Bug #5481
closedCeph OSD Connection refused
0%
Description
Hi all,
i found an error in ceph osd log file.in my osd tree, there're 2 osd marked down, not running.
in osd1(192.168.4.101) log:
192.168.4.101:6828/10551 >> 192.168.4.104:6809/1218 pipe(0x5005000 sd=55 :35763 s=1 pgs=574 cs=4 l=0).connect error 192.168.4.104:6809/1218, 111: Connection refused
in osd3(192.168.4.103) log:
192.168.4.103:6826/16315 >> 192.168.4.104:6809/1218 pipe(0x53f3a00 sd=75 :44172 s=1 pgs=566 cs=4 l=0).connect error 192.168.4.104:6809/1218, 111: Connection refused
the two ceph-osd processes seem to connect to osd.4, but failed.
in osd4(192.168.4.104) log:
192.168.4.104:6809/1218 >> 192.168.4.103:6832/16097 pipe(0x2922780 sd=43 :45945 s=2 pgs=5128 cs=3 l=0).reader got old message 5 <= 75 0x1f30400 osd_map(1844..1883 src has 1373..1883) v3, discarding
And I’m trying connect to 192.168.4.104:6809...and the connection established.Anyone be able to explain these findings?BR
chen
Updated by Sage Weil almost 11 years ago
- Priority changed from Urgent to Normal
if the ceph-osd daemon isn't running, other daemons will get connection refused. look in the log for the down osd to see why it stopped or crashed.
Updated by Sage Weil almost 11 years ago
- Status changed from New to Rejected
ceph-users is a better forum for these sorts of questions. thanks!
Updated by chen atrmat almost 11 years ago
Sage Weil wrote:
if the ceph-osd daemon isn't running, other daemons will get connection refused. look in the log for the down osd to see why it stopped or crashed.
i only found this error log in the down OSD.
in this case, osd1 tried to connect the osd4 and osd4 to osd3. is it mean that the osd1 is the primary OSD? or any other understanding?
THX!