mon: overwrite in put_bl

This fixes a situation where we accept a large value, there is some failure
and recovery, and then we commit a smaller value with the same version.

E.g.,

INFO:teuthology.task.ceph.mon.b.err:terminate called after throwing an instance of 'ceph::buffer::end_of_buffer'
INFO:teuthology.task.ceph.mon.b.err:  what():  buffer::end_of_buffer
INFO:teuthology.task.ceph.mon.b.err:*** Caught signal (Aborted) **
INFO:teuthology.task.ceph.mon.b.err: in thread 7f0a6037c700
INFO:teuthology.task.ceph.mon.b.err: ceph version 0.37-365-g5b20830 (commit:5b208302e1ad134f56933dfdbccb074e03c88be3)
INFO:teuthology.task.ceph.mon.b.err: 1: (ceph::BackTrace::BackTrace(int)+0x2d) [0x6f4d1b]
INFO:teuthology.task.ceph.mon.b.err: 2: /tmp/cephtest/binary/usr/local/bin/ceph-mon() [0x7e9492]
INFO:teuthology.task.ceph.mon.b.err: 3: (()+0xfb40) [0x7f0a63bf4b40]
INFO:teuthology.task.ceph.mon.b.err: 4: (gsignal()+0x35) [0x7f0a625cdba5]
INFO:teuthology.task.ceph.mon.b.err: 5: (abort()+0x180) [0x7f0a625d16b0]
INFO:teuthology.task.ceph.mon.b.err: 6: (__gnu_cxx::__verbose_terminate_handler()+0x11d) [0x7f0a62e716bd]
INFO:teuthology.task.ceph.mon.b.err: 7: (()+0xb9906) [0x7f0a62e6f906]
INFO:teuthology.task.ceph.mon.b.err: 8: (()+0xb9933) [0x7f0a62e6f933]
INFO:teuthology.task.ceph.mon.b.err: 9: (()+0xb9a3e) [0x7f0a62e6fa3e]
INFO:teuthology.task.ceph.mon.b.err: 10: (ceph::buffer::list::iterator::copy(unsigned int, std::string&)+0xcb) [0x7d73a7]
INFO:teuthology.task.ceph.mon.b.err: 11: (decode(std::string&, ceph::buffer::list::iterator&)+0x44) [0x5fa2e8]
INFO:teuthology.task.ceph.mon.b.err: 12: (LogEntry::decode(ceph::buffer::list::iterator&)+0xa8) [0x6ceee8]
INFO:teuthology.task.ceph.mon.b.err: 13: (LogMonitor::update_from_paxos()+0x346) [0x6cce9a]
INFO:teuthology.task.ceph.mon.b.err: 14: (PaxosService::_active()+0x13b) [0x647ab5]
INFO:teuthology.task.ceph.mon.b.err: 15: (PaxosService::C_Active::finish(int)+0x25) [0x647cb9]
INFO:teuthology.task.ceph.mon.b.err: 16: (Context::complete(int)+0x2b) [0x61a5a9]
INFO:teuthology.task.ceph.mon.b.err: 17: (finish_contexts(CephContext*, std::list<Context*, std::allocator<Context*> >&, int)+0x20b) [0x61a7ef]
INFO:teuthology.task.ceph.mon.b.err: 18: (Paxos::handle_last(MMonPaxos*)+0xea7) [0x63d081]
INFO:teuthology.task.ceph.mon.b.err: 19: (Paxos::dispatch(PaxosServiceMessage*)+0x29c) [0x642046]
INFO:teuthology.task.ceph.mon.b.err: 20: (Monitor::_ms_dispatch(Message*)+0xd78) [0x61636e]
INFO:teuthology.task.ceph.mon.b.err: 21: (Monitor::ms_dispatch(Message*)+0x3a) [0x61de84]
INFO:teuthology.task.ceph.mon.b.err: 22: (Messenger::ms_deliver_dispatch(Message*)+0x63) [0x7c690f]
INFO:teuthology.task.ceph.mon.b.err: 23: (SimpleMessenger::dispatch_entry()+0x7c2) [0x7b0156]
INFO:teuthology.task.ceph.mon.b.err: 24: (SimpleMessenger::DispatchThread::entry()+0x2c) [0x5fd6ac]
INFO:teuthology.task.ceph.mon.b.err: 25: (Thread::_entry_func(void*)+0x23) [0x6e9261]
INFO:teuthology.task.ceph.mon.b.err: 26: (()+0x7971) [0x7f0a63bec971]
INFO:teuthology.task.ceph.mon.b.err: 27: (clone()+0x6d) [0x7f0a6268092d]

Signed-off-by: Sage Weil <sage@newdream.net>

diff --git a/src/mon/MonitorStore.cc b/src/mon/MonitorStore.cc
index 7f0e61118874280b7c7cc8841ff74d7acf8d6fe8..f93ab772ac61a78a58f15f1e97dbae3f70af75a5 100644 (file)
--- a/src/mon/MonitorStore.cc
+++ b/src/mon/MonitorStore.cc
@@ -313,7 +313,7 @@ int MonitorStore::write_bl_ss_impl(bufferlist& bl, const char *a, const char *b,
     }
   } else {
     snprintf(tfn, sizeof(tfn), "%s.new", fn);
-    fd = ::open(tfn, O_WRONLY|O_CREAT, 0644);
+    fd = ::open(tfn, O_WRONLY|O_CREAT|O_TRUNC, 0644);
     if (fd < 0) {
       err = -errno;
       derr << "failed to open " << tfn << ": " << cpp_strerror(err) << dendl;