Have you guys changed something with the systemctl startup of the OSDs?
I've stopped and disabled all the OSDs on all my hosts via "systemctl stop|disable ceph-osd.target" and rebooted all the nodes. Everything look just the same.
The I started all the OSD daemons one after the other via the CLI with "/usr/bin/ceph-osd -f --cluster ceph --id $NR --setuser ceph --setgroup ceph > /tmp/osd.${NR}.log 2>&1 & " and now everything (ok, beside the ZABBIX mgr module?!?) seems to work :|
cluster:
id: 2a919338-4e44-454f-bf45-e94a01c2a5e6
health: HEALTH_WARN
Failed to send data to Zabbix
services:
mon: 3 daemons, quorum sds20,sds21,sds22
mgr: sds22(active), standbys: sds20, sds21
osd: 18 osds: 18 up, 18 in
rgw: 4 daemons active
data:
pools: 25 pools, 1390 pgs
objects: 2.55 k objects, 3.4 GiB
usage: 26 GiB used, 8.8 TiB / 8.8 TiB avail
pgs: 1390 active+clean
io:
client: 11 KiB/s rd, 10 op/s rd, 0 op/s wr
Any hints?
----------------------------------------------------------------------
Gesendet: Samstag, 28. Juli 2018 um 23:35 Uhr
Von: ceph.novice@xxxxxxxxxxxxxxxx
An: "Sage Weil" <sage@xxxxxxxxxxxx>
Cc: ceph-users@xxxxxxxxxxxxxx, ceph-devel@xxxxxxxxxxxxxxx
Betreff: Re: HELP! --> CLUSER DOWN (was "v13.2.1 Mimic released")
Hi Sage.
Sure. Any specific OSD(s) log(s)? Or just any?
Gesendet: Samstag, 28. Juli 2018 um 16:49 Uhr
Von: "Sage Weil" <sage@xxxxxxxxxxxx>
An: ceph.novice@xxxxxxxxxxxxxxxx, ceph-users@xxxxxxxxxxxxxx, ceph-devel@xxxxxxxxxxxxxxx
Betreff: Re: HELP! --> CLUSER DOWN (was "v13.2.1 Mimic released")
Can you include more or your osd log file?
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
