Add etcd metrics, Prometheus scrapes, and Grafana dash

* Use etcd v3.3 --listen-metrics-urls to expose only metrics
data via http://0.0.0.0:2381 on controllers
* Add Prometheus discovery for etcd peers on controller nodes
* Temporarily drop two noisy Prometheus alerts
This commit is contained in:
Dalton Hubble
2018-03-28 21:45:24 -07:00
parent 642f7ec22f
commit d770393dbc
10 changed files with 58 additions and 22 deletions

View File

@ -13,6 +13,7 @@ systemd:
Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${etcd_domain}:2380"
Environment="ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379"
Environment="ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380"
Environment="ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381"
Environment="ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}"
Environment="ETCD_STRICT_RECONFIG_CHECK=true"
Environment="ETCD_SSL_DIR=/etc/ssl/etcd"

View File

@ -81,6 +81,16 @@ resource "aws_security_group_rule" "controller-node-exporter" {
source_security_group_id = "${aws_security_group.worker.id}"
}
resource "aws_security_group_rule" "controller-node-exporter-self" {
security_group_id = "${aws_security_group.controller.id}"
type = "ingress"
protocol = "tcp"
from_port = 9100
to_port = 9100
self = true
}
resource "aws_security_group_rule" "controller-kubelet-self" {
security_group_id = "${aws_security_group.controller.id}"
@ -256,6 +266,16 @@ resource "aws_security_group_rule" "worker-flannel-self" {
resource "aws_security_group_rule" "worker-node-exporter" {
security_group_id = "${aws_security_group.worker.id}"
type = "ingress"
protocol = "tcp"
from_port = 9100
to_port = 9100
source_security_group_id = "${aws_security_group.controller.id}"
}
resource "aws_security_group_rule" "worker-node-exporter-self" {
security_group_id = "${aws_security_group.worker.id}"
type = "ingress"
protocol = "tcp"
from_port = 9100