On Wed, Sep 22, 2010 at 7:47 AM, cang lin <fwdflywl@xxxxxxxxx> wrote: > I found the clients(1 local,2 remote) can’t access ceph today. The clients require an active MDS to connect, since that handles all the filesystem components of connection. > 10.09.21_23:37:20.331651 b4d43b70 -- ???.???.248.176:6800/3780 --> > mon0 ???.???.248.177:6789/0 -- mdsbeacon(4298/lz05 up:active seq > 497179 v27) v1 -- ?+0 0x8be0de0 > 10.09.21_23:37:20.332446 b6347b70 -- ???.???.248.176:6800/3780 <== > mon0 ???.???.248.177:6789/0 511955 ==== mdsbeacon(4298/ceph02 > up:active seq 497179 v27) v1 ==== 70+0+0 (116627713 0 0) 0xb2c967a8 > 10.09.21_23:37:22.602613 af9ffb70 -- ???.???.248.176:6800/3780 >> > ???.??.229.124:0/2562359250 pipe(0x8c26b80 sd=23 pgs=0 cs=0 > l=0).accept peer addr is really ???.???.229.124:0/2562359250 (socket > is ???.???.229.124:52272/0) > 10.09.21_23:37:22.602813 af9ffb70 -- ???.???.248.176:6800/3780 >> > ???.???.229.124:0/2562359250 pipe(0x8c26b80 sd=23 pgs=0 cs=0 > l=0).accept connect_seq 1 vs existing 1 state 2 > msg/SimpleMessenger.cc: In function 'int SimpleMessenger::Pipe::accept()': > msg/SimpleMessenger.cc:740: FAILED assert(existing->state == > STATE_CONNECTING || existing->state == STATE_STANDBY || > existing->state == STATE_WAIT) > 1: (SimpleMessenger::Pipe::reader()+0x830) [0x80c4ba0] > 2: (SimpleMessenger::Pipe::Reader::entry()+0x14) [0x80b7d14] > 3: (Thread::_entry_func(void*)+0x11) [0x80ca7c1] > 4: (()+0x596e) [0x4a896e] > 5: (clone()+0x5e) [0x86ca4e] > NOTE: a copy of the executable, or `objdump -rdS <executable>` is > needed to interpret this. Well, this is interesting. Could you gzip up your mds log and send it to me or Sage? This shouldn't be able to happen! -Greg -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
