Switch to host names in integration tests (#950)

* Support host names in TLS certificates

This commit updates TLS certificate generator to detect if IP address or
host name was used as host value. If host name is detected field `DNSNames`
of x509 SAN extenstion is used instead of `IPAddresses`.

* https://en.wikipedia.org/wiki/Subject_Alternative_Name
* https://tools.ietf.org/html/rfc5280#section-4.2.1.6

This contributes towards fixing #337.

* Fix PD --peer-urls flag to use listen_host variable

This commit updates run_pd.sh template to use `listen_host` for
--peer-urls flag instead of `host`.

This allows us to use server hostname instead of IP addresse. Without
this change if PD service is declared using hostname it fails to start,
reporting an error that it can not bind to given interface.

Metadata variable `listen_host` was introduced in #495 and is already used for
the --client-urls flag.

This should resolve #337 and partially implement #691.

* Switch to host names in integration tests

This PR updates refactors integration tests to use host names instead of
IP addresses. It resolves #337.

All IP literals in the integration tests are replaced with host names
`n1` to `n5`.

This allows us to make integration test topology files immutable and
remove extra topology file templating step.

Extra topology file `full_scale_in_tidb_2nd.yaml` is introduced for
second tidb scaling operation to avoid topology file mutation during the
test.

Using host names in the integration tests will help us to maintain
compatibility with services declared using host names. There should be
no extra maintenance to support using IP addresses.

Co-authored-by: SIGSEGV <gnu.crazier@gmail.com>

tests/tiup-cluster/script/cmd_subtest.sh

@@ -6,15 +6,13 @@ function cmd_subtest() {
     version=$1
     test_tls=$2
     native_ssh=$3
-    ipprefix=${TIUP_TEST_IP_PREFIX:-"$ipprefix"}
 
     name="test_cmd_$RANDOM"
     if [ $test_tls = true ]; then
         topo=./topo/full_tls.yaml
     else
         topo=./topo/full.yaml
     fi
-    sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
 
     client=""
     if [ $native_ssh == true ]; then
@@ -41,9 +39,9 @@ function cmd_subtest() {
     tiup-cluster $client --yes deploy $name $version $topo -i ~/.ssh/id_rsa --skip-create-user
 
     # check the local config
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "grep magic-string-for-test /home/tidb/deploy/prometheus-9090/conf/tidb.rules.yml"
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "grep magic-string-for-test /home/tidb/deploy/grafana-3000/dashboards/tidb.json"
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "grep magic-string-for-test /home/tidb/deploy/alertmanager-9093/conf/alertmanager.yml"
+    tiup-cluster $client exec $name -N n1 --command "grep magic-string-for-test /home/tidb/deploy/prometheus-9090/conf/tidb.rules.yml"
+    tiup-cluster $client exec $name -N n1 --command "grep magic-string-for-test /home/tidb/deploy/grafana-3000/dashboards/tidb.json"
+    tiup-cluster $client exec $name -N n1 --command "grep magic-string-for-test /home/tidb/deploy/alertmanager-9093/conf/alertmanager.yml"
 
     tiup-cluster $client list | grep "$name"
 
@@ -59,9 +57,9 @@ function cmd_subtest() {
 
     # check the data dir of tikv
     # it's ok to omit client type after deploy
-    tiup-cluster exec $name -N $ipprefix.101 --command "grep /home/tidb/deploy/tikv-20160/data /home/tidb/deploy/tikv-20160/scripts/run_tikv.sh"
-    tiup-cluster exec $name -N $ipprefix.101 --command "grep advertise-status-addr /home/tidb/deploy/tikv-20160/scripts/run_tikv.sh"
-    tiup-cluster exec $name -N $ipprefix.103 --command "grep /home/tidb/my_kv_data /home/tidb/deploy/tikv-20160/scripts/run_tikv.sh"
+    tiup-cluster exec $name -N n1 --command "grep /home/tidb/deploy/tikv-20160/data /home/tidb/deploy/tikv-20160/scripts/run_tikv.sh"
+    tiup-cluster exec $name -N n1 --command "grep advertise-status-addr /home/tidb/deploy/tikv-20160/scripts/run_tikv.sh"
+    tiup-cluster exec $name -N n3 --command "grep /home/tidb/my_kv_data /home/tidb/deploy/tikv-20160/scripts/run_tikv.sh"
 
     # test patch overwrite
     tiup-cluster $client --yes patch $name ~/.tiup/storage/cluster/packages/tidb-$version-linux-amd64.tar.gz -R tidb --overwrite
@@ -95,11 +93,11 @@ function cmd_subtest() {
     tiup-cluster $client exec $name -R tidb --command="systemctl status tidb-4000|grep 'enabled;'"
     tiup-cluster $client exec $name -R pd --command="systemctl status pd-2379|grep 'enabled;'"
 
-    tiup-cluster $client --yes clean $name --data --all --ignore-node $ipprefix.101:9090
+    tiup-cluster $client --yes clean $name --data --all --ignore-node n1:9090
 
     echo "checking cleanup data and log"
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "ls /home/tidb/deploy/prometheus-9090/log/prometheus.log"
-    ! tiup-cluster $client exec $name -N $ipprefix.101 --command "ls /home/tidb/deploy/tikv-20160/log/tikv.log"
+    tiup-cluster $client exec $name -N n1 --command "ls /home/tidb/deploy/prometheus-9090/log/prometheus.log"
+    ! tiup-cluster $client exec $name -N n1 --command "ls /home/tidb/deploy/tikv-20160/log/tikv.log"
 
     tiup-cluster $client --yes start $name
 
@@ -109,6 +107,6 @@ function cmd_subtest() {
     tiup-cluster $client --yes destroy $name
 
     # after destroy the cluster, the public key should be deleted
-    ! ssh -o "StrictHostKeyChecking=no" -o "PasswordAuthentication=no" -i "/tmp/$name.id_rsa" tidb@$ipprefix.101 "ls"
+    ! ssh -o "StrictHostKeyChecking=no" -o "PasswordAuthentication=no" -i "/tmp/$name.id_rsa" tidb@n1 "ls"
     unlink "/tmp/$name.id_rsa"
 }

tests/tiup-cluster/script/scale_core.sh

@@ -6,7 +6,6 @@ function scale_core() {
     version=$1
     test_tls=$2
     native_ssh=$3
-    ipprefix=${TIUP_TEST_IP_PREFIX:-"172.19.0"}
 
     client=""
     if [ $native_ssh == true ]; then
@@ -19,7 +18,6 @@ function scale_core() {
     else
         topo=./topo/full.yaml
     fi
-    sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
 
     tiup-cluster $client --yes deploy $name $version $topo -i ~/.ssh/id_rsa
 
@@ -40,55 +38,51 @@ function scale_core() {
     fi
 
     echo "start scale in tidb"
-    tiup-cluster $client --yes scale-in $name -N $ipprefix.101:4000
+    tiup-cluster $client --yes scale-in $name -N n1:4000
     wait_instance_num_reach $name $total_sub_one $native_ssh
     echo "start scale out tidb"
     topo=./topo/full_scale_in_tidb.yaml
-    sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
     tiup-cluster $client --yes scale-out $name $topo
     # after scale-out, ensure the service is enabled
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "systemctl status tidb-4000 | grep Loaded |grep 'enabled; vendor'"
+    tiup-cluster $client exec $name -N n1 --command "systemctl status tidb-4000 | grep Loaded |grep 'enabled; vendor'"
 
     # echo "start scale in tikv"
-    # tiup-cluster --yes scale-in $name -N $ipprefix.103:20160
+    # tiup-cluster --yes scale-in $name -N n3:20160
     # wait_instance_num_reach $name $total_sub_one $native_ssh
     # echo "start scale out tikv"
     # topo=./topo/full_scale_in_tikv.yaml
-    # sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
     # tiup-cluster --yes scale-out $name $topo
 
     echo "start scale in pd"
-    tiup-cluster $client --yes scale-in $name -N $ipprefix.103:2379
+    tiup-cluster $client --yes scale-in $name -N n3:2379
     wait_instance_num_reach $name $total_sub_one $native_ssh
 
     # validate https://github.com/pingcap/tiup/issues/786
     # ensure that this instance is removed from the startup scripts of other components that need to rely on PD
-    ! tiup-cluster $client exec $name -N $ipprefix.101 --command "grep -q $ipprefix.103:2379 /home/tidb/deploy/tidb-4000/scripts/run_tidb.sh"
+    ! tiup-cluster $client exec $name -N n1 --command "grep -q n3:2379 /home/tidb/deploy/tidb-4000/scripts/run_tidb.sh"
 
     echo "start scale out pd"
     topo=./topo/full_scale_in_pd.yaml
-    sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
     tiup-cluster $client --yes scale-out $name $topo
     # after scale-out, ensure this instance come back
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "grep -q $ipprefix.103:2379 /home/tidb/deploy/tidb-4000/scripts/run_tidb.sh"
+    tiup-cluster $client exec $name -N n1 --command "grep -q n3:2379 /home/tidb/deploy/tidb-4000/scripts/run_tidb.sh"
 
     echo "start scale in tidb"
-    tiup-cluster $client --yes scale-in $name -N $ipprefix.102:4000
+    tiup-cluster $client --yes scale-in $name -N n2:4000
     wait_instance_num_reach $name $total_sub_one $native_ssh
-    ! tiup-cluster $client exec $name -N $ipprefix.102 --command "ls /home/tidb/deploy/monitor-9100/deploy/monitor-9100"
-    ! tiup-cluster $client exec $name -N $ipprefix.102 --command "ps aux | grep node_exporter | grep -qv grep"
-    ! tiup-cluster $client exec $name -N $ipprefix.102 --command "ps aux | grep blackbox_exporter | grep -qv grep"
+    ! tiup-cluster $client exec $name -N n2 --command "ls /home/tidb/deploy/monitor-9100/deploy/monitor-9100"
+    ! tiup-cluster $client exec $name -N n2 --command "ps aux | grep node_exporter | grep -qv grep"
+    ! tiup-cluster $client exec $name -N n2 --command "ps aux | grep blackbox_exporter | grep -qv grep"
     # after all components on the node were scale-ined, the SSH public is automatically deleted
-    ! ssh -o "StrictHostKeyChecking=no "-o "PasswordAuthentication=no" -i ~/.tiup/storage/cluster/$name/ssh/id_rsa tidb@$ipprefix.102 "ls"
+    ! ssh -o "StrictHostKeyChecking=no "-o "PasswordAuthentication=no" -i ~/.tiup/storage/cluster/$name/ssh/id_rsa tidb@n2 "ls"
 
     echo "start scale out tidb"
-    topo=./topo/full_scale_in_tidb.yaml
-    sed "s/__IPPREFIX__.101/$ipprefix.102/g" $topo.tpl > $topo
+    topo=./topo/full_scale_in_tidb_2nd.yaml
     tiup-cluster $client --yes scale-out $name $topo
     # after scalue-out, ensure node_exporter and blackbox_exporter come back
-    tiup-cluster $client exec $name -N $ipprefix.102 --command "ls /home/tidb/deploy/monitor-9100/deploy/monitor-9100"
-    tiup-cluster $client exec $name -N $ipprefix.102 --command "ps aux | grep node_exporter | grep -qv grep"
-    tiup-cluster $client exec $name -N $ipprefix.102 --command "ps aux | grep blackbox_exporter | grep -qv grep"
+    tiup-cluster $client exec $name -N n2 --command "ls /home/tidb/deploy/monitor-9100/deploy/monitor-9100"
+    tiup-cluster $client exec $name -N n2 --command "ps aux | grep node_exporter | grep -qv grep"
+    tiup-cluster $client exec $name -N n2 --command "ps aux | grep blackbox_exporter | grep -qv grep"
 
     tiup-cluster $client _test $name writable
 }

tests/tiup-cluster/script/scale_tools.sh

@@ -6,7 +6,6 @@ function scale_tools() {
     version=$1
     test_tls=$2
     native_ssh=$3
-    ipprefix=${TIUP_TEST_IP_PREFIX:-"172.19.0"}
 
     client=""
     if [ $native_ssh == true ]; then
@@ -19,14 +18,13 @@ function scale_tools() {
     else
         topo=./topo/full.yaml
     fi
-    sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
 
     tiup-cluster $client --yes deploy $name $version $topo -i ~/.ssh/id_rsa
 
     # check the local config
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "grep magic-string-for-test /home/tidb/deploy/prometheus-9090/conf/tidb.rules.yml"
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "grep magic-string-for-test /home/tidb/deploy/grafana-3000/dashboards/tidb.json"
-    tiup-cluster $client exec $name -N $ipprefix.101 --command "grep magic-string-for-test /home/tidb/deploy/alertmanager-9093/conf/alertmanager.yml"
+    tiup-cluster $client exec $name -N n1 --command "grep magic-string-for-test /home/tidb/deploy/prometheus-9090/conf/tidb.rules.yml"
+    tiup-cluster $client exec $name -N n1 --command "grep magic-string-for-test /home/tidb/deploy/grafana-3000/dashboards/tidb.json"
+    tiup-cluster $client exec $name -N n1 --command "grep magic-string-for-test /home/tidb/deploy/alertmanager-9093/conf/alertmanager.yml"
 
     tiup-cluster $client list | grep "$name"
 
@@ -43,59 +41,54 @@ function scale_tools() {
     fi
 
     echo "start scale in pump"
-    tiup-cluster $client --yes scale-in $name -N $ipprefix.103:8250
+    tiup-cluster $client --yes scale-in $name -N n3:8250
     wait_instance_num_reach $name $total_sub_one $native_ssh
     echo "start scale out pump"
     topo=./topo/full_scale_in_pump.yaml
-    sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
     tiup-cluster $client --yes scale-out $name $topo
 
     echo "start scale in cdc"
-    yes | tiup-cluster $client scale-in $name -N $ipprefix.103:8300
+    yes | tiup-cluster $client scale-in $name -N n3:8300
     wait_instance_num_reach $name $total_sub_one $native_ssh
     echo "start scale out cdc"
     topo=./topo/full_scale_in_cdc.yaml
-    sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
     yes | tiup-cluster $client scale-out $name $topo
 
     if [ $test_tls = false ]; then
         echo "start scale in tispark"
-        yes | tiup-cluster $client --yes scale-in $name -N $ipprefix.104:7078
+        yes | tiup-cluster $client --yes scale-in $name -N n4:7078
         wait_instance_num_reach $name $total_sub_one $native_ssh
         echo "start scale out tispark"
         topo=./topo/full_scale_in_tispark.yaml
-        sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
         yes | tiup-cluster $client --yes scale-out $name $topo
     fi
 
     echo "start scale in grafana"
-    tiup-cluster $client --yes scale-in $name -N $ipprefix.101:3000
+    tiup-cluster $client --yes scale-in $name -N n1:3000
     wait_instance_num_reach $name $total_sub_one $native_ssh
     echo "start scale out grafana"
     topo=./topo/full_scale_in_grafana.yaml
-    sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
     tiup-cluster $client --yes scale-out $name $topo
 
     # make sure grafana dashboards has been set to default (since the full_sale_in_grafana.yaml didn't provide a local dashboards dir)
-    ! tiup-cluster $client exec $name -N $ipprefix.101 --command "grep magic-string-for-test /home/tidb/deploy/grafana-3000/dashboards/tidb.json"
+    ! tiup-cluster $client exec $name -N n1 --command "grep magic-string-for-test /home/tidb/deploy/grafana-3000/dashboards/tidb.json"
 
     # currently tiflash is not supported in TLS enabled cluster
     # and only Tiflash support data-dir in multipath
     if [ $test_tls = false ]; then
         # ensure tiflash's data dir exists
-        tiup-cluster $client exec $name -N $ipprefix.103 --command "ls /home/tidb/deploy/tiflash-9000/data1"
-        tiup-cluster $client exec $name -N $ipprefix.103 --command "ls /data/tiflash-data"
+        tiup-cluster $client exec $name -N n3 --command "ls /home/tidb/deploy/tiflash-9000/data1"
+        tiup-cluster $client exec $name -N n3 --command "ls /data/tiflash-data"
         echo "start scale in tiflash"
-        tiup-cluster $client --yes scale-in $name -N $ipprefix.103:9000
+        tiup-cluster $client --yes scale-in $name -N n3:9000
         tiup-cluster $client display $name | grep Tombstone
         echo "start prune tiflash"
         yes | tiup-cluster $client prune $name
         wait_instance_num_reach $name $total_sub_one $native_ssh
-        ! tiup-cluster $client exec $name -N $ipprefix.103 --command "ls /home/tidb/deploy/tiflash-9000/data1"
-        ! tiup-cluster $client exec $name -N $ipprefix.103 --command "ls /data/tiflash-data"
+        ! tiup-cluster $client exec $name -N n3 --command "ls /home/tidb/deploy/tiflash-9000/data1"
+        ! tiup-cluster $client exec $name -N n3 --command "ls /data/tiflash-data"
         echo "start scale out tiflash"
         topo=./topo/full_scale_in_tiflash.yaml
-        sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
         tiup-cluster $client --yes scale-out $name $topo
     fi
 

tests/tiup-cluster/test_upgrade.sh

@@ -6,8 +6,6 @@ version=${version-v4.0.4}
 old_version=${old_version-v3.0.16}
 name=test_upgrade
 topo=./topo/upgrade.yaml
-ipprefix=${TIUP_TEST_IP_PREFIX:-"172.19.0"}
-sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
 
 mkdir -p ~/.tiup/bin && cp -f ./root.json ~/.tiup/bin/
 

tests/tiup-cluster/test_upgrade_tls.sh

@@ -6,8 +6,6 @@ version=${version-v4.0.4}
 old_version=${old_version-v3.0.16}
 name=test_upgrade_tls
 topo=./topo/upgrade_tls.yaml
-ipprefix=${TIUP_TEST_IP_PREFIX:-"172.19.0"}
-sed "s/__IPPREFIX__/$ipprefix/g" $topo.tpl > $topo
 
 mkdir -p ~/.tiup/bin && cp -f ./root.json ~/.tiup/bin/
 

tests/tiup-cluster/topo/full.yaml.tpl → tests/tiup-cluster/topo/full.yaml

@@ -12,60 +12,60 @@ server_configs:
     storage.stop-write-at-available-space: 1 mib
 
 tidb_servers:
-  - host: __IPPREFIX__.101
-  - host: __IPPREFIX__.102
+  - host: n1
+  - host: n2
 
 pd_servers:
-  - host: __IPPREFIX__.103
-  - host: __IPPREFIX__.104
-  - host: __IPPREFIX__.105
+  - host: n3
+  - host: n4
+  - host: n5
 
 # Note if only 3 instance, when scale-in one of it.
 # It may not be tombstone.
 tikv_servers:
-  - host: __IPPREFIX__.101
-  - host: __IPPREFIX__.103
+  - host: n1
+  - host: n3
     data_dir: "/home/tidb/my_kv_data"
-  - host: __IPPREFIX__.104
-  - host: __IPPREFIX__.105
+  - host: n4
+  - host: n5
 
 # tiflash eat too much memory
 # and binary is more than 1G..
 tiflash_servers:
-  - host: __IPPREFIX__.103
+  - host: n3
     data_dir: "data1,/data/tiflash-data"
-#   - host: __IPPREFIX__.104
-#   - host: __IPPREFIX__.105
+#   - host: n4
+#   - host: n5
 
 pump_servers:
-  - host: __IPPREFIX__.103
-  - host: __IPPREFIX__.104
-  - host: __IPPREFIX__.105
+  - host: n3
+  - host: n4
+  - host: n5
 
 drainer_servers:
-  - host: __IPPREFIX__.101
+  - host: n1
     data_dir: /home/tidb/data/drainer-8249/data
     commit_ts: -1
     config:
       syncer.db-type: "file"
 
 cdc_servers:
-  - host: __IPPREFIX__.103
-  - host: __IPPREFIX__.104
-  - host: __IPPREFIX__.105
+  - host: n3
+  - host: n4
+  - host: n5
 
 tispark_masters:
-  - host: __IPPREFIX__.103
+  - host: n3
 
 tispark_workers:
-  - host: __IPPREFIX__.104
+  - host: n4
 
 monitoring_servers:
-  - host: __IPPREFIX__.101
+  - host: n1
     rule_dir: /tmp/local/prometheus
 grafana_servers:
-  - host: __IPPREFIX__.101
+  - host: n1
     dashboard_dir: /tmp/local/grafana
 alertmanager_servers:
-  - host: __IPPREFIX__.101
+  - host: n1
     config_file: /tmp/local/alertmanager/alertmanager.yml

tests/tiup-cluster/topo/full_scale_in_cdc.yaml

@@ -0,0 +1,2 @@
+cdc_servers:
+  - host: n3

tests/tiup-cluster/topo/full_scale_in_grafana.yaml

@@ -0,0 +1,2 @@
+grafana_servers:
+  - host: n1

tests/tiup-cluster/topo/full_scale_in_pd.yaml

@@ -0,0 +1,2 @@
+pd_servers:
+  - host: n3

tests/tiup-cluster/topo/full_scale_in_pump.yaml

@@ -0,0 +1,2 @@
+pump_servers:
+  - host: n3

tests/tiup-cluster/topo/full_scale_in_tidb.yaml

@@ -0,0 +1,2 @@
+tidb_servers:
+  - host: n1

tests/tiup-cluster/topo/full_scale_in_tidb_2nd.yaml

@@ -0,0 +1,2 @@
+tidb_servers:
+  - host: n2

tests/tiup-cluster/topo/full_scale_in_tiflash.yaml

@@ -0,0 +1,2 @@
+tiflash_servers:
+  - host: n3

tests/tiup-cluster/topo/full_scale_in_tikv.yaml

@@ -0,0 +1,2 @@
+tikv_servers:
+  - host: n3

tests/tiup-cluster/topo/full_scale_in_tispark.yaml

@@ -0,0 +1,2 @@
+tispark_workers:
+  - host: n5