diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Active-Active.xml b/doc/Clusters_from_Scratch/en-US/Ch-Active-Active.xml
index f655447e2a..329cfd7178 100644
--- a/doc/Clusters_from_Scratch/en-US/Ch-Active-Active.xml
+++ b/doc/Clusters_from_Scratch/en-US/Ch-Active-Active.xml
@@ -1,722 +1,721 @@
%BOOK_ENTITIES;
]>
Conversion to Active/Active
Requirements
The primary requirement for an Active/Active cluster is that the data required for your services are available, simultaneously, on both machines.
Pacemaker makes no requirement on how this is achieved, you could use a SAN if you had one available, however since DRBD supports multiple Primaries, we can also use that.
The only hitch is that we need to use a cluster-aware filesystem (and the one we used earlier with DRBD, ext4, is not one of those).
Both OCFS2 and GFS2 are supported, however here we will use GFS2 which comes with &DISTRO; &DISTRO_VERSION; .
Install a Cluster Filesystem - GFS2
The first thing to do is install gfs2-utils on each machine.
[root@pcmk-1 ~]# yum install -y gfs2-utils gfs-pcmk
Setting up Install Process
Resolving Dependencies
--> Running transaction check
---> Package gfs-pcmk.x86_64 0:3.0.5-2.fc12 set to be updated
--> Processing Dependency: libSaCkpt.so.3(OPENAIS_CKPT_B.01.01)(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64
--> Processing Dependency: dlm-pcmk for package: gfs-pcmk-3.0.5-2.fc12.x86_64
--> Processing Dependency: libccs.so.3()(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64
--> Processing Dependency: libdlmcontrol.so.3()(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64
--> Processing Dependency: liblogthread.so.3()(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64
--> Processing Dependency: libSaCkpt.so.3()(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64
---> Package gfs2-utils.x86_64 0:3.0.5-2.fc12 set to be updated
--> Running transaction check
---> Package clusterlib.x86_64 0:3.0.5-2.fc12 set to be updated
---> Package dlm-pcmk.x86_64 0:3.0.5-2.fc12 set to be updated
---> Package openaislib.x86_64 0:1.1.0-1.fc12 set to be updated
--> Finished Dependency Resolution
Dependencies Resolved
===========================================================================================
Package Arch Version Repository Size
===========================================================================================
Installing:
gfs-pcmk x86_64 3.0.5-2.fc12 custom 101 k
gfs2-utils x86_64 3.0.5-2.fc12 custom 208 k
Installing for dependencies:
clusterlib x86_64 3.0.5-2.fc12 custom 65 k
dlm-pcmk x86_64 3.0.5-2.fc12 custom 93 k
openaislib x86_64 1.1.0-1.fc12 fedora 76 k
Transaction Summary
===========================================================================================
Install 5 Package(s)
Upgrade 0 Package(s)
Total download size: 541 k
Downloading Packages:
(1/5): clusterlib-3.0.5-2.fc12.x86_64.rpm | 65 kB 00:00
(2/5): dlm-pcmk-3.0.5-2.fc12.x86_64.rpm | 93 kB 00:00
(3/5): gfs-pcmk-3.0.5-2.fc12.x86_64.rpm | 101 kB 00:00
(4/5): gfs2-utils-3.0.5-2.fc12.x86_64.rpm | 208 kB 00:00
(5/5): openaislib-1.1.0-1.fc12.x86_64.rpm | 76 kB 00:00
-------------------------------------------------------------------------------------------
Total 992 kB/s | 541 kB 00:00
Running rpm_check_debug
Running Transaction Test
Finished Transaction Test
Transaction Test Succeeded
Running Transaction
Installing : clusterlib-3.0.5-2.fc12.x86_64 1/5
Installing : openaislib-1.1.0-1.fc12.x86_64 2/5
Installing : dlm-pcmk-3.0.5-2.fc12.x86_64 3/5
Installing : gfs-pcmk-3.0.5-2.fc12.x86_64 4/5
Installing : gfs2-utils-3.0.5-2.fc12.x86_64 5/5
Installed:
gfs-pcmk.x86_64 0:3.0.5-2.fc12 gfs2-utils.x86_64 0:3.0.5-2.fc12
Dependency Installed:
clusterlib.x86_64 0:3.0.5-2.fc12 dlm-pcmk.x86_64 0:3.0.5-2.fc12
openaislib.x86_64 0:1.1.0-1.fc12
Complete!
[root@pcmk-1 x86_64]#
If this step fails, it is likely that your version/distribution does not ship the "Pacemaker" versions of dlm_controld and/or gfs_controld.
Normally these files would be called dlm_controld.pcmk and gfs_controld.pcmk and live in the /usr/sbin directory.
If you cannot locate an installation source for these files, you will need to install a package called cman and reconfigure Corosync to use it as outlined in .
When using CMAN, you can skip where dlm-clone and gfs-clone are created, and proceed directly to .
Setup Pacemaker-GFS2 Integration
GFS2 needs two services to be running, the first is the user-space interface to the kernel’s distributed lock manager (DLM). The DLM is used to co-ordinate which node(s) can access a given file (and when) and integrates with Pacemaker to obtain node membership
The list of nodes the cluster considers to be available
information and fencing capabilities.
The second service is GFS2’s own control daemon which also integrates with Pacemaker to obtain node membership data.
Add the DLM service
The DLM control daemon needs to run on all active cluster nodes, so we will use the shells interactive mode to create a cloned resource.
[root@pcmk-1 ~]# crm
crm(live)# cib new stack-glue
INFO: stack-glue shadow CIB created
crm(stack-glue)# configure primitive dlm ocf:pacemaker:controld op monitor interval=120s
crm(stack-glue)# configure clone dlm-clone dlm meta interleave=true
crm(stack-glue)# configure show xml
crm(stack-glue)# configure show
node pcmk-1
node pcmk-2
primitive WebData ocf:linbit:drbd \
params drbd_resource="wwwdata" \
op monitor interval="60s"
primitive WebFS ocf:heartbeat:Filesystem \
params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype="ext4"
primitive WebSite ocf:heartbeat:apache \
params configfile="/etc/httpd/conf/httpd.conf" \
op monitor interval="1min"
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip="192.168.122.101" cidr_netmask="32" \
op monitor interval="30s"
primitive dlm ocf:pacemaker:controld \
op monitor interval="120s"
ms WebDataClone WebData \
meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
clone dlm-clone dlm \
meta interleave="true"
location prefer-pcmk-1 WebSite 50: pcmk-1
colocation WebSite-with-WebFS inf: WebSite WebFS
colocation fs_on_drbd inf: WebFS WebDataClone:Master
colocation website-with-ip inf: WebSite ClusterIP
order WebFS-after-WebData inf: WebDataClone:promote WebFS:start
order WebSite-after-WebFS inf: WebFS WebSite
order apache-after-ip inf: ClusterIP WebSite
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes=”2” \
stonith-enabled="false" \
no-quorum-policy="ignore"
rsc_defaults $id="rsc-options" \
resource-stickiness=”100”
TODO: Explain the meaning of the interleave option
Review the configuration before uploading it to the cluster, quitting the shell and watching the cluster’s response
crm(stack-glue)# cib commit stack-glue
INFO: commited 'stack-glue' shadow CIB to the cluster
crm(stack-glue)# quit
bye
[root@pcmk-1 ~]# crm_mon
============
Last updated: Thu Sep 3 20:49:54 2009
Stack: openais
Current DC: pcmk-2 - partition with quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
5 Resources configured.
============
Online: [ pcmk-1 pcmk-2 ]
WebSite (ocf::heartbeat:apache): Started pcmk-2
Master/Slave Set: WebDataClone
Masters: [ pcmk-1 ]
Slaves: [ pcmk-2 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-2
Clone Set: dlm-clone
Started: [ pcmk-2 pcmk-1 ]
WebFS (ocf::heartbeat:Filesystem): Started pcmk-2
Add the GFS2 service
Once the DLM is active, we can add the GFS2 control daemon.
Use the crm shell to create the gfs-control cluster resource:
[root@pcmk-1 ~]# crm
crm(live)# cib new gfs-glue --force
INFO: gfs-glue shadow CIB created
crm(gfs-glue)# configure primitive gfs-control ocf:pacemaker:controld params daemon=gfs_controld.pcmk args="-g 0" op monitor interval=120s
crm(gfs-glue)# configure clone gfs-clone gfs-control meta interleave=true
Now ensure Pacemaker only starts the gfs-control service on nodes that also have a copy of the dlm service (created above) already running
crm(gfs-glue)# configure colocation gfs-with-dlm INFINITY: gfs-clone dlm-clone
crm(gfs-glue)# configure order start-gfs-after-dlm mandatory: dlm-clone gfs-clone
Review the configuration before uploading it to the cluster, quitting the shell and watching the cluster’s response
crm(gfs-glue)# configure show
node pcmk-1
node pcmk-2
primitive WebData ocf:linbit:drbd \
params drbd_resource="wwwdata" \
op monitor interval="60s"
primitive WebFS ocf:heartbeat:Filesystem \
params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype="ext4"
primitive WebSite ocf:heartbeat:apache \
params configfile="/etc/httpd/conf/httpd.conf" \
op monitor interval="1min"
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip="192.168.122.101" cidr_netmask="32" \
op monitor interval="30s"
primitive dlm ocf:pacemaker:controld \
op monitor interval="120s"
primitive gfs-control ocf:pacemaker:controld \
params daemon=”gfs_controld.pcmk” args=”-g 0” \
op monitor interval="120s"
ms WebDataClone WebData \
meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
clone dlm-clone dlm \
meta interleave="true"
clone gfs-clone gfs-control \
meta interleave="true"
location prefer-pcmk-1 WebSite 50: pcmk-1
colocation WebSite-with-WebFS inf: WebSite WebFS
colocation fs_on_drbd inf: WebFS WebDataClone:Master
colocation gfs-with-dlm inf: gfs-clone dlm-clone
colocation website-with-ip inf: WebSite ClusterIP
order WebFS-after-WebData inf: WebDataClone:promote WebFS:start
order WebSite-after-WebFS inf: WebFS WebSite
order apache-after-ip inf: ClusterIP WebSite
order start-gfs-after-dlm inf: dlm-clone gfs-clone
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes=”2” \
stonith-enabled="false" \
no-quorum-policy="ignore"
rsc_defaults $id="rsc-options" \
resource-stickiness=”100”
crm(gfs-glue)# cib commit gfs-glue
INFO: commited 'gfs-glue' shadow CIB to the cluster
crm(gfs-glue)# quit
bye
[root@pcmk-1 ~]# crm_mon
============
Last updated: Thu Sep 3 20:49:54 2009
Stack: openais
Current DC: pcmk-2 - partition with quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
6 Resources configured.
============
Online: [ pcmk-1 pcmk-2 ]
WebSite (ocf::heartbeat:apache): Started pcmk-2
Master/Slave Set: WebDataClone
Masters: [ pcmk-1 ]
Slaves: [ pcmk-2 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-2
Clone Set: dlm-clone
Started: [ pcmk-2 pcmk-1 ]
Clone Set: gfs-clone
Started: [ pcmk-2 pcmk-1 ]
WebFS (ocf::heartbeat:Filesystem): Started pcmk-1
Create a GFS2 Filesystem
Preparation
Before we do anything to the existing partition, we need to make sure it is unmounted. We do this by tell the cluster to stop the WebFS resource. This will ensure that other resources (in our case, Apache) using WebFS are not only stopped, but stopped in the correct order.
[root@pcmk-1 ~]# crm_resource --resource WebFS --set-parameter target-role --meta --parameter-value Stopped
[root@pcmk-1 ~]# crm_mon
============
Last updated: Thu Sep 3 15:18:06 2009
Stack: openais
Current DC: pcmk-1 - partition with quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
6 Resources configured.
============
Online: [ pcmk-1 pcmk-2 ]
Master/Slave Set: WebDataClone
Masters: [ pcmk-1 ]
Slaves: [ pcmk-2 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-1
Clone Set: dlm-clone
Started: [ pcmk-2 pcmk-1 ]
Clone Set: gfs-clone
Started: [ pcmk-2 pcmk-1 ]
Note that both Apache and WebFS have been stopped.
Create and Populate an GFS2 Partition
Now that the cluster stack and integration pieces are running smoothly, we can create an GFS2 partition.
This will erase all previous content stored on the DRBD device. Ensure you have a copy of any important data.
We need to specify a number of additional parameters when creating a GFS2 partition.
First we must use the -p option to specify that we want to use the the Kernel’s DLM. Next we use -j to indicate that it should reserve enough space for two journals (one per node accessing the filesystem).
Lastly, we use -t to specify the lock table name. The format for this field is clustername:fsname. For the fsname, we just need to pick something unique and descriptive and since we haven’t specified a clustername yet, we will use the default (pcmk).
To specify an alternate name for the cluster, locate the service section containing “name: pacemaker” in corosync.conf and insert the following line anywhere inside the block:
clustername: myname
Do this on each node in the cluster and be sure to restart them before continuing.
-mkfs.gfs2 -p lock_dlm -j 2 -t pcmk:web /dev/drbd1
-[root@pcmk-1 ~]# mkfs.gfs2 -t pcmk:web -p lock_dlm -j 2 /dev/vdb
-This will destroy any data on /dev/vdb.
+[root@pcmk-1 ~]# mkfs.gfs2 -p lock_dlm -j 2 -t pcmk:web /dev/drbd1
+This will destroy any data on /dev/drbd1.
It appears to contain: data
Are you sure you want to proceed? [y/n] y
-Device: /dev/vdb
+Device: /dev/drbd1
Blocksize: 4096
Device Size 1.00 GB (131072 blocks)
Filesystem Size: 1.00 GB (131070 blocks)
Journals: 2
Resource Groups: 2
Locking Protocol: "lock_dlm"
Lock Table: "pcmk:web"
UUID: 6B776F46-177B-BAF8-2C2B-292C0E078613
[root@pcmk-1 ~]#
Then (re)populate the new filesystem with data (web pages). For now we’ll create another variation on our home page.
[root@pcmk-1 ~]# mount /dev/drbd1 /mnt/
[root@pcmk-1 ~]# cat <<-END >/mnt/index.html
<html>
<body>My Test Site - GFS2</body>
</html>
END
[root@pcmk-1 ~]# umount /dev/drbd1
[root@pcmk-1 ~]# drbdadm verify wwwdata
[root@pcmk-1 ~]#
Reconfigure the Cluster for GFS2
[root@pcmk-1 ~]# crm
crm(live)# cib new GFS2
INFO: GFS2 shadow CIB created
crm(GFS2)# configure delete WebFS
crm(GFS2)# configure primitive WebFS ocf:heartbeat:Filesystem params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2”
Now that we’ve recreated the resource, we also need to recreate all the constraints that used it. This is because the shell will automatically remove any constraints that referenced WebFS.
crm(GFS2)# configure colocation WebSite-with-WebFS inf: WebSite WebFS
crm(GFS2)# configure colocation fs_on_drbd inf: WebFS WebDataClone:Master
crm(GFS2)# configure order WebFS-after-WebData inf: WebDataClone:promote WebFS:start
crm(GFS2)# configure order WebSite-after-WebFS inf: WebFS WebSite
crm(GFS2)# configure colocation WebFS-with-gfs-control INFINITY: WebFS gfs-clone
crm(GFS2)# configure order start-WebFS-after-gfs-control mandatory: gfs-clone WebFS
crm(GFS2)# configure show
node pcmk-1
node pcmk-2
primitive WebData ocf:linbit:drbd \
params drbd_resource="wwwdata" \
op monitor interval="60s"
primitive WebFS ocf:heartbeat:Filesystem \
params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2”
primitive WebSite ocf:heartbeat:apache \
params configfile="/etc/httpd/conf/httpd.conf" \
op monitor interval="1min"
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip="192.168.122.101" cidr_netmask="32" \
op monitor interval="30s"
primitive dlm ocf:pacemaker:controld \
op monitor interval="120s"
primitive gfs-control ocf:pacemaker:controld \
params daemon=”gfs_controld.pcmk” args=”-g 0” \
op monitor interval="120s"
ms WebDataClone WebData \
meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
clone dlm-clone dlm \
meta interleave="true"
clone gfs-clone gfs-control \
meta interleave="true"
colocation WebFS-with-gfs-control inf: WebFS gfs-clone
colocation WebSite-with-WebFS inf: WebSite WebFS
colocation fs_on_drbd inf: WebFS WebDataClone:Master
colocation gfs-with-dlm inf: gfs-clone dlm-clone
colocation website-with-ip inf: WebSite ClusterIP
order WebFS-after-WebData inf: WebDataClone:promote WebFS:start
order WebSite-after-WebFS inf: WebFS WebSite
order apache-after-ip inf: ClusterIP WebSite
order start-WebFS-after-gfs-control inf: gfs-clone WebFS
order start-gfs-after-dlm inf: dlm-clone gfs-clone
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes=”2” \
stonith-enabled="false" \
no-quorum-policy="ignore"
rsc_defaults $id="rsc-options" \
resource-stickiness=”100”
Review the configuration before uploading it to the cluster, quitting the shell and watching the cluster’s response
crm(GFS2)# cib commit GFS2
INFO: commited 'GFS2' shadow CIB to the cluster
crm(GFS2)# quit
bye
[root@pcmk-1 ~]# crm_mon
============
Last updated: Thu Sep 3 20:49:54 2009
Stack: openais
Current DC: pcmk-2 - partition with quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
6 Resources configured.
============
Online: [ pcmk-1 pcmk-2 ]
WebSite (ocf::heartbeat:apache): Started pcmk-2
Master/Slave Set: WebDataClone
Masters: [ pcmk-1 ]
Slaves: [ pcmk-2 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-2
Clone Set: dlm-clone
Started: [ pcmk-2 pcmk-1 ]
Clone Set: gfs-clone
Started: [ pcmk-2 pcmk-1 ]
WebFS (ocf::heartbeat:Filesystem): Started pcmk-1
Reconfigure Pacemaker for Active/Active
Almost everything is in place.
Recent versions of DRBD are capable of operating in Primary/Primary mode and the filesystem we’re using is cluster aware.
All we need to do now is reconfigure the cluster to take advantage of this.
This will involve a number of changes, so we’ll again use interactive mode.
[root@pcmk-1 ~]# crm
[root@pcmk-1 ~]# cib new active
There’s no point making the services active on both locations if we can’t reach them, so lets first clone the IP address.
Cloned IPaddr2 resources use an iptables rule to ensure that each request only processed by one of the two clone instances.
The additional meta options tell the cluster how many instances of the clone we want (one “request bucket” for each node) and that if all other nodes fail, then the remaining node should hold all of them.
Otherwise the requests would be simply discarded.
[root@pcmk-1 ~]# configure clone WebIP ClusterIP \
meta globally-unique=”true” clone-max=”2” clone-node-max=”2”
Now we must tell the ClusterIP how to decide which requests are processed by which hosts.
To do this we must specify the clusterip_hash parameter.
Open the ClusterIP resource
[root@pcmk-1 ~]# configure edit ClusterIP
And add the following to the params line
clusterip_hash="sourceip"
So that the complete definition looks like:
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip="192.168.122.101" cidr_netmask="32" clusterip_hash="sourceip" \
op monitor interval="30s"
Here is the full transcript
[root@pcmk-1 ~]# crm
crm(live)# cib new active
INFO: active shadow CIB created
crm(active)# configure clone WebIP ClusterIP \
meta globally-unique=”true” clone-max=”2” clone-node-max=”2”
crm(active)# configure show
node pcmk-1
node pcmk-2
primitive WebData ocf:linbit:drbd \
params drbd_resource="wwwdata" \
op monitor interval="60s"
primitive WebFS ocf:heartbeat:Filesystem \
params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2”
primitive WebSite ocf:heartbeat:apache \
params configfile="/etc/httpd/conf/httpd.conf" \
op monitor interval="1min"
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip=”192.168.122.101” cidr_netmask=”32” clusterip_hash=”sourceip” \
op monitor interval="30s"
primitive dlm ocf:pacemaker:controld \
op monitor interval="120s"
primitive gfs-control ocf:pacemaker:controld \
params daemon=”gfs_controld.pcmk” args=”-g 0” \
op monitor interval="120s"
ms WebDataClone WebData \
meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
clone WebIP ClusterIP \
meta globally-unique=”true” clone-max=”2” clone-node-max=”2”
clone dlm-clone dlm \
meta interleave="true"
clone gfs-clone gfs-control \
meta interleave="true"
colocation WebFS-with-gfs-control inf: WebFS gfs-clone
colocation WebSite-with-WebFS inf: WebSite WebFS
colocation fs_on_drbd inf: WebFS WebDataClone:Master
colocation gfs-with-dlm inf: gfs-clone dlm-clone
colocation website-with-ip inf: WebSite WebIP
order WebFS-after-WebData inf: WebDataClone:promote WebFS:start
order WebSite-after-WebFS inf: WebFS WebSite
order apache-after-ip inf: WebIP WebSite
order start-WebFS-after-gfs-control inf: gfs-clone WebFS
order start-gfs-after-dlm inf: dlm-clone gfs-clone
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes=”2” \
stonith-enabled="false" \
no-quorum-policy="ignore"
rsc_defaults $id="rsc-options" \
resource-stickiness=”100”
Notice how any constraints that referenced ClusterIP have been updated to use WebIP instead.
This is an additional benefit of using the crm shell.
Next we need to convert the filesystem and Apache resources into clones.
Again, the shell will automatically update any relevant constraints.
crm(active)# configure clone WebFSClone WebFS
crm(active)# configure clone WebSiteClone WebSite
The last step is to tell the cluster that it is now allowed to promote both instances to be Primary (aka. Master).
crm(active)# configure edit WebDataClone
Change master-max to 2
crm(active)# configure show
node pcmk-1
node pcmk-2
primitive WebData ocf:linbit:drbd \
params drbd_resource="wwwdata" \
op monitor interval="60s"
primitive WebFS ocf:heartbeat:Filesystem \
params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2”
primitive WebSite ocf:heartbeat:apache \
params configfile="/etc/httpd/conf/httpd.conf" \
op monitor interval="1min"
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip=”192.168.122.101” cidr_netmask=”32” clusterip_hash=”sourceip” \
op monitor interval="30s"
primitive dlm ocf:pacemaker:controld \
op monitor interval="120s"
primitive gfs-control ocf:pacemaker:controld \
params daemon=”gfs_controld.pcmk” args=”-g 0” \
op monitor interval="120s"
ms WebDataClone WebData \
meta master-max="2" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
clone WebFSClone WebFS
clone WebIP ClusterIP \
meta globally-unique=”true” clone-max=”2” clone-node-max=”2”
clone WebSiteClone WebSite
clone dlm-clone dlm \
meta interleave="true"
clone gfs-clone gfs-control \
meta interleave="true"
colocation WebFS-with-gfs-control inf: WebFSClone gfs-clone
colocation WebSite-with-WebFS inf: WebSiteClone WebFSClone
colocation fs_on_drbd inf: WebFSClone WebDataClone:Master
colocation gfs-with-dlm inf: gfs-clone dlm-clone
colocation website-with-ip inf: WebSiteClone WebIP
order WebFS-after-WebData inf: WebDataClone:promote WebFSClone:start
order WebSite-after-WebFS inf: WebFSClone WebSiteClone
order apache-after-ip inf: WebIP WebSiteClone
order start-WebFS-after-gfs-control inf: gfs-clone WebFSClone
order start-gfs-after-dlm inf: dlm-clone gfs-clone
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes=”2” \
stonith-enabled="false" \
no-quorum-policy="ignore"
rsc_defaults $id="rsc-options" \
resource-stickiness=”100”
Review the configuration before uploading it to the cluster, quitting the shell and watching the cluster’s response
crm(active)# cib commit active
INFO: commited 'active' shadow CIB to the cluster
crm(active)# quit
bye
[root@pcmk-1 ~]# crm_mon
============
Last updated: Thu Sep 3 21:37:27 2009
Stack: openais
Current DC: pcmk-2 - partition with quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
6 Resources configured.
============
Online: [ pcmk-1 pcmk-2 ]
Master/Slave Set: WebDataClone
Masters: [ pcmk-1 pcmk-2 ]
Clone Set: dlm-clone
Started: [ pcmk-2 pcmk-1 ]
Clone Set: gfs-clone
Started: [ pcmk-2 pcmk-1 ]
Clone Set: WebIP
Started: [ pcmk-1 pcmk-2 ]
Clone Set: WebFSClone
Started: [ pcmk-1 pcmk-2 ]
Clone Set: WebSiteClone
Started: [ pcmk-1 pcmk-2 ]
Testing Recovery
TODO: Put one node into standby to demonstrate failover
diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.xml b/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.xml
index 593a9c5d5a..29197d2bc4 100644
--- a/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.xml
+++ b/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.xml
@@ -1,408 +1,408 @@
%BOOK_ENTITIES;
]>
Creating an Active/Passive Cluster
Exploring 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.
This is what the base configuration should look like.
[root@pcmk-2 ~]# crm configure show
node pcmk-1
node pcmk-2
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2"
For those that are not of afraid of XML, you can see the raw configuration by appending “xml” to the previous command.
[root@pcmk-2 ~]# crm configure show xml
<?xml version="1.0" ?>
<cib admin_epoch="0" crm_feature_set="3.0.1" dc-uuid="pcmk-1" epoch="13" have-quorum="1" num_updates="7" validate-with="pacemaker-1.0">
<configuration>
<crm_config>
<cluster_property_set id="cib-bootstrap-options">
<nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f"/>
<nvpair id="cib-bootstrap-options-cluster-infrastructure" name="cluster-infrastructure" value="openais"/>
<nvpair id="cib-bootstrap-options-expected-quorum-votes" name="expected-quorum-votes" value="2"/>
</cluster_property_set>
</crm_config>
<rsc_defaults/>
<op_defaults/>
<nodes>
<node id="pcmk-1" type="normal" uname="pcmk-1"/>
<node id="pcmk-2" type="normal" uname="pcmk-2"/>
</nodes>
<resources/>
<constraints/>
</configuration>
</cib>
The last XML you’ll see in this document
Before we make any changes, its a good idea to check the validity of the configuration.
[root@pcmk-1 ~]# crm_verify -L
crm_verify[2195]: 2009/08/27_16:57:12 ERROR: unpack_resources: Resource start-up disabled since no STONITH resources have been defined
crm_verify[2195]: 2009/08/27_16:57:12 ERROR: unpack_resources: Either configure some or disable STONITH with the stonith-enabled option
crm_verify[2195]: 2009/08/27_16:57:12 ERROR: unpack_resources: NOTE: Clusters with shared data need STONITH to ensure data integrity
Errors found during check: config not valid
-V may provide more details
[root@pcmk-1 ~]#
As you can see, the tool has found some errors.
In order to guarantee the safety of your data
If the data is corrupt, there is little point in continuing to make it available
, Pacemaker ships with STONITH
A common node fencing mechanism. Used to ensure data integrity by powering off “bad” nodes.
enabled. However it also knows when no STONITH configuration has been supplied and reports this as a problem (since the cluster would not be able to make progress if a situation requiring node fencing arose).
For now, we will disable this feature and configure it later in the Configuring STONITH section. It is important to note that the use of STONITH is highly encouraged, turning it off tells the cluster to simply pretend that failed nodes are safely powered off. Some vendors will even refuse to support clusters that have it disabled.
To disable STONITH, we set the stonith-enabled cluster option to false.
crm configure property stonith-enabled=false
crm_verify -L
With the new cluster option set, the configuration is now valid.
The use of stonith-enabled=false is completely inappropriate for a production cluster.
We use it here to defer the discussion of its configuration which can differ widely from one installation to the next.
See for information on why STONITH is important and details on how to configure it.
Adding a Resource
The first thing we should do is configure an IP address. Regardless of where the cluster service(s) are running, we need a consistent address to contact them on. Here I will choose and add 192.168.122.101 as the floating address, give it the imaginative name ClusterIP and tell the cluster to check that its running every 30 seconds.
The chosen address must not be one already associated with a physical node
crm configure primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip=192.168.122.101 cidr_netmask=32 \
op monitor interval=30s
The other 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, is the standard to which the resource script conforms to and where to find it. The second field is specific to OCF resources and tells the cluster which namespace to find the resource script in, in this case heartbeat. The last field indicates the name of the resource script.
To obtain a list of the available resource classes, run
[root@pcmk-1 ~]# crm ra classes
heartbeat
lsb
ocf / heartbeat pacemaker
stonith
To then find all the OCF resource agents provided by Pacemaker and Heartbeat, run
[root@pcmk-1 ~]# crm ra list ocf pacemaker
ClusterMon Dummy Stateful SysInfo SystemHealth controld
ping pingd
[root@pcmk-1 ~]# crm ra list ocf heartbeat
AoEtarget AudibleAlarm ClusterMon Delay
Dummy EvmsSCC Evmsd Filesystem
ICP IPaddr IPaddr2 IPsrcaddr
LVM LinuxSCSI MailTo ManageRAID
ManageVE Pure-FTPd Raid1 Route
SAPDatabase SAPInstance SendArp ServeRAID
SphinxSearchDaemon Squid Stateful SysInfo
VIPArip VirtualDomain WAS WAS6
WinPopup Xen Xinetd anything
apache db2 drbd eDir88
iSCSILogicalUnit iSCSITarget ids iscsi
ldirectord mysql mysql-proxy nfsserver
oracle oralsnr pgsql pingd
portblock rsyncd scsi2reservation sfex
tomcat vmware
[root@pcmk-1 ~]#
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 ~]# crm configure show
node pcmk-1
node pcmk-2
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip="192.168.122.101" cidr_netmask="32" \
op monitor interval="30s"
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false" \
[root@pcmk-1 ~]# crm_mon
============
Last updated: Fri Aug 28 15:23:48 2009
Stack: openais
Current DC: pcmk-1 - partition with quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ pcmk-1 pcmk-2 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-1
Perform a Failover
Being a high-availability cluster, 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 ~]# crm resource status ClusterIP
resource ClusterIP is running on: pcmk-1
[root@pcmk-1 ~]#
Shut down Pacemaker and Corosync on that machine.
[root@pcmk-1 ~]# ssh pcmk-1 -- /etc/init.d/pacemaker stop
Signaling Pacemaker Cluster Manager to terminate: [ OK ]
Waiting for cluster services to unload:. [ OK ]
[root@pcmk-1 ~]# ssh pcmk-1 -- /etc/init.d/corosync stop
Stopping Corosync Cluster Engine (corosync): [ OK ]
Waiting for services to unload: [ OK ]
[root@pcmk-1 ~]#
Once Corosync is no longer running, go to the other node and check the cluster status with crm_mon.
[root@pcmk-2 ~]# crm_mon
============
Last updated: Fri Aug 28 15:27:35 2009
Stack: openais
Current DC: pcmk-2 - partition WITHOUT quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ pcmk-2 ]
OFFLINE: [ pcmk-1 ]
There are three things to notice about the cluster’s current state. The first is that, as expected, pcmk-1 is now offline. However we can also see that ClusterIP isn’t running anywhere!
Quorum and Two-Node Clusters
This is because the cluster no longer has quorum, as can be seen by the text “partition WITHOUT quorum” (emphasised green) in the output above. In order to reduce the possibility of data corruption, Pacemaker’s default behavior is to stop all resources if the cluster does not have quorum.
A cluster is said to have quorum when more than half the known or expected nodes are online, or for the mathematically inclined, whenever the following equation is true:
total_nodes < 2 * active_nodes
Therefore a two-node cluster only has quorum when both nodes are running, which is no longer the case for our cluster. This would normally make the creation of a two-node cluster pointless
Actually some would argue that two-node clusters are always pointless, but that is an argument for another time.
, however it is possible to control how Pacemaker behaves when quorum is lost. In particular, we can tell the cluster to simply ignore quorum altogether.
[root@pcmk-1 ~]# crm configure property no-quorum-policy=ignore
[root@pcmk-1 ~]# crm configure show
node pcmk-1
node pcmk-2
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip="192.168.122.101" cidr_netmask="32" \
op monitor interval="30s"
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false" \
no-quorum-policy="ignore"
After a few moments, the cluster will start the IP address on the remaining node. Note that the cluster still does not have quorum.
[root@pcmk-2 ~]# crm_mon
============
Last updated: Fri Aug 28 15:30:18 2009
Stack: openais
Current DC: pcmk-2 - partition WITHOUT quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ pcmk-2 ]
OFFLINE: [ pcmk-1 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-2
Now simulate node recovery by restarting the cluster stack on pcmk-1 and check the cluster’s status.
[root@pcmk-1 ~]# /etc/init.d/corosync start
Starting Corosync Cluster Engine (corosync): [ OK ]
[root@pcmk-1 ~]# /etc/init.d/pacemaker start
Starting Pacemaker Cluster Manager: [ OK ]
[root@pcmk-1 ~]# crm_mon
============
Last updated: Fri Aug 28 15:32:13 2009
Stack: openais
Current DC: pcmk-2 - partition with quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ pcmk-1 pcmk-2 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-1
Here we see something that some may consider surprising, the IP is back running at its original location!
Prevent Resources from Moving after Recovery
In some circumstances it is highly desirable to prevent healthy resources from being moved around the cluster. Move resources almost always requires a period of downtime and for complex services like Oracle databases, this period can be quite long.
To address this, Pacemaker has the concept of resource stickiness which controls how much 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
It should be noted that 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 create implicit preferences (required in order to create a stabile solution) in situations where the administrator had not explicitly specified some.
” resource placement. We can specify a different stickiness for every resource, but it is often sufficient to change the default.
-crm configure rsc_defaults resource-stickiness=100
+[root@pcmk-2 ~]# crm configure rsc_defaults resource-stickiness=100
[root@pcmk-2 ~]# crm configure show
node pcmk-1
node pcmk-2
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip="192.168.122.101" cidr_netmask="32" \
op monitor interval="30s"
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false" \
no-quorum-policy="ignore"
rsc_defaults $id="rsc-options" \
resource-stickiness="100"
If we now retry the failover test, we see that as expected ClusterIP still moves to pcmk-2 when pcmk-1 is taken offline.
[root@pcmk-1 ~]# ssh pcmk-1 -- /etc/init.d/pacemaker stop
Signaling Pacemaker Cluster Manager to terminate: [ OK ]
Waiting for cluster services to unload:. [ OK ]
[root@pcmk-1 ~]# ssh pcmk-1 -- /etc/init.d/corosync stop
Stopping Corosync Cluster Engine (corosync): [ OK ]
Waiting for services to unload: [ OK ]
[root@pcmk-1 ~]# ssh pcmk-2 -- crm_mon -1
============
Last updated: Fri Aug 28 15:39:38 2009
Stack: openais
Current DC: pcmk-2 - partition WITHOUT quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ pcmk-2 ]
OFFLINE: [ pcmk-1 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-2
However when we bring pcmk-1 back online, ClusterIP now remains running on pcmk-2.
[root@pcmk-1 ~]# /etc/init.d/corosync start
Starting Corosync Cluster Engine (corosync): [ OK ]
[root@pcmk-1 ~]# /etc/init.d/pacemaker start
Starting Pacemaker Cluster Manager: [ OK ]
[root@pcmk-1 ~]# crm_mon
============
Last updated: Fri Aug 28 15:41:23 2009
Stack: openais
Current DC: pcmk-2 - partition with quorum
Version: 1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ pcmk-1 pcmk-2 ]
ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-2
diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Stonith.xml b/doc/Clusters_from_Scratch/en-US/Ch-Stonith.xml
index 5b88f4c69a..eb8d76f7bf 100644
--- a/doc/Clusters_from_Scratch/en-US/Ch-Stonith.xml
+++ b/doc/Clusters_from_Scratch/en-US/Ch-Stonith.xml
@@ -1,161 +1,160 @@
%BOOK_ENTITIES;
]>
Configure STONITH
Why You Need STONITH
STONITH is an acronym for Shoot-The-Other-Node-In-The-Head and it protects your data from being corrupted by rouge nodes or concurrent access.
Just because a node is unresponsive, this doesn’t mean it isn’t accessing your data. The only way to be 100% sure that your data is safe, is to use STONITH so we can be certain that the node is truly offline, before allowing the data to be accessed from another node.
STONITH also has a role to play in the event that a clustered service cannot be stopped. In this case, the cluster uses STONITH to force the whole node offline, thereby making it safe to start the service elsewhere.
What STONITH Device Should You Use
It is crucial that the STONITH device can allow the cluster to differentiate between a node failure and a network one.
The biggest mistake people make in choosing a STONITH device is to use remote power switch (such as many onboard IMPI controllers) that shares power with the node it controls. In such cases, the cluster cannot be sure if the node is really offline, or active and suffering from a network fault.
Likewise, any device that relies on the machine being active (such as SSH-based “devices” used during testing) are inappropriate.
Configuring STONITH
Find the correct driver: stonith -L
Since every device is different, the parameters needed to configure it will vary. To find out the parameters required by the device: stonith -t {type} -n
Hopefully the developers chose names that make sense, if not you can query for some additional information by finding an active cluster node and running:
lrmadmin -M stonith {type} pacemaker
The output should be XML formatted text containing additional parameter descriptions
Create a file called stonith.xml containing a primitive resource with a class of stonith, a type of {type} and a parameter for each of the values returned in step 2
Create a clone from the primitive resource if the device can shoot more than one node and supports multiple simultaneous connections.
Upload it into the CIB using cibadmin: cibadmin -C -o resources --xml-file stonith.xml
Example
Assuming we have an IBM BladeCenter containing our two nodes and the management interface is active on 192.168.122.31, then we would chose the external/ibmrsa driver in step 2 and obtain the following list of parameters
-stonith -t external/ibmrsa -n
[root@pcmk-1 ~]# stonith -t external/ibmrsa -n
hostname ipaddr userid passwd type
Assuming we know the username and password for the management interface, we would create a STONITH resource with the shell
[root@pcmk-1 ~]# crm
crm(live)# cib new stonith
INFO: stonith shadow CIB created
crm(stonith)# configure primitive rsa-fencing stonith::external/ibmrsa \
params hostname=”pcmk-1 pcmk-2" ipaddr=192.168.122.31 userid=mgmt passwd=abc123 type=ibm \
op monitor interval="60s"
crm(stonith)# configure clone Fencing rsa-fencing
And finally, since we disabled it earlier, we need to re-enable STONITH
crm(stonith)# configure property stonith-enabled="true"
crm(stonith)# configure show
node pcmk-1
node pcmk-2
primitive WebData ocf:linbit:drbd \
params drbd_resource="wwwdata" \
op monitor interval="60s"
primitive WebFS ocf:heartbeat:Filesystem \
params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2”
primitive WebSite ocf:heartbeat:apache \
params configfile="/etc/httpd/conf/httpd.conf" \
op monitor interval="1min"
primitive ClusterIP ocf:heartbeat:IPaddr2 \
params ip=”192.168.122.101” cidr_netmask=”32” clusterip_hash=”sourceip” \
op monitor interval="30s"
primitive dlm ocf:pacemaker:controld \
op monitor interval="120s"
primitive gfs-control ocf:pacemaker:controld \
params daemon=”gfs_controld.pcmk” args=”-g 0” \
op monitor interval="120s"
primitive rsa-fencing stonith::external/ibmrsa \
params hostname=”pcmk-1 pcmk-2" ipaddr=192.168.122.31 userid=mgmt passwd=abc123 type=ibm \
op monitor interval="60s"
ms WebDataClone WebData \
meta master-max="2" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
clone Fencing rsa-fencing
clone WebFSClone WebFS
clone WebIP ClusterIP \
meta globally-unique=”true” clone-max=”2” clone-node-max=”2”
clone WebSiteClone WebSite
clone dlm-clone dlm \
meta interleave="true"
clone gfs-clone gfs-control \
meta interleave="true"
colocation WebFS-with-gfs-control inf: WebFSClone gfs-clone
colocation WebSite-with-WebFS inf: WebSiteClone WebFSClone
colocation fs_on_drbd inf: WebFSClone WebDataClone:Master
colocation gfs-with-dlm inf: gfs-clone dlm-clone
colocation website-with-ip inf: WebSiteClone WebIP
order WebFS-after-WebData inf: WebDataClone:promote WebFSClone:start
order WebSite-after-WebFS inf: WebFSClone WebSiteClone
order apache-after-ip inf: WebIP WebSiteClone
order start-WebFS-after-gfs-control inf: gfs-clone WebFSClone
order start-gfs-after-dlm inf: dlm-clone gfs-clone
property $id="cib-bootstrap-options" \
dc-version="1.1.5-bdd89e69ba545404d02445be1f3d72e6a203ba2f" \
cluster-infrastructure="openais" \
expected-quorum-votes=”2” \
stonith-enabled="true" \
no-quorum-policy="ignore"
rsc_defaults $id="rsc-options" \
resource-stickiness=”100”