diff --git a/doc/Clusters_from_Scratch/en-US/Ap-Configuration.txt b/doc/Clusters_from_Scratch/en-US/Ap-Configuration.txt
index 9c15be4af8..83e8d029d3 100644
--- a/doc/Clusters_from_Scratch/en-US/Ap-Configuration.txt
+++ b/doc/Clusters_from_Scratch/en-US/Ap-Configuration.txt
@@ -1,388 +1,388 @@
:compat-mode: legacy
[appendix]
== Configuration Recap ==
=== Final Cluster Configuration ===
----
[root@pcmk-1 ~]# pcs resource
Master/Slave Set: WebDataClone [WebData]
Masters: [ pcmk-1 pcmk-2 ]
Clone Set: dlm-clone [dlm]
Started: [ pcmk-1 pcmk-2 ]
Clone Set: ClusterIP-clone [ClusterIP] (unique)
ClusterIP:0 (ocf::heartbeat:IPaddr2): Started pcmk-2
ClusterIP:1 (ocf::heartbeat:IPaddr2): Started pcmk-1
Clone Set: WebFS-clone [WebFS]
Started: [ pcmk-1 pcmk-2 ]
Clone Set: WebSite-clone [WebSite]
Started: [ pcmk-1 pcmk-2 ]
----
----
[root@pcmk-1 ~]# pcs resource op defaults
timeout: 240s
----
----
[root@pcmk-1 ~]# pcs stonith
impi-fencing (stonith:fence_ipmilan): Started pcmk-1
----
----
[root@pcmk-1 ~]# pcs constraint
Location Constraints:
Ordering Constraints:
start ClusterIP-clone then start WebSite-clone (kind:Mandatory)
promote WebDataClone then start WebFS-clone (kind:Mandatory)
start WebFS-clone then start WebSite-clone (kind:Mandatory)
start dlm-clone then start WebFS-clone (kind:Mandatory)
Colocation Constraints:
WebSite-clone with ClusterIP-clone (score:INFINITY)
WebFS-clone with WebDataClone (score:INFINITY) (with-rsc-role:Master)
WebSite-clone with WebFS-clone (score:INFINITY)
WebFS-clone with dlm-clone (score:INFINITY)
Ticket Constraints:
----
----
[root@pcmk-1 ~]# pcs status
Cluster name: mycluster
Stack: corosync
Current DC: pcmk-1 (version 1.1.18-11.el7_5.3-2b07d5c5a9) - partition with quorum
Last updated: Tue Sep 11 10:41:53 2018
Last change: Tue Sep 11 10:40:16 2018 by root via cibadmin on pcmk-1
2 nodes configured
11 resources configured
Online: [ pcmk-1 pcmk-2 ]
Full list of resources:
ipmi-fencing (stonith:fence_ipmilan): Started pcmk-1
Master/Slave Set: WebDataClone [WebData]
Masters: [ pcmk-1 pcmk-2 ]
Clone Set: dlm-clone [dlm]
Started: [ pcmk-1 pcmk-2 ]
Clone Set: ClusterIP-clone [ClusterIP] (unique)
ClusterIP:0 (ocf::heartbeat:IPaddr2): Started pcmk-2
ClusterIP:1 (ocf::heartbeat:IPaddr2): Started pcmk-1
Clone Set: WebFS-clone [WebFS]
Started: [ pcmk-1 pcmk-2 ]
Clone Set: WebSite-clone [WebSite]
Started: [ pcmk-1 pcmk-2 ]
Daemon Status:
corosync: active/disabled
pacemaker: active/disabled
pcsd: active/enabled
----
----
[root@pcmk-1 ~]# pcs cluster cib --config
----
[source,XML]
----
<configuration>
<crm_config>
<cluster_property_set id="cib-bootstrap-options">
<nvpair id="cib-bootstrap-options-have-watchdog" name="have-watchdog" value="false"/>
<nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="1.1.18-11.el7_5.3-2b07d5c5a9"/>
<nvpair id="cib-bootstrap-options-cluster-infrastructure" name="cluster-infrastructure" value="corosync"/>
<nvpair id="cib-bootstrap-options-cluster-name" name="cluster-name" value="mycluster"/>
<nvpair id="cib-bootstrap-options-stonith-enabled" name="stonith-enabled" value="true"/>
<nvpair id="cib-bootstrap-options-last-lrm-refresh" name="last-lrm-refresh" value="1536679009"/>
</cluster_property_set>
</crm_config>
<nodes>
<node id="1" uname="pcmk-1"/>
<node id="2" uname="pcmk-2"/>
</nodes>
<resources>
<primitive class="stonith" id="impi-fencing" type="fence_ipmilan">
<instance_attributes id="impi-fencing-instance_attributes">
<nvpair id="impi-fencing-instance_attributes-pcmk_host_list" name="pcmk_host_list" value="pcmk-1 pcmk-2"/>
<nvpair id="impi-fencing-instance_attributes-ipaddr" name="ipaddr" value="10.0.0.1"/>
<nvpair id="impi-fencing-instance_attributes-login" name="login" value="testuser"/>
<nvpair id="impi-fencing-instance_attributes-passwd" name="passwd" value="acd123"/>
</instance_attributes>
<operations>
<op id="impi-fencing-interval-60s" interval="60s" name="monitor"/>
</operations>
</primitive>
<master id="WebDataClone">
<primitive class="ocf" id="WebData" provider="linbit" type="drbd">
<instance_attributes id="WebData-instance_attributes">
<nvpair id="WebData-instance_attributes-drbd_resource" name="drbd_resource" value="wwwdata"/>
</instance_attributes>
<operations>
<op id="WebData-demote-interval-0s" interval="0s" name="demote" timeout="90"/>
<op id="WebData-monitor-interval-60s" interval="60s" name="monitor"/>
<op id="WebData-notify-interval-0s" interval="0s" name="notify" timeout="90"/>
<op id="WebData-promote-interval-0s" interval="0s" name="promote" timeout="90"/>
<op id="WebData-reload-interval-0s" interval="0s" name="reload" timeout="30"/>
<op id="WebData-start-interval-0s" interval="0s" name="start" timeout="240"/>
<op id="WebData-stop-interval-0s" interval="0s" name="stop" timeout="100"/>
</operations>
</primitive>
<meta_attributes id="WebDataClone-meta_attributes">
<nvpair id="WebDataClone-meta_attributes-master-node-max" name="master-node-max" value="1"/>
<nvpair id="WebDataClone-meta_attributes-clone-max" name="clone-max" value="2"/>
<nvpair id="WebDataClone-meta_attributes-notify" name="notify" value="true"/>
<nvpair id="WebDataClone-meta_attributes-master-max" name="master-max" value="2"/>
<nvpair id="WebDataClone-meta_attributes-clone-node-max" name="clone-node-max" value="1"/>
</meta_attributes>
</master>
<clone id="dlm-clone">
<primitive class="ocf" id="dlm" provider="pacemaker" type="controld">
<operations>
<op id="dlm-monitor-interval-60s" interval="60s" name="monitor"/>
<op id="dlm-start-interval-0s" interval="0s" name="start" timeout="90"/>
<op id="dlm-stop-interval-0s" interval="0s" name="stop" timeout="100"/>
</operations>
</primitive>
<meta_attributes id="dlm-clone-meta_attributes">
<nvpair id="dlm-clone-meta_attributes-clone-max" name="clone-max" value="2"/>
<nvpair id="dlm-clone-meta_attributes-clone-node-max" name="clone-node-max" value="1"/>
</meta_attributes>
</clone>
<clone id="ClusterIP-clone">
<primitive class="ocf" id="ClusterIP" provider="heartbeat" type="IPaddr2">
<instance_attributes id="ClusterIP-instance_attributes">
- <nvpair id="ClusterIP-instance_attributes-cidr_netmask" name="cidr_netmask" value="32"/>
+ <nvpair id="ClusterIP-instance_attributes-cidr_netmask" name="cidr_netmask" value="24"/>
<nvpair id="ClusterIP-instance_attributes-ip" name="ip" value="192.168.122.120"/>
<nvpair id="ClusterIP-instance_attributes-clusterip_hash" name="clusterip_hash" value="sourceip"/>
</instance_attributes>
<operations>
<op id="ClusterIP-monitor-interval-30s" interval="30s" name="monitor"/>
<op id="ClusterIP-start-interval-0s" interval="0s" name="start" timeout="20s"/>
<op id="ClusterIP-stop-interval-0s" interval="0s" name="stop" timeout="20s"/>
</operations>
<meta_attributes id="ClusterIP-meta_attributes">
<nvpair id="ClusterIP-meta_attributes-resource-stickiness" name="resource-stickiness" value="0"/>
</meta_attributes>
</primitive>
<meta_attributes id="ClusterIP-clone-meta_attributes">
<nvpair id="ClusterIP-clone-meta_attributes-clone-max" name="clone-max" value="2"/>
<nvpair id="ClusterIP-clone-meta_attributes-clone-node-max" name="clone-node-max" value="2"/>
<nvpair id="ClusterIP-clone-meta_attributes-globally-unique" name="globally-unique" value="true"/>
</meta_attributes>
</clone>
<clone id="WebFS-clone">
<primitive class="ocf" id="WebFS" provider="heartbeat" type="Filesystem">
<instance_attributes id="WebFS-instance_attributes">
<nvpair id="WebFS-instance_attributes-device" name="device" value="/dev/drbd1"/>
<nvpair id="WebFS-instance_attributes-directory" name="directory" value="/var/www/html"/>
<nvpair id="WebFS-instance_attributes-fstype" name="fstype" value="gfs2"/>
</instance_attributes>
<operations>
<op id="WebFS-monitor-interval-20" interval="20" name="monitor" timeout="40"/>
<op id="WebFS-notify-interval-0s" interval="0s" name="notify" timeout="60"/>
<op id="WebFS-start-interval-0s" interval="0s" name="start" timeout="60"/>
<op id="WebFS-stop-interval-0s" interval="0s" name="stop" timeout="60"/>
</operations>
</primitive>
</clone>
<clone id="WebSite-clone">
<primitive class="ocf" id="WebSite" provider="heartbeat" type="apache">
<instance_attributes id="WebSite-instance_attributes">
<nvpair id="WebSite-instance_attributes-configfile" name="configfile" value="/etc/httpd/conf/httpd.conf"/>
<nvpair id="WebSite-instance_attributes-statusurl" name="statusurl" value="http://localhost/server-status"/>
</instance_attributes>
<operations>
<op id="WebSite-monitor-interval-1min" interval="1min" name="monitor"/>
<op id="WebSite-start-interval-0s" interval="0s" name="start" timeout="40s"/>
<op id="WebSite-stop-interval-0s" interval="0s" name="stop" timeout="60s"/>
</operations>
</primitive>
<meta_attributes id="WebSite-clone-meta_attributes"/>
</clone>
</resources>
<constraints>
<rsc_colocation id="colocation-WebSite-ClusterIP-INFINITY" rsc="WebSite-clone" score="INFINITY" with-rsc="ClusterIP-clone"/>
<rsc_order first="ClusterIP-clone" first-action="start" id="order-ClusterIP-WebSite-mandatory" then="WebSite-clone" then-action="start"/>
<rsc_colocation id="colocation-WebFS-WebDataClone-INFINITY" rsc="WebFS-clone" score="INFINITY" with-rsc="WebDataClone" with-rsc-role="Master"/>
<rsc_order first="WebDataClone" first-action="promote" id="order-WebDataClone-WebFS-mandatory" then="WebFS-clone" then-action="start"/>
<rsc_colocation id="colocation-WebSite-WebFS-INFINITY" rsc="WebSite-clone" score="INFINITY" with-rsc="WebFS-clone"/>
<rsc_order first="WebFS-clone" first-action="start" id="order-WebFS-WebSite-mandatory" then="WebSite-clone" then-action="start"/>
<rsc_colocation id="colocation-WebFS-dlm-clone-INFINITY" rsc="WebFS-clone" score="INFINITY" with-rsc="dlm-clone"/>
<rsc_order first="dlm-clone" first-action="start" id="order-dlm-clone-WebFS-mandatory" then="WebFS-clone" then-action="start"/>
</constraints>
<rsc_defaults>
<meta_attributes id="rsc_defaults-options">
<nvpair id="rsc_defaults-options-resource-stickiness" name="resource-stickiness" value="100"/>
</meta_attributes>
</rsc_defaults>
<op_defaults>
<meta_attributes id="op_defaults-options">
<nvpair id="op_defaults-options-timeout" name="timeout" value="240s"/>
</meta_attributes>
</op_defaults>
</configuration>
----
=== Node List ===
----
[root@pcmk-1 ~]# pcs status nodes
Pacemaker Nodes:
Online: pcmk-1 pcmk-2
Standby:
Maintenance:
Offline:
Pacemaker Remote Nodes:
Online:
Standby:
Maintenance:
Offline:
----
=== Cluster Options ===
----
[root@pcmk-1 ~]# pcs property
Cluster Properties:
cluster-infrastructure: corosync
cluster-name: mycluster
dc-version: 1.1.18-11.el7_5.3-2b07d5c5a9
have-watchdog: false
last-lrm-refresh: 1536679009
stonith-enabled: true
----
The output shows state information automatically obtained about the cluster, including:
* *cluster-infrastructure* - the cluster communications layer in use
* *cluster-name* - the cluster name chosen by the administrator when the cluster was created
* *dc-version* - the version (including upstream source-code hash) of Pacemaker
used on the Designated Controller, which is the node elected to determine what
actions are needed when events occur
The output also shows options set by the administrator that control the way the cluster operates, including:
* *stonith-enabled=true* - whether the cluster is allowed to use STONITH resources
=== Resources ===
==== Default Options ====
----
[root@pcmk-1 ~]# pcs resource defaults
resource-stickiness: 100
----
This shows cluster option defaults that apply to every resource that does not
explicitly set the option itself. Above:
* *resource-stickiness* - Specify the aversion to moving healthy resources to other machines
==== Fencing ====
----
[root@pcmk-1 ~]# pcs stonith show
ipmi-fencing (stonith:fence_ipmilan): Started pcmk-1
[root@pcmk-1 ~]# pcs stonith show ipmi-fencing
Resource: ipmi-fencing (class=stonith type=fence_ipmilan)
Attributes: ipaddr="10.0.0.1" login="testuser" passwd="acd123" pcmk_host_list="pcmk-1 pcmk-2"
Operations: monitor interval=60s (fence-monitor-interval-60s)
----
==== Service Address ====
Users of the services provided by the cluster require an unchanging
address with which to access it. Additionally, we cloned the address so
it will be active on both nodes. An iptables rule (created as part of the
resource agent) is used to ensure that each request only gets processed by one
of the two clone instances. The additional meta options tell the cluster
that we want two instances of the clone (one "request bucket" for each
node) and that if one node fails, then the remaining node should hold
both.
----
[root@pcmk-1 ~]# pcs resource show ClusterIP-clone
Clone: ClusterIP-clone
Meta Attrs: clone-max=2 clone-node-max=2 globally-unique=true
Resource: ClusterIP (class=ocf provider=heartbeat type=IPaddr2)
- Attributes: cidr_netmask=32 ip=192.168.122.120 clusterip_hash=sourceip
+ Attributes: cidr_netmask=24 ip=192.168.122.120 clusterip_hash=sourceip
Meta Attrs: resource-stickiness=0
Operations: monitor interval=30s (ClusterIP-monitor-interval-30s)
start interval=0s timeout=20s (ClusterIP-start-interval-0s)
stop interval=0s timeout=20s (ClusterIP-stop-interval-0s)
----
==== DRBD - Shared Storage ====
Here, we define the DRBD service and specify which DRBD resource (from
/etc/drbd.d/*.res) it should manage. We make it a master clone resource and, in
order to have an active/active setup, allow both instances to be promoted to master
at the same time. We also set the notify option so that the
cluster will tell DRBD agent when its peer changes state.
----
[root@pcmk-1 ~]# pcs resource show WebDataClone
Master: WebDataClone
Meta Attrs: master-node-max=1 clone-max=2 notify=true master-max=2 clone-node-max=1
Resource: WebData (class=ocf provider=linbit type=drbd)
Attributes: drbd_resource=wwwdata
Operations: demote interval=0s timeout=90 (WebData-demote-interval-0s)
monitor interval=60s (WebData-monitor-interval-60s)
notify interval=0s timeout=90 (WebData-notify-interval-0s)
promote interval=0s timeout=90 (WebData-promote-interval-0s)
reload interval=0s timeout=30 (WebData-reload-interval-0s)
start interval=0s timeout=240 (WebData-start-interval-0s)
stop interval=0s timeout=100 (WebData-stop-interval-0s)
[root@pcmk-1 ~]# pcs constraint ref WebDataClone
Resource: WebDataClone
colocation-WebFS-WebDataClone-INFINITY
order-WebDataClone-WebFS-mandatory
----
==== Cluster Filesystem ====
The cluster filesystem ensures that files are read and written correctly.
We need to specify the block device (provided by DRBD), where we want it
mounted and that we are using GFS2. Again, it is a clone because it is
intended to be active on both nodes. The additional constraints ensure
that it can only be started on nodes with active DLM and DRBD instances.
----
[root@pcmk-1 ~]# pcs resource show WebFS-clone
Clone: WebFS-clone
Resource: WebFS (class=ocf provider=heartbeat type=Filesystem)
Attributes: device=/dev/drbd1 directory=/var/www/html fstype=gfs2
Operations: monitor interval=20 timeout=40 (WebFS-monitor-interval-20)
notify interval=0s timeout=60 (WebFS-notify-interval-0s)
start interval=0s timeout=60 (WebFS-start-interval-0s)
stop interval=0s timeout=60 (WebFS-stop-interval-0s)
[root@pcmk-1 ~]# pcs constraint ref WebFS-clone
Resource: WebFS-clone
colocation-WebFS-WebDataClone-INFINITY
colocation-WebSite-WebFS-INFINITY
colocation-WebFS-dlm-clone-INFINITY
order-WebDataClone-WebFS-mandatory
order-WebFS-WebSite-mandatory
order-dlm-clone-WebFS-mandatory
----
==== Apache ====
Lastly, we have the actual service, Apache. We need only tell the cluster
where to find its main configuration file and restrict it to running on
nodes that have the required filesystem mounted and the IP address active.
----
[root@pcmk-1 ~]# pcs resource show WebSite-clone
Clone: WebSite-clone
Resource: WebSite (class=ocf provider=heartbeat type=apache)
Attributes: configfile=/etc/httpd/conf/httpd.conf statusurl=http://localhost/server-status
Operations: monitor interval=1min (WebSite-monitor-interval-1min)
start interval=0s timeout=40s (WebSite-start-interval-0s)
stop interval=0s timeout=60s (WebSite-stop-interval-0s)
[root@pcmk-1 ~]# pcs constraint ref WebSite-clone
Resource: WebSite-clone
colocation-WebSite-ClusterIP-INFINITY
colocation-WebSite-WebFS-INFINITY
order-ClusterIP-WebSite-mandatory
order-WebFS-WebSite-mandatory
----
diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.txt b/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.txt
index b0d950c5e1..0cd3463113 100644
--- a/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.txt
+++ b/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.txt
@@ -1,377 +1,377 @@
:compat-mode: legacy
= Create an Active/Passive Cluster =
== Explore the Existing Configuration ==
When Pacemaker starts up, it automatically records the number and details
of the nodes in the cluster, as well as which stack is being used and the
version of Pacemaker being used.
The first few lines of output should look like this:
----
[root@pcmk-1 ~]# pcs status
Cluster name: mycluster
WARNING: no stonith devices and stonith-enabled is not false
Stack: corosync
Current DC: pcmk-2 (version 1.1.18-11.el7_5.3-2b07d5c5a9) - partition with quorum
Last updated: Mon Sep 10 16:41:46 2018
Last change: Mon Sep 10 16:30:53 2018 by hacluster via crmd on pcmk-2
2 nodes configured
0 resources configured
Online: [ pcmk-1 pcmk-2 ]
----
For those who are not of afraid of XML, you can see the raw cluster
configuration and status by using the `pcs cluster cib` command.
.The last XML you'll see in this document
======
----
[root@pcmk-1 ~]# pcs cluster cib
----
[source,XML]
----
<cib crm_feature_set="3.0.14" validate-with="pacemaker-2.10" epoch="5" num_updates="4" admin_epoch="0" cib-last-written="Mon Sep 10 16:30:53 2018" update-origin="pcmk-2" update-client="crmd" update-user="hacluster" have-quorum="1" dc-uuid="2">
<configuration>
<crm_config>
<cluster_property_set id="cib-bootstrap-options">
<nvpair id="cib-bootstrap-options-have-watchdog" name="have-watchdog" value="false"/>
<nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="1.1.18-11.el7_5.3-2b07d5c5a9"/>
<nvpair id="cib-bootstrap-options-cluster-infrastructure" name="cluster-infrastructure" value="corosync"/>
<nvpair id="cib-bootstrap-options-cluster-name" name="cluster-name" value="mycluster"/>
</cluster_property_set>
</crm_config>
<nodes>
<node id="1" uname="pcmk-1"/>
<node id="2" uname="pcmk-2"/>
</nodes>
<resources/>
<constraints/>
</configuration>
<status>
<node_state id="1" uname="pcmk-1" in_ccm="true" crmd="online" crm-debug-origin="do_state_transition" join="member" expected="member">
<lrm id="1">
<lrm_resources/>
</lrm>
</node_state>
<node_state id="2" uname="pcmk-2" in_ccm="true" crmd="online" crm-debug-origin="do_state_transition" join="member" expected="member">
<lrm id="2">
<lrm_resources/>
</lrm>
</node_state>
</status>
</cib>
----
======
Before we make any changes, it's a good idea to check the validity of
the configuration.
----
[root@pcmk-1 ~]# crm_verify -L -V
error: unpack_resources: Resource start-up disabled since no STONITH resources have been defined
error: unpack_resources: Either configure some or disable STONITH with the stonith-enabled option
error: unpack_resources: NOTE: Clusters with shared data need STONITH to ensure data integrity
Errors found during check: config not valid
----
As you can see, the tool has found some errors.
In order to guarantee the safety of your data,
footnote:[If the data is corrupt, there is little point in continuing to make it available]
fencing (also called STONITH) is enabled by default. However, it also knows
when no STONITH configuration has been supplied and reports this as a problem
(since the cluster will not be able to make progress if a situation requiring
node fencing arises).
We will disable this feature for now and configure it later.
To disable STONITH, set the *stonith-enabled* cluster option to
false:
----
[root@pcmk-1 ~]# pcs property set stonith-enabled=false
[root@pcmk-1 ~]# crm_verify -L
----
With the new cluster option set, the configuration is now valid.
[WARNING]
=========
The use of `stonith-enabled=false` is completely inappropriate for a
production cluster. It tells the cluster to simply pretend that failed nodes
are safely powered off. Some vendors will refuse to support clusters that have
STONITH disabled. We disable STONITH here only to defer the discussion of its
configuration, which can differ widely from one installation to the
next. See <<_what_is_stonith>> for information on why STONITH is important
and details on how to configure it.
=========
== Add a Resource ==
Our first resource will be a unique IP address that the cluster can bring up on
either node. Regardless of where any cluster service(s) are running, end
users need a consistent address to contact them on. Here, I will choose
192.168.122.120 as the floating address, give it the imaginative name ClusterIP
and tell the cluster to check whether it is running every 30 seconds.
[WARNING]
===========
The chosen address must not already be in use on the network.
Do not reuse an IP address one of the nodes already has configured.
===========
----
[root@pcmk-1 ~]# pcs resource create ClusterIP ocf:heartbeat:IPaddr2 \
- ip=192.168.122.120 cidr_netmask=32 op monitor interval=30s
+ ip=192.168.122.120 cidr_netmask=24 op monitor interval=30s
----
Another important piece of information here is *ocf:heartbeat:IPaddr2*.
This tells Pacemaker three things about the resource you want to add:
* The first field (*ocf* in this case) is the standard to which the resource
script conforms and where to find it.
* The second field (*heartbeat* in this case) is standard-specific; for OCF
resources, it tells the cluster which OCF namespace the resource script is in.
* The third field (*IPaddr2* in this case) is the name of the resource script.
To obtain a list of the available resource standards (the *ocf* part of
*ocf:heartbeat:IPaddr2*), run:
----
[root@pcmk-1 ~]# pcs resource standards
lsb
ocf
service
systemd
----
To obtain a list of the available OCF resource providers (the *heartbeat*
part of *ocf:heartbeat:IPaddr2*), run:
----
[root@pcmk-1 ~]# pcs resource providers
heartbeat
openstack
pacemaker
----
Finally, if you want to see all the resource agents available for
a specific OCF provider (the *IPaddr2* part of *ocf:heartbeat:IPaddr2*), run:
----
[root@pcmk-1 ~]# pcs resource agents ocf:heartbeat
apache
aws-vpc-move-ip
awseip
awsvip
azure-lb
clvm
.
. (skipping lots of resources to save space)
.
symlink
tomcat
VirtualDomain
Xinetd
----
Now, verify that the IP resource has been added, and display the cluster's
status to see that it is now active:
----
[root@pcmk-1 ~]# pcs status
Cluster name: mycluster
Stack: corosync
Current DC: pcmk-2 (version 1.1.18-11.el7_5.3-2b07d5c5a9) - partition with quorum
Last updated: Mon Sep 10 16:55:26 2018
Last change: Mon Sep 10 16:53:42 2018 by root via cibadmin on pcmk-1
2 nodes configured
1 resource configured
Online: [ pcmk-1 pcmk-2 ]
Full list of resources:
ClusterIP (ocf::heartbeat:IPaddr2): Started pcmk-1
Daemon Status:
corosync: active/disabled
pacemaker: active/disabled
pcsd: active/enabled
----
== Perform a Failover ==
Since our ultimate goal is high availability, we should test failover of
our new resource before moving on.
First, find the node on which the IP address is running.
----
[root@pcmk-1 ~]# pcs status
Cluster name: mycluster
Stack: corosync
Current DC: pcmk-2 (version 1.1.18-11.el7_5.3-2b07d5c5a9) - partition with quorum
Last updated: Mon Sep 10 16:55:26 2018
Last change: Mon Sep 10 16:53:42 2018 by root via cibadmin on pcmk-1
2 nodes configured
1 resource configured
Online: [ pcmk-1 pcmk-2 ]
Full list of resources:
ClusterIP (ocf::heartbeat:IPaddr2): Started pcmk-1
----
You can see that the status of the *ClusterIP* resource
is *Started* on a particular node (in this example, *pcmk-1*).
Shut down Pacemaker and Corosync on that machine to trigger a failover.
----
[root@pcmk-1 ~]# pcs cluster stop pcmk-1
Stopping Cluster (pacemaker)...
Stopping Cluster (corosync)...
----
[NOTE]
======
A cluster command such as +pcs cluster stop pass:[<replaceable>nodename</replaceable>]+ can be run
from any node in the cluster, not just the affected node.
======
Verify that pacemaker and corosync are no longer running:
----
[root@pcmk-1 ~]# pcs status
Error: cluster is not currently running on this node
----
Go to the other node, and check the cluster status.
----
[root@pcmk-2 ~]# pcs status
Cluster name: mycluster
Stack: corosync
Current DC: pcmk-2 (version 1.1.18-11.el7_5.3-2b07d5c5a9) - partition with quorum
Last updated: Mon Sep 10 16:57:22 2018
Last change: Mon Sep 10 16:53:42 2018 by root via cibadmin on pcmk-1
2 nodes configured
1 resource configured
Online: [ pcmk-2 ]
OFFLINE: [ pcmk-1 ]
Full list of resources:
ClusterIP (ocf::heartbeat:IPaddr2): Started pcmk-2
Daemon Status:
corosync: active/disabled
pacemaker: active/disabled
pcsd: active/enabled
----
Notice that *pcmk-1* is *OFFLINE* for cluster purposes (its *pcsd* is still
active, allowing it to receive `pcs` commands, but it is not participating in
the cluster).
Also notice that *ClusterIP* is now running on *pcmk-2* -- failover happened
automatically, and no errors are reported.
[IMPORTANT]
.Quorum
====
If a cluster splits into two (or more) groups of nodes that can no longer
communicate with each other (aka. _partitions_), _quorum_ is used to prevent
resources from starting on more nodes than desired, which would risk
data corruption.
A cluster has quorum when more than half of all known nodes are online in
the same partition, or for the mathematically inclined, whenever the following
equation is true:
....
total_nodes < 2 * active_nodes
....
For example, if a 5-node cluster split into 3- and 2-node paritions,
the 3-node partition would have quorum and could continue serving resources.
If a 6-node cluster split into two 3-node partitions, neither partition
would have quorum; pacemaker's default behavior in such cases is to
stop all resources, in order to prevent data corruption.
Two-node clusters are a special case. By the above definition,
a two-node cluster would only have quorum when both nodes are
running. This would make the creation of a two-node cluster pointless,
but corosync has the ability to treat two-node clusters as if only one node
is required for quorum.
The `pcs cluster setup` command will automatically configure *two_node: 1*
in +corosync.conf+, so a two-node cluster will "just work".
If you are using a different cluster shell, you will have to configure
+corosync.conf+ appropriately yourself.
====
Now, simulate node recovery by restarting the cluster stack on *pcmk-1*, and
check the cluster's status. (It may take a little while before the cluster
gets going on the node, but it eventually will look like the below.)
----
[root@pcmk-1 ~]# pcs cluster start pcmk-1
pcmk-1: Starting Cluster...
[root@pcmk-1 ~]# pcs status
Cluster name: mycluster
Stack: corosync
Current DC: pcmk-2 (version 1.1.18-11.el7_5.3-2b07d5c5a9) - partition with quorum
Last updated: Mon Sep 10 17:00:04 2018
Last change: Mon Sep 10 16:53:42 2018 by root via cibadmin on pcmk-1
2 nodes configured
1 resource configured
Online: [ pcmk-1 pcmk-2 ]
Full list of resources:
ClusterIP (ocf::heartbeat:IPaddr2): Started pcmk-2
Daemon Status:
corosync: active/disabled
pacemaker: active/disabled
pcsd: active/enabled
----
== Prevent Resources from Moving after Recovery ==
In most circumstances, it is highly desirable to prevent healthy
resources from being moved around the cluster. Moving resources almost
always requires a period of downtime. For complex services such as
databases, this period can be quite long.
To address this, Pacemaker has the concept of resource _stickiness_,
which controls how strongly a service prefers to stay running where it
is. You may like to think of it as the "cost" of any downtime. By
default, Pacemaker assumes there is zero cost associated with moving
resources and will do so to achieve "optimal"
footnote:[Pacemaker's definition of optimal may not always agree with that of a
human's. The order in which Pacemaker processes lists of resources and nodes
creates implicit preferences in situations where the administrator has not
explicitly specified them.]
resource placement. We can specify a different stickiness for every
resource, but it is often sufficient to change the default.
----
[root@pcmk-1 ~]# pcs resource defaults resource-stickiness=100
Warning: Defaults do not apply to resources which override them with their own defined values
[root@pcmk-1 ~]# pcs resource defaults
resource-stickiness: 100
----
diff --git a/doc/pcs-crmsh-quick-ref.md b/doc/pcs-crmsh-quick-ref.md
index a293823d98..5bd54cc4d0 100644
--- a/doc/pcs-crmsh-quick-ref.md
+++ b/doc/pcs-crmsh-quick-ref.md
@@ -1,355 +1,355 @@
<!-- (new version of doctoc removed this, so added above:) -->
<!-- *generated with [DocToc](https://github.com/thlorenz/doctoc-web/)* -->
<!-- START doctoc generated TOC please keep comment here to allow auto update -->
<!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
**Table of Contents**
- [General Operations](#general-operations)
- [Display the configuration](#display-the-configuration)
- [Display the current status](#display-the-current-status)
- [Node standby](#node-standby)
- [Set cluster property](#set-cluster-property)
- [Resource manipulation](#resource-manipulation)
- [List Resource Agent (RA) classes](#list-resource-agent-ra-classes)
- [List available RAs](#list-available-ras)
- [List RA info](#list-ra-info)
- [Create a resource](#create-a-resource)
- [Display a resource](#display-a-resource)
- [Display fencing resources](#display-fencing-resources)
- [Display Stonith RA info](#display-stonith-ra-info)
- [Start a resource](#start-a-resource)
- [Stop a resource](#stop-a-resource)
- [Remove a resource](#remove-a-resource)
- [Modify a resource](#modify-a-resource)
- [Delete parameters for a given resource](#delete-parameters-for-a-given-resource)
- [List the current resource defaults](#list-the-current-resource-defaults)
- [Set resource defaults](#set-resource-defaults)
- [List the current operation defaults](#list-the-current-operation-defaults)
- [Set operation defaults](#set-operation-defaults)
- [Set Colocation](#set-colocation)
- [Set ordering](#set-ordering)
- [Set preferred location](#set-preferred-location)
- [Move resources](#move-resources)
- [Resource tracing](#resource-tracing)
- [Clear fail counts](#clear-fail-counts)
- [Edit fail counts](#edit-fail-counts)
- [Handling configuration elements by type](#handling-configuration-elements-by-type)
- [Create a clone](#create-a-clone)
- [Create a master/slave clone](#create-a-masterslave-clone)
- [Other operations](#other-operations)
- [Batch changes](#batch-changes)
- [Template creation](#template-creation)
- [Log analysis](#log-analysis)
- [Configuration scripts](#configuration-scripts)
<!-- END doctoc generated TOC please keep comment here to allow auto update -->
# General Operations
## Display the configuration
crmsh # crm configure show xml
pcs # pcs cluster cib
To show a simplified (non-xml) syntax
crmsh # crm configure show
pcs # pcs config
## Display the current status
crmsh # crm status
pcs # pcs status
also
# crm_mon -1
## Node standby
Put node in standby
crmsh # crm node standby pcmk-1
pcs # pcs cluster standby pcmk-1
Remove node from standby
crmsh # crm node online pcmk-1
pcs # pcs cluster unstandby pcmk-1
crm has the ability to set the status on reboot or forever.
pcs can apply the change to all the nodes.
## Set cluster property
crmsh # crm configure property stonith-enabled=false
pcs # pcs property set stonith-enabled=false
# Resource manipulation
## List Resource Agent (RA) classes
crmsh # crm ra classes
pcs # pcs resource standards
## List available RAs
crmsh # crm ra list ocf
crmsh # crm ra list lsb
crmsh # crm ra list service
crmsh # crm ra list stonith
pcs # pcs resource agents ocf
pcs # pcs resource agents lsb
pcs # pcs resource agents service
pcs # pcs resource agents stonith
pcs # pcs resource agents
You can also filter by provider
crmsh # crm ra list ocf pacemaker
pcs # pcs resource agents ocf:pacemaker
## List RA info
crmsh # crm ra meta IPaddr2
pcs # pcs resource describe IPaddr2
Use any RA name (like IPaddr2) from the list displayed with the previous command
You can also use the full class:provider:RA format if multiple RAs with the same name are available :
crmsh # crm ra meta ocf:heartbeat:IPaddr2
pcs # pcs resource describe ocf:heartbeat:IPaddr2
## Create a resource
crmsh # crm configure primitive ClusterIP ocf:heartbeat:IPaddr2 \
- params ip=192.168.122.120 cidr_netmask=32 \
+ params ip=192.168.122.120 cidr_netmask=24 \
op monitor interval=30s
- pcs # pcs resource create ClusterIP IPaddr2 ip=192.168.0.120 cidr_netmask=32
+ pcs # pcs resource create ClusterIP IPaddr2 ip=192.168.0.120 cidr_netmask=24
The standard and provider (`ocf:heartbeat`) are determined automatically since `IPaddr2` is unique.
The monitor operation is automatically created based on the agent's metadata.
## Display a resource
crmsh # crm configure show
pcs # pcs resource show
crmsh also displays fencing resources.
The result can be filtered by supplying a resource name (IE `ClusterIP`):
crmsh # crm configure show ClusterIP
pcs # pcs resource show ClusterIP
crmsh also displays fencing resources.
## Display fencing resources
crmsh # crm resource show
pcs # pcs stonith show
pcs treats STONITH devices separately.
## Display Stonith RA info
crmsh # crm ra meta stonith:fence_ipmilan
pcs # pcs stonith describe fence_ipmilan
## Start a resource
crmsh # crm resource start ClusterIP
pcs # pcs resource enable ClusterIP
## Stop a resource
crmsh # crm resource stop ClusterIP
pcs # pcs resource disable ClusterIP
## Remove a resource
crmsh # crm configure delete ClusterIP
pcs # pcs resource delete ClusterIP
## Modify a resource
crmsh # crm resource param ClusterIP set clusterip_hash=sourceip
pcs # pcs resource update ClusterIP clusterip_hash=sourceip
crmsh also has an `edit` command which edits the simplified CIB syntax
(same commands as the command line) via a configurable text editor.
crmsh # crm configure edit ClusterIP
Using the interactive shell mode of crmsh, multiple changes can be
edited and verified before committing to the live configuration.
crmsh # crm configure
crmsh # edit
crmsh # verify
crmsh # commit
## Delete parameters for a given resource
crmsh # crm resource param ClusterIP delete nic
pcs # pcs resource update ClusterIP ip=192.168.0.98 nic=
## List the current resource defaults
crmsh # crm configure show type:rsc_defaults
pcs # pcs resource rsc defaults
## Set resource defaults
crmsh # crm configure rsc_defaults resource-stickiness=100
pcs # pcs resource rsc defaults resource-stickiness=100
## List the current operation defaults
crmsh # crm configure show type:op_defaults
pcs # pcs resource op defaults
## Set operation defaults
crmsh # crm configure op_defaults timeout=240s
pcs # pcs resource op defaults timeout=240s
## Set Colocation
crmsh # crm configure colocation website-with-ip INFINITY: WebSite ClusterIP
pcs # pcs constraint colocation add ClusterIP with WebSite INFINITY
With roles
crmsh # crm configure colocation another-ip-with-website inf: AnotherIP WebSite:Master
pcs # pcs constraint colocation add Started AnotherIP with Master WebSite INFINITY
## Set ordering
crmsh # crm configure order apache-after-ip mandatory: ClusterIP WebSite
pcs # pcs constraint order ClusterIP then WebSite
With roles:
crmsh # crm configure order ip-after-website Mandatory: WebSite:Master AnotherIP
pcs # pcs constraint order promote WebSite then start AnotherIP
## Set preferred location
crmsh # crm configure location prefer-pcmk-1 WebSite 50: pcmk-1
pcs # pcs constraint location WebSite prefers pcmk-1=50
With roles:
crmsh # crm configure location prefer-pcmk-1 WebSite rule role=Master 50: \#uname eq pcmk-1
pcs # pcs constraint location WebSite rule role=master 50 \#uname eq pcmk-1
## Move resources
crmsh # crm resource move WebSite pcmk-1
pcs # pcs resource move WebSite pcmk-1
crmsh # crm resource unmove WebSite
pcs # pcs resource clear WebSite
A resource can also be moved away from a given node:
crmsh # crm resource ban Website pcmk-2
pcs # pcs resource ban Website pcmk-2
Remember that moving a resource sets a stickyness to -INF to a given node until unmoved
## Resource tracing
crmsh # crm resource trace Website
## Clear fail counts
crmsh # crm resource cleanup Website
pcs # pcs resource cleanup Website
## Edit fail counts
crmsh # crm resource failcount Website show pcmk-1
crmsh # crm resource failcount Website set pcmk-1 100
## Handling configuration elements by type
pcs deals with constraints differently. These can be manipulated by the command above as well as the following and others
pcs # pcs constraint list --full
pcs # pcs constraint remove cli-ban-Website-on-pcmk-1
Removing a constraint in crmsh uses the same command as removing a
resource.
crmsh # crm configure remove cli-ban-Website-on-pcmk-1
The `show` and `edit` commands in crmsh can be used to manage
resources and constraints by type:
crmsh # crm configure show type:primitive
crmsh # crm configure edit type:colocation
## Create a clone
crmsh # crm configure clone WebIP ClusterIP meta globally-unique=true clone-max=2 clone-node-max=2
pcs # pcs resource clone ClusterIP globally-unique=true clone-max=2 clone-node-max=2
## Create a master/slave clone
crmsh # crm configure ms WebDataClone WebData \
meta master-max=1 master-node-max=1 \
clone-max=2 clone-node-max=1 notify=true
pcs # pcs resource master WebDataClone WebData \
master-max=1 master-node-max=1 \
clone-max=2 clone-node-max=1 notify=true
# Other operations
## Batch changes
crmsh # crm
crmsh # cib new drbd_cfg
crmsh # configure primitive WebData ocf:linbit:drbd params drbd_resource=wwwdata \
op monitor interval=60s
crmsh # configure ms WebDataClone WebData meta master-max=1 master-node-max=1 \
clone-max=2 clone-node-max=1 notify=true
crmsh # cib commit drbd_cfg
crmsh # quit
.
pcs # pcs cluster cib drbd_cfg
pcs # pcs -f drbd_cfg resource create WebData ocf:linbit:drbd drbd_resource=wwwdata \
op monitor interval=60s
pcs # pcs -f drbd_cfg resource master WebDataClone WebData master-max=1 master-node-max=1 \
clone-max=2 clone-node-max=1 notify=true
pcs # pcs cluster push cib drbd_cfg
## Template creation
Create a resource template based on a list of primitives of the same
type
crmsh # crm configure assist template ClusterIP AdminIP
## Log analysis
Display information about recent cluster events
crmsh # crm history
crmsh # peinputs
crmsh # transition pe-input-10
crmsh # transition log pe-input-10
## Configuration scripts
Create and apply multiple-step cluster configurations including
configuration of cluster resources
crmsh # crm script show apache
crmsh # crm script run apache \
id=WebSite \
install=true \
virtual-ip:ip=192.168.0.15 \
database:id=WebData \
database:install=true