Closed smithfarm closed 4 years ago
@sebastian-philipp could you take a look at this. I believe the problem is due to a mismatch between short hostnames and FQDNs that need to be solved in the cephadm mgr module.
Could you please add the output of
ceph orchestrator host ls
ceph {osd|mon|mgr} metadata
?
I have a cluster with the same error and here's the output of the commands:
HEALTH_WARN 3 stray host(s) with 12 service(s) not managed by cephadm
[WRN] CEPHADM_STRAY_HOST: 3 stray host(s) with 12 service(s) not managed by cephadm
stray host node1.test.com has 4 stray daemons: ['mgr.zbxtqs', 'mon.node1.test.com', 'osd.0', 'osd.1']
stray host node2.test.com has 4 stray daemons: ['mgr.kjsbck', 'mon.node2', 'osd.2', 'osd.3']
stray host node3.test.com has 4 stray daemons: ['mgr.awsyva', 'mon.node3', 'osd.4', 'osd.5']
node1:~ # ceph orchestrator host ls
HOST LABELS
node2
admin
node3
node1
ceph mon metadata
[
{
"name": "node1.test.com",
"addrs": "[v2:10.20.163.201:3300/0,v1:10.20.163.201:6789/0]",
"arch": "x86_64",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10021-g36f5e3b (36f5e3b115584df022186965dbcb29282376d091) octopus (dev)",
"ceph_version_short": "15.0.0-10021-g36f5e3b",
"compression_algorithms": "none, snappy, zlib, zstd, lz4",
"container_hostname": "node1",
"container_image": "docker.io/ceph/daemon-base:latest-master-devel",
"cpu": "Intel(R) Xeon(R) CPU E5-1620 v3 @ 3.50GHz",
"device_ids": "",
"device_paths": "vda=/dev/disk/by-path/pci-0000:00:03.0",
"devices": "vda",
"distro": "centos",
"distro_description": "CentOS Linux 8 (Core)",
"distro_version": "8",
"hostname": "node1.test.com",
"kernel_description": "#1 SMP Mon Nov 4 04:30:26 UTC 2019 (242bd27)",
"kernel_version": "5.3.8-lp152.2-default",
"mem_swap_kb": "0",
"mem_total_kb": "2027176",
"os": "Linux"
},
{
"name": "node2",
"addrs": "[v2:10.20.163.202:3300/0,v1:10.20.163.202:6789/0]",
"arch": "x86_64",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10021-g36f5e3b (36f5e3b115584df022186965dbcb29282376d091) octopus (dev)",
"ceph_version_short": "15.0.0-10021-g36f5e3b",
"compression_algorithms": "none, snappy, zlib, zstd, lz4",
"container_hostname": "node2",
"container_image": "docker.io/ceph/daemon-base:latest-master-devel",
"cpu": "Intel(R) Xeon(R) CPU E5-1620 v3 @ 3.50GHz",
"device_ids": "",
"device_paths": "vda=/dev/disk/by-path/pci-0000:00:03.0",
"devices": "vda",
"distro": "centos",
"distro_description": "CentOS Linux 8 (Core)",
"distro_version": "8",
"hostname": "node2.test.com",
"kernel_description": "#1 SMP Mon Nov 4 04:30:26 UTC 2019 (242bd27)",
"kernel_version": "5.3.8-lp152.2-default",
"mem_swap_kb": "0",
"mem_total_kb": "2027176",
"os": "Linux"
},
{
"name": "node3",
"addrs": "[v2:10.20.163.203:3300/0,v1:10.20.163.203:6789/0]",
"arch": "x86_64",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10021-g36f5e3b (36f5e3b115584df022186965dbcb29282376d091) octopus (dev)",
"ceph_version_short": "15.0.0-10021-g36f5e3b",
"compression_algorithms": "none, snappy, zlib, zstd, lz4",
"container_hostname": "node3",
"container_image": "docker.io/ceph/daemon-base:latest-master-devel",
"cpu": "Intel(R) Xeon(R) CPU E5-1620 v3 @ 3.50GHz",
"device_ids": "",
"device_paths": "vda=/dev/disk/by-path/pci-0000:00:03.0",
"devices": "vda",
"distro": "centos",
"distro_description": "CentOS Linux 8 (Core)",
"distro_version": "8",
"hostname": "node3.test.com",
"kernel_description": "#1 SMP Mon Nov 4 04:30:26 UTC 2019 (242bd27)",
"kernel_version": "5.3.8-lp152.2-default",
"mem_swap_kb": "0",
"mem_total_kb": "2027176",
"os": "Linux"
}
]
node1:~ #
node1:~ # ceph mgr metadata
[
{
"name": "awsyva",
"addr": "10.20.163.203",
"addrs": "10.20.163.203:0/1",
"arch": "x86_64",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10021-g36f5e3b (36f5e3b115584df022186965dbcb29282376d091) octopus (dev)",
"ceph_version_short": "15.0.0-10021-g36f5e3b",
"container_hostname": "node3",
"container_image": "docker.io/ceph/daemon-base:latest-master-devel",
"cpu": "Intel(R) Xeon(R) CPU E5-1620 v3 @ 3.50GHz",
"distro": "centos",
"distro_description": "CentOS Linux 8 (Core)",
"distro_version": "8",
"hostname": "node3.test.com",
"kernel_description": "#1 SMP Mon Nov 4 04:30:26 UTC 2019 (242bd27)",
"kernel_version": "5.3.8-lp152.2-default",
"mem_swap_kb": "0",
"mem_total_kb": "2027176",
"os": "Linux"
},
{
"name": "kjsbck",
"addr": "10.20.163.202",
"addrs": "10.20.163.202:0/1",
"arch": "x86_64",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10021-g36f5e3b (36f5e3b115584df022186965dbcb29282376d091) octopus (dev)",
"ceph_version_short": "15.0.0-10021-g36f5e3b",
"container_hostname": "node2",
"container_image": "docker.io/ceph/daemon-base:latest-master-devel",
"cpu": "Intel(R) Xeon(R) CPU E5-1620 v3 @ 3.50GHz",
"distro": "centos",
"distro_description": "CentOS Linux 8 (Core)",
"distro_version": "8",
"hostname": "node2.test.com",
"kernel_description": "#1 SMP Mon Nov 4 04:30:26 UTC 2019 (242bd27)",
"kernel_version": "5.3.8-lp152.2-default",
"mem_swap_kb": "0",
"mem_total_kb": "2027176",
"os": "Linux"
},
{
"name": "zbxtqs",
"addr": "10.20.163.201",
"addrs": "10.20.163.201:0/1",
"arch": "x86_64",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10021-g36f5e3b (36f5e3b115584df022186965dbcb29282376d091) octopus (dev)",
"ceph_version_short": "15.0.0-10021-g36f5e3b",
"container_hostname": "node1",
"container_image": "docker.io/ceph/daemon-base:latest-master-devel",
"cpu": "Intel(R) Xeon(R) CPU E5-1620 v3 @ 3.50GHz",
"distro": "centos",
"distro_description": "CentOS Linux 8 (Core)",
"distro_version": "8",
"hostname": "node1.test.com",
"kernel_description": "#1 SMP Mon Nov 4 04:30:26 UTC 2019 (242bd27)",
"kernel_version": "5.3.8-lp152.2-default",
"mem_swap_kb": "0",
"mem_total_kb": "2027176",
"os": "Linux"
}
]
node1:~ #
node1:~ # ceph osd metadata
[
{
"id": 0,
"arch": "x86_64",
"back_addr": "[v2:10.20.163.201:6802/1,v1:10.20.163.201:6803/1]",
"back_iface": "eth1",
"bluefs": "1",
"bluefs_dedicated_db": "0",
"bluefs_dedicated_wal": "0",
"bluefs_single_shared_device": "1",
"bluestore_bdev_access_mode": "blk",
"bluestore_bdev_block_size": "4096",
"bluestore_bdev_dev_node": "/dev/dm-1",
"bluestore_bdev_devices": "vdb",
"bluestore_bdev_driver": "KernelDevice",
"bluestore_bdev_partition_path": "/dev/dm-1",
"bluestore_bdev_rotational": "1",
"bluestore_bdev_size": "8585740288",
"bluestore_bdev_support_discard": "0",
"bluestore_bdev_type": "hdd",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10021-g36f5e3b (36f5e3b115584df022186965dbcb29282376d091) octopus (dev)",
"ceph_version_short": "15.0.0-10021-g36f5e3b",
"container_hostname": "node1",
"container_image": "docker.io/ceph/daemon-base:latest-master-devel",
"cpu": "Intel(R) Xeon(R) CPU E5-1620 v3 @ 3.50GHz",
"default_device_class": "hdd",
"device_ids": "vdb=590749",
"device_paths": "vdb=/dev/disk/by-path/pci-0000:00:04.0",
"devices": "vdb",
"distro": "centos",
"distro_description": "CentOS Linux 8 (Core)",
"distro_version": "8",
"front_addr": "[v2:10.20.163.201:6800/1,v1:10.20.163.201:6801/1]",
"front_iface": "eth1",
"hb_back_addr": "[v2:10.20.163.201:6806/1,v1:10.20.163.201:6807/1]",
"hb_front_addr": "[v2:10.20.163.201:6804/1,v1:10.20.163.201:6805/1]",
"hostname": "node1.test.com",
"journal_rotational": "1",
"kernel_description": "#1 SMP Mon Nov 4 04:30:26 UTC 2019 (242bd27)",
"kernel_version": "5.3.8-lp152.2-default",
"mem_swap_kb": "0",
"mem_total_kb": "2027176",
"network_numa_nodes": "-1",
"objectstore_numa_unknown_devices": "vdb",
"os": "Linux",
"osd_data": "/var/lib/ceph/osd/ceph-0",
"osd_objectstore": "bluestore",
"rotational": "1"
},
...
admin:~ # ceph -s
cluster:
id: 8dc510f6-434e-11ea-9e8e-525400039d93
health: HEALTH_WARN
1 stray host(s) with 6 service(s) not managed by cephadm
services:
mon: 1 daemons, quorum admin.octopus_test1.com (age 74m)
mgr: sikjie(active, since 74m)
osd: 4 osds: 4 up (since 73m), 4 in (since 73m)
data:
pools: 0 pools, 0 pgs
objects: 0 objects, 0 B
usage: 4.0 GiB used, 28 GiB / 32 GiB avail
pgs:
admin:~ # ceph orchestrator host ls
HOST LABELS
admin
admin:~ # hostname
admin.octopus_test1.com
admin:~ # ceph osd metadata
[
{
"id": 0,
"arch": "x86_64",
"back_addr": "[v2:10.20.70.200:6804/1,v1:10.20.70.200:6805/1]",
"back_iface": "eth1",
"bluefs": "1",
"bluefs_dedicated_db": "0",
"bluefs_dedicated_wal": "0",
"bluefs_single_shared_device": "1",
"bluestore_bdev_access_mode": "blk",
"bluestore_bdev_block_size": "4096",
"bluestore_bdev_dev_node": "/dev/dm-0",
"bluestore_bdev_devices": "vdb",
"bluestore_bdev_driver": "KernelDevice",
"bluestore_bdev_partition_path": "/dev/dm-0",
"bluestore_bdev_rotational": "1",
"bluestore_bdev_size": "8585740288",
"bluestore_bdev_support_discard": "0",
"bluestore_bdev_type": "hdd",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10067-g6bb36f862f (6bb36f862fb7721a65a4f7a705e3ec0fff46a884) octopus (rc)",
"ceph_version_short": "15.0.0-10067-g6bb36f862f",
"container_hostname": "admin.octopus_test1.com",
"container_image": "registry.opensuse.org/filesystems/ceph/master/upstream/images/ceph/ceph",
"cpu": "Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz",
"default_device_class": "hdd",
"device_ids": "vdb=234527",
"device_paths": "vdb=/dev/disk/by-path/pci-0000:00:04.0",
"devices": "vdb",
"distro": "opensuse-leap",
"distro_description": "openSUSE Leap 15.2 Alpha",
"distro_version": "15.2",
"front_addr": "[v2:10.20.70.200:6802/1,v1:10.20.70.200:6803/1]",
"front_iface": "eth1",
"hb_back_addr": "[v2:10.20.70.200:6808/1,v1:10.20.70.200:6809/1]",
"hb_front_addr": "[v2:10.20.70.200:6806/1,v1:10.20.70.200:6807/1]",
"hostname": "admin.octopus_test1.com",
"journal_rotational": "1",
"kernel_description": "#1 SMP Thu Nov 14 18:57:19 UTC 2019 (041cc7d)",
"kernel_version": "5.3.11-lp152.1-default",
"mem_swap_kb": "0",
"mem_total_kb": "4022716",
"network_numa_nodes": "-1",
"objectstore_numa_unknown_devices": "vdb",
"os": "Linux",
"osd_data": "/var/lib/ceph/osd/ceph-0",
"osd_objectstore": "bluestore",
"rotational": "1"
},
{
"id": 1,
"arch": "x86_64",
"back_addr": "[v2:10.20.70.200:6812/1,v1:10.20.70.200:6813/1]",
"back_iface": "eth1",
"bluefs": "1",
"bluefs_dedicated_db": "0",
"bluefs_dedicated_wal": "0",
"bluefs_single_shared_device": "1",
"bluestore_bdev_access_mode": "blk",
"bluestore_bdev_block_size": "4096",
"bluestore_bdev_dev_node": "/dev/dm-1",
"bluestore_bdev_devices": "vdc",
"bluestore_bdev_driver": "KernelDevice",
"bluestore_bdev_partition_path": "/dev/dm-1",
"bluestore_bdev_rotational": "1",
"bluestore_bdev_size": "8585740288",
"bluestore_bdev_support_discard": "0",
"bluestore_bdev_type": "hdd",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10067-g6bb36f862f (6bb36f862fb7721a65a4f7a705e3ec0fff46a884) octopus (rc)",
"ceph_version_short": "15.0.0-10067-g6bb36f862f",
"container_hostname": "admin.octopus_test1.com",
"container_image": "registry.opensuse.org/filesystems/ceph/master/upstream/images/ceph/ceph",
"cpu": "Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz",
"default_device_class": "hdd",
"device_ids": "vdc=944523",
"device_paths": "vdc=/dev/disk/by-path/pci-0000:00:05.0",
"devices": "vdc",
"distro": "opensuse-leap",
"distro_description": "openSUSE Leap 15.2 Alpha",
"distro_version": "15.2",
"front_addr": "[v2:10.20.70.200:6810/1,v1:10.20.70.200:6811/1]",
"front_iface": "eth1",
"hb_back_addr": "[v2:10.20.70.200:6816/1,v1:10.20.70.200:6817/1]",
"hb_front_addr": "[v2:10.20.70.200:6814/1,v1:10.20.70.200:6815/1]",
"hostname": "admin.octopus_test1.com",
"journal_rotational": "1",
"kernel_description": "#1 SMP Thu Nov 14 18:57:19 UTC 2019 (041cc7d)",
"kernel_version": "5.3.11-lp152.1-default",
"mem_swap_kb": "0",
"mem_total_kb": "4022716",
"network_numa_nodes": "-1",
"objectstore_numa_unknown_devices": "vdc",
"os": "Linux",
"osd_data": "/var/lib/ceph/osd/ceph-1",
"osd_objectstore": "bluestore",
"rotational": "1"
},
{
"id": 2,
"arch": "x86_64",
"back_addr": "[v2:10.20.70.200:6820/1,v1:10.20.70.200:6821/1]",
"back_iface": "eth1",
"bluefs": "1",
"bluefs_dedicated_db": "0",
"bluefs_dedicated_wal": "0",
"bluefs_single_shared_device": "1",
"bluestore_bdev_access_mode": "blk",
"bluestore_bdev_block_size": "4096",
"bluestore_bdev_dev_node": "/dev/dm-2",
"bluestore_bdev_devices": "vdd",
"bluestore_bdev_driver": "KernelDevice",
"bluestore_bdev_partition_path": "/dev/dm-2",
"bluestore_bdev_rotational": "1",
"bluestore_bdev_size": "8585740288",
"bluestore_bdev_support_discard": "0",
"bluestore_bdev_type": "hdd",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10067-g6bb36f862f (6bb36f862fb7721a65a4f7a705e3ec0fff46a884) octopus (rc)",
"ceph_version_short": "15.0.0-10067-g6bb36f862f",
"container_hostname": "admin.octopus_test1.com",
"container_image": "registry.opensuse.org/filesystems/ceph/master/upstream/images/ceph/ceph",
"cpu": "Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz",
"default_device_class": "hdd",
"device_ids": "vdd=362968",
"device_paths": "vdd=/dev/disk/by-path/pci-0000:00:06.0",
"devices": "vdd",
"distro": "opensuse-leap",
"distro_description": "openSUSE Leap 15.2 Alpha",
"distro_version": "15.2",
"front_addr": "[v2:10.20.70.200:6818/1,v1:10.20.70.200:6819/1]",
"front_iface": "eth1",
"hb_back_addr": "[v2:10.20.70.200:6824/1,v1:10.20.70.200:6825/1]",
"hb_front_addr": "[v2:10.20.70.200:6822/1,v1:10.20.70.200:6823/1]",
"hostname": "admin.octopus_test1.com",
"journal_rotational": "1",
"kernel_description": "#1 SMP Thu Nov 14 18:57:19 UTC 2019 (041cc7d)",
"kernel_version": "5.3.11-lp152.1-default",
"mem_swap_kb": "0",
"mem_total_kb": "4022716",
"network_numa_nodes": "-1",
"objectstore_numa_unknown_devices": "vdd",
"os": "Linux",
"osd_data": "/var/lib/ceph/osd/ceph-2",
"osd_objectstore": "bluestore",
"rotational": "1"
},
{
"id": 3,
"arch": "x86_64",
"back_addr": "[v2:10.20.70.200:6828/1,v1:10.20.70.200:6829/1]",
"back_iface": "eth1",
"bluefs": "1",
"bluefs_dedicated_db": "0",
"bluefs_dedicated_wal": "0",
"bluefs_single_shared_device": "1",
"bluestore_bdev_access_mode": "blk",
"bluestore_bdev_block_size": "4096",
"bluestore_bdev_dev_node": "/dev/dm-3",
"bluestore_bdev_devices": "vde",
"bluestore_bdev_driver": "KernelDevice",
"bluestore_bdev_partition_path": "/dev/dm-3",
"bluestore_bdev_rotational": "1",
"bluestore_bdev_size": "8585740288",
"bluestore_bdev_support_discard": "0",
"bluestore_bdev_type": "hdd",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10067-g6bb36f862f (6bb36f862fb7721a65a4f7a705e3ec0fff46a884) octopus (rc)",
daemonperf {type.id | path} list|ls [stat-pats] [priority]
"ceph_version_short": "15.0.0-10067-g6bb36f862f",
"container_hostname": "admin.octopus_test1.com",
"container_image": "registry.opensuse.org/filesystems/ceph/master/upstream/images/ceph/ceph",
"cpu": "Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz",
"default_device_class": "hdd",
"device_ids": "vde=608188",
"device_paths": "vde=/dev/disk/by-path/pci-0000:00:07.0",
"devices": "vde",
"distro": "opensuse-leap",
"distro_description": "openSUSE Leap 15.2 Alpha",
"distro_version": "15.2",
"front_addr": "[v2:10.20.70.200:6826/1,v1:10.20.70.200:6827/1]",
"front_iface": "eth1",
"hb_back_addr": "[v2:10.20.70.200:6832/1,v1:10.20.70.200:6833/1]",
"hb_front_addr": "[v2:10.20.70.200:6830/1,v1:10.20.70.200:6831/1]",
"hostname": "admin.octopus_test1.com",
"journal_rotational": "1",
"kernel_description": "#1 SMP Thu Nov 14 18:57:19 UTC 2019 (041cc7d)",
"kernel_version": "5.3.11-lp152.1-default",
"mem_swap_kb": "0",
"mem_total_kb": "4022716",
"network_numa_nodes": "-1",
"objectstore_numa_unknown_devices": "vde",
"os": "Linux",
"osd_data": "/var/lib/ceph/osd/ceph-3",
"osd_objectstore": "bluestore",
"rotational": "1"
}
]
admin:~ # ceph mon metadata
[
{
"name": "admin.octopus_test1.com",
"addrs": "[v2:10.20.70.200:3300/0,v1:10.20.70.200:6789/0]",
"arch": "x86_64",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10067-g6bb36f862f (6bb36f862fb7721a65a4f7a705e3ec0fff46a884) octopus (rc)",
"ceph_version_short": "15.0.0-10067-g6bb36f862f",
"compression_algorithms": "none, snappy, zlib, zstd, lz4",
"container_hostname": "admin.octopus_test1.com",
"container_image": "registry.opensuse.org/filesystems/ceph/master/upstream/images/ceph/ceph",
"cpu": "Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz",
"device_ids": "",
"device_paths": "vda=/dev/disk/by-path/pci-0000:00:03.0",
"devices": "vda",
"distro": "opensuse-leap",
"distro_description": "openSUSE Leap 15.2 Alpha",
"distro_version": "15.2",
"hostname": "admin.octopus_test1.com",
"kernel_description": "#1 SMP Thu Nov 14 18:57:19 UTC 2019 (041cc7d)",
"kernel_version": "5.3.11-lp152.1-default",
"mem_swap_kb": "0",
"mem_total_kb": "4022716",
"os": "Linux"
}
]
admin:~ # ceph mgr metadata
[
{
"name": "sikjie",
"addr": "10.20.70.200",
"addrs": "10.20.70.200:0/1",
"arch": "x86_64",
"ceph_release": "octopus",
"ceph_version": "ceph version 15.0.0-10067-g6bb36f862f (6bb36f862fb7721a65a4f7a705e3ec0fff46a884) octopus (rc)",
"ceph_version_short": "15.0.0-10067-g6bb36f862f",
"container_hostname": "admin.octopus_test1.com",
"container_image": "registry.opensuse.org/filesystems/ceph/master/upstream/images/ceph/ceph",
"cpu": "Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz",
"distro": "opensuse-leap",
"distro_description": "openSUSE Leap 15.2 Alpha",
"distro_version": "15.2",
"hostname": "admin.octopus_test1.com",
"kernel_description": "#1 SMP Thu Nov 14 18:57:19 UTC 2019 (041cc7d)",
"kernel_version": "5.3.11-lp152.1-default",
"mem_swap_kb": "0",
"mem_total_kb": "4022716",
"os": "Linux"
}
]
@sebastian-philipp This bug is easy to reproduce with:
sesdev create octopus --roles="[admin,mon,mgr,storage]" --ceph-bootstrap-repo https://github.com/SUSE/ceph-bootstrap.git --ceph-bootstrap-branch master --ceph-container-image registry.opensuse.org/filesystems/ceph/master/upstream/images/ceph/ceph --num-disks 4 octopus_test1
Not happening anymore with ceph v15.2.0
UPDATE: The workaround is to explicitly add the hosts - e.g.: