From e267e5d38d7a7171fe6e38ea9fa034c63c8b948b Mon Sep 17 00:00:00 2001
From: Diogo Guerra <diogo.filipe.tomas.guerra@cern.ch>
Date: Tue, 18 Jan 2022 17:10:06 +0100
Subject: [PATCH] [cern] monitoring from upstream chart
Install monitoring by using the updated kube-prometheus-stack
helm chart.
Signed-off-by: Diogo Guerra <diogo.filipe.tomas.guerra@cern.ch>
Change-Id: I12ccfed3308d02600ccf09c5a9aa7e92a2eb7348
---
.../fragments/write-heat-params-master.sh | 1 +
.../templates/kubernetes/helm/cern-chart.sh | 16 ++++++++++++++++
.../kubernetes/helm/prometheus-adapter.sh | 3 ++-
.../kubernetes/helm/prometheus-operator.sh | 3 ++-
.../templates/kubemaster.yaml | 1 +
5 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/magnum/drivers/common/templates/kubernetes/fragments/write-heat-params-master.sh b/magnum/drivers/common/templates/kubernetes/fragments/write-heat-params-master.sh
index d2d6eb515..ed620b3c4 100644
--- a/magnum/drivers/common/templates/kubernetes/fragments/write-heat-params-master.sh
+++ b/magnum/drivers/common/templates/kubernetes/fragments/write-heat-params-master.sh
@@ -42,6 +42,7 @@ CLUSTER_SUBNET="$CLUSTER_SUBNET"
TLS_DISABLED="$TLS_DISABLED"
KUBE_DASHBOARD_ENABLED="$KUBE_DASHBOARD_ENABLED"
INFLUX_GRAFANA_DASHBOARD_ENABLED="$INFLUX_GRAFANA_DASHBOARD_ENABLED"
+GRAFANA_ADMIN_PASSWD="$GRAFANA_ADMIN_PASSWD"
VERIFY_CA="$VERIFY_CA"
CLUSTER_UUID="$CLUSTER_UUID"
MAGNUM_URL="$MAGNUM_URL"
diff --git a/magnum/drivers/common/templates/kubernetes/helm/cern-chart.sh b/magnum/drivers/common/templates/kubernetes/helm/cern-chart.sh
index 4be926b7d..194864ab7 100644
--- a/magnum/drivers/common/templates/kubernetes/helm/cern-chart.sh
+++ b/magnum/drivers/common/templates/kubernetes/helm/cern-chart.sh
@@ -125,6 +125,22 @@ ${NVIDIA_GPU_VALUES}
role: ${INGRESS_CONTROLLER_ROLE}
metrics-server:
enabled: ${METRICS_SERVER_ENABLED}
+ kube-prometheus-stack:
+ enabled: ${MONITORING_ENABLED}
+ grafana:
+ adminPassword: ${GRAFANA_ADMIN_PASSWD}
+ prometheus:
+ prometheusSpec:
+ externalLabels:
+ cluster_uuid: ${CLUSTER_UUID}
+ resources:
+ requests:
+ cpu: $(expr 128 + 7 \* ${MAX_NODE_COUNT} )m
+ memory: $(expr 256 + 40 \* ${MAX_NODE_COUNT})M
+ prometheus-adapter:
+ enabled: ${PROMETHEUS_ADAPTER_ENABLED}
+ rules:
+ existing: ${PROMETHEUS_ADAPTER_CONFIGMAP}
EOF
fi
diff --git a/magnum/drivers/common/templates/kubernetes/helm/prometheus-adapter.sh b/magnum/drivers/common/templates/kubernetes/helm/prometheus-adapter.sh
index ef5c03de2..469d87d13 100644
--- a/magnum/drivers/common/templates/kubernetes/helm/prometheus-adapter.sh
+++ b/magnum/drivers/common/templates/kubernetes/helm/prometheus-adapter.sh
@@ -12,7 +12,8 @@ CHART_NAME="prometheus-adapter"
if [ "$(echo ${MONITORING_ENABLED} | tr '[:upper:]' '[:lower:]')" = "true" ] && \
- [ "$(echo ${PROMETHEUS_ADAPTER_ENABLED} | tr '[:upper:]' '[:lower:]')" = "true" ]; then
+ [ "$(echo ${PROMETHEUS_ADAPTER_ENABLED} | tr '[:upper:]' '[:lower:]')" = "true" ] && \
+ [[ ( $(echo ${CERN_CHART_VERSION} | cut -d. -f2) -lt 10 ) ]]; then
HELM_MODULE_CONFIG_FILE="/srv/magnum/kubernetes/helm/${CHART_NAME}.yaml"
[ -f ${HELM_MODULE_CONFIG_FILE} ] || {
diff --git a/magnum/drivers/common/templates/kubernetes/helm/prometheus-operator.sh b/magnum/drivers/common/templates/kubernetes/helm/prometheus-operator.sh
index 6d0c69ccd..3dc333228 100644
--- a/magnum/drivers/common/templates/kubernetes/helm/prometheus-operator.sh
+++ b/magnum/drivers/common/templates/kubernetes/helm/prometheus-operator.sh
@@ -10,7 +10,8 @@ printf "Starting to run ${step}\n"
###############################################################################
CHART_NAME="prometheus-operator"
-if [ "$(echo ${MONITORING_ENABLED} | tr '[:upper:]' '[:lower:]')" = "true" ]; then
+if [ "$(echo ${MONITORING_ENABLED} | tr '[:upper:]' '[:lower:]')" = "true" ] && \
+ [[ ( $(echo ${CERN_CHART_VERSION} | cut -d. -f2) -lt 10 ) ]]; then
# Calculate resources needed to run the Prometheus Monitoring Solution
# MAX_NODE_COUNT so we can have metrics even if cluster scales
diff --git a/magnum/drivers/k8s_fedora_coreos_v1/templates/kubemaster.yaml b/magnum/drivers/k8s_fedora_coreos_v1/templates/kubemaster.yaml
index 4667dc576..70403f84b 100644
--- a/magnum/drivers/k8s_fedora_coreos_v1/templates/kubemaster.yaml
+++ b/magnum/drivers/k8s_fedora_coreos_v1/templates/kubemaster.yaml
@@ -960,6 +960,7 @@ resources:
"$TRAEFIK_INGRESS_CONTROLLER_TAG": {get_param: traefik_ingress_controller_tag}
"$KUBE_DASHBOARD_ENABLED": {get_param: kube_dashboard_enabled}
"$INFLUX_GRAFANA_DASHBOARD_ENABLED": {get_param: influx_grafana_dashboard_enabled}
+ "$GRAFANA_ADMIN_PASSWD": {get_param: grafana_admin_passwd}
"$VERIFY_CA": {get_param: verify_ca}
"$CLUSTER_UUID": {get_param: cluster_uuid}
"$MAGNUM_URL": {get_param: magnum_url}
--
GitLab