osdc/Objecter: handle race between calc_target and handle_osd_map

If we fail to get an existing session and have to take the exclusive lock,
we may race with an OSDMap update and end up with a stale target.  Check
for an epoch change and, if it happens, recalculate the mapping.

Fixes: http://tracker.ceph.com/issues/17942
Reported-by: wangdongxu <wangdongxu@cmss.chinamobile.com>
Reported-by: menglingkun <menglingkun@cmss.chinamobile.com>
Signed-off-by: Sage Weil <sage@redhat.com>

diff --git a/src/osdc/Objecter.cc b/src/osdc/Objecter.cc
index 963c81082781ea7cae9877ab9b5ac4c03303a73a..81a92a30116ced19816d71ccaecff8aa85e0b0c9 100644 (file)
--- a/src/osdc/Objecter.cc
+++ b/src/osdc/Objecter.cc
@@ -2296,27 +2296,29 @@ void Objecter::_op_submit(Op *op, shunique_lock& sul, ceph_tid_t *ptid)
   assert(op->session == NULL);
   OSDSession *s = NULL;
 
-  bool const check_for_latest_map = _calc_target(&op->target,
-                                                &op->last_force_resend)
+  bool check_for_latest_map = _calc_target(&op->target, &op->last_force_resend)
     == RECALC_OP_TARGET_POOL_DNE;
 
   // Try to get a session, including a retry if we need to take write lock
   int r = _get_session(op->target.osd, &s, sul);
-  if (r == -EAGAIN) {
-    assert(s == NULL);
+  if (r == -EAGAIN ||
+      (check_for_latest_map && sul.owns_lock_shared())) {
+    epoch_t orig_epoch = osdmap->get_epoch();
     sul.unlock();
     sul.lock();
+    if (orig_epoch != osdmap->get_epoch()) {
+      // map changed; recalculate mapping
+      check_for_latest_map = _calc_target(&op->target, &op->last_force_resend)
+       == RECALC_OP_TARGET_POOL_DNE;
+    }
+  }
+  if (r == -EAGAIN) {
+    assert(s == NULL);
     r = _get_session(op->target.osd, &s, sul);
   }
   assert(r == 0);
   assert(s);  // may be homeless
 
-  // We may need to take wlock if we will need to _set_op_map_check later.
-  if (check_for_latest_map && sul.owns_lock_shared()) {
-    sul.unlock();
-    sul.lock();
-  }
-
   _send_op_account(op);
 
   // send?