CentOS 8
Sponsored Link

Ceph Nautilus : Add or Remove OSDs
2020/07/02
 
This is how to add or remove OSDs from exisiting Cluster.
                                         |
        +--------------------+           |
        |   [dlp.srv.world]  |10.0.0.30  |
        |     Ceph Client    +-----------+
        |                    |           |
        +--------------------+           |
            +----------------------------+----------------------------+
            |                            |                            |
            |10.0.0.51                   |10.0.0.52                   |10.0.0.53 
+-----------+-----------+    +-----------+-----------+    +-----------+-----------+
|   [node01.srv.world]  |    |   [node02.srv.world]  |    |   [node03.srv.world]  |
|     Object Storage    +----+     Object Storage    +----+     Object Storage    |
|     Monitor Daemon    |    |                       |    |                       |
|     Manager Daemon    |    |                       |    |                       |
+-----------------------+    +-----------------------+    +-----------------------+

[1] For example, Add a [node04] node to OSDs on Admin Node.
For Block device on new [node04] Node, use [/dev/sdb] on this example.
# transfer public key

[root@node01 ~]#
ssh-copy-id node04

# if Firewalld is running, allow service

[root@node01 ~]#
ssh node04 "firewall-cmd --add-service=ceph --permanent; firewall-cmd --reload"

# install required packages

[root@node01 ~]#
ssh node04 "dnf -y install centos-release-ceph-nautilus; dnf -y install ceph"
# transfer required files

[root@node01 ~]#
scp /etc/ceph/ceph.conf node04:/etc/ceph/ceph.conf

[root@node01 ~]#
scp /etc/ceph/ceph.client.admin.keyring node04:/etc/ceph

[root@node01 ~]#
scp /var/lib/ceph/bootstrap-osd/ceph.keyring node04:/var/lib/ceph/bootstrap-osd
# configure OSD

[root@node01 ~]# ssh node04 \
"chown ceph. /etc/ceph/ceph.* /var/lib/ceph/bootstrap-osd/*; \
parted --script /dev/sdb 'mklabel gpt'; \
parted --script /dev/sdb "mkpart primary 0% 100%"; \
ceph-volume lvm create --data /dev/sdb1" 
Running command: /usr/bin/ceph-authtool --gen-print-key
Running command: /usr/bin/ceph --cluster ceph --name client.bootstrap-osd --keyring /var/lib/ceph/bootstrap-osd/ceph.keyring -i - osd new fa9633cf-b3d1-4644-be4e-6c9cc931b345
.....
.....
Running command: /usr/bin/systemctl enable ceph-volume@lvm-3-fa9633cf-b3d1-4644-be4e-6c9cc931b345
 stderr: Created symlink /etc/systemd/system/multi-user.target.wants/ceph-volume@lvm-3-fa9633cf-b3d1-4644-be4e-6c9cc931b345.service → /usr/lib/systemd/system/ceph-volume@.service.
Running command: /usr/bin/systemctl enable --runtime ceph-osd@3
 stderr: Created symlink /run/systemd/system/ceph-osd.target.wants/ceph-osd@3.service → /usr/lib/systemd/system/ceph-osd@.service.
Running command: /usr/bin/systemctl start ceph-osd@3
--> ceph-volume lvm activate successful for osd ID: 3
--> ceph-volume lvm create successful for: /dev/sdb1

[root@node01 ~]# ceph -s 
  cluster:
    id:     018c84db-7c76-46bf-8c85-a7520748233b
    health: HEALTH_OK

  services:
    mon: 1 daemons, quorum node01 (age 19m)
    mgr: node01(active, since 19m)
    osd: 4 osds: 4 up (since 55s), 4 in (since 55s)

  data:
    pools:   0 pools, 0 pgs
    objects: 0 objects, 0 B
    usage:   4.0 GiB used, 316 GiB / 320 GiB avail
    pgs:
[2] To remove an OSD Node from existing Cluster, run commands like follows.
For example, Remove [node04] node.
[root@node01 ~]#
ceph -s

  cluster:
    id:     018c84db-7c76-46bf-8c85-a7520748233b
    health: HEALTH_OK

  services:
    mon: 1 daemons, quorum node01 (age 11m)
    mgr: node01(active, since 10m)
    osd: 4 osds: 4 up (since 81s), 4 in (since 81s)

  data:
    pools:   1 pools, 128 pgs
    objects: 5 objects, 709 B
    usage:   4.0 GiB used, 316 GiB / 320 GiB avail
    pgs:     128 active+clean

[root@node01 ~]#
ceph osd tree

ID CLASS WEIGHT  TYPE NAME       STATUS REWEIGHT PRI-AFF
-1       0.31238 root default
-3       0.07809     host node01
 0   hdd 0.07809         osd.0       up  1.00000 1.00000
-5       0.07809     host node02
 1   hdd 0.07809         osd.1       up  1.00000 1.00000
-7       0.07809     host node03
 2   hdd 0.07809         osd.2       up  1.00000 1.00000
-9       0.07809     host node04
 3   hdd 0.07809         osd.3       up  1.00000 1.00000

# specify OSD ID of a node you'd like to remove

[root@node01 ~]#
ceph osd out 3

marked out osd.3.
# live watch cluster status

# after running [ceph osd out ***], rebalancing is executed automatically

# to quit live watch, push [Ctrl + c]

[root@node01 ~]#
ceph -w

  cluster:
    id:     018c84db-7c76-46bf-8c85-a7520748233b
    health: HEALTH_WARN
            Degraded data redundancy: 1/15 objects degraded (6.667%), 1 pg degraded

  services:
    mon: 1 daemons, quorum node01 (age 11m)
    mgr: node01(active, since 11m)
    osd: 4 osds: 4 up (since 118s), 3 in (since 4s)

  data:
    pools:   1 pools, 128 pgs
    objects: 5 objects, 709 B
    usage:   4.0 GiB used, 316 GiB / 320 GiB avail
    pgs:     1/15 objects degraded (6.667%)
             126 active+clean
             1   active+recovering
             1   active+recovery_wait+degraded

  io:
    client:   255 B/s rd, 0 op/s rd, 0 op/s wr
    recovery: 84 B/s, 0 objects/s

  progress:
    Rebalancing after osd.3 marked out
      [..............................]


2020-07-01 23:16:56.814332 mon.node01 [WRN] Health check failed: Degraded data redundancy: 1/15 objects degraded (6.667%), 1 pg degraded (PG_DEGRADED)
2020-07-01 23:17:02.366541 mon.node01 [INF] Health check cleared: PG_DEGRADED (was: Degraded data redundancy: 1/15 objects degraded (6.667%), 1 pg degraded)
2020-07-01 23:17:02.366565 mon.node01 [INF] Cluster is now healthy

# after status turns to [HEALTH_OK], disable OSD service on the target node

[root@node01 ~]#
ssh node04 "systemctl disable --now ceph-osd@3.service"

Removed /run/systemd/system/ceph-osd.target.wants/ceph-osd@3.service.
# remove the node to specify target OSD ID

[root@node01 ~]#
ceph osd purge 3 --yes-i-really-mean-it

purged osd.3
[root@node01 ~]#
ceph -s

  cluster:
    id:     018c84db-7c76-46bf-8c85-a7520748233b
    health: HEALTH_OK

  services:
    mon: 1 daemons, quorum node01 (age 13m)
    mgr: node01(active, since 13m)
    osd: 3 osds: 3 up (since 30s), 3 in (since 2m)

  data:
    pools:   1 pools, 128 pgs
    objects: 5 objects, 709 B
    usage:   3.0 GiB used, 237 GiB / 240 GiB avail
    pgs:     128 active+clean
Matched Content