From: Somnath Roy <somnath.roy@sandisk.com>
Date: Tue, 9 Sep 2014 02:40:29 +0000 (-0700)
Subject: OpTracker: Race condition removed while dumping ops through admin socket
X-Git-Tag: v0.86~43^2
X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=11082f7aa02f3f41c7c74c5930b67216dba88ea1;p=ceph.git

OpTracker: Race condition removed while dumping ops through admin socket

OSD was crashing due to a race condition while IO was going on and
user wants to dump in flight ops. This was happening because Message
data and payloads are removed before the op itself is removed from
the in flight list. Calling op->_unregistered() after removing
the op from the in flight list fixes the issue.

Fixes: #9384

Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
---

diff --git a/src/common/TrackedOp.cc b/src/common/TrackedOp.cc
index d7a95b87ac1f..32dbc5398dcc 100644
--- a/src/common/TrackedOp.cc
+++ b/src/common/TrackedOp.cc
@@ -145,6 +145,7 @@ void OpTracker::unregister_inflight_op(TrackedOp *i)
     assert(i->xitem.get_list() == &sdata->ops_in_flight_sharded);
     i->xitem.remove_myself();
   }
+  i->_unregistered();
   utime_t now = ceph_clock_now(cct);
   history.insert(now, TrackedOpRef(i));
 }
@@ -294,8 +295,8 @@ void OpTracker::_mark_event(TrackedOp *op, const string &evt,
 
 void OpTracker::RemoveOnDelete::operator()(TrackedOp *op) {
   op->mark_event("done");
-  op->_unregistered();
   if (!tracker->tracking_enabled) {
+    op->_unregistered();
     delete op;
     return;
   }