Removes node_exporter monitoring of old Linode IPv6 monitoring VM

config/federation/prometheus/alerts.yml

@@ -128,10 +128,10 @@ groups:
       cluster: prometheus-federation
     annotations:
       summary: The blackbox_exporter service is down or missing for IPv6 probes.
-      description: The blackbox_exporter for IPv6 checks runs in a Linode VM.
-        Make sure the VM is up and running. If it is, check the status of the
-        BBE container running in the VM. Domains for VMs are like
-        blackbox-exporter-ipv6.<project>.measurementlab.net.
+      description: The blackbox_exporter for IPv6 checks runs in a GCE VM in
+        each M-Lab GCP project. Make sure the VM is up and running. If it is,
+        check the status of the BBE container running in the VM. Domains for
+        VMs are like blackbox-exporter-ipv6.<project>.measurementlab.net.
 
 # Unable to scrape the Github Maintenance exporter or the job is missing.
   - alert: GithubMaintenanceExporterDownOrMissing

config/federation/prometheus/prometheus.yml.template

@@ -370,17 +370,16 @@ scrape_configs:
     static_configs:
       - targets: ['eb.measurementlab.net:9100']
 
+  # Scrape config for the node_exporter on the IPv6 GCE monitoring VM.
+  - job_name: 'ipv6-node-exporter'
+    static_configs:
+      - targets: ['blackbox-exporter-ipv6.{{PROJECT}}.measurementlab.net:9100']
+
   # Scrape config for the epoxy-boot-api.
   - job_name: 'epoxy-boot-api'
     static_configs:
       - targets: ['epoxy-boot-api.{{PROJECT}}.measurementlab.net:9000']
 
-  # Scrape config for the node_exporter on the IPv6 Linode VM we use for
-  # monitoring IPv6.
-  - job_name: 'ipv6-node-exporter'
-    static_configs:
-      - targets: ['blackbox-exporter-ipv6.{{PROJECT}}.measurementlab.net:9100']
-
   # Scrape config for services running in data-pipeline cluster, which is
   # region based, so m-lab/gcp-service-discovery#33 causes problems.  These
   # metrics are needed by the alerts like up{container="etl-gardener",instance=~".*:9090"} == 0

deploy_bbe_config.sh

@@ -19,6 +19,8 @@ VM_CONFIG_DIR="/etc/blackbox-exporter"
 VM_CONFIG_FILE="${VM_CONFIG_DIR}/config.yml"
 BBE_IMAGE="prom/blackbox-exporter:v0.20.0"
 CONTAINER_NAME="blackbox-exporter"
+NODE_EXPORTER_IMAGE="prom/node-exporter:v1.8.2"
+NODE_EXPORTER_CONTAINER="node-exporter"
 
 # Map projects to zones where the monitoring VM is deployed.
 ZONE_mlab_sandbox="us-central1-c"
@@ -46,5 +48,38 @@ gcloud compute ssh ${GCE_OPTS} "${VM_NAME}" --command=" \
             --volume ${VM_CONFIG_DIR}:${VM_CONFIG_DIR}:ro \
             --restart always --name ${CONTAINER_NAME} ${BBE_IMAGE} \
             --config.file=${VM_CONFIG_FILE}; \
+    fi && \
+    if ! sudo docker inspect ${NODE_EXPORTER_CONTAINER} > /dev/null 2>&1; then \
+        sudo docker run --detach --network=host --pid=host \
+            --volume /:/host:ro,rslave \
+            --restart always --name ${NODE_EXPORTER_CONTAINER} ${NODE_EXPORTER_IMAGE} \
+            --path.rootfs=/host \
+            --no-collector.arp \
+            --no-collector.bcache \
+            --no-collector.bonding \
+            --no-collector.conntrack \
+            --no-collector.cpu \
+            --no-collector.diskstats \
+            --no-collector.edac \
+            --no-collector.entropy \
+            --no-collector.filefd \
+            --no-collector.hwmon \
+            --no-collector.infiniband \
+            --no-collector.ipvs \
+            --no-collector.mdadm \
+            --no-collector.netclass \
+            --no-collector.netstat \
+            --no-collector.nfs \
+            --no-collector.nfsd \
+            --no-collector.sockstat \
+            --no-collector.stat \
+            --no-collector.systemd \
+            --no-collector.textfile \
+            --no-collector.time \
+            --no-collector.timex \
+            --no-collector.uname \
+            --no-collector.vmstat \
+            --no-collector.xfs \
+            --no-collector.zfs; \
     fi \
 "