summaryrefslogtreecommitdiffstats
path: root/extraconfig/tasks/yum_update.sh
blob: 4ca0b1400903d8568091bc25c1e22a59d89a78d3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
#!/bin/bash

# A heat-config-script which runs yum update during a stack-update.
# Inputs:
#   deploy_action - yum will only be run if this is UPDATE
#   update_identifier - yum will only run for previously unused values of update_identifier
#   command - yum sub-command to run, defaults to "update"
#   command_arguments - yum command arguments, defaults to ""

echo "Started yum_update.sh on server $deploy_server_id at `date`"
echo -n "false" > $heat_outputs_path.update_managed_packages

if [[ -z "$update_identifier" ]]; then
    echo "Not running due to unset update_identifier"
    exit 0
fi

timestamp_dir=/var/lib/overcloud-yum-update
mkdir -p $timestamp_dir

# sanitise to remove unusual characters
update_identifier=${update_identifier//[^a-zA-Z0-9-_]/}

# seconds to wait for this node to rejoin the cluster after update
cluster_start_timeout=600
galera_sync_timeout=1800
cluster_settle_timeout=1800

timestamp_file="$timestamp_dir/$update_identifier"
if [[ -a "$timestamp_file" ]]; then
    echo "Not running for already-run timestamp \"$update_identifier\""
    exit 0
fi
touch "$timestamp_file"

command_arguments=${command_arguments:-}

list_updates=$(yum list updates)

if [[ "$list_updates" == "" ]]; then
    echo "No packages require updating"
    exit 0
fi

pacemaker_status=$(systemctl is-active pacemaker)

# Fix the redis/rabbit resource start/stop timeouts. See https://bugs.launchpad.net/tripleo/+bug/1633455
# and https://bugs.launchpad.net/tripleo/+bug/1634851
if [[ "$pacemaker_status" == "active" && \
      "$(hiera -c /etc/puppet/hiera.yaml bootstrap_nodeid)" = "$(facter hostname)" ]] ; then
    if pcs resource show rabbitmq | grep -E "start.*timeout=100"; then
        pcs resource update rabbitmq op start timeout=200s
    fi
    if pcs resource show rabbitmq | grep -E "stop.*timeout=90"; then
        pcs resource update rabbitmq op stop timeout=200s
    fi
    if pcs resource show redis | grep -E "start.*timeout=120"; then
        pcs resource update redis op start timeout=200s
    fi
    if pcs resource show redis | grep -E "stop.*timeout=120"; then
        pcs resource update redis op stop timeout=200s
    fi
fi


if [[ "$pacemaker_status" == "active" ]] ; then
    echo "Pacemaker running, stopping cluster node and doing full package update"
    node_count=$(pcs status xml | grep -o "<nodes_configured.*/>" | grep -o 'number="[0-9]*"' | grep -o "[0-9]*")
    if [[ "$node_count" == "1" ]] ; then
        echo "Active node count is 1, stopping node with --force"
        pcs cluster stop --force
    else
        pcs cluster stop
    fi
else
    echo "Upgrading openstack-puppet-modules"
    yum -q -y update openstack-puppet-modules
    echo "Upgrading other packages is handled by config management tooling"
    echo -n "true" > $heat_outputs_path.update_managed_packages
    exit 0
fi


# Special-case OVS for https://bugs.launchpad.net/tripleo/+bug/1635205
if [[ -n $(rpm -q --scripts openvswitch | awk '/postuninstall/,/*/' | grep "systemctl.*try-restart") ]]; then
    echo "Manual upgrade of openvswitch - restart in postun detected"
    mkdir OVS_UPGRADE || true
    pushd OVS_UPGRADE
    echo "Attempting to downloading latest openvswitch with yumdownloader"
    yumdownloader --resolve openvswitch
    echo "Updating openvswitch with nopostun"
    rpm -U --nopostun ./*.rpm
    popd
else
    echo "Skipping manual upgrade of openvswitch - no restart in postun detected"
fi

command=${command:-update}
full_command="yum -q -y $command $command_arguments"
echo "Running: $full_command"

result=$($full_command)
return_code=$?
echo "$result"
echo "yum return code: $return_code"

if [[ "$pacemaker_status" == "active" ]] ; then
    echo "Starting cluster node"
    pcs cluster start

    hostname=$(hostname -s)
    tstart=$(date +%s)
    while [[ "$(pcs status | grep "^Online" | grep -F -o $hostname)" == "" ]]; do
        sleep 5
        tnow=$(date +%s)
        if (( tnow-tstart > cluster_start_timeout )) ; then
            echo "ERROR $hostname failed to join cluster in $cluster_start_timeout seconds"
            pcs status
            exit 1
        fi
    done

    tstart=$(date +%s)
    while ! clustercheck; do
        sleep 5
        tnow=$(date +%s)
        if (( tnow-tstart > galera_sync_timeout )) ; then
            echo "ERROR galera sync timed out"
            exit 1
        fi
    done

    echo "Waiting for pacemaker cluster to settle"
    if ! timeout -k 10 $cluster_settle_timeout crm_resource --wait; then
        echo "ERROR timed out while waiting for the cluster to settle"
        exit 1
    fi

    pcs status
fi

echo "Finished yum_update.sh on server $deploy_server_id at `date`"

exit $return_code