Re: OSD will never become up. HEALTH_ERR

[Gonzalo Aguilar Delgado <gaguilar.delgado@gmail.com>]

Hello Sage, 

Thank you al lot for answering. Ideed this was the problem. But it was
strange as I told it booted from update without problems until the
ceph-disk command on boot. 


I was updating from Ubuntu 14.04 so quite old ceph. Yes. 

I posted what I did just in case another one has the same problem. 

Thank you a lot.

On mié, 2016-05-11 at 08:55 -0400, Sage Weil wrote:
> On Wed, 11 May 2016, Gonzalo Aguilar Delgado wrote:
> > Hello, 
> > 
> > I just upgraded my cluster to the version 10.1.2 and it worked well
> for
> > a while until I saw that systemctl ceph-disk@dev-sdc1.service was
> > failed and I reruned it.
> 
> What version did you upgrade *from*?  If it was older than 0.94.4
> then 
> that is the problem.  Check for messages in /var/log/ceph/ceph.log.
> 
> Also, you probably want to use 10.2.0, not 10.1.2 (which was a
> release 
> candidate).
> 
> sage
> 
> 
> > From there the OSD stopped working. 
> > 
> > This is ubuntu 16.04. 
> > 
> > I connected to the IRC looking for help where people pointed me to
> one
> > or another place but none of the investigations helped to resolve.
> > 
> > My configuration is rather simple:
> > 
> > oot@red-compute:~# ceph osd tree
> > ID WEIGHT  TYPE NAME                 UP/DOWN REWEIGHT PRIMARY-
> AFFINITY 
> > -1 1.00000 root
> default                                                
> > -4 1.00000     rack rack-
> 1                                             
> > -2 1.00000         host blue-
> compute                                   
> >  0 1.00000             osd.0            down        0         
> 1.00000 
> >  2 1.00000             osd.2            down        0         
> 1.00000 
> > -3 1.00000         host red-
> compute                                    
> >  1 1.00000             osd.1            down        0         
> 1.00000 
> >  3 0.50000             osd.3              up  1.00000         
> 1.00000 
> >  4 1.00000             osd.4            down        0         
> 1.00000 
> > 
> > It seems that all nodes are in preboot status. I was looking at the
> > latests commits and it seems that there's a patch
> > to make OSDs to wait for cluster to become healthy before
> rejoining.
> > Can this be the source of my problems?
> > 
> > root@red-compute:/var/lib/ceph/osd/ceph-1# ceph daemon osd.1 status
> > {
> >     "cluster_fsid": "9028f4da-0d77-462b-be9b-dbdf7fa57771",
> >     "osd_fsid": "adf9890a-e680-48e4-82c6-e96f4ed56889",
> >     "whoami": 1,
> >     "state": "preboot",
> >     "oldest_map": 1764,
> >     "newest_map": 2504,
> >     "num_pgs": 323
> > }
> > 
> > root@red-compute:/var/lib/ceph/osd/ceph-1# ceph daemon osd.3 status
> > {
> >     "cluster_fsid": "9028f4da-0d77-462b-be9b-dbdf7fa57771",
> >     "osd_fsid": "8dd085d4-0b50-4c80-a0ca-c5bc4ad972f7",
> >     "whoami": 3,
> >     "state": "preboot",
> >     "oldest_map": 1764,
> >     "newest_map": 2504,
> >     "num_pgs": 150
> > }
> > 
> > 3 is up and in. 
> > 
> > 
> > This is what I got sofar:
> > 
> > Once upgraded I discovered that daemon runs under ceph. I just ran
> > chown on ceph directories. and it worked. 
> > Firewall is fully disabled. Checked connectivity with nc and nmap. 
> > Configuration seems to be right. I can post if you want. 
> > Enabling logging on OSD shows that for example osd.1 is
> reconnecting
> > all the time.
> > 2016-05-10 14:35:48.199573 7f53e8f1a700  1 -- 0.0.0.0:6806/13962 >>
> :/0
> > pipe(0x556f99413400 sd=84 :6806 s=0 pgs=0 cs=0 l=0
> > c=0x556f993b3a80).accept sd=84 172.16.0.119:35388/0
> >  2016-05-10 14:35:48.199966 7f53e8f1a700  2
> -- 0.0.0.0:6806/13962 >>
> > :/0 pipe(0x556f99413400 sd=84 :6806 s=4 pgs=0 cs=0 l=0
> > c=0x556f993b3a80).fault (0) Success
> >  2016-05-10 14:35:48.200018 7f53fb941700  1 osd.1 2468
> ms_handle_reset
> > con 0x556f993b3a80 session 0
> > OSD.3 goes ok because never left out because ceph restriction.
> > I rebooted all services at once for it to have available all OSD at
> the
> > same time and don't mark it down. Don't work. 
> > I forced up from commandline. ceph osd in 1-5. They appear as in
> for a
> > while then out.
> > We tried ceph-disk activate-all to boot everything. Don't work.
> > 
> > The strange thing is that culster started worked just right after
> > upgrade. But the systemctrl command broke both servers. 
> > root@blue-compute:~# ceph -w
> >     cluster 9028f4da-0d77-462b-be9b-dbdf7fa57771
> >      health HEALTH_ERR
> >             694 pgs are stuck inactive for more than 300 seconds
> >             694 pgs stale
> >             694 pgs stuck stale
> >             too many PGs per OSD (1528 > max 300)
> >             mds cluster is degraded
> >             crush map has straw_calc_version=0
> >      monmap e10: 2 mons at {blue-compute=172.16.0.119:6789/0,red-
> > compute=172.16.0.100:6789/0}
> >             election epoch 3600, quorum 0,1 red-compute,blue-
> compute
> >       fsmap e673: 1/1/1 up {0:0=blue-compute=up:replay}
> >      osdmap e2495: 5 osds: 1 up, 1 in; 5 remapped pgs
> >       pgmap v40765481: 764 pgs, 6 pools, 410 GB data, 103 kobjects
> >             87641 MB used, 212 GB / 297 GB avail
> >                  694 stale+active+clean
> >                   70 active+clean
> > 
> > 2016-05-10 17:03:55.822440 mon.0 [INF] HEALTH_ERR; 694 pgs are
> stuck
> > inactive for more than 300 seconds; 694 pgs stale; 694 pgs stuck
> stale;
> > too many PGs per OSD (1528 > max 300); mds cluster is degraded;
> crush
> > map has straw_calc_version=
> > cat /etc/ceph/ceph.conf 
> > [global]
> > 
> > fsid = 9028f4da-0d77-462b-be9b-dbdf7fa57771
> > mon_initial_members = blue-compute, red-compute
> > mon_host = 172.16.0.119, 172.16.0.100
> > auth_cluster_required = cephx
> > auth_service_required = cephx
> > auth_client_required = cephx
> > filestore_xattr_use_omap = true
> > public_network = 172.16.0.0/24
> > osd_pool_default_pg_num = 100
> > osd_pool_default_pgp_num = 100
> > osd_pool_default_size = 2  # Write an object 3 times.
> > osd_pool_default_min_size = 1 # Allow writing one copy in a
> degraded
> > state.
> > 
> > ## Required upgrade
> > osd max object name len = 256
> > osd max object namespace len = 64
> > 
> > [mon.]
> > 
> >     debug mon = 9
> >     caps mon = "allow *"
> > 
> > Any help on this? Any clue of what's going wrong?
> > 
> > 
> > I also see this, I don't know if it's related or not
> > 
> > => ceph-osd.admin.log <==
> > 2016-05-10 18:21:46.060278 7fa8f30cc8c0  0 ceph version 10.1.2
> > (4a2a6f72640d6b74a3bbd92798bb913ed380dcd4), process ceph-osd, pid
> 14135
> > 2016-05-10 18:21:46.060460 7fa8f30cc8c0 -1 bluestore(/dev/sdc2)
> > _read_bdev_label unable to decode label at offset 66:
> > buffer::malformed_input: void
> > bluestore_bdev_label_t::decode(ceph::buffer::list::iterator&)
> decode
> > past end of struct encoding
> > 2016-05-10 18:21:46.062949 7fa8f30cc8c0  1 journal _open /dev/sdc2
> fd
> > 4: 5367660544 bytes, block size 4096 bytes, directio = 0, aio = 0
> > 2016-05-10 18:21:46.062991 7fa8f30cc8c0  1 journal close /dev/sdc2
> > 2016-05-10 18:21:46.063026 7fa8f30cc8c0  0 probe_block_device_fsid
> > /dev/sdc2 is filestore, 119a9f4e-73d8-4a1f-877c-d60b01840c96
> > 2016-05-10 18:21:47.072082 7eff735598c0  0 ceph version 10.1.2
> > (4a2a6f72640d6b74a3bbd92798bb913ed380dcd4), process ceph-osd, pid
> 14177
> > 2016-05-10 18:21:47.072285 7eff735598c0 -1 bluestore(/dev/sdf2)
> > _read_bdev_label unable to decode label at offset 66:
> > buffer::malformed_input: void
> > bluestore_bdev_label_t::decode(ceph::buffer::list::iterator&)
> decode
> > past end of struct encoding
> > 2016-05-10 18:21:47.074799 7eff735598c0  1 journal _open /dev/sdf2
> fd
> > 4: 5367660544 bytes, block size 4096 bytes, directio = 0, aio = 0
> > 2016-05-10 18:21:47.074844 7eff735598c0  1 journal close /dev/sdf2
> > 2016-05-10 18:21:47.074881 7eff735598c0  0 probe_block_device_fsid
> > /dev/sdf2 is filestore, fd069e6a-9a62-4286-99cb-d8a523bd946a
> > 
> > 
> > --
> > To unsubscribe from this list: send the line "unsubscribe ceph-
> devel" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html
> > 
> > 
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html