ceph维护.docx
《ceph维护.docx》由会员分享，可在线阅读，更多相关《ceph维护.docx（22页珍藏版）》请在冰豆网上搜索。
ceph维护
Ceph维护命令（持续更新中）eddy
一、集群
1、启动一个ceph进程
启动mon进程
servicecephstart mon.node1
启动msd进程
servicecephstartmds.node1
启动osd进程
servicecephstartosd.0
2、查看机器的监控状态
[root@client~]#cephhealth
HEALTH_OK
3、查看ceph的实时运行状态
[root@client~]#ceph-w
clusterbe1756f2-54f7-4d8f-8790-820c82721f17
healthHEALTH_OK
monmape2:
3monsat{node1=10.240.240.211:
6789/0,node2=10.240.240.212:
6789/0,node3=10.240.240.213:
6789/0},electionepoch294,quorum0,1,2node1,node2,node3
mdsmape95:
1/1/1up{0=node2=up:
active},1up:
standby
osdmape88:
3osds:
3up,3in
pgmapv1164:
448pgs,4pools,10003MBdata,2520objects
23617MBused,37792MB/61410MBavail
448active+clean
2014-06-3000:
48:
28.756948mon.0[INF]pgmapv1163:
448pgs:
448active+clean;10003MBdata,23617MBused,37792MB/61410MBavail
4、检查信息状态信息
[root@client~]#ceph-s
clusterbe1756f2-54f7-4d8f-8790-820c82721f17
healthHEALTH_OK
monmape2:
3monsat{node1=10.240.240.211:
6789/0,node2=10.240.240.212:
6789/0,node3=10.240.240.213:
6789/0},electionepoch294,quorum0,1,2node1,node2,node3
mdsmape95:
1/1/1up{0=node2=up:
active},1up:
standby
osdmape88:
3osds:
3up,3in
pgmapv1164:
448pgs,4pools,10003MBdata,2520objects
23617MBused,37792MB/61410MBavail
448active+clean
[root@client~]#
5、查看ceph存储空间
[root@client~]#cephdf
GLOBAL:
SIZE AVAIL RAWUSED %RAWUSED
61410M 37792M 23617M 38.46
POOLS:
NAME ID USED %USED OBJECTS
data 0 10000M 16.28 2500
metadata 1 3354k 0 20
rbd 2 0 0 0
jiayuan 3 0 0 0
[root@client~]#
6、删除一个节点的所有的ceph数据包
[root@node1~]#ceph-deploypurgenode1
[root@node1~]#ceph-deploypurgedatanode1
7、为ceph创建一个admin用户并为admin用户创建一个密钥，把密钥保存到/etc/ceph目录下：
cephauthget-or-createclient.adminmds'allow'osd'allow*'mon'allow*'>/etc/ceph/ceph.client.admin.keyring
或
cephauthget-or-createclient.adminmds'allow'osd'allow*'mon'allow*'-o/etc/ceph/ceph.client.admin.keyring
8、为osd.0创建一个用户并创建一个key
cephauthget-or-createosd.0mon'allowrwx'osd'allow*'-o/var/lib/ceph/osd/ceph-0/keyring
9、为mds.node1创建一个用户并创建一个key
cephauthget-or-createmds.node1mon'allowrwx'osd'allow*'mds'allow*'-o/var/lib/ceph/mds/ceph-node1/keyring
10、查看ceph集群中的认证用户及相关的key
cephauthlist
11、删除集群中的一个认证用户
cephauthdelosd.0
12、查看集群的详细配置
[root@node1~]#cephdaemonmon.node1configshow|more
13、查看集群健康状态细节
[root@admin~]#cephhealthdetail
HEALTH_WARN12pgsdown;12pgspeering;12pgsstuckinactive;12pgsstuckunclean
pg3.3bisstuckinactivesinceforever,currentstatedown+peering,lastacting[1,2]
pg3.36isstuckinactivesinceforever,currentstatedown+peering,lastacting[1,2]
pg3.79isstuckinactivesinceforever,currentstatedown+peering,lastacting[1,0]
pg3.5isstuckinactivesinceforever,currentstatedown+peering,lastacting[1,2]
pg3.30isstuckinactivesinceforever,currentstatedown+peering,lastacting[1,2]
pg3.1aisstuckinactivesinceforever,currentstatedown+peering,lastacting[1,0]
pg3.2disstuckinactivesinceforever,currentstatedown+peering,lastacting[1,0]
pg3.16isstuckinactivesinceforever,currentstatedown+peering,lastacting[1,2]
14、查看cephlog日志所在的目录
[root@node1~]#ceph-conf--namemon.node1--show-config-valuelog_file
/var/log/ceph/ceph-mon.node1.log
二、mon
1、查看mon的状态信息
[root@client~]#cephmonstat
e2:
3monsat{node1=10.240.240.211:
6789/0,node2=10.240.240.212:
6789/0,node3=10.240.240.213:
6789/0},electionepoch294,quorum0,1,2node1,node2,node3
2、查看mon的选举状态
[root@client~]#cephquorum_status
{"election_epoch":
294,"quorum":
[0,1,2],"quorum_names":
["node1","node2","node3"],"quorum_leader_name":
"node1","monmap":
{"epoch":
2,"fsid":
"be1756f2-54f7-4d8f-8790-820c82721f17","modified":
"2014-06-2618:
43:
51.671106","created":
"0.000000","mons":
[{"rank":
0,"name":
"node1","addr":
"10.240.240.211:
6789\/0"},{"rank":
1,"name":
"node2","addr":
"10.240.240.212:
6789\/0"},{"rank":
2,"name":
"node3","addr":
"10.240.240.213:
6789\/0"}]}}
3、查看mon的映射信息
[root@client~]#cephmondump
dumpedmonmapepoch2
epoch2
fsidbe1756f2-54f7-4d8f-8790-820c82721f17
last_changed2014-06-2618:
43:
51.671106
created0.000000
0:
10.240.240.211:
6789/0mon.node1
1:
10.240.240.212:
6789/0mon.node2
2:
10.240.240.213:
6789/0mon.node3
4、删除一个mon节点
[root@node1~]#cephmonremovenode1
removedmon.node1at10.39.101.1:
6789/0,therearenow3monitors
2014-07-0718:
11:
04.9741887f4d16bfd700 0monclient:
huntingfornewmon
5、获得一个正在运行的monmap，并保存在1.txt文件中
[root@node3~]#cephmongetmap-o1.txt
gotmonmapepoch6
6、查看上面获得的map
[root@node3~]# monmaptool--print1.txt
monmaptool:
monmapfile1.txt
epoch6
fsid92552333-a0a8-41b8-8b45-c93a8730525e
last_changed2014-07-0718:
22:
51.927205
created0.000000
0:
10.39.101.1:
6789/0mon.node1
1:
10.39.101.2:
6789/0mon.node2
2:
10.39.101.3:
6789/0mon.node3
[root@node3~]#
7、把上面的monmap注入新加入的节点
ceph-mon-inode4--inject-monmap1.txt
8、查看mon的aminsocket
root@node1~]#ceph-conf--namemon.node1--show-config-valueadmin_socket
/var/run/ceph/ceph-mon.node1.asok
9、查看mon的详细状态
[root@node1~]#cephdaemonmon.node1 mon_status
{"name":
"node1",
"rank":
0,
"state":
"leader",
"election_epoch":
96,
"quorum":
[
0,
1,
2],
"outside_quorum":
[],
"extra_probe_peers":
[
"10.39.101.4:
6789\/0"],
"sync_provider":
[],
"monmap":
{"epoch":
6,
"fsid":
"92552333-a0a8-41b8-8b45-c93a8730525e",
"modified":
"2014-07-0718:
22:
51.927205",
"created":
"0.000000",
"mons":
[
{"rank":
0,
"name":
"node1",
"addr":
"10.39.101.1:
6789\/0"},
{"rank":
1,
"name":
"node2",
"addr":
"10.39.101.2:
6789\/0"},
{"rank":
2,
"name":
"node3",
"addr":
"10.39.101.3:
6789\/0"}]}
10、删除一个mon节点
[root@os-node1~]#cephmonremoveos-node1
removedmon.os-node1at10.40.10.64:
6789/0,therearenow3monitors
三、msd
1、查看msd状态
[root@client~]#cephmdsstat
e95:
1/1/1up{0=node2=up:
active},1up:
standby
2、查看msd的映射信息
[root@client~]#cephmdsdump
dumpedmdsmapepoch95
epoch 95
flags 0
created2014-06-2618:
41:
57.686801
modified 2014-06-3000:
24:
11.749967
tableserver 0
root 0
session_timeout60
session_autoclose 300
max_file_size 1099511627776
last_failure 84
last_failure_osd_epoch 81
compat compat={},rocompat={},incompat={1=basev0.20,2=clientwriteableranges,3=defaultfilelayoutsondirs,4=dirinodeinseparateobject,5=mdsusesversionedencoding,6=dirfragisstoredinomap}
max_mds1
in 0
up {0=5015}
failed
stopped
data_pools 0
metadata_pool 1
inline_data disabled
5015:
10.240.240.212:
6808/3032'node2'mds.0.12up:
activeseq30
5012:
10.240.240.211:
6807/3459'node1'mds.-1.0up:
standbyseq38
3、删除一个mds节点
[root@node1~]#ceph mdsrm0mds.node1
mdsgid0dne
四、osd
1、查看cephosd运行状态
[root@client~]#cephosdstat
osdmape88:
3osds:
3up,3in
2、查看osd映射信息
[root@client~]#cephosddump
epoch88
fsidbe1756f2-54f7-4d8f-8790-820c82721f17
created2014-06-2618:
41:
57.687442
modified2014-06-3000:
46:
27.179793
flags
pool0'data'replicatedsize2min_size1crush_ruleset0object_hashrjenkinspg_num64pgp_num64last_change1owner0flagshashpspoolcrash_replay_interval45stripe_width0
pool1'metadata'replicatedsize2min_size1crush_ruleset0object_hashrjenkinspg_num64pgp_num64last_change1owner0flagshashpspoolstripe_width0
pool2'rbd'replicatedsize2min_size1crush_ruleset0object_hashrjenkinspg_num64pgp_num64last_change1owner0flagshashpspoolstripe_width0
pool3'jiayuan'replicatedsize2min_size1crush_ruleset0object_hashrjenkinspg_num256pgp_num256last_change73owner0flagshashpspoolstripe_width0
max_osd3
osd.0up in weight1up_from65up_thru75down_at64last_clean_interval[53,55）10.240.240.211:
6800/308910.240.240.211:
6801/308910.240.240.211:
6802/308910.240.240.211:
6803/3089exists,up8a24ad16-a483-4bac-a56a-6ed44ab74ff0
osd.1up in weight1up_from59up_thru74down_at58last_clean_interval[31,55）10.240.240.212:
6800/269610.240.240.212:
6801/269610.240.240.212:
6802/269610.240.240.212:
6803/2696exists,up8619c083-0273-4203-ba57-4b1dabb89339
osd.2up in weight1up_from62up_thru74down_at61last_clean_interval[39,55）10.240.240.213:
6800/266210.240.240.213:
6801/266210.240.240.213:
6802/266210.240.240.213:
6803/2662exists,upf8107c04-35d7-4fb8-8c82-09eb885f0e58
[root@client~]#
3、查看osd的目录树
[root@client~]#cephosdtree
#id weight typename up/downreweight
-1 3 rootdefault
-2 1 hostnode1
0 1 osd.0 up 1
-3 1 hostnode2
1 1 osd.1 up 1
-4 1 hostnode3
2 1 osd.2 up 1
4、down掉一个osd硬盘
[root@node1~]#cephosddown0 #down掉osd.0节点
5、在集群中删除一个osd硬盘
[root@node4~]#cephosdrm0
removedosd.0
6、在集群中删除一个osd硬盘crushmap
[root@node1~]#cephosdcrushrmosd.0
7、在集群中删除一个osd的host节点
[root@node1~]#cephosdcrushrmnode1
removeditemid-2name'node1'fromcrushmap
查看最大osd的个数
[root@node1~]#cephosdgetmaxosd
max_osd=4inepoch514 #默认最大是4个osd节点
8、设置最大的osd的个数（当扩大osd节点的时候必须扩大这个值）
[root@node1~]#cephosdsetmaxosd10
9、设置osdcrush的权重为1.0
cephosdcrushset{id}{weight}[{loc1}[{loc2}...]]
例如：
[root@admin~]#cephosdcrushset33.0host=node
升级会员 