如何安装Ceph并对接OpenStack
安装Ceph
准备工作：
- 关闭SELinux
sed -i 's/SELINUX=enforcing/SELINUX=disabled/g' /etc/selinux/config
setenforce 0- 打开Ceph端口
# firewall-cmd --zone=public --add-port=6789/tcp --permanent
# firewall-cmd --zone=public --add-port=6800-7100/tcp --permanent
# firewall-cmd --reload- 安装epel源
# yum -y install epel-relea- 安装 ntp 同步时间
# yum -y install ntp ntpdate ntp-doc
# ntpdate 0.us.pool.ntp.org
# hwclock --systohc
# systemctl enable ntpd.service
# systemctl start ntpd.service安装Ceph
安装Ceph源
# rpm -Uvh http://ceph.com/rpm-hammer/el7/noarch/ceph-release-1-1.el7.noarch.rpm
# yum update -y安装ceph-deploy工具
# yum install ceph-deploy -y创建安装Ceph的工作目录
# mkdir ~/ceph-installation创建Monitor节点
#ceph-deploy new mon1 mon2 mon3为每个节点安装Ceph包（包含Monitor节点与OSD节点）
# ceph-deploy install mon1 mon2 mon3 osd1初始化Monitor节点
# ceph-deploy mon create-initial安装一个OSD
- 分区：
parted /dev/sdb
mklabel gpt
mkpart primary 0% 50GB
mkpart primary xfs 50GB 100%- 格式化数据分区
mkfs.xfs /dev/sdb2- 创建OSD
ceph-deploy osd create osd1:/dev/sdb2:/dev/sdb1- 激活OSD
ceph-deploy osd activate osd1:/dev/sdb2:/dev/sdb1同时创建多个
ceph-deploy osd create controller2:/dev/sdb2:/dev/sdb1 controller2:/dev/sdd2:/dev/sdd1 controller2:/dev/sde2:/dev/sde1
ceph-deploy osd activate controller2:/dev/sdb2:/dev/sdb1 controller2:/dev/sdd2:/dev/sdd1 controller2:/dev/sde2:/dev/sde1
注意点：
步骤1-6只需要在一台机器上,即安装节点上做
只有这两步必须在各个节点做
格式化数据分区
mkfs.xfs /dev/sdb2
创建OSD
ceph-deploy osd create osd1:/dev/sdb2:/dev/sdb1机械硬盘
第一个盘的第一个分区给日志分区
SSD
SSD的多个分区给多个osd做log存储
基本配置与检查
[root@controller3 ceph]# ceph health[root@controller3 ceph]# ceph -w[root@controller2 ~(keystone_admin)]# lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
sda 8:0 0 2.7T 0 disk
├─sda1 8:1 0 1M 0 part
├─sda2 8:2 0 500M 0 part /boot
└─sda3 8:3 0 2.7T 0 part
├─centos-swap 253:0 0 7.9G 0 lvm [SWAP]
├─centos-root 253:1 0 50G 0 lvm /
└─centos-home 253:2 0 2.7T 0 lvm /home
sdb 8:16 0 2.7T 0 disk
sdd 8:48 0 2.7T 0 disk
sde 8:64 0 2.7T 0 disk
loop0 7:0 0 2G 0 loop /srv/node/swiftloopback
loop2 7:2 0 20.6G 0 loop[root@controller2 ~(keystone_admin)]# parted /dev/sdb
GNU Parted 3.1
Using /dev/sdb
Welcome to GNU Parted! Type 'help' to view a list of commands.
(parted) mklabel gpt
(parted) mkpart primary 0% 50GB
(parted) mkpart primary xfs 50GB 100%
(parted) p
Model: ATA HGST HUS724030AL (scsi)
Disk /dev/sdb: 3001GB
Sector size (logical/physical): 512B/512B
Partition Table: gpt
Disk Flags:
Number Start End Size File system Name Flags
1 1049kB 50.0GB 50.0GB primary
2 50.0GB 3001GB 2951GB primary
(parted) [root@controller3 ceph]# ceph osd df
ID WEIGHT REWEIGHT SIZE USE AVAIL %USE VAR
0 2.67999 1.00000 2746G 37096k 2746G 0.00 1.03
7 2.67999 1.00000 2746G 35776k 2746G 0.00 0.99
8 2.67999 1.00000 2746G 35256k 2746G 0.00 0.98
1 2.67999 1.00000 2746G 36800k 2746G 0.00 1.02
5 2.67999 1.00000 2746G 35568k 2746G 0.00 0.99
6 2.67999 1.00000 2746G 35572k 2746G 0.00 0.99
2 2.67999 1.00000 2746G 36048k 2746G 0.00 1.00
3 2.67999 1.00000 2746G 36128k 2746G 0.00 1.00
4 2.67999 1.00000 2746G 35664k 2746G 0.00 0.99
TOTAL 24719G 316M 24719G 0.00
MIN/MAX VAR: 0.98/1.03 STDDEV: 0
[root@controller3 ceph]# ceph osd pool get rbd size
[root@controller3 ceph]# ceph osd pool set rbd pg_num 256
set pool 0 pg_num to 256
[root@controller3 ceph]# ceph osd pool set rbd pgp_num 256
Error EBUSY: currently creating pgs, wait
[root@controller3 ceph]# ceph osd pool set rbd pgp_num 256
set pool 0 pgp_num to 256[root@controller3 ceph]# ceph osd tree
ID WEIGHT TYPE NAME UP/DOWN REWEIGHT PRIMARY-AFFINITY
-1 24.11993 root default
-2 8.03998 host controller3
0 2.67999 osd.0 up 1.00000 1.00000
7 2.67999 osd.7 up 1.00000 1.00000
8 2.67999 osd.8 up 1.00000 1.00000
-3 8.03998 host controller1
1 2.67999 osd.1 up 1.00000 1.00000
5 2.67999 osd.5 up 1.00000 1.00000
6 2.67999 osd.6 up 1.00000 1.00000
-4 8.03998 host controller2
2 2.67999 osd.2 up 1.00000 1.00000
3 2.67999 osd.3 up 1.00000 1.00000
4 2.67999 osd.4 up 1.00000 1.00000 
[root@controller3 ceph]# ceph df
GLOBAL:
SIZE AVAIL RAW USED %RAW USED
24719G 24719G 307M 0
POOLS:
NAME ID USED %USED MAX AVAIL OBJECTS
rbd 0 0 0 8239G 0 写下去Ceph对接OpenStack
环境：3台Controller的硬盘作为ceph存储，每台Controller上有3块硬盘，其余为Compute节点
install clients
每个节点安装（要访问ceph集群的节点）
sudo yum install python-rbd
sudo yum install ceph-commoncreate pools
只需在一个ceph节点上操作即可
ceph osd pool create images 1024
ceph osd pool create vms 1024
ceph osd pool create volumes 1024显示pool的状态
ceph osd lspools
ceph -w
3328 pgs: 3328 active+clean创建用户
只需在一个ceph节点上操作即可
ceph auth get-or-create client.glance mon 'allow r' osd 'allow class-read object_prefix rbd_children, allow rwx pool=images'
ceph auth get-or-create client.cinder mon 'allow r' osd 'allow class-read object_prefix rbd_children, allow rwx pool=volumes, allow rwx pool=vms, allow rx pool=images'
nova使用cinder用户，就不单独创建了拷贝ceph-ring
只需在一个ceph节点上操作即可
ceph auth get-or-create client.glance > /etc/ceph/ceph.client.glance.keyring
ceph auth get-or-create client.cinder > /etc/ceph/ceph.client.cinder.keyring使用scp拷贝到其他节点
[root@controller1 ceph]# ls
ceph.client.admin.keyring ceph.conf tmpOZNQbH
ceph.client.cinder.keyring rbdmap tmpPbf5oV
ceph.client.glance.keyring tmpJSCMCV tmpUKxBQB权限
更改文件的权限(所有客户端节点均执行)
sudo chown glance:glance /etc/ceph/ceph.client.glance.keyring
sudo chown cinder:cinder /etc/ceph/ceph.client.cinder.keyring更改libvirt权限（只需在nova-compute节点上操作即可）
uuidgen
生成uuid
cat > secret.xml <<EOF
<secret ephemeral='no' private='no'>
<uuid>457eb676-33da-42ec-9a8c-9293d545c337</uuid>
<usage type='ceph'>
<name>client.cinder secret</name>
</usage>
</secret>
EOF拷贝到所有compute节点
sudo virsh secret-define --file secret.xml
生成key
ceph auth get-key client.cinder > ./client.cinder.key
sudo virsh secret-set-value --secret adc522c4-237c-4cb8-8e39-682adcf4a830 --base64 $(cat ./client.cinder.key)最后所有compute节点的client.cinder.key和secret.xml都是一样的
记下之前生成的uuid
adc522c4-237c-4cb8-8e39-682adcf4a830配置Glance
在所有的controller节点上做如下更改
etc/glance/glance-api.conf
[DEFAULT]
default_store = rbd
show_image_direct_url=False
bind_host=controller1
bind_port=9292
workers=24
backlog=4096
image_cache_dir=/var/lib/glance/image-cache
registry_host=controller1
registry_port=9191
registry_client_protocol=http
debug=False
verbose=True
log_file=/var/log/glance/api.log
log_dir=/var/log/glance
use_syslog=False
syslog_log_facility=LOG_USER
use_stderr=True
[database]
connection=mysql+pymysql://glance:a9717e6e21384389@controller:3305/glance
idle_timeout=3600
[glance_store]
os_region_name=RegionOne
stores = rbd
default_store = rbd
rbd_store_pool = images
rbd_store_user = glance
rbd_store_ceph_conf = /etc/ceph/ceph.conf
rbd_store_chunk_size = 8
[image_format]
[keystone_authtoken]
auth_uri=http://controller:5000/v2.0
identity_uri=http://controller:35357
admin_user=glance
admin_password=79c14ca2ba51415b
admin_tenant_name=services
[matchmaker_redis]
[matchmaker_ring]
[oslo_concurrency]
[oslo_messaging_amqp]
[oslo_messaging_qpid]
[oslo_messaging_rabbit]
rabbit_host=controller1,controller2,controller3
rabbit_hosts=controller1:5672,controller2:5672,controller3:5672
[oslo_policy]
[paste_deploy]
flavor=keystone
[store_type_location_strategy]
[task]
[taskflow_executor]验证Glance
在所有的controller节点上做如下更改
重启服务
openstack-service restart glance- 1
查看状态
[root@controller1 ~]# openstack-service status glance
MainPID=23178 Id=openstack-glance-api.service ActiveState=active
MainPID=23155 Id=openstack-glance-registry.service ActiveState=active[root@controller1 ~]# netstat -plunt | grep 9292
tcp 0 0 192.168.53.58:9292 0.0.0.0:* LISTEN 23178/python2
tcp 0 0 192.168.53.23:9292 0.0.0.0:* LISTEN 11435/haproxy- 传一个镜像
[root@controller1 ~]# rbd ls images
ac5c334f-fbc2-4c56-bf48-47912693b692这样就说明成功了
配置 Cinder
/etc/cinder/cinder.conf
[DEFAULT]
enabled_backends = ceph
glance_host = controller
enable_v1_api = True
enable_v2_api = True
host = controller1
storage_availability_zone = nova
default_availability_zone = nova
auth_strategy = keystone
#enabled_backends = lvm
osapi_volume_listen = controller1
osapi_volume_workers = 24
nova_catalog_info = compute:nova:publicURL
nova_catalog_admin_info = compute:nova:adminURL
debug = False
verbose = True
log_dir = /var/log/cinder
notification_driver =messagingv2
rpc_backend = rabbit
control_exchange = openstack
api_paste_config=/etc/cinder/api-paste.ini
[ceph]
volume_driver = cinder.volume.drivers.rbd.RBDDriver
rbd_pool = volumes
rbd_ceph_conf = /etc/ceph/ceph.conf
rbd_flatten_volume_from_snapshot = false
rbd_max_clone_depth = 5
rbd_store_chunk_size = 4
rados_connect_timeout = -1
glance_api_version = 2
rbd_user = cinder
rbd_secret_uuid = adc522c4-237c-4cb8-8e39-682adcf4a830
volume_backend_name=ceph
[BRCD_FABRIC_EXAMPLE]
[CISCO_FABRIC_EXAMPLE]
[cors]
[cors.subdomain]
[database]
connection = mysql+pymysql://cinder:02d2f2f82467400d@controller:3305/cinder
[fc-zone-manager]
[keymgr]
[keystone_authtoken]
auth_uri = http://controller:5000
identity_uri = http://controller:35357
admin_user = cinder
admin_password = 7281b7bf47044f96
admin_tenant_name = services
memcache_servers = 127.0.0.1:11211
token_cache_time = 3600
cache = true
[matchmaker_redis]
[matchmaker_ring]
[oslo_concurrency]
[oslo_messaging_amqp]
[oslo_messaging_qpid]
[oslo_messaging_rabbit]
amqp_durable_queues = False
kombu_ssl_keyfile =
kombu_ssl_certfile =
kombu_ssl_ca_certs =
rabbit_host = controller1,controller2,controller3
rabbit_port = 5672
rabbit_hosts = controller1:5672,controller2:5672,controller3:5672
rabbit_use_ssl = False
rabbit_userid = guest
rabbit_password = guest
rabbit_virtual_host = /
rabbit_ha_queues = False
heartbeat_timeout_threshold = 0
heartbeat_rate = 2
[oslo_middleware]
[oslo_policy]
[oslo_reports]
[profiler]
[lvm]
iscsi_helper=lioadm
volume_group=cinder-volumes
iscsi_ip_address=192.168.56.251
volume_driver=cinder.volume.drivers.lvm.LVMVolumeDriver
volumes_dir=/var/lib/cinder/volumes
iscsi_protocol=iscsi
volume_backend_name=lvm
注意：ceph段在文本中要重新创建
验证Cinder
openstack-service restart cinder
创建一个云硬盘
[root@controller1 ~]# rbd ls volumes
volume-463c3495-1747-480f-974f-51ac6e1c5612这样就成功了
配置Nova
/etc/nova/nova.conf
[DEFAULT]
internal_service_availability_zone=internal
default_availability_zone=nova
use_ipv6=False
notify_api_faults=False
state_path=/var/lib/nova
report_interval=10
compute_manager=nova.compute.manager.ComputeManager
service_down_time=60
rootwrap_config=/etc/nova/rootwrap.conf
volume_api_class=nova.volume.cinder.API
auth_strategy=keystone
allow_resize_to_same_host=False
heal_instance_info_cache_interval=60
reserved_host_memory_mb=512
network_api_class=nova.network.neutronv2.api.API
force_snat_range =0.0.0.0/0
metadata_host=192.168.56.200
dhcp_domain=novalocal
security_group_api=neutron
compute_driver=libvirt.LibvirtDriver
vif_plugging_is_fatal=True
vif_plugging_timeout=300
firewall_driver=nova.virt.firewall.NoopFirewallDriver
force_raw_images=True
debug=False
verbose=True
log_dir=/var/log/nova
use_syslog=False
syslog_log_facility=LOG_USER
use_stderr=True
notification_topics=notifications
rpc_backend=rabbit
vncserver_proxyclient_address=compute1
vnc_keymap=en-us
sql_connection=mysql+pymysql://nova:8a5033019dcf46c7@192.168.56.200/nova
vnc_enabled=True
image_service=nova.image.glance.GlanceImageService
lock_path=/var/lib/nova/tmp
vncserver_listen=0.0.0.0
novncproxy_base_url=http://192.168.56.200:6080/vnc_auto.html
[api_database]
[barbican]
[cells]
[cinder]
catalog_info=volumev2:cinderv2:publicURL
[conductor]
[cors]
[cors.subdomain]
[database]
[ephemeral_storage_encryption]
[glance]
api_servers=192.168.56.200:9292
[guestfs]
[hyperv]
[image_file_url]
[ironic]
[keymgr]
[keystone_authtoken]
[libvirt]
images_type = rbd
images_rbd_pool = vms
images_rbd_ceph_conf = /etc/ceph/ceph.conf
rbd_user = cinder
rbd_secret_uuid = 5b059071-1aff-4b72-bc5f-0122a7d6c1df
disk_cachemodes="network=writeback"
inject_password = false
inject_key = false
inject_partition = -2
live_migration_flag="VIR_MIGRATE_UNDEFINE_SOURCE,VIR_MIGRATE_PEER2PEER,VIR_MIGRATE_LIVE,VIR_MIGRATE_PERSIST_DEST,VIR_MIGRATE_TUNNELLED"
virt_type=kvm
inject_password=False
inject_key=False
inject_partition=-1
live_migration_uri=qemu+tcp://nova@%s/system
cpu_mode=host-model
vif_driver=nova.virt.libvirt.vif.LibvirtGenericVIFDriver
[matchmaker_redis]
[matchmaker_ring]
[metrics]
[neutron]
url=http://192.168.56.200:9696
admin_username=neutron
admin_password=0cccbadebaa14569
admin_tenant_name=services
region_name=RegionOne
admin_auth_url=http://192.168.56.200:5000/v2.0
auth_strategy=keystone
ovs_bridge=br-int
extension_sync_interval=600
timeout=30
default_tenant_id=default
[osapi_v21]
[oslo_concurrency]
[oslo_messaging_amqp]
[oslo_messaging_qpid]
[oslo_messaging_rabbit]
amqp_durable_queues=False
kombu_reconnect_delay=1.0
rabbit_host=controller1,controller2,controller3
rabbit_port=5672
rabbit_hosts=controller1:5672,controller2:5672,controller3:5672
rabbit_use_ssl=False
rabbit_userid=guest
rabbit_password=guest
rabbit_virtual_host=/
rabbit_ha_queues=False
heartbeat_timeout_threshold=0
heartbeat_rate=2
[oslo_middleware]
[rdp]
[serial_console]
[spice]
[ssl]
[trusted_computing]
[upgrade_levels]
[vmware]
[vnc]
[workarounds]
[xenserver]
[zookeeper]配置Neutron网络
[root@compute1 ~]# ovs-vsctl add-br br-data
[root@compute1 ~]# ovs-vsctl add-port br-data enp7s0f0
[root@compute1 ~]# egrep -v "^$|^#" /etc/neutron/plugins/ml2/openvswitch_agent.ini
[ovs]
integration_bridge = br-int
bridge_mappings =default:br-data
enable_tunneling=False
[agent]
polling_interval = 2
l2_population = False
arp_responder = False
prevent_arp_spoofing = True
enable_distributed_routing = False
extensions =
drop_flows_on_start=False
[securitygroup]
firewall_driver = neutron.agent.linux.iptables_firewall.OVSHybridIptablesFirewallDriver磁盘总量如下，使用了3T*9=27T(ceph3备份)
出处：https://blog.csdn.net/Tomstrong_369/article/details/53330734
补充：
配置Ceph为openstack后端
尝试给nova，cinder-volume/cinder-backup，glance配置Ceph作为后端。
参考Ceph文档：http://docs.ceph.com/docs/master/rbd/rbd-openstack/
先在devstack安装的Kilo版本的环境中配置。
1. 创建pool
[root@controller-1 ~]# ceph osd pool create volumes-maqi-kilo 128
pool 'volumes-maqi-kilo' created
[root@controller-1 ~]# ceph osd pool create backups-maqi-kilo 128
pool 'backups-maqi-kilo' created
[root@controller-1 ~]# ceph osd pool create images-maqi-kilo 128
pool 'images-maqi-kilo' created
[root@controller-1 ~]# ceph osd pool create vms-maqi-kilo 128
pool 'vms-maqi-kilo' created
[root@controller-1 ~]# ceph osd lspools
0 rbd,1 volumes-maqi-kilo,2 backups-maqi-kilo,3 images-maqi-kilo,4 vms-maqi-kilo,128是pg（Placement Group） number，少于5个OSD的环境推荐设为128。
Update 2015/11/16: pg number设置不准确
admin@maqi-kilo:~|⇒ ceph -s
cluster d3752df9-221d-43c7-8cf5-f39061a630da
health HEALTH_WARN
too many PGs per OSD (576 > max 300)
monmap e1: 1 mons at {controller-1=10.134.1.3:6789/0}
election epoch 2, quorum 0 controller-1
osdmap e18: 2 osds: 2 up, 2 in
pgmap v48: 576 pgs, 5 pools, 394 bytes data, 4 objects
20567 MB used, 36839 GB / 36860 GB avail
576 active+clean创建的4个pool，每个128个pg，默认的rbd pool有64个pg，一共128*4+64=576个pg。这些pg分布在两个osd上。
看warning信息，max 300，貌似一个osd只能150？
2. 拷贝ceph节点的ssh public key到openstack 节点上
[root@controller-1 ~]# ssh-copy-id admin@10.133.16.1953. 在openstack节点上创建ceph目录
admin@maqi-kilo:~|⇒ sudo mkdir /etc/ceph4. 配置openstack ceph client
跑cinder-volume、cinder-backup，nova-compute，glance-xxx的节点都是ceph cluster的client，需要ceph.conf配置文件
[root@controller-1 ~]# ssh admin@10.133.16.195 sudo tee /etc/ceph/ceph.conf </etc/ceph/ceph.conf
[global]
fsid = 1c9f72d3-3ebc-465b-97a4-2784f2db1db3
mon_initial_members = controller-1
mon_host = 10.254.4.3
auth_cluster_required = cephx
auth_service_required = cephx
auth_client_required = cephx
filestore_xattr_use_omap = true
osd_pool_default_size = 2
public_network = 10.254.4.3/245. 在openstack节点上安装ceph包
admin@maqi-kilo:~|⇒ sudo apt-get install ceph-common6. Setup Ceph client authentication
为cinder-volume，cinder-backup，glance创建用户
[root@controller-1 ~]# ceph auth get-or-create client.cinder-maqi-kilo mon 'allow r' osd 'allow class-read object_prefix rbd_children, allow rwx pool=volumes-maqi-kilo , allow rwx pool=vms-maqi-kilo, allow rx pool=images-maqi-kilo'
[client.cinder-maqi-kilo]
key = AQDJYkhWwv4uKRAAI/JPWK2H4qV+DqMSkkliOQ==
[root@controller-1 ~]# ceph auth get-or-create client.glance-maqi-kilo mon 'allow r' osd 'allow class-read object_prefix rbd_children, allow rwx pool=images-maqi-kilo'
[client.glance-maqi-kilo]
key = AQAPY0hW+1YQOBAA3aRlTVGkfzTA4ZfaBEmM8Q==
[root@controller-1 ~]# ceph auth get-or-create client.cinder-backup-maqi-kilo mon 'allow r' osd 'allow class-read object_prefix rbd_children, allow rwx pool=backups-maqi-kilo'
[client.cinder-backup-maqi-kilo]
key = AQA7Y0hWxegCChAAhTHc7abrE9bGON97bSsLgw==把key拷贝到openstack节点上并修改ownership：【注意，这一步中的keyring文件名是错误的，详见问题1】
[root@controller-1 ~]# ceph auth get-or-create client.cinder-maqi-kilo | ssh admin@10.133.16.195 sudo tee /etc/ceph/ceph.client.cinder.keyring
[client.cinder-maqi-kilo]
key = AQDJYkhWwv4uKRAAI/JPWK2H4qV+DqMSkkliOQ==
[root@controller-1 ~]# ssh admin@10.133.16.195 sudo chown admin:admin /etc/ceph/ceph.client.cinder.keyring
[root@controller-1 ~]# ceph auth get-or-create client.cinder-backup-maqi-kilo | ssh admin@10.133.16.195 sudo tee /etc/ceph/ceph.client.cinder-backup.keyring
[client.cinder-backup-maqi-kilo]
key = AQA7Y0hWxegCChAAhTHc7abrE9bGON97bSsLgw==
[root@controller-1 ~]# ssh admin@10.133.16.195 sudo chown admin:admin /etc/ceph/ceph.client.cinder-backup.keyring
[root@controller-1 ~]# ceph auth get-or-create client.glance-maqi-kilo | ssh admin@10.133.16.195 sudo tee /etc/ceph/ceph.client.glance.keyring
[client.glance-maqi-kilo]
key = AQAPY0hW+1YQOBAA3aRlTVGkfzTA4ZfaBEmM8Q==
[root@controller-1 ~]# ssh admin@10.133.16.195 sudo chown admin:admin /etc/ceph/ceph.client.glance.keyring注意：
- 这里的owner是admin，因为我们执行devstack安装脚本的用户是admin，所以用admin用户就可以。但是在手动安装的环境中，需要把owner:group设置为
cinder:cinder
对于跑nova-compute的节点，首先需要取得ceph.client.cinder.keyring：
[root@controller-1 ~]# ceph auth get-or-create client.cinder-maqi-kilo | ssh admin@10.133.16.195 sudo tee /etc/ceph/ceph.client.cinder.keyring然后libvirt也需要这个key，创建过程需要一个临时文件：
在ceph节点上：
[root@controller-1 ~]# ceph auth get-key client.cinder-maqi-kilo | ssh admin@10.133.16.195 tee client.cinder.key AQDJYkhWwv4uKRAAI/JPWK2H4qV+DqMSkkliOQ==[root@controller-1 ~]#在nova-compute节点上：
admin@maqi-kilo:~|⇒ uuidgen 57ac147c-199b-4b1c-a3d8-70be795c4d07 admin@maqi-kilo:~|⇒ cat > secret.xml <<EOF heredoc> <secret ephemeral='no' private='no'> heredoc> <uuid>57ac147c-199b-4b1c-a3d8-70be795c4d07</uuid> heredoc> <usage type='ceph'> heredoc> <name>client.cinder-maqi-kilo secret</name> heredoc> </usage> heredoc> </secret> heredoc> EOF admin@maqi-kilo:~|⇒ sudo virsh secret-define --file secret.xml Secret 57ac147c-199b-4b1c-a3d8-70be795c4d07 created admin@maqi-kilo:~|⇒ ls client.cinder.key secret.xml client.cinder.key secret.xml admin@maqi-kilo:~|⇒ admin@maqi-kilo:~|⇒ sudo virsh secret-set-value --secret 57ac147c-199b-4b1c-a3d8-70be795c4d07 --base64 $(cat client.cinder.key) && rm client.cinder.key secret.xml Secret value setNote：UUID最好在各个nova-compute节点上保持一致。
7. 配置glance
/etc/glance/glance-api.conf
[DEFAULT]
default_store = rbd
show_image_direct_url = True
[glance_store]
stores = rbd
rbd_store_pool = images-maqi-kilo
rbd_store_user = glance-maqi-kilo
rbd_store_ceph_conf = /etc/ceph/ceph.conf
rbd_store_chunk_size = 8
[paste_deploy]
flavor = keystone8. 配置cinder
/etc/cinder/cinder.conf
[DEFAULT]
enabled_backends = ceph
glance_api_version = 2
backup_driver = cinder.backup.drivers.ceph
backup_ceph_conf = /etc/ceph/ceph.conf
backup_ceph_user = cinder-backup-maqi-kilo
#backup_ceph_chunk_size = 134217728
backup_ceph_pool = backups-maqi-kilo
backup_ceph_stripe_unit = 0
backup_ceph_stripe_count = 0
restore_discard_excess_bytes = true
[ceph]
volume_driver = cinder.volume.drivers.rbd.RBDDriver
rbd_pool = volumes-maqi-kilo
rbd_ceph_conf = /etc/ceph/ceph.conf
rbd_flatten_volume_from_snapshot = false
rbd_max_clone_depth = 5
#rbd_store_chunk_size = 4
#rados_connect_timeout = -1
rbd_user = cinder-maqi-kilo
rbd_secret_uuid = 57ac147c-199b-4b1c-a3d8-70be795c4d07
volume_backend_name = ceph9. 配置nova
nova.conf
[libvirt]
images_rbd_ceph_conf = /etc/ceph/ceph.conf
images_rbd_pool = vms-maqi-kilo
images_type = rbd
disk_cachemodes = network=writeback
inject_key = false
rbd_secret_uuid = 57ac147c-199b-4b1c-a3d8-70be795c4d07
rbd_user = cinder-maqi-kilo问题
- 配置完成之后，所有的client都连不上ceph cluster。例如cinder-volume报错：
2015-11-15 11:45:15.998 21172 ERROR cinder.volume.drivers.rbd [req-b016ccb5-1544-4b5d-9ec9-1431457f4679 - - - - -] Error connecting to ceph cluster.
2015-11-15 11:45:15.998 21172 TRACE cinder.volume.drivers.rbd Traceback (most recent call last):
2015-11-15 11:45:15.998 21172 TRACE cinder.volume.drivers.rbd File "/home/openstack/workspace/cinder/cinder/volume/drivers/rbd.py", line 314, in _connect_to_rados
2015-11-15 11:45:15.998 21172 TRACE cinder.volume.drivers.rbd client.connect()
2015-11-15 11:45:15.998 21172 TRACE cinder.volume.drivers.rbd File "/usr/lib/python2.7/dist-packages/rados.py", line 417, in connect
2015-11-15 11:45:15.998 21172 TRACE cinder.volume.drivers.rbd raise make_ex(ret, "error calling connect")
2015-11-15 11:45:15.998 21172 TRACE cinder.volume.drivers.rbd ObjectNotFound: error calling connect
2015-11-15 11:45:15.998 21172 TRACE cinder.volume.drivers.rbd
2015-11-15 11:45:15.999 21165 DEBUG cinder.openstack.common.service [req-b3ad30cb-853a-4d68-846d-d5500f8cd0dc - - - - -] glance_ca_certificates_file = None log_opt_values /usr/local/lib/python2.7/dist-packages/oslo_config/cfg.py:2187
2015-11-15 11:45:16.000 21172 ERROR cinder.volume.manager [req-b016ccb5-1544-4b5d-9ec9-1431457f4679 - - - - -] Error encountered during initialization of driver: RBDDriver
。。。。。。
。。。。。。
2015-11-15 11:45:16.000 21172 ERROR cinder.volume.manager [req-b016ccb5-1544-4b5d-9ec9-1431457f4679 - - - - -] Bad or unexpected response from the storage volume backend API: Error connecting to ceph cluster.
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager Traceback (most recent call last):
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager File "/home/openstack/workspace/cinder/cinder/volume/manager.py", line 302, in init_host
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager self.driver.check_for_setup_error()
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager File "/usr/local/lib/python2.7/dist-packages/osprofiler/profiler.py", line 105, in wrapper
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager return f(*args, **kwargs)
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager File "/home/openstack/workspace/cinder/cinder/volume/drivers/rbd.py", line 287, in check_for_setup_error
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager with RADOSClient(self):
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager File "/home/openstack/workspace/cinder/cinder/volume/drivers/rbd.py", line 242, in __init__
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager self.cluster, self.ioctx = driver._connect_to_rados(pool)
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager File "/home/openstack/workspace/cinder/cinder/volume/drivers/rbd.py", line 322, in _connect_to_rados
2015-11-15 11:45:16.000 21172 TRACE cinder.volume.manager raise exception.VolumeBackendAPIException(data=msg)
分析：
cinder应该是通过librados连接到ceph cluster的，先不研究这个library怎么用，先看看用现有的配置文件等能否通过命令行连接：
admin@maqi-kilo:/etc/ceph|⇒ ls
ceph.client.admin.keyring ceph.client.cinder-backup.keyring ceph.client.cinder.keyring ceph.client.glance.keyring ceph.conf
admin@maqi-kilo:/etc/ceph|⇒ ceph osd lspools
0 rbd,1 volumes-maqi-kilo,2 backups-maqi-kilo,3 images-maqi-kilo,4 vms-maqi-kilo,
admin@maqi-kilo:/etc/ceph|⇒ rbd ls volumes-maqi-kilo --keyring ceph.client.cinder.keyring --id cinder-maqi-kilo没有报错，所以如果cinder-volume用这些配置的话应该没问题。
cinder.conf也没问题：
admin@maqi-kilo:/etc/ceph|⇒ grep cinder-maqi-kilo /etc/cinder/cinder.conf
rbd_user = cinder-maqi-kilo
admin@maqi-kilo:/etc/ceph|⇒ grep volumes-maqi-kilo /etc/cinder/cinder.conf
rbd_pool = volumes-maqi-kilo现在的问题是，启动cinder-volume时，在ceph-mon上抓包，根本看不到cinder-volume发过来的包！！但是直接在cinder-volume节点上执行ceph osd lspools时，能抓到包。看起来像cinder-volume没有读取到ceph.conf中的mon IP地址呢？
尝试用rados.py/rdb.py连接ceph cluster（文档）
>>> import rados
>>> import rbd
>>> cluster = rados.Rados(conffile='/etc/ceph/ceph.conf')
>>> cluster.connect()
>>> ioctx = cluster.open_ioctx('rbd')
>>> rbd_inst = rbd.RBD()
>>> size = 4 * 1024**3
>>> rbd_inst.create(ioctx, 'testimage', size)
>>> rbd_inst.create(ioctx, 'testimage2', size)也没问题啊：
admin@maqi-kilo:/etc/ceph|⇒ rbd ls
myimage
testimage
testimage2Update 2015/11/16：
大概能猜想到原因：cinder-volume用client cinder-maqi-kilo去连接ceph，但是在/etc/ceph/下找不到同名的（或者按照某种规则命名的）keyring文件。
看了一下Rados类的初始化代码，如果不指定client，那么就用默认的client.admin，而/etc/ceph/下存在ceph.client.admin.keyring文件。我尝试把这个keyring文件拿走，那么就连不上了：
>>> cluster = rados.Rados(conffile='/etc/ceph/ceph.conf')
>>> cluster.connect()
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/lib/python2.7/dist-packages/rados.py", line 417, in connect
raise make_ex(ret, "error calling connect")
rados.ObjectNotFound: error calling connect最终的解决方法：
重命名cinder-volume使用的keyring文件：
admin@maqi-kilo:/etc/ceph|⇒ cp -p ceph.client.cinder.keyring ceph.client.cinder-maqi-kilo.keyring
admin@maqi-kilo:/etc/ceph|⇒ ll
total 24K
-rw-r--r-- 1 root root 66 Nov 15 10:44 ceph.client.admin.keyring
-rw-r--r-- 1 admin admin 81 Nov 15 10:52 ceph.client.cinder-backup.keyring
-rw-r--r-- 1 admin admin 74 Nov 15 10:51 ceph.client.cinder.keyring
-rw-r--r-- 1 admin admin 74 Nov 15 10:51 ceph.client.cinder-maqi-kilo.keyring
-rw-r--r-- 1 admin admin 74 Nov 15 10:53 ceph.client.glance.keyring
-rw-r--r-- 1 root root 289 Nov 15 10:39 ceph.conf
>>> cluster = rados.Rados(name='client.cinder-maqi-kilo', conffile='')
>>> cluster.connect()
957
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
