mds: fix file existing check in Server::handle_client_openc()

Creating new file needs to be handled by directory fragment's auth
MDS, opening existing file in write mode needs to be handled by
corresponding inode's auth MDS. If a file is remote link, its parent
directory fragment's auth MDS can be different from corresponding
inode's auth MDS. So which MDS to handle create file request can be
affected by if the corresponding file already exists.

handle_client_openc() calls rdlock_path_xlock_dentry() at the very
beginning. It always assumes the request needs to be handled by
directory fragment's auth MDS. When handling a create file request,
if the file already exists and remotely linked to a non-auth inode,
handle_client_openc() falls back to handle_client_open(),
handle_client_open() forwards the request because the MDS is not
inode's auth MDS. Then when the request arrives at inode's auth MDS,
rdlock_path_xlock_dentry() is called, it will forward the request
back.

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

diff --git a/src/mds/MDCache.cc b/src/mds/MDCache.cc
index 79fc0da25d941cfb9d8995bf32fb06bc98289e05..25f726924e394f6266b55796e9223c6b272a7fcf 100644 (file)
--- a/src/mds/MDCache.cc
+++ b/src/mds/MDCache.cc
@@ -6726,13 +6726,18 @@ int MDCache::path_traverse(MDRequest *mdr, Message *req, Context *fin,     // wh
     
     // can we conclude ENOENT?
     if (dnl && dnl->is_null()) {
-      if (mds->locker->rdlock_try(&dn->lock, client, NULL)) {
+      if (dn->lock.can_read(client) ||
+         (dn->lock.is_xlocked() && dn->lock.get_xlock_by() == mdr)) {
         dout(10) << "traverse: miss on null+readable dentry " << path[depth] << " " << *dn << dendl;
         return -ENOENT;
-      } else {
+      } else if (curdir->is_auth()) {
         dout(10) << "miss on dentry " << *dn << ", can't read due to lock" << dendl;
         dn->lock.add_waiter(SimpleLock::WAIT_RD, _get_waiter(mdr, req, fin));
         return 1;
+      } else {
+       // non-auth and can not read, treat this as no dentry
+       dn = NULL;
+       dnl = NULL;
       }
     }
 

diff --git a/src/mds/Server.cc b/src/mds/Server.cc
index 81c9c7c1a12015dabada21332f2c8982dc94bc2c..02a717af6164427fa78a38213a895d0cbedc9652 100644 (file)
--- a/src/mds/Server.cc
+++ b/src/mds/Server.cc
@@ -2590,6 +2590,29 @@ void Server::handle_client_openc(MDRequest *mdr)
     return;
   }
 
+  if (!(req->head.args.open.flags & O_EXCL)) {
+    int r = mdcache->path_traverse(mdr, NULL, NULL, req->get_filepath(),
+                                  &mdr->dn[0], NULL, MDS_TRAVERSE_FORWARD);
+    if (r > 0) return;
+    if (r == 0) {
+      // it existed.
+      handle_client_open(mdr);
+      return;
+    }
+    if (r < 0 && r != -ENOENT) {
+      if (r == -ESTALE) {
+       dout(10) << "FAIL on ESTALE but attempting recovery" << dendl;
+       Context *c = new C_MDS_TryFindInode(this, mdr);
+       mdcache->find_ino_peers(req->get_filepath().get_ino(), c);
+      } else {
+       dout(10) << "FAIL on error " << r << dendl;
+       reply_request(mdr, r);
+      }
+      return;
+    }
+    // r == -ENOENT
+  }
+
   bool excl = (req->head.args.open.flags & O_EXCL);
   set<SimpleLock*> rdlocks, wrlocks, xlocks;
   ceph_file_layout *dir_layout = NULL;
@@ -2639,13 +2662,9 @@ void Server::handle_client_openc(MDRequest *mdr)
 
   if (!dnl->is_null()) {
     // it existed.  
-    if (req->head.args.open.flags & O_EXCL) {
-      dout(10) << "O_EXCL, target exists, failing with -EEXIST" << dendl;
-      reply_request(mdr, -EEXIST, dnl->get_inode(), dn);
-      return;
-    } 
-    
-    handle_client_open(mdr);
+    assert(req->head.args.open.flags & O_EXCL);
+    dout(10) << "O_EXCL, target exists, failing with -EEXIST" << dendl;
+    reply_request(mdr, -EEXIST, dnl->get_inode(), dn);
     return;
   }