设置一个ceph-mgr
创建一个身份验证密钥
ceph --cluster ceph auth get-or-create mgr.ceph4 mon 'allow profile mgr' osd 'allow *' mds 'allow *'
[mgr.ceph4]
key = AQBHFcxciXa/LRAAyuJBnVr8M2ICIwxNPw5XcQ==
mkdir /var/lib/ceph/mgr/ceph-ceph4/
ceph --cluster ceph auth get-or-create mgr.ceph4 -o /var/lib/ceph/mgr/ceph-ceph4/keyring
启动守护进程
ceph-mgr -i ceph4
ceph mgr -h
ceph mgr -h
General usage:
==============
usage: ceph [-h] [-c CEPHCONF] [-i INPUT_FILE] [-o OUTPUT_FILE]
[--id CLIENT_ID] [--name CLIENT_NAME] [--cluster CLUSTER]
[--admin-daemon ADMIN_SOCKET] [-s] [-w] [--watch-debug]
[--watch-info] [--watch-sec] [--watch-warn] [--watch-error]
[--watch-channel WATCH_CHANNEL] [--version] [--verbose]
[--concise] [-f {json,json-pretty,xml,xml-pretty,plain}]
[--connect-timeout CLUSTER_TIMEOUT]
Ceph administration tool
optional arguments:
-h, --help request mon help
-c CEPHCONF, --conf CEPHCONF
ceph configuration file
-i INPUT_FILE, --in-file INPUT_FILE
input file, or "-" for stdin
-o OUTPUT_FILE, --out-file OUTPUT_FILE
output file, or "-" for stdout
--id CLIENT_ID, --user CLIENT_ID
client id for authentication
--name CLIENT_NAME, -n CLIENT_NAME
client name for authentication
--cluster CLUSTER cluster name
--admin-daemon ADMIN_SOCKET
submit admin-socket commands ("help" for help
-s, --status show cluster status
-w, --watch watch live cluster changes
--watch-debug watch debug events
--watch-info watch info events
--watch-sec watch security events
--watch-warn watch warn events
--watch-error watch error events
--watch-channel WATCH_CHANNEL
which log channel to follow when using -w/--watch. One
of ['cluster', 'audit', '*'
--version, -v display version
--verbose make verbose
--concise make less verbose
-f {json,json-pretty,xml,xml-pretty,plain}, --format {json,json-pretty,xml,xml-pretty,plain}
--connect-timeout CLUSTER_TIMEOUT
set a timeout for connecting to the cluster
Local commands:
===============
ping <mon.id> Send simple presence/life test to a mon
<mon.id> may be 'mon.*' for all mons
daemon {type.id|path} <cmd>
Same as --admin-daemon, but auto-find admin socket
daemonperf {type.id | path} [stat-pats] [priority] [<interval>] [<count>]
daemonperf {type.id | path} list|ls [stat-pats] [priority]
Get selected perf stats from daemon/admin socket
Optional shell-glob comma-delim match string stat-pats
Optional selection priority (can abbreviate name):
critical, interesting, useful, noninteresting, debug
List shows a table of all available stats
Run <count> times (default forever),
once per <interval> seconds (default 1)
Monitor commands:
=================
mgr count-metadata <property> count ceph-mgr daemons by metadata field property
mgr dump {<int[0-]>} dump the latest MgrMap
mgr fail <who> treat the named manager daemon as failed
mgr metadata {<id>} dump metadata for all daemons or a specific daemon
mgr module disable <module> disable mgr module
mgr module enable <module> {--force} enable mgr module
mgr module ls list active mgr modules
mgr services list service endpoints provided by mgr modules
mgr versions check running versions of ceph-mgr daemons
根据元数据字段属性计算ceph-mgr守护进程
ceph mgr count-metadata os
{
"Linux": 1
}
获取mgrmap，默认最新
ceph mgr dump 22 #22可省略，
{
"epoch": 22,
"active_gid": 14103,
"active_name": "ceph4",
"active_addr": "10.1.1.24:6804/7416",
"available": true,
"standbys": [],
"modules": [
"balancer",
"dashboard",
"restful",
"status"
],
"available_modules": [
"balancer",
"dashboard",
"influx",
"localpool",
"prometheus",
"restful",
"selftest",
"status",
"zabbix"
],
"services": {
"dashboard": "http://ceph4:7000/"
}
}
将mgr.ceph4视为失败，模拟失败，后自动拉起啦
ceph mgr fail ceph4
[root@ceph4 ~]# ceph -s
cluster:
id: 1f0490cd-f938-4e20-8ea5-d817d941a6e6
health: HEALTH_OK
services:
mon: 1 daemons, quorum ceph4
mgr: ceph4(active, starting)
osd: 1 osds: 1 up, 1 in
data:
pools: 0 pools, 0 pgs
objects: 0 objects, 0B
usage: 1.00GiB used, 3.90GiB / 4.90GiB avail
pgs:
ceph mgr metadata ceph4
[
{
"id": "ceph4",
"arch": "x86_64",
"ceph_version": "ceph version 12.2.11 (26dc3775efc7bb286a1d6d66faee0ba30ea23eee) luminous (stable)",
"cpu": "Intel(R) Core(TM) i5-6200U CPU @ 2.30GHz",
"distro": "centos",
"distro_description": "CentOS Linux 7 (Core)",
"distro_version": "7",
"hostname": "ceph4",
"kernel_description": "#1 SMP Thu Nov 8 23:39:32 UTC 2018",
"kernel_version": "3.10.0-957.el7.x86_64",
"mem_swap_kb": "2097148",
"mem_total_kb": "995896",
"os": "Linux"
}
]
查看哪些模块可用
ceph mgr module ls
{
"enabled_modules": [
"balancer",
"restful",
"status"
],
"disabled_modules": [
"dashboard",
"influx",
"localpool",
"prometheus",
"selftest",
"zabbix"
]
}
启用模块dashboard
ceph mgr module enable dashboard
ceph mgr module ls
{
"enabled_modules": [
"balancer",
"dashboard",
"restful",
"status"
],
"disabled_modules": [
"influx",
"localpool",
"prometheus",
"selftest",
"zabbix"
]
}
配置文件修改
/etc/ceph/ceph.conf [mgr] mgr modules = dashboard
ceph mgr services
{
"dashboard": "http://ceph4:7000/"
}
ceph mgr versions
{
"ceph version 12.2.11 (26dc3775efc7bb286a1d6d66faee0ba30ea23eee) luminous (stable)": 1
}
修改mgr监听地址及端口
修改前确认：
ceph config-key ls
[]
ceph config-key dump
{}
修改
ceph config-key set mgr/dashboard/ceph4/server_addr 10.1.1.24 set mgr/dashboard/ceph4/server_addr ceph config-key set mgr/dashboard/ceph4/server_port 8000 set mgr/dashboard/ceph4/server_port
修改后确认
ceph config-key ls
[
"mgr/dashboard/ceph4/server_addr",
"mgr/dashboard/ceph4/server_port"
]
ceph config-key dump
{
"mgr/dashboard/ceph4/server_addr": "10.1.1.24",
"mgr/dashboard/ceph4/server_port": "8000"
}
服务管理
cp /usr/lib/systemd/system/ceph-mgr@.service /usr/lib/systemcd/system/ceph-mgr@ceph4.service
注意：mgr服务命名需要跟ceph -s中mgr定义的命名匹配
查看ceph-mgr状态，并重启生效
systemctl status ceph-mgr@ceph4 systemctl restart ceph-mgr@ceph4
简述：
dashboard，luminous版本新特色，由mgr提供的一个web界面，只能够用于监控显示，无法进行信息更改
关于高可用
ceph-mgr对于当前ceph版本十分重要：
主要用于管理pg map作用
当ceph-mgr发生故障，相当于整个ceph集群都会出现严重问题
建议在每个mon节点中都创建独立的ceph-mgr（至少3个ceph-mon节点 ）
只需要在每个mon节点进行创建（每个mgr需要不同的独立的命名）
ceph -s
其中一个为active，另外的均为standby
dashboard只可用于active ceph-mgr中
访问dashboard
默认7000