add prom module

This commit is contained in:
nitram 2019-02-25 18:06:37 -08:00
parent 8912748f24
commit 8badc6a9ea
No known key found for this signature in database
GPG key ID: 2352C35346C5D534
5 changed files with 412 additions and 0 deletions

View file

@ -0,0 +1,412 @@
bootcmd:
- blkid /dev/disk/by-id/google-data || mkfs.ext4 -L data -E lazy_itable_init=0,lazy_journal_init=0,discard /dev/disk/by-id/google-data
mounts:
- [ /dev/disk/by-label/data, /mnt/disks/data, auto, defaults ]
users:
- name: exec
uid: 2000
write_files:
- path: /home/exec/prometheus/alertmanager.yml
permissions: 0644
owner: root
content: |
route:
group_by: [cluster, alertname]
# If an alert isn't caught by a route, send it to the pager.
receiver: noc-pager
routes:
- match:
severity: warning
receiver: noc-email
- match:
severity: page
receiver: noc-pager
receivers:
- name: noc-email
email_configs:
- to: noc@blockstream.io
from: noreply@blockstream.io
smarthost: smtp.gmail.com:587
auth_username: ${email_username}
auth_password: ${email_password}
- name: noc-pager
opsgenie_configs:
- api_key: ${opsgenie_api_key}
teams: SecOps
tags: lightning-store
- path: /home/exec/prometheus/rules/alerts.yml
permissions: 0644
owner: root
content: |
groups:
- name: node
rules:
#- alert: NoHostsInNetwork
# expr: sum by (name) (up{name=~".+"}) == 0
# for: 1m
# labels:
# severity: page
# annotations:
# summary: No hosts in network {{ $labels.name }}, production traffic impacted!
# description: There are currently no hosts up in the network {{ $labels.name }}, verify the instance groups. https://wiki.blockstream.io/OpsPlaybooks/Esplora-Runbooks#NoHostsInNetwork
- path: /home/exec/prometheus/prometheus.yml
permissions: 0644
owner: root
content: |
global:
evaluation_interval: 15s
scrape_interval: 15s
external_labels:
project: blockstream-store
rule_files:
- /config/rules/alerts.yml
alerting:
alertmanagers:
- scheme: http
static_configs:
- targets:
- "127.0.0.1:9093"
scrape_configs:
- job_name: prometheus
relabel_configs:
- source_labels:
- '__meta_gce_label_network'
target_label: 'network'
- source_labels:
- '__meta_gce_label_name'
target_label: 'name'
- source_labels:
- '__meta_gce_instance_name'
target_label: 'instance_name'
gce_sd_configs:
- project: blockstream-store
zone: asia-northeast1-a
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: asia-northeast1-b
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: asia-northeast1-c
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: europe-west4-a
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: europe-west4-b
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: europe-west4-c
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: us-central1-a
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: us-central1-b
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: us-central1-c
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: us-central1-f
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: us-east1-d
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: us-east1-b
filter: (labels.type = "prometheus")
port: 9100
- project: blockstream-store
zone: us-east1-c
filter: (labels.type = "prometheus")
port: 9100
- job_name: wordpress
relabel_configs:
- source_labels:
- '__meta_gce_label_network'
target_label: 'network'
- source_labels:
- '__meta_gce_label_name'
target_label: 'name'
- source_labels:
- '__meta_gce_instance_name'
target_label: 'instance_name'
gce_sd_configs:
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: asia-northeast1-a
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: asia-northeast1-b
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: asia-northeast1-c
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: europe-west4-a
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: europe-west4-b
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: europe-west4-c
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: us-central1-a
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: us-central1-b
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: us-central1-c
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: us-central1-f
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: us-east1-d
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: us-east1-b
port: 9100
- project: blockstream-store
filter: (labels.type = "wordpress")
zone: us-east1-c
port: 9100
- job_name: satellite-api
relabel_configs:
- source_labels:
- '__meta_gce_label_network'
target_label: 'network'
- source_labels:
- '__meta_gce_label_name'
target_label: 'name'
- source_labels:
- '__meta_gce_instance_name'
target_label: 'instance_name'
gce_sd_configs:
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: asia-northeast1-a
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: asia-northeast1-b
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: asia-northeast1-c
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: europe-west4-a
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: europe-west4-b
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: europe-west4-c
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-central1-a
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-central1-b
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-central1-c
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-central1-f
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-east1-d
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-east1-b
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-east1-c
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-west1-a
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-west1-b
port: 9100
- project: blockstream-store
filter: (labels.type = "lightning-app")
zone: us-west1-c
port: 9100
- job_name: btcpayserver
relabel_configs:
- source_labels:
- '__meta_gce_label_network'
target_label: 'network'
- source_labels:
- '__meta_gce_label_name'
target_label: 'name'
- source_labels:
- '__meta_gce_instance_name'
target_label: 'instance_name'
gce_sd_configs:
- project: blockstream-store
filter: (labels.type = "btcpayserver")
zone: us-west1-a
port: 9100
- project: blockstream-store
filter: (labels.type = "btcpayserver")
zone: us-west1-b
port: 9100
- project: blockstream-store
filter: (labels.type = "btcpayserver")
zone: us-west1-c
port: 9100
- path: /etc/systemd/system/prometheus.service
permissions: 0644
owner: root
content: |
[Unit]
Description=prometheus-server instance
Wants=gcr-online.target docker.service
After=gcr-online.service docker.service
[Service]
Restart=always
RestartSec=1
Environment=HOME=/home/exec
ExecStartPre=/usr/bin/docker-credential-gcr configure-docker
ExecStartPre=/usr/bin/docker pull ${docker_tag}
ExecStartPre=/sbin/iptables -A INPUT -m tcp -p tcp --dport 9090 -j ACCEPT
ExecStartPre=/sbin/iptables -A INPUT -m tcp -p tcp --dport 80 -j ACCEPT
ExecStartPre=/sbin/iptables -A PREROUTING -t nat -p tcp --dport 80 -j REDIRECT --to-port 9090
ExecStart=/usr/bin/docker run \
--network=host \
-v /mnt/disks/data:/data:rw \
-v /home/exec/prometheus:/config:ro \
--read-only \
--name prometheus \
"${docker_tag}" --config.file=/config/prometheus.yml --web.enable-lifecycle --web.enable-admin-api --storage.tsdb.path=/data/metrics --storage.tsdb.retention=${retention}
ExecStop=/usr/bin/docker stop prometheus
ExecStopPost=/usr/bin/docker rm prometheus
ExecStopPost=/sbin/iptables -D INPUT -m tcp -p tcp --dport 9090 -j ACCEPT
ExecStopPost=/sbin/iptables -D INPUT -m tcp -p tcp --dport 80 -j ACCEPT
ExecStopPost=/sbin/iptables -D PREROUTING -t nat -p tcp --dport 80 -j REDIRECT --to-port 9090
[Install]
WantedBy=multi-user.target
- path: /etc/systemd/system/alertmanager.service
permissions: 0644
owner: root
content: |
[Unit]
Description=alertmanager-server instance
Wants=gcr-online.target docker.service
After=gcr-online.service docker.service
[Service]
Restart=always
RestartSec=1
Environment=HOME=/home/exec
ExecStartPre=/usr/bin/docker-credential-gcr configure-docker
ExecStartPre=/usr/bin/docker pull ${docker_tag}
ExecStartPre=/sbin/iptables -A INPUT -m tcp -p tcp --dport 9093 -j ACCEPT
ExecStart=/usr/bin/docker run \
--network=host \
-v /mnt/disks/data:/data:rw \
-v /home/exec/prometheus:/config:ro \
--read-only \
--name alertmanager \
--entrypoint=/bin/alertmanager \
"${docker_tag}" --config.file=/config/alertmanager.yml
ExecStop=/usr/bin/docker stop alertmanager
ExecStopPost=/usr/bin/docker rm alertmanager
ExecStopPost=/sbin/iptables -D INPUT -m tcp -p tcp --dport 9093 -j ACCEPT
[Install]
WantedBy=multi-user.target
- path: /etc/systemd/system/node-exporter.service
permissions: 0644
owner: root
content: |
[Unit]
Description=prometheus node-exporter
Wants=gcr-online.target docker.service
After=gcr-online.service docker.service
[Service]
Restart=always
RestartSec=1
Environment=HOME=/home/exec
ExecStartPre=/usr/bin/docker-credential-gcr configure-docker
ExecStartPre=/usr/bin/docker pull ${docker_tag_node_exporter}
ExecStartPre=/sbin/iptables -A INPUT -m tcp -p tcp --dport 9100 -j ACCEPT
ExecStart=/usr/bin/docker run \
--name=node-exporter \
--network=host \
--read-only \
-v /proc:/host/proc:ro \
-v /sys:/host/sys:ro \
-v /:/rootfs:ro \
-v metrics:/metrics:ro \
"${docker_tag_node_exporter}" --path.procfs /host/proc --path.sysfs /host/sys --collector.textfile.directory /metrics --collector.filesystem.ignored-mount-points "^/(sys|proc|dev|host|etc($|/))"
ExecStop=/usr/bin/docker stop node-exporter
ExecStopPost=/usr/bin/docker rm node-exporter
ExecStopPost=/sbin/iptables -D INPUT -m tcp -p tcp --dport 9100 -j ACCEPT
[Install]
WantedBy=multi-user.target
runcmd:
- /bin/mkdir -p /mnt/disks/data/metrics
- /bin/chown nobody:nobody /mnt/disks/data/metrics
- systemctl daemon-reload
- systemctl start prometheus.service
- systemctl enable prometheus.service
- systemctl start alertmanager.service
- systemctl enable alertmanager.service
- systemctl start node-exporter.service
- systemctl enable node-exporter.service

View file

View file

View file