LOCK_SCAN);
+
+  lock->set_state(LOCK_SCAN);
+  if (gather)
+    in->state_set(CInode::STATE_NEEDSRECOVER);
+  else
     mds->mdcache->queue_file_recover(in);
-  }
 }
 
 
diff --git a/src/mds/Locker.h b/src/mds/Locker.h
index b97307d6cb2..b39eff175d6 100644
--- a/src/mds/Locker.h
+++ b/src/mds/Locker.h
@@ -143,7 +143,7 @@ public:
   void remote_wrlock_finish(SimpleLock *lock, int target, Mutation *mut);
 
   bool xlock_start(SimpleLock *lock, MDRequest *mut);
-  void _finish_xlock(SimpleLock *lock, bool *pneed_issue);
+  void _finish_xlock(SimpleLock *lock, client_t xlocker, bool *pneed_issue);
   void xlock_finish(SimpleLock *lock, Mutation *mut, bool *pneed_issue);
 
   void xlock_export(SimpleLock *lock, Mutation *mut);
diff --git a/src/mds/MDCache.cc b/src/mds/MDCache.cc
index 77d3d8b97b8..898dcd39f48 100644
--- a/src/mds/MDCache.cc
+++ b/src/mds/MDCache.cc
@@ -5718,6 +5718,7 @@ void MDCache::identify_files_to_recover(vector<CInode*>& recover_q, vector<CInod
     }
 
     if (recover) {
+      in->auth_pin(&in->filelock);
       in->filelock.set_state(LOCK_PRE_SCAN);
       recover_q.push_back(in);
       
diff --git a/src/mds/locks.c b/src/mds/locks.c
index 90310874411..37e3f5ea764 100644
--- a/src/mds/locks.c
+++ b/src/mds/locks.c
@@ -122,8 +122,7 @@ const struct sm_state_t filelock[LOCK_MAX] = {
     [LOCK_EXCL_XSYN] = { LOCK_XSYN, false, LOCK_LOCK, 0,    0,   XCL, 0,   0,   0,   0,   0,CEPH_CAP_GCACHE|CEPH_CAP_GBUFFER,0,0 },
 
     [LOCK_PRE_SCAN]  = { LOCK_SCAN, false, LOCK_LOCK, 0,    0,   0,   0,   0,   0,   0,   0,0,0,0 },
-    [LOCK_SCAN]      = { 0,         false, LOCK_LOCK, 0,    0,   0,   0,   0,   0,   0,   0,0,0,0 },
-    [LOCK_SCAN_LOCK] = { LOCK_LOCK, false, LOCK_LOCK, 0,    0,   0,   0,   0,   0,   0,   0,0,0,0 },
+    [LOCK_SCAN]      = { LOCK_LOCK, false, LOCK_LOCK, 0,    0,   0,   0,   0,   0,   0,   0,0,0,0 },
 };
 
 const struct sm_t sm_filelock = {
diff --git a/src/mds/locks.h b/src/mds/locks.h
index 2adcbf21fea..d1585cec576 100644
--- a/src/mds/locks.h
+++ b/src/mds/locks.h
@@ -86,7 +86,6 @@ enum {
 
   LOCK_PRE_SCAN,
   LOCK_SCAN,
-  LOCK_SCAN_LOCK,
 
   LOCK_SNAP_SYNC,