04 Ceph 集群管理（转载）
Ceph 集群管理
Ceph 资源对象
Ceph组件
- mon monitor 管理集群
- mgr manager 监控管理
- mds CephFS 源数据管理
- rgw 对象存储
- osd 存储
monitor、mgr 和 osd、csi provisioner 以 Deployments 的形式部署
[root@m1 ceph]# kubectl -n rook-ceph get deployments.apps
NAME READY UP-TO-DATE AVAILABLE AGE
csi-cephfsplugin-provisioner 2/2 2 2 7h21m
csi-rbdplugin-provisioner 2/2 2 2 7h21m
rook-ceph-crashcollector-192.168.100.133 1/1 1 1 6h30m
rook-ceph-crashcollector-192.168.100.134 1/1 1 1 7h10m
rook-ceph-crashcollector-192.168.100.135 1/1 1 1 7h14m
rook-ceph-crashcollector-192.168.100.136 1/1 1 1 7h21m
rook-ceph-crashcollector-192.168.100.137 1/1 1 1 7h12m
rook-ceph-mgr-a 1/1 1 1 7h11m
rook-ceph-mon-a 1/1 1 1 7h21m
rook-ceph-mon-b 1/1 1 1 7h14m
rook-ceph-mon-c 1/1 1 1 7h12m
rook-ceph-operator 1/1 1 1 8h
rook-ceph-osd-0 1/1 1 1 7h10m
rook-ceph-osd-1 1/1 1 1 7h10m
rook-ceph-osd-2 1/1 1 1 7h10m
rook-ceph-osd-3 1/1 1 1 7h10m
rook-ceph-osd-4 1/1 1 1 6h30m
CSI 的 CephFS 驱动和 RBD 驱动以 DaemonSets 的方式部署
[root@m1 ceph]# kubectl -n rook-ceph get daemonsets.apps
NAME DESIRED CURRENT READY UP-TO-DATE AVAILABLE NODE SELECTOR AGE
csi-cephfsplugin 5 5 5 5 5 <none> 7h31m
csi-rbdplugin 5 5 5 5 5 <none> 7h31m
对外提供服务均通过 service 的形式
由于
pods的地址可能会经常发生变化，如重建，漂移，重启等
[root@m1 ceph]# kubectl -n rook-ceph get svc
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
csi-cephfsplugin-metrics ClusterIP 10.68.182.104 <none> 8080/TCP,8081/TCP 7h32m
csi-rbdplugin-metrics ClusterIP 10.68.37.66 <none> 8080/TCP,8081/TCP 7h32m
rook-ceph-mgr ClusterIP 10.68.5.125 <none> 9283/TCP 7h22m
rook-ceph-mgr-dashboard ClusterIP 10.68.136.162 <none> 8443/TCP 7h22m
rook-ceph-mon-a ClusterIP 10.68.31.244 <none> 6789/TCP,3300/TCP 7h32m
rook-ceph-mon-b ClusterIP 10.68.196.47 <none> 6789/TCP,3300/TCP 7h26m
rook-ceph-mon-c ClusterIP 10.68.212.28 <none> 6789/TCP,3300/TCP 7h23m
初始化 osd 的使用的 jobs 控制器
[root@m1 ceph]# kubectl -n rook-ceph get jobs
NAME COMPLETIONS DURATION AGE
rook-ceph-osd-prepare-192.168.100.133 1/1 8s 6h42m
rook-ceph-osd-prepare-192.168.100.134 1/1 2s 6h42m
rook-ceph-osd-prepare-192.168.100.135 1/1 3s 6h42m
rook-ceph-osd-prepare-192.168.100.136 1/1 3s 6h42m
rook-ceph-osd-prepare-192.168.100.137 1/1 2s 6h42m
toolbox 客户端
使用
toolbox客户端连接Ceph集群，执行ceph命令等
toolbox 资源清单
# rook 部署包中提供了 toolbox yaml 资源清单
[root@m1 ceph]# cat toolbox.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: rook-ceph-tools
namespace: rook-ceph # namespace:cluster
labels:
app: rook-ceph-tools
spec:
replicas: 1
selector:
matchLabels:
app: rook-ceph-tools
template:
metadata:
labels:
app: rook-ceph-tools
spec:
dnsPolicy: ClusterFirstWithHostNet
containers:
- name: rook-ceph-tools
image: rook/ceph:v1.5.5
command: ["/tini"]
args: ["-g", "--", "/usr/local/bin/toolbox.sh"]
imagePullPolicy: IfNotPresent
env:
- name: ROOK_CEPH_USERNAME
valueFrom:
secretKeyRef:
name: rook-ceph-mon
key: ceph-username
- name: ROOK_CEPH_SECRET
valueFrom:
secretKeyRef:
name: rook-ceph-mon
key: ceph-secret
volumeMounts:
- mountPath: /etc/ceph
name: ceph-config
- name: mon-endpoint-volume
mountPath: /etc/rook
volumes:
- name: mon-endpoint-volume
configMap:
name: rook-ceph-mon-endpoints
items:
- key: data
path: mon-endpoints
- name: ceph-config
emptyDir: {}
tolerations:
- key: "node.kubernetes.io/unreachable"
operator: "Exists"
effect: "NoExecute"
tolerationSeconds: 5
toolbox 客户端的部署
[root@m1 ceph]# kubectl apply -f toolbox.yaml
deployment.apps/rook-ceph-tools created
连接 Ceph 集群
[root@m1 ceph]# kubectl -n rook-ceph exec -it rook-ceph-tools-77bf5b9b7d-rxdjb -- bash
[root@rook-ceph-tools-77bf5b9b7d-rxdjb /]# ceph -s
cluster:
id: d9084983-64b8-480f-ba73-38a718d6b076
health: HEALTH_OK
services:
mon: 3 daemons, quorum a,c,b (age 8h)
mgr: a(active, since 8h)
osd: 5 osds: 5 up (since 7h), 5 in (since 7h)
data:
pools: 1 pools, 1 pgs
objects: 0 objects, 0 B
usage: 5.0 GiB used, 245 GiB / 250 GiB avail
pgs: 1 active+clean
常⻅ Ceph 命令
- ceph status
- cph osd status
- ceph df
- rados df
[root@rook-ceph-tools-77bf5b9b7d-rxdjb /]# ceph osd status
ID HOST USED AVAIL WR OPS WR DATA RD OPS RD DATA STATE
0 192.168.100.135 1027M 48.9G 0 0 0 0 exists,up
1 192.168.100.136 1027M 48.9G 0 0 0 0 exists,up
2 192.168.100.137 1027M 48.9G 0 0 0 0 exists,up
3 192.168.100.134 1027M 48.9G 0 0 0 0 exists,up
4 192.168.100.133 1027M 48.9G 0 0 0 0 exists,up
[root@rook-ceph-tools-77bf5b9b7d-rxdjb /]# ceph osd tree
ID CLASS WEIGHT TYPE NAME STATUS REWEIGHT PRI-AFF
-1 0.24399 root default
-11 0.04880 host 192-168-100-133
4 hdd 0.04880 osd.4 up 1.00000 1.00000
-9 0.04880 host 192-168-100-134
3 hdd 0.04880 osd.3 up 1.00000 1.00000
-5 0.04880 host 192-168-100-135
0 hdd 0.04880 osd.0 up 1.00000 1.00000
-3 0.04880 host 192-168-100-136
1 hdd 0.04880 osd.1 up 1.00000 1.00000
-7 0.04880 host 192-168-100-137
2 hdd 0.04880 osd.2 up 1.00000 1.00000
[root@rook-ceph-tools-77bf5b9b7d-rxdjb /]# ceph df
--- RAW STORAGE ---
CLASS SIZE AVAIL USED RAW USED %RAW USED
hdd 250 GiB 245 GiB 18 MiB 5.0 GiB 2.01
TOTAL 250 GiB 245 GiB 18 MiB 5.0 GiB 2.01
--- POOLS ---
POOL ID PGS STORED OBJECTS USED %USED MAX AVAIL
device_health_metrics 1 1 0 B 0 0 B 0 77 GiB
[root@rook-ceph-tools-77bf5b9b7d-rxdjb /]# rados df
POOL_NAME USED OBJECTS CLONES COPIES MISSING_ON_PRIMARY UNFOUND DEGRADED RD_OPS RD WR_OPS WR USED COMPR UNDER COMPR
device_health_metrics 0 B 0 0 0 0 0 0 0 0 B 0 0 B 0 B 0 B
total_objects 0
total_used 5.0 GiB
total_avail 245 GiB
total_space 250 GiB
k8s 访问 ceph
kubernetes需要配置文件和认证文件来访问ceph集群
配置文件和认证文件可以直接使用tools容器中的信息
配置 Ceph yum 源
[root@m1 ceph]# cat /etc/yum.repos.d/ceph.repo
[ceph]
name=ceph
baseurl=https://mirrors.aliyun.com/ceph/rpm-octopus/el7/x86_64/
enabled=1
gpgcheck=0
安装 ceph-common
[root@m1 ceph]# yum -y install ceph-common -y
拷⻉ ceph.conf 文件和 kering 文件
[root@m1 ceph]# kubectl -n rook-ceph exec -it rook-ceph-tools-77bf5b9b7d-rxdjb -- cat /etc/ceph/ceph.conf | tee /etc/ceph/ceph.conf
[global]
mon_host = 10.68.196.47:6789,10.68.212.28:6789,10.68.31.244:6789
[client.admin]
keyring = /etc/ceph/keyring
[root@m1 ceph]# kubectl -n rook-ceph exec -it rook-ceph-tools-77bf5b9b7d-rxdjb -- cat /etc/ceph/keyring | tee /etc/ceph/keyring
[client.admin]
key = AQA5hn1jLkAIBBAA2cYo8uGuiwBCIXxtTBizGQ==
[root@m1 ~]# ls /etc/ceph/ -lh
total 12K
-rw-r--r-- 1 root root 123 Nov 23 19:29 ceph.conf
-rw-r--r-- 1 root root 64 Nov 23 19:30 keyring
-rw-r--r-- 1 root root 92 Aug 10 01:34 rbdmap
本地运行 ceph 命令查看集群状态
[root@m1 ceph]# ceph -s
cluster:
id: d9084983-64b8-480f-ba73-38a718d6b076
health: HEALTH_OK
services:
mon: 3 daemons, quorum a,c,b (age 8h)
mgr: a(active, since 8h)
osd: 5 osds: 5 up (since 8h), 5 in (since 8h)
data:
pools: 1 pools, 1 pgs
objects: 0 objects, 0 B
usage: 5.0 GiB used, 245 GiB / 250 GiB avail
pgs: 1 active+clean
访问 RBD 块存储
创建 pool
[root@m1 ceph]# ceph osd pool create rook 16 16
pool 'rook' created
[root@m1 ceph]# ceph osd lspools
1 device_health_metrics
2 rook
在 pool 上创建 RBD 块设备
[root@m1 ceph]# rbd create -p rook --image rook-rbd.img --size 10G
[root@m1 ceph]# rbd -p rook ls
rook-rbd.img
[root@m1 ceph]# rbd info rook/rook-rbd.img
rbd image 'rook-rbd.img':
size 10 GiB in 2560 objects
order 22 (4 MiB objects)
snapshot_count: 0
id: 86b5b4bdb2ca
block_name_prefix: rbd_data.86b5b4bdb2ca
format: 2
features: layering
op_features:
flags:
create_timestamp: Wed Nov 23 19:41:48 2022
access_timestamp: Wed Nov 23 19:41:48 2022
modify_timestamp: Wed Nov 23 19:41:48 2022
客户挂载 RBD 块
[root@m1 ceph]# rbd map rook/rook-rbd.img
/dev/rbd0
[root@m1 ceph]# rbd device ls
id pool namespace image snap device
0 rook rook-rbd.img - /dev/rbd0
[root@m1 ceph]# rbd showmapped
id pool namespace image snap device
0 rook rook-rbd.img - /dev/rbd0
[root@m1 ceph]# mkfs.xfs /dev/rbd0
Discarding blocks...Done.
meta-data=/dev/rbd0 isize=512 agcount=16, agsize=163840 blks
= sectsz=512 attr=2, projid32bit=1
= crc=1 finobt=0, sparse=0
data = bsize=4096 blocks=2621440, imaxpct=25
= sunit=1024 swidth=1024 blks
naming =version 2 bsize=4096 ascii-ci=0 ftype=1
log =internal log bsize=4096 blocks=2560, version=2
= sectsz=512 sunit=8 blks, lazy-count=1
realtime =none extsz=4096 blocks=0, rtextents=0
[root@m1 ceph]# mount /dev/rbd0 /mnt/
[root@m1 ceph]# ls /mnt
[root@m1 ceph]# df -h
Filesystem Size Used Avail Use% Mounted on
devtmpfs 1.4G 0 1.4G 0% /dev
tmpfs 1.4G 0 1.4G 0% /dev/shm
tmpfs 1.4G 29M 1.4G 3% /run
tmpfs 1.4G 0 1.4G 0% /sys/fs/cgroup
/dev/mapper/centos-root 37G 13G 25G 35% /
/dev/sda1 1014M 151M 864M 15% /boot
......
/dev/rbd0 10G 33M 10G 1% /mnt
