In an effort to try ceph and hadoop I am facing the problem where "cmon" dies immediately. I have debug level set to 20. ./cmon -i 0 -c ceph.conf ** WARNING: Ceph is still under heavy development, and is only suitable for ** ** testing and review. Do not trust it with important data. ** starting mon0 at 192.168.2.118:6789/0 mon_data /data/mon0 fsid af52ab64-5ad2-9e9f-1e33-12f340b7d10c [root@recline18 src]# ps -aux | grep ceph Warning: bad syntax, perhaps a bogus '-'? See /usr/share/doc/procps-3.2.7/FAQ root 3633 0.0 0.0 0 0 ? S 18:17 0:00 [ceph-msgr/0] root 3634 0.0 0.0 0 0 ? S 18:17 0:00 [ceph-msgr/1] root 3635 0.0 0.0 0 0 ? S 18:17 0:00 [ceph-msgr/2] root 3636 0.0 0.0 0 0 ? S 18:17 0:00 [ceph-msgr/3] root 4344 0.0 0.0 148164 1636 ? Ssl 18:20 0:00 ./cmds -i 0 -c ceph.conf root 4767 0.0 0.1 525312 2292 ? Ssl 18:25 0:00 /usr/local/bin/cmds -i 0 -c /tmp/ceph.conf.4510 root 4966 0.0 0.1 606308 2332 ? Ssl 18:25 0:00 /usr/local/bin/cosd -i 0 -c /tmp/ceph.conf.4510 root 5299 0.0 0.0 61252 732 pts/0 S+ 18:33 0:00 grep ceph **** I don't see cmon running anymore.. I tried to run it under "gdb" and I see no errors. Here is copy of my ceph.conf file: ; global [global] ; enable secure authentication log dir = /usr/src/ceph/ceph-0.20.2/src/out logger dir = /usr/src/ceph/ceph-0.20.2/src/log ; monitors [mon] mon data = /data/mon$id ; some minimal logging (just message traffic) to aid debugging debug ms = 1 debug mon = 20 [mon0] host = r18 mon addr = 192.168.2.118:6789 ; mds ; You need at least one. Define two to get a standby. [mds] ; where the mds keeps it's secret encryption keys debug ms = 1 debug mds = 20 [mds0] host = r18 ; osd ; You need at least one. Two if you want data to be replicated. ; Define as many as you like. [osd] debug ms = 1 debug osd = 25 debug journal = 20 debug filestore = 20 ; This is where the btrfs volume will be mounted. osd data = /data/osd$id osd journal = /data/osd$id/journal osd journal size = 100 [osd0] host = r18 btrfs devs = /dev/sda3 [osd1] host = r19 btrfs devs = /dev/sda3 [osd2] host = r20 btrfs devs = /dev/sda3 **** Other daemons are running fine ***** In last 2 weeks I was able to have thing running for say 2 hours where "mount ceph" worked and afterwards it hangs and I found it is due to "monitor" getting killed. -- 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
