seasharp
/
anvil
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

* Added a check to fence_pacemaker that exits with 7 if the target node is already out of the pacemaker cluster.

Browse Source 
* Verified that the logic works in a 3-node (Anvil! + DR) cluster.

Signed-off-by: Digimer <digimer@alteeve.ca>
main
Digimer 7 years ago
parent 26f956e429
commit 6405483fea
2 changed files with 242 additions and 191 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 355
      notes
  2. 78
      tools/fence_pacemaker

355
notes
Unescape View File

@ -33,46 +33,39 @@ Bridge
* STP=no is default, we'll test 'yes'. * STP=no is default, we'll test 'yes'.
* DOMAIN="<client_domain>" * DOMAIN="<client_domain>"
# Network Setup
hostnamectl set-hostname m3-a02n01.alteeve.com --static
hostnamectl set-hostname --pretty "Alteeve's Niche! - Anvil! 02, Node 01"
hostname m3-a02n01.alteeve.com
ssh-keygen -t rsa -N "" -b 8191 -f ~/.ssh/id_rsa
hosts:
====
10.1.20.1 m3-a02n01.bcn m3-a02n01 m3-a02n01.alteeve.com
10.41.20.1 m3-a02n01.sn
10.255.20.1 m3-a02n01.ifn
10.1.20.2 m3-a02n02.bcn m3-a02n02 m3-a02n02.alteeve.com
10.41.20.2 m3-a02n02.sn
10.255.20.2 m3-a02n02.ifn
10.1.20.3 m3-a02dr01.bcn m3-a02dr01 m3-a02dr01.alteeve.com
10.41.20.3 m3-a02dr01.sn
10.255.20.3 m3-a02dr01.ifn
====
Example Link config: Example Link config:
==== ====
HWADDR="52:54:00:D4:54:4F" # The MAC address of the interface that this file configures
UUID="e054949f-5e47-34de-ad75-9c5b61cc24df" # Unique identifier for this interface
DEVICE="bcn1_link1" # The interface device name. This sets a consistent name for the HWADDR device.
NAME="BCN 1 - Link 1" # The name is used in some network config tools. It doesn't effect anything functional
ONBOOT="yes" # Start the interface on boot
USERCTL="no" # Disable user control
BOOTPROTO="none" # Set no IP
MTU="1500" # MTU size in bytes
DEFROUTE="no" # Do not route through this interface
NM_CONTROLLED="yes" # Let Network Manager control this interface
SLAVE="yes" # Sets this interface as a bonding slave
MASTER="bcn1_bond1" # This is the device name of the bond we're slaved to
TYPE="Ethernet" # Set this as an ethernet device
IPV6INIT="no" # Disable IPv6
==== ====
Example Bonding config: Example Bonding config:
==== ====
# Back-Channel Network - Bond 1
UUID="954e6b64-534c-4eeb-ba42-d7fd6adab8c6"
DEVICE="bcn1_bond1"
NAME="BCN 1 - Bond 1"
BONDING_OPTS="mode=active-backup primary=bcn1_link1 updelay=120000 downdelay=0 miimon=100 primary_reselect=better"
TYPE="Bond"
BONDING_MASTER="yes"
BOOTPROTO="none"
IPV6INIT="no"
ONBOOT="yes"
IPADDR="10.1.10.1"
PREFIX="16"
DEFROUTE="no"
==== ====
Example Bridge config: Example Bridge config:
===== =====
===== =====
======= =======
virt-manager stores information in dconf-editor -> /org/virt-manager/virt-manager/connections ($HOME/.config/dconf/user) virt-manager stores information in dconf-editor -> /org/virt-manager/virt-manager/connections ($HOME/.config/dconf/user)
@ -83,7 +76,6 @@ virt-manager stores information in dconf-editor -> /org/virt-manager/virt-manage
==== ====
### Setup - Striker ### Setup - Striker
# Packages # Packages
@ -138,19 +130,23 @@ clear; journalctl -f -a -S "$(date +"%F %R:%S")" -t anvil
** subscription-manager repos --enable=rhel-ha-for-rhel-7-server-rpms ** subscription-manager repos --enable=rhel-ha-for-rhel-7-server-rpms
** subscription-manager repos --enable=rhel-7-server-optional-rpms ** subscription-manager repos --enable=rhel-7-server-optional-rpms
* Packages to install; * Packages to install;
** bash-completion bind-utils bridge-utils fence-agents-all fence-agents-virsh gpm kernel-doc libvirt libvirt-daemon libvirt-daemon-driver-qemu libvirt-daemon-kvm libvirt-docs mlocate pacemaker pcs perl-Data-Dumper perl-XML-Simple qemu-kvm qemu-kvm-common qemu-kvm-tools rsync vim virt-install
rpm -Uvh https://www.alteeve.com/an-repo/el7/alteeve-el7-repo-0.1-1.noarch.rpm
yum install bash-completion bind-utils bridge-utils drbd drbd-bash-completion drbd-kernel drbd-utils fence-agents-all fence-agents-virsh gpm kernel-doc kmod-drbd libvirt libvirt-daemon libvirt-daemon-driver-qemu libvirt-daemon-kvm libvirt-docs mlocate pacemaker pcs perl-Data-Dumper perl-XML-Simple qemu-kvm qemu-kvm-common qemu-kvm-tools rsync vim virt-install
* Packages to remove; * Packages to remove;
** biosdevname yum remove biosdevname
* For now only;
** rpm -Uvh https://www.alteeve.com/an-repo/el7/alteeve-el7-repo-0.1-1.noarch.rpm
** rpm -Uvh https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm
* Service management; * Service management;
** systemctl start gpm.service systemctl start gpm.service
* Network; * Network;
** {bc,if,s}nX_{link,bond,bridge}Y naming ** {bc,if,s}nX_{link,bond,bridge}Y naming
** firewall; - https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/7/html/high_availability_add-on_reference/s1-firewalls-haar ** firewall; - https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/7/html/high_availability_add-on_reference/s1-firewalls-haar
*** firewall-cmd --permanent --add-service=high-availability firewall-cmd --permanent --add-service=high-availability
*** firewall-cmd --add-service=high-availability firewall-cmd --add-service=high-availability
firewall-cmd --reload
* Cluster Config; * Cluster Config;
==== Both nodes ==== Both nodes
echo Initial1 | passwd hacluster --stdin echo Initial1 | passwd hacluster --stdin
@ -169,12 +165,10 @@ pcs stonith create virsh_node1 fence_virsh pcmk_host_list="m3-a01n01" ipaddr="19
pcs stonith create virsh_node2 fence_virsh pcmk_host_list="m3-a01n02" ipaddr="192.168.122.1" passwd="secret" login="root" port="m3-a01n02" op monitor interval="60" pcs stonith create virsh_node2 fence_virsh pcmk_host_list="m3-a01n02" ipaddr="192.168.122.1" passwd="secret" login="root" port="m3-a01n02" op monitor interval="60"
pcs resource create hypervisor systemd:libvirtd op monitor interval=60 pcs resource create hypervisor systemd:libvirtd op monitor interval=60
pcs resource create drbd systemd:drbd op monitor interval=60
pcs resource clone hypervisor clone-max=2 notify="false" pcs resource clone hypervisor clone-max=2 notify="false"
pcs resource clone drbd clone-max=2 notify="false"
pcs resource create drbd systemd:drbd op monitor interval=60
pcs resource clone drbd clone-max=2 notify="false"
stonith_admin --fence m3-a01n02 --verbose; crm_error $? stonith_admin --fence m3-a01n02 --verbose; crm_error $?
@ -215,7 +209,7 @@ Provisioning a server will need to:
* Open up a DRBD port (or more, if multiple resources are created). * Open up a DRBD port (or more, if multiple resources are created).
* Create the DRBD resource(s); Find the lowest free rX.res, create it locally and on the peer (if up), * Create the DRBD resource(s); Find the lowest free rX.res, create it locally and on the peer (if up),
firewall-cmd --zone=public --permanent --add-port=7788/tcp firewall-cmd --zone=public --permanent --add-port=7788-7790/tcp
firewall-cmd --reload firewall-cmd --reload
* Provision the server via virt-install * Provision the server via virt-install
@ -243,144 +237,32 @@ r0 node-id:1 role:Primary suspended:no
[root@m3-a01n02 ~]# drbdadm primary r0 [root@m3-a01n02 ~]# drbdadm primary r0
r0: State change failed: (-1) Multiple primaries not allowed by config r0: State change failed: (-1) Multiple primaries not allowed by config
Command 'drbdsetup primary r0' terminated with exit code 11 Command 'drbdsetup primary r0' terminated with exit code 11
[root@m3-a01n02 ~]# drbdadm net-options --allow-two-primaries=yes r0 [root@m3-a01n02 ~]# drbdadm net-options --allow-two-primaries=yes r0
[root@m3-a01n02 ~]# drbdadm primary r0
[root@m3-a01n02 ~]# drbdadm net-options --allow-two-primaries=no r0 [root@m3-a01n02 ~]# drbdadm net-options --allow-two-primaries=no r0
[root@m3-a01n01 drbd.d]# drbdsetup show all drbdsetup show all
resource r0 { drbdsetup show all --show-defaults
_this_host {
node-id 1;
volume 0 {
device minor 0;
disk "/dev/new-node1_vg0/test";
meta-disk internal;
disk {
disk-flushes no;
md-flushes no;
}
}
}
connection {
_peer_node_id 0;
path {
_this_host ipv4 10.41.10.1:7788;
_remote_host ipv4 10.41.10.2:7788;
}
net {
after-sb-0pri discard-zero-changes;
after-sb-1pri discard-secondary;
data-integrity-alg "md5";
csums-alg "md5";
_name "m3-a01n02.alteeve.com";
}
}
}
[root@m3-a01n01 drbd.d]# drbdsetup show all --show-defaults
resource r0 {
options {
cpu-mask ""; # default
on-no-data-accessible io-error; # default
auto-promote yes; # default
peer-ack-window 4096s; # bytes, default
peer-ack-delay 100; # milliseconds, default
twopc-timeout 300; # 1/10 seconds, default
twopc-retry-timeout 1; # 1/10 seconds, default
auto-promote-timeout 20; # 1/10 seconds, default
max-io-depth 8000; # default
quorum off; # default
on-no-quorum suspend-io; # default
quorum-minimum-redundancy off; # default
}
_this_host {
node-id 1;
volume 0 {
device minor 0;
disk "/dev/new-node1_vg0/test";
meta-disk internal;
disk {
size 0s; # bytes, default
on-io-error detach; # default
disk-barrier no; # default
disk-flushes no;
disk-drain yes; # default
md-flushes no;
resync-after -1; # default
al-extents 1237; # default
al-updates yes; # default
discard-zeroes-if-aligned yes; # default
disable-write-same no; # default
disk-timeout 0; # 1/10 seconds, default
read-balancing prefer-local; # default
rs-discard-granularity 0; # bytes, default
}
}
}
connection {
_peer_node_id 0;
path {
_this_host ipv4 10.41.10.1:7788;
_remote_host ipv4 10.41.10.2:7788;
}
net {
transport ""; # default
protocol C; # default
timeout 60; # 1/10 seconds, default
max-epoch-size 2048; # default
connect-int 10; # seconds, default
ping-int 10; # seconds, default
sndbuf-size 0; # bytes, default
rcvbuf-size 0; # bytes, default
ko-count 7; # default
allow-two-primaries no; # default
cram-hmac-alg ""; # default
shared-secret ""; # default
after-sb-0pri discard-zero-changes;
after-sb-1pri discard-secondary;
after-sb-2pri disconnect; # default
always-asbp no; # default
rr-conflict disconnect; # default
ping-timeout 5; # 1/10 seconds, default
data-integrity-alg "md5";
tcp-cork yes; # default
on-congestion block; # default
congestion-fill 0s; # bytes, default
congestion-extents 1237; # default
csums-alg "md5";
csums-after-crash-only no; # default
verify-alg ""; # default
use-rle yes; # default
socket-check-timeout 0; # default
fencing dont-care; # default
max-buffers 2048; # default
_name "m3-a01n02.alteeve.com";
}
volume 0 {
disk {
resync-rate 250k; # bytes/second, default
c-plan-ahead 20; # 1/10 seconds, default
c-delay-target 10; # 1/10 seconds, default
c-fill-target 100s; # bytes, default
c-max-rate 102400k; # bytes/second, default
c-min-rate 250k; # bytes/second, default
bitmap yes; # default
}
}
}
}
== virt-install stuff == virt-install stuff
* Get a list of --os-variants: 'osinfo-query os' * Get a list of --os-variants: 'osinfo-query os'
* virt-install --print-xml (or --transient) * virt-install --print-xml (or --transient)
* Migate; * Migate;
# For all resources under the server; # For all resources under the server;
drbdadm net-options r0 --allow-two-primaries=yes #drbdadm net-options r0 --allow-two-primaries=yes
drbdsetup net-options srv01-c7_0 2 --_name=m3-a02n01.alteeve.com --csums-alg=md5 --data-integrity-alg=md5 --after-sb-0pri=discard-zero-changes --after-sb-1pri=discard-secondary --after-sb-2pri=disconnect --protocol=C --fencing=resource-and-stonith --allow-two-primaries=yes
drbdsetup net-options srv01-c7_0 2 --_name=m3-a02n01.alteeve.com --csums-alg=md5 --data-integrity-alg=md5 --after-sb-0pri=discard-zero-changes --after-sb-1pri=discard-secondary --after-sb-2pri=disconnect --protocol=C --fencing=resource-and-stonith --allow-two-primaries=yes
# Migrate: # Migrate:
virsh migrate --unsafe --undefinesource --live srv01-c7 qemu+ssh://m3-a01n02.alteeve.com/system virsh migrate --unsafe --undefinesource --live srv01-c7 qemu+ssh://m3-a01n02.alteeve.com/system
# Again for all resource under the server; # Again for all resource under the server;
drbdadm net-options r0 --allow-two-primaries=no drbdadm net-options r0 --allow-two-primaries=no
drbdsetup net-options <resource> <target_node_id> --_name=<target_node_name> --allow-two-primaries=yes
virsh migrate --undefinesource --live <server> qemu+ssh://<target_node>/system
drbdsetup net-options <resource> <target_node_id> --_name=<target_node_name> --allow-two-primaries=no
Set to 90% of BCN bandwidth Set to 90% of BCN bandwidth
migrate-setspeed domain bandwidth migrate-setspeed domain bandwidth
Set the maximum migration bandwidth (in MiB/s) for a domain which is being migrated to another host. bandwidth is interpreted as an Set the maximum migration bandwidth (in MiB/s) for a domain which is being migrated to another host. bandwidth is interpreted as an
@ -390,8 +272,147 @@ Set to 90% of BCN bandwidth
migrate-getspeed domain migrate-getspeed domain
Get the maximum migration bandwidth (in MiB/s) for a domain. Get the maximum migration bandwidth (in MiB/s) for a domain.
==== /etc/drbd.d/global_common.conf
# DRBD is the result of over a decade of development by LINBIT.
# In case you need professional services for DRBD or have
# feature requests visit http://www.linbit.com
global {
usage-count yes;
# Decide what kind of udev symlinks you want for "implicit" volumes
# (those without explicit volume <vnr> {} block, implied vnr=0):
# /dev/drbd/by-resource/<resource>/<vnr> (explicit volumes)
# /dev/drbd/by-resource/<resource> (default for implict)
udev-always-use-vnr; # treat implicit the same as explicit volumes
# minor-count dialog-refresh disable-ip-verification
# cmd-timeout-short 5; cmd-timeout-medium 121; cmd-timeout-long 600;
}
common {
handlers {
# These are EXAMPLE handlers only.
# They may have severe implications,
# like hard resetting the node under certain circumstances.
# Be careful when choosing your poison.
# pri-on-incon-degr "/usr/lib/drbd/notify-pri-on-incon-degr.sh; /usr/lib/drbd/notify-emergency-reboot.sh; echo b > /proc/sysrq-trigger ; reboot -f";
# pri-lost-after-sb "/usr/lib/drbd/notify-pri-lost-after-sb.sh; /usr/lib/drbd/notify-emergency-reboot.sh; echo b > /proc/sysrq-trigger ; reboot -f";
# local-io-error "/usr/lib/drbd/notify-io-error.sh; /usr/lib/drbd/notify-emergency-shutdown.sh; echo o > /proc/sysrq-trigger ; halt -f";
# fence-peer "/usr/lib/drbd/crm-fence-peer.sh";
# split-brain "/usr/lib/drbd/notify-split-brain.sh root";
# out-of-sync "/usr/lib/drbd/notify-out-of-sync.sh root";
# before-resync-target "/usr/lib/drbd/snapshot-resync-target-lvm.sh -p 15 -- -c 16k";
# after-resync-target /usr/lib/drbd/unsnapshot-resync-target-lvm.sh;
# quorum-lost "/usr/lib/drbd/notify-quorum-lost.sh root";
fence-peer "/usr/sbin/fence_pacemaker";
}
startup {
# wfc-timeout degr-wfc-timeout outdated-wfc-timeout wait-after-sb
}
options {
# cpu-mask on-no-data-accessible
# RECOMMENDED for three or more storage nodes with DRBD 9:
# quorum majority;
# on-no-quorum suspend-io | io-error;
auto-promote yes;
}
disk {
# size on-io-error fencing disk-barrier disk-flushes
# disk-drain md-flushes resync-rate resync-after al-extents
# c-plan-ahead c-delay-target c-fill-target c-max-rate
# c-min-rate disk-timeout
disk-flushes no;
md-flushes no;
}
net {
# protocol timeout max-epoch-size max-buffers
# connect-int ping-int sndbuf-size rcvbuf-size ko-count
# allow-two-primaries cram-hmac-alg shared-secret after-sb-0pri
# after-sb-1pri after-sb-2pri always-asbp rr-conflict
# ping-timeout data-integrity-alg tcp-cork on-congestion
# congestion-fill congestion-extents csums-alg verify-alg
# use-rle
# This computes an md5 sum of the block before replicating/synchronizing and skips if it matches already.
# This can help with increasing replication/sync speed in some cases, but at the cost of CPU time. We may
# disable this (or make it user-changable).
csums-alg md5;
# Use md5 sums to verify replicated data. More CPU overhead, but safer.
data-integrity-alg md5;
# We'll override this just before a migration as needed.
allow-two-primaries no;
# Traditional split-brain handling.
after-sb-0pri discard-zero-changes;
after-sb-1pri discard-secondary;
after-sb-2pri disconnect;
}
}
====
==== cat /etc/drbd.d/srv01-c7_0.res
# Server srv01-c7 Disk 0
resource srv01-c7_0 {
device /dev/drbd0;
meta-disk internal;
on m3-a02n01.alteeve.com {
node-id 0;
disk /dev/node01_vg0/srv01-c7;
}
on m3-a02n02.alteeve.com {
node-id 1;
disk /dev/node02_vg0/srv01-c7;
}
on m3-a02dr01.alteeve.com {
node-id 2;
disk /dev/dr01_vg0/srv01-c7;
}
connection {
host m3-a02n01.alteeve.com address 10.41.20.1:7788;
host m3-a02n02.alteeve.com address 10.41.20.2:7788;
net {
protocol C;
fencing resource-and-stonith;
}
}
connection {
host m3-a02n01.alteeve.com address 10.41.20.1:7789;
host m3-a02dr01.alteeve.com address 10.41.20.3:7789;
net {
protocol A;
fencing dont-care;
}
}
connection {
host m3-a02n02.alteeve.com address 10.41.20.2:7790;
host m3-a02dr01.alteeve.com address 10.41.20.3:7790;
net {
protocol A;
fencing dont-care;
}
}
}
====
# Provision servers
mkdir /mnt/anvil/{provision,files,archive,definitions}
pcs resource create srv01-c7 ocf:heartbeat:VirtualDomain hypervisor="qemu:///system" config="/mnt/anvil/definitions/srv01-c7.xml" meta allow-migrate="true" op monitor interval="10"
== Resource Agent; https://github.com/ClusterLabs/resource-agents/blob/master/doc/dev-guides/ra-dev-guide.asc == Resource Agent; https://github.com/ClusterLabs/resource-agents/blob/master/doc/dev-guides/ra-dev-guide.asc
* A resource agent receives all configuration information about the resource it manages via environment variables. The names of these environment variables are always the name of the resource parameter, prefixed with OCF_RESKEY_. For example, if the resource has an ip parameter set to 192.168.1.1, then the resource agent will have access to an environment variable OCF_RESKEY_ip holding that value. * A resource agent receives all configuration information about the resource it manages via environment variables. The names of these environment variables are always the name of the resource parameter, prefixed with OCF_RESKEY_. For example, if the resource has an ip parameter set to 192.168.1.1, then the resource agent will have access to an environment variable OCF_RESKEY_ip holding that value.
* *

78
tools/fence_pacemaker
Unescape View File

@ -107,6 +107,12 @@ my $conf = {
}, },
}; };
# Find executables.
find_executables($conf);
# Something for the logs
to_log($conf, {message => "Attempting to fence the peer via pacemaker's stonith...", 'line' => __LINE__});
# These are the full host names of the nodes given their IDs. # These are the full host names of the nodes given their IDs.
foreach my $i (0..31) foreach my $i (0..31)
{ {
@ -118,21 +124,16 @@ foreach my $i (0..31)
} }
} }
# Find executables.
find_executables($conf);
# Something for the logs
to_log($conf, {message => "Attempting to fence the peer via pacemaker's stonith...", 'line' => __LINE__});
### TESTING - Simulate a call from node 1 against node 2 ### TESTING - Simulate a call from node 1 against node 2
$conf->{environment}{DRBD_NODE_ID_0} = "m3-a01n02.alteeve.com"; # $conf->{environment}{DRBD_NODE_ID_0} = "m3-a02n01.alteeve.com";
$conf->{environment}{DRBD_NODE_ID_1} = "m3-a01n01.alteeve.com"; # $conf->{environment}{DRBD_NODE_ID_1} = "m3-a02n02.alteeve.com";
$conf->{environment}{DRBD_MINOR} = "0"; # $conf->{environment}{DRBD_NODE_ID_2} = "m3-a02dr01.alteeve.com";
$conf->{environment}{DRBD_MY_NODE_ID} = "1"; # $conf->{environment}{DRBD_MINOR} = "0";
$conf->{environment}{DRBD_PEER_ADDRESS} = "10.41.10.2"; # $conf->{environment}{DRBD_MY_NODE_ID} = "0";
$conf->{environment}{DRBD_PEER_AF} = "ipv4"; # $conf->{environment}{DRBD_PEER_NODE_ID} = "1";
$conf->{environment}{DRBD_PEER_NODE_ID} = "0"; # $conf->{environment}{DRBD_PEER_ADDRESS} = "10.41.20.2";
$conf->{environment}{DRBD_RESOURCE} = "r0"; # $conf->{environment}{DRBD_PEER_AF} = "ipv4";
# $conf->{environment}{DRBD_RESOURCE} = "srv01-c7_0";
### TESTING ### TESTING
# Record the environment variables # Record the environment variables
@ -210,7 +211,7 @@ sub get_drbd_status
to_log($conf, {message => "resource: [$resource], peer: [$peer]", 'line' => __LINE__, level => 2}); to_log($conf, {message => "resource: [$resource], peer: [$peer]", 'line' => __LINE__, level => 2});
next; next;
} }
if ($line ~= /^(\S+)\s+role/) if ($line =~ /^(\S+)\s+role/)
{ {
$resource = $1; $resource = $1;
to_log($conf, {message => "resource: [$resource]", 'line' => __LINE__, level => 2}); to_log($conf, {message => "resource: [$resource]", 'line' => __LINE__, level => 2});
@ -226,7 +227,8 @@ sub get_drbd_status
{ {
if ($line =~ /disk:(.*)$/) if ($line =~ /disk:(.*)$/)
{ {
my $local_dstate = $1; my $local_dstate = $1;
$local_dstate =~ s/\s.*$//;
to_log($conf, {message => "local_dstate: [$local_dstate]", 'line' => __LINE__, level => 2}); to_log($conf, {message => "local_dstate: [$local_dstate]", 'line' => __LINE__, level => 2});
if (lc($local_dstate) ne "uptodate") if (lc($local_dstate) ne "uptodate")
{ {
@ -237,7 +239,8 @@ sub get_drbd_status
} }
if ($line =~ /peer-disk:(.*)$/) if ($line =~ /peer-disk:(.*)$/)
{ {
my $peer_dstate = $1; my $peer_dstate = $1;
$peer_dstate =~ s/\s.*$//;
to_log($conf, {message => "peer_dstate: [$peer_dstate]", 'line' => __LINE__, level => 2}); to_log($conf, {message => "peer_dstate: [$peer_dstate]", 'line' => __LINE__, level => 2});
if (lc($peer_dstate) ne "uptodate") if (lc($peer_dstate) ne "uptodate")
{ {
@ -254,6 +257,7 @@ sub get_drbd_status
to_log($conf, {message => "Return code: [$return_code]", 'line' => __LINE__, level => 2}); to_log($conf, {message => "Return code: [$return_code]", 'line' => __LINE__, level => 2});
# If we're not all UpToDate, but the peer is, abort # If we're not all UpToDate, but the peer is, abort
to_log($conf, {message => "local_all_uptodate: [$local_all_uptodate], peer_all_uptodate: [$peer_all_uptodate]", 'line' => __LINE__, level => 2});
if ((not $local_all_uptodate) && ($peer_all_uptodate)) if ((not $local_all_uptodate) && ($peer_all_uptodate))
{ {
# We're not good # We're not good
@ -335,7 +339,8 @@ sub identify_peer
} }
close $file_handle; close $file_handle;
my $return_code = $?; my $return_code = $?;
to_log($conf, {message => "Return code: [$return_code]", 'line' => __LINE__, level => 2}); to_log($conf, {message => "Return code: [$return_code]", 'line' => __LINE__, level => 3});
to_log($conf, {message => "cib: ==========\n$cib\n==========", 'line' => __LINE__, level => 3});
# Now parse the CIB XML if I read it OK. # Now parse the CIB XML if I read it OK.
to_log($conf, {message => "xml_opened: [$xml_opened], xml_closed: [$xml_closed].", 'line' => __LINE__, level => 2}); to_log($conf, {message => "xml_opened: [$xml_opened], xml_closed: [$xml_closed].", 'line' => __LINE__, level => 2});
@ -349,9 +354,9 @@ sub identify_peer
{ {
chomp $@; chomp $@;
my $error = "[ Error ] - The was a problem parsing: [$cib]. The error was:\n"; my $error = "[ Error ] - The was a problem parsing: [$cib]. The error was:\n";
$error .= "===========================================================\n"; $error .= "===========================================================\n";
$error .= $@."\n"; $error .= $@."\n";
$error .= "===========================================================\n"; $error .= "===========================================================\n";
to_log($conf, {message => $error, 'line' => __LINE__, level => 0, priority => "err"}); to_log($conf, {message => $error, 'line' => __LINE__, level => 0, priority => "err"});
exit(1); exit(1);
} }
@ -360,7 +365,7 @@ sub identify_peer
# Parse the XML. # Parse the XML.
my $host_name = $ENV{HOSTNAME}; my $host_name = $ENV{HOSTNAME};
my $short_host_name = $ENV{HOSTNAME}; my $short_host_name = $ENV{HOSTNAME};
$short_host_name =~ s/\..*$//; $short_host_name =~ s/\..*$//;
#print "XML body: [$body]\n"; #print "XML body: [$body]\n";
foreach my $key (sort {$a cmp $b} keys %{$body}) foreach my $key (sort {$a cmp $b} keys %{$body})
@ -393,7 +398,6 @@ sub identify_peer
exit(1); exit(1);
} }
} }
#print Dumper $hash_ref;
} }
} }
@ -404,6 +408,32 @@ sub identify_peer
to_log($conf, {message => "This not is not quorate. Refusing to fence the peer!", 'line' => __LINE__, level => 0, priority => "err"}); to_log($conf, {message => "This not is not quorate. Refusing to fence the peer!", 'line' => __LINE__, level => 0, priority => "err"});
exit(1); exit(1);
} }
# If I have a target node, see if it is already out of the cluster.
if ($conf->{cluster}{target_node})
{
foreach my $hash_ref (@{$body->{status}{node_state}})
{
my $node = $hash_ref->{uname};
my $join = $hash_ref->{'join'};
my $expected = $hash_ref->{expected};
to_log($conf, {message => "node: [$node] join: [$join], expected: [$expected]", 'line' => __LINE__, level => 2});
if ($node eq $conf->{cluster}{target_node})
{
to_log($conf, {message => "Checking the status of target node: [$node].", 'line' => __LINE__, level => 1});
if (($join eq "down") && ($expected eq "down"))
{
# The node is out.
to_log($conf, {message => "The node: [$node] is already down. No actual fence needed.", 'line' => __LINE__, level => 1});
exit(7);
}
else
{
to_log($conf, {message => "The node: [$node] is: [$join/$expected] (join/expected). Proceeding with the fence action.", 'line' => __LINE__, level => 1});
}
}
}
}
} }
} }
else else
@ -632,7 +662,7 @@ sub to_log
# Clean up the string for bash # Clean up the string for bash
$message =~ s/"/\\\"/gs; $message =~ s/"/\\\"/gs;
$message =~ s/\(/\\\(/gs; #$message =~ s/\(/\\\(/gs;
my $shell_call = $conf->{path}{exe}{logger}." --priority ".$priority_string." --tag ".$conf->{'log'}{tag}." -- \"".$message."\""; my $shell_call = $conf->{path}{exe}{logger}." --priority ".$priority_string." --tag ".$conf->{'log'}{tag}." -- \"".$message."\"";
open (my $file_handle, $shell_call." 2>&1 |") or die "Failed to call: [".$shell_call."]. The error was: $!\n"; open (my $file_handle, $shell_call." 2>&1 |") or die "Failed to call: [".$shell_call."]. The error was: $!\n";

Write Preview
Loading…
Cancel
Save