Project

General

Profile

Bug #2014

librados shutdown race

Added by Sage Weil almost 12 years ago. Updated almost 12 years ago.

Status:
Resolved
Priority:
Normal
Assignee:
-
Category:
librados
Target version:
v0.42
% Done:

0%

Source:
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description


(gdb) 
#0  Lock (this=0x0, idx=123207, amt=1) at ./common/Mutex.h:107
#1  Locker (this=0x0, idx=123207, amt=1) at ./common/Mutex.h:135
#2  PerfCounters::inc (this=0x0, idx=123207, amt=1) at common/perf_counters.cc:92
#3  0x00007fe89c86e0f7 in Objecter::handle_osd_op_reply (this=0x67fe80, m=<value optimized out>) at osdc/Objecter.cc:1238
#4  0x00007fe89c83b574 in librados::RadosClient::_dispatch (this=0x67bbf0, m=0x1e147) at librados.cc:1069
#5  0x00007fe89c83b603 in librados::RadosClient::ms_dispatch (this=0x67bbf0, m=0x7fe8214f45c0) at librados.cc:1039
#6  0x00007fe89c93bfaa in ms_deliver_dispatch (this=0x67f000) at msg/Messenger.h:102
#7  SimpleMessenger::dispatch_entry (this=0x67f000) at msg/SimpleMessenger.cc:364
#8  0x00007fe89c84827c in SimpleMessenger::DispatchThread::entry (this=0x67f488) at msg/SimpleMessenger.h:545
#9  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x0) at common/Thread.cc:41
#10 0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#11 0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#12 0x0000000000000000 in ?? ()
(gdb) thr app all bt

Thread 16 (Thread 21411):
#0  SimpleMessenger::Pipe::fault (this=0x750380, onconnect=false, onread=true) at msg/SimpleMessenger.cc:1430
#1  0x00007fe89c9550b6 in SimpleMessenger::Pipe::reader (this=0x750380) at msg/SimpleMessenger.cc:1570
#2  0x00007fe89c848315 in SimpleMessenger::Pipe::Reader::entry (this=<value optimized out>) at msg/SimpleMessenger.h:209
#3  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x750380) at common/Thread.cc:41
#4  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#5  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#6  0x0000000000000000 in ?? ()

Thread 15 (Thread 21406):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:136
#1  0x00007fe89c59b71e in _L_cond_lock_1028 () from /lib/libpthread.so.0
#2  0x00007fe89c59b54b in __pthread_mutex_cond_lock (mutex=0x750458) at ../nptl/pthread_mutex_lock.c:61
#3  0x00007fe89c595b36 in pthread_cond_wait@@GLIBC_2.3.2 () at ../nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S:236
#4  0x00007fe89c95c6ad in Wait (this=0x750380) at ./common/Cond.h:48
#5  SimpleMessenger::Pipe::writer (this=0x750380) at msg/SimpleMessenger.cc:1781
#6  0x00007fe89c848345 in SimpleMessenger::Pipe::Writer::entry (this=<value optimized out>) at msg/SimpleMessenger.h:217
#7  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x750458) at common/Thread.cc:41
#8  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#9  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#10 0x0000000000000000 in ?? ()

Thread 14 (Thread 21394):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:136
#1  0x00007fe89c593849 in _L_lock_953 () from /lib/libpthread.so.0
#2  0x00007fe89c59366b in __pthread_mutex_lock (mutex=0x67c3f0) at pthread_mutex_lock.c:61
#3  0x00007fe89c92405c in Lock (this=0x67c458) at common/Mutex.h:108
#4  SafeTimer::shutdown (this=0x67c458) at common/Timer.cc:77
#5  0x00007fe89c8286c4 in librados::RadosClient::shutdown (this=0x67bbf0) at librados.cc:1016
#6  0x00007fe89c828942 in librados::Rados::shutdown (this=0x7fff5d5ea750) at librados.cc:3172
#7  0x0000000000409785 in shutdown (argc=<value optimized out>, argv=<value optimized out>) at ./test/osd/RadosModel.h:148
#8  main (argc=<value optimized out>, argv=<value optimized out>) at test/osd/TestRados.cc:250

Thread 13 (Thread 21423):
#0  SimpleMessenger::Pipe::fault (this=0xfce3d0, onconnect=false, onread=true) at msg/SimpleMessenger.cc:1430
#1  0x00007fe89c9550b6 in SimpleMessenger::Pipe::reader (this=0xfce3d0) at msg/SimpleMessenger.cc:1570
#2  0x00007fe89c848315 in SimpleMessenger::Pipe::Reader::entry (this=<value optimized out>) at msg/SimpleMessenger.h:209
#3  0x00007fe89c9b3292 in Thread::_entry_func (arg=0xfce3d0) at common/Thread.cc:41
#4  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#5  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#6  0x0000000000000000 in ?? ()

Thread 12 (Thread 21396):
#0  0x00007fe89bdc5203 in __poll (fds=<value optimized out>, nfds=<value optimized out>, timeout=-1) at ../sysdeps/unix/sysv/linux/poll.c:87
#1  0x00007fe89c919df6 in AdminSocket::entry (this=0x67b460) at common/admin_socket.cc:211
#2  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x7fe89a79cdf0) at common/Thread.cc:41
#3  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#4  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#5  0x0000000000000000 in ?? ()

Thread 11 (Thread 21405):
#0  SimpleMessenger::Pipe::fault (this=0x6883f0, onconnect=false, onread=true) at msg/SimpleMessenger.cc:1430
#1  0x00007fe89c9550b6 in SimpleMessenger::Pipe::reader (this=0x6883f0) at msg/SimpleMessenger.cc:1570
#2  0x00007fe89c848315 in SimpleMessenger::Pipe::Reader::entry (this=<value optimized out>) at msg/SimpleMessenger.h:209
#3  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x6883f0) at common/Thread.cc:41
#4  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#5  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#6  0x0000000000000000 in ?? ()

Thread 10 (Thread 21424):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:136
#1  0x00007fe89c59b71e in _L_cond_lock_1028 () from /lib/libpthread.so.0
#2  0x00007fe89c59b54b in __pthread_mutex_cond_lock (mutex=0x7fe89028e6f8) at ../nptl/pthread_mutex_lock.c:61
#3  0x00007fe89c595b36 in pthread_cond_wait@@GLIBC_2.3.2 () at ../nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S:236
#4  0x00007fe89c95c6ad in Wait (this=0x7fe89028e620) at ./common/Cond.h:48
#5  SimpleMessenger::Pipe::writer (this=0x7fe89028e620) at msg/SimpleMessenger.cc:1781
#6  0x00007fe89c848345 in SimpleMessenger::Pipe::Writer::entry (this=<value optimized out>) at msg/SimpleMessenger.h:217
#7  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x7fe89028e6f8) at common/Thread.cc:41
#8  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#9  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#10 0x0000000000000000 in ?? ()

Thread 9 (Thread 21422):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:136
---Type <return> to continue, or q <return> to quit---
#1  0x00007fe89c59b71e in _L_cond_lock_1028 () from /lib/libpthread.so.0
#2  0x00007fe89c59b54b in __pthread_mutex_cond_lock (mutex=0xfce4a8) at ../nptl/pthread_mutex_lock.c:61
#3  0x00007fe89c595b36 in pthread_cond_wait@@GLIBC_2.3.2 () at ../nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S:236
#4  0x00007fe89c95c6ad in Wait (this=0xfce3d0) at ./common/Cond.h:48
#5  SimpleMessenger::Pipe::writer (this=0xfce3d0) at msg/SimpleMessenger.cc:1781
#6  0x00007fe89c848345 in SimpleMessenger::Pipe::Writer::entry (this=<value optimized out>) at msg/SimpleMessenger.h:217
#7  0x00007fe89c9b3292 in Thread::_entry_func (arg=0xfce4a8) at common/Thread.cc:41
#8  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#9  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#10 0x0000000000000000 in ?? ()

Thread 8 (Thread 21395):
#0  sem_timedwait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/sem_timedwait.S:103
#1  0x00007fe89c9ab27f in CephContextServiceThread::entry (this=0x67bad0) at common/ceph_context.cc:53
#2  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x67bae8) at common/Thread.cc:41
#3  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#4  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#5  0x0000000000000000 in ?? ()

Thread 7 (Thread 21402):
#0  0x00007fe89bdc5203 in __poll (fds=<value optimized out>, nfds=<value optimized out>, timeout=900000) at ../sysdeps/unix/sysv/linux/poll.c:87
#1  0x00007fe89c939469 in tcp_read_wait (sd=<value optimized out>, timeout=<value optimized out>) at msg/tcp.cc:53
#2  0x00007fe89c947d40 in tcp_read (cct=0x672680, sd=7, buf=0x7fe897f97d9f "ΓΏ\005", len=1, timeout=0) at msg/tcp.cc:26
#3  0x00007fe89c95470d in SimpleMessenger::Pipe::reader (this=0x681090) at msg/SimpleMessenger.cc:1566
#4  0x00007fe89c848315 in SimpleMessenger::Pipe::Reader::entry (this=<value optimized out>) at msg/SimpleMessenger.h:209
#5  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x7fe897f97cc0) at common/Thread.cc:41
#6  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#7  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#8  0x0000000000000000 in ?? ()

Thread 6 (Thread 21427):
#0  SimpleMessenger::Pipe::fault (this=0x7fe89028e620, onconnect=false, onread=true) at msg/SimpleMessenger.cc:1430
#1  0x00007fe89c9550b6 in SimpleMessenger::Pipe::reader (this=0x7fe89028e620) at msg/SimpleMessenger.cc:1570
#2  0x00007fe89c848315 in SimpleMessenger::Pipe::Reader::entry (this=<value optimized out>) at msg/SimpleMessenger.h:209
#3  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x7fe89028e620) at common/Thread.cc:41
#4  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#5  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#6  0x0000000000000000 in ?? ()

Thread 5 (Thread 21401):
#0  pthread_cond_wait@@GLIBC_2.3.2 () at ../nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S:162
#1  0x00007fe89c95c6ad in Wait (this=0x681090) at ./common/Cond.h:48
#2  SimpleMessenger::Pipe::writer (this=0x681090) at msg/SimpleMessenger.cc:1781
#3  0x00007fe89c848345 in SimpleMessenger::Pipe::Writer::entry (this=<value optimized out>) at msg/SimpleMessenger.h:217
#4  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x68126c) at common/Thread.cc:41
#5  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#6  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#7  0x0000000000000000 in ?? ()

Thread 4 (Thread 21414):
#0  SimpleMessenger::Pipe::fault (this=0x75cb80, onconnect=false, onread=true) at msg/SimpleMessenger.cc:1430
#1  0x00007fe89c9550b6 in SimpleMessenger::Pipe::reader (this=0x75cb80) at msg/SimpleMessenger.cc:1570
#2  0x00007fe89c848315 in SimpleMessenger::Pipe::Reader::entry (this=<value optimized out>) at msg/SimpleMessenger.h:209
#3  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x75cb80) at common/Thread.cc:41
#4  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#5  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#6  0x0000000000000000 in ?? ()

Thread 3 (Thread 21398):
#0  pthread_cond_wait@@GLIBC_2.3.2 () at ../nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S:162
#1  0x00007fe89c94c848 in Wait (this=0x67f000) at ./common/Cond.h:48
#2  SimpleMessenger::reaper_entry (this=0x67f000) at msg/SimpleMessenger.cc:2286
#3  0x00007fe89c848f2c in SimpleMessenger::ReaperThread::entry (this=0x67f430) at msg/SimpleMessenger.h:496
#4  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x67f45c) at common/Thread.cc:41
#5  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#6  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#7  0x0000000000000000 in ?? ()

Thread 2 (Thread 21410):
#0  SimpleMessenger::Pipe::fault (this=0x694480, onconnect=false, onread=true) at msg/SimpleMessenger.cc:1430
#1  0x00007fe89c9550b6 in SimpleMessenger::Pipe::reader (this=0x694480) at msg/SimpleMessenger.cc:1570
#2  0x00007fe89c848315 in SimpleMessenger::Pipe::Reader::entry (this=<value optimized out>) at msg/SimpleMessenger.h:209
#3  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x694480) at common/Thread.cc:41
#4  0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#5  0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
---Type <return> to continue, or q <return> to quit---
#6  0x0000000000000000 in ?? ()

Thread 1 (Thread 21397):
#0  Lock (this=0x0, idx=123207, amt=1) at ./common/Mutex.h:107
#1  Locker (this=0x0, idx=123207, amt=1) at ./common/Mutex.h:135
#2  PerfCounters::inc (this=0x0, idx=123207, amt=1) at common/perf_counters.cc:92
#3  0x00007fe89c86e0f7 in Objecter::handle_osd_op_reply (this=0x67fe80, m=<value optimized out>) at osdc/Objecter.cc:1238
#4  0x00007fe89c83b574 in librados::RadosClient::_dispatch (this=0x67bbf0, m=0x1e147) at librados.cc:1069
#5  0x00007fe89c83b603 in librados::RadosClient::ms_dispatch (this=0x67bbf0, m=0x7fe8214f45c0) at librados.cc:1039
#6  0x00007fe89c93bfaa in ms_deliver_dispatch (this=0x67f000) at msg/Messenger.h:102
#7  SimpleMessenger::dispatch_entry (this=0x67f000) at msg/SimpleMessenger.cc:364
#8  0x00007fe89c84827c in SimpleMessenger::DispatchThread::entry (this=0x67f488) at msg/SimpleMessenger.h:545
#9  0x00007fe89c9b3292 in Thread::_entry_func (arg=0x0) at common/Thread.cc:41
#10 0x00007fe89c591971 in start_thread (arg=<value optimized out>) at pthread_create.c:304
#11 0x00007fe89bdd192d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#12 0x0000000000000000 in ?? ()

objecter was shut down, but we're still processing messages.

History

#1 Updated by Sage Weil almost 12 years ago 


diff --git a/src/librados.cc b/src/librados.cc
index d9cd8ad..6b3018a 100644
--- a/src/librados.cc
+++ b/src/librados.cc
@@ -1035,8 +1035,14 @@ librados::RadosClient::~RadosClient()

 bool librados::RadosClient::ms_dispatch(Message *m)
 {
+  bool ret;
   lock.Lock();
-  bool ret = _dispatch(m);
+  if (state == DISCONNECTED) {
+    m->put();
+    ret = true;
+  } else {
+    ret = _dispatch(m);
+  }
   lock.Unlock();
   return ret;
 }

#2 Updated by Sage Weil almost 12 years ago

  • Status changed from New to Resolved

resolved by 33659521a92315f71040551b2699d9961acc07f7 and neighbors.

Also available in: Atom PDF