From 1d84818b53f66e7850f1d74a68229a59fab92b39 Mon Sep 17 00:00:00 2001
From: Dr Wajdi Hajji <wh330@cam.ac.uk>
Date: Mon, 17 Jan 2022 13:46:51 +0000
Subject: [PATCH] Support creating a monitoring dashboard
The dashboard, defined in ./dashboard.json, contains:
- Request counts broken down by response code class (ignoring 404s).
- Request latencies for 50th, 95th and 99th percentile.
- Container CPU and memory utilisations for 50th, 95th and 99th percentile.
- Container instance count and billable instance time.
---
CHANGELOG | 6 +
dashboard.json | 334 +++++++++++++++++++++++++++++++++++++++++++++++++
dashboard.tf | 22 ++++
variables.tf | 9 ++
4 files changed, 371 insertions(+)
create mode 100644 dashboard.json
create mode 100644 dashboard.tf
diff --git a/CHANGELOG b/CHANGELOG
index fba9df1..067463c 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+## [4.1.1] - 2022-01-17
+### Added
+ - Add a monitoring dashboard, defined in ./dashboard.json, for the Cloud Run service.
+ The dashboard contains charts for Request count and latency, CPU and memory utilisation,
+ and container instance count and billable time.
+
## [4.1.0] - 2021-07-28
### Added
- Support load balancer ingress style alongside Cloud Run domain mapping.
diff --git a/dashboard.json b/dashboard.json
new file mode 100644
index 0000000..a470eca
--- /dev/null
+++ b/dashboard.json
@@ -0,0 +1,334 @@
+{
+ "displayName": "Cloud Run service: ${service_name}",
+ "mosaicLayout": {
+ "columns": 12,
+ "tiles": [
+ {
+ "width": 6,
+ "height": 4,
+ "widget": {
+ "title": "Request Counts",
+ "xyChart": {
+ "dataSets": [
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/request_count\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" metric.label.\"response_code\"!=\"404\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_RATE",
+ "crossSeriesReducer": "REDUCE_SUM",
+ "groupByFields": [
+ "metric.label.\"response_code_class\""
+ ]
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ }
+ ],
+ "timeshiftDuration": "0s",
+ "yAxis": {
+ "label": "y1Axis",
+ "scale": "LINEAR"
+ },
+ "chartOptions": {
+ "mode": "COLOR"
+ }
+ }
+ }
+ },
+ {
+ "xPos": 6,
+ "width": 6,
+ "height": 4,
+ "widget": {
+ "title": "Request Latencies",
+ "xyChart": {
+ "dataSets": [
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/request_latencies\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_DELTA",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_99",
+ "groupByFields": [
+ "resource.label.\"service_name\""
+ ]
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ },
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/request_latencies\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_DELTA",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_95",
+ "groupByFields": [
+ "resource.label.\"service_name\""
+ ]
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ },
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/request_latencies\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_DELTA",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_50",
+ "groupByFields": [
+ "resource.label.\"service_name\""
+ ]
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ }
+ ],
+ "timeshiftDuration": "0s",
+ "yAxis": {
+ "label": "y1Axis",
+ "scale": "LINEAR"
+ },
+ "chartOptions": {
+ "mode": "COLOR"
+ }
+ }
+ }
+ },
+ {
+ "yPos": 4,
+ "width": 6,
+ "height": 3,
+ "widget": {
+ "title": "Container CPU Utilisation",
+ "xyChart": {
+ "dataSets": [
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/container/cpu/utilizations\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_SUM",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_99"
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ },
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/container/cpu/utilizations\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_SUM",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_95"
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ },
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/container/cpu/utilizations\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_SUM",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_50"
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ }
+ ],
+ "timeshiftDuration": "0s",
+ "yAxis": {
+ "label": "y1Axis",
+ "scale": "LINEAR"
+ },
+ "chartOptions": {
+ "mode": "COLOR"
+ }
+ }
+ }
+ },
+ {
+ "xPos": 6,
+ "yPos": 4,
+ "width": 6,
+ "height": 3,
+ "widget": {
+ "title": "Container Memory Utiliation",
+ "xyChart": {
+ "dataSets": [
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/container/memory/utilizations\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_SUM",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_99",
+ "groupByFields": [
+ "resource.label.\"service_name\""
+ ]
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ },
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/container/memory/utilizations\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_SUM",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_95",
+ "groupByFields": [
+ "resource.label.\"service_name\""
+ ]
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ },
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/container/memory/utilizations\" resource.type=\"cloud_run_revision\" resource.label.\"service_name\"=\"${service_name}\" resource.label.\"location\"=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_SUM",
+ "crossSeriesReducer": "REDUCE_PERCENTILE_50",
+ "groupByFields": [
+ "resource.label.\"service_name\""
+ ]
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ }
+ ],
+ "timeshiftDuration": "0s",
+ "yAxis": {
+ "label": "y1Axis",
+ "scale": "LINEAR"
+ },
+ "chartOptions": {
+ "mode": "COLOR"
+ }
+ }
+ }
+ },
+ {
+ "yPos": 7,
+ "width": 6,
+ "height": 3,
+ "widget": {
+ "title": "Instance Count",
+ "xyChart": {
+ "dataSets": [
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/container/instance_count\" resource.type=\"cloud_run_revision\" resource.labels.service_name=\"${service_name}\" resource.labels.location=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_MAX",
+ "crossSeriesReducer": "REDUCE_SUM",
+ "groupByFields": [
+ "resource.label.service_name",
+ "metric.label.state"
+ ]
+ }
+ },
+ "unitOverride": "count"
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ }
+ ],
+ "xAxis": {
+ "scale": "LINEAR"
+ },
+ "chartOptions": {
+ "mode": "COLOR"
+ }
+ }
+ }
+ },
+ {
+ "xPos": 6,
+ "yPos": 7,
+ "width": 6,
+ "height": 3,
+ "widget": {
+ "title": "Billable instance time",
+ "xyChart": {
+ "dataSets": [
+ {
+ "timeSeriesQuery": {
+ "timeSeriesFilter": {
+ "filter": "metric.type=\"run.googleapis.com/container/billable_instance_time\" resource.type=\"cloud_run_revision\" resource.labels.service_name=\"${service_name}\" resource.labels.location=\"${region}\"",
+ "aggregation": {
+ "alignmentPeriod": "60s",
+ "perSeriesAligner": "ALIGN_RATE",
+ "crossSeriesReducer": "REDUCE_SUM",
+ "groupByFields": [
+ "resource.label.service_name"
+ ]
+ }
+ }
+ },
+ "plotType": "LINE",
+ "minAlignmentPeriod": "60s",
+ "targetAxis": "Y1"
+ }
+ ],
+ "xAxis": {
+ "scale": "LINEAR"
+ },
+ "chartOptions": {
+ "mode": "COLOR"
+ }
+ }
+ }
+ }
+ ]
+ }
+}
diff --git a/dashboard.tf b/dashboard.tf
new file mode 100644
index 0000000..b639e7c
--- /dev/null
+++ b/dashboard.tf
@@ -0,0 +1,22 @@
+# Create a monitoring dashboard for the provisioned Cloud Run service.
+#
+# The dashboard, defined in ./dashboard.json, contains:
+# - Request counts broken down by response code class (ignoring 404s).
+# - Request latencies for 50th, 95th and 99th percentile.
+# - Container CPU and memory utilisations for 50th, 95th and 99th percentile.
+# - Container instance count and billable instance time.
+
+data "template_file" "dashboard_json" {
+ count = var.create_monitoring_dashboard ? 1 : 0
+
+ template = file("${path.module}/dashboard.json")
+ vars = {
+ service_name = var.name
+ region = var.cloud_run_region
+ }
+}
+
+resource "google_monitoring_dashboard" "dashboard" {
+ for_each = toset([for template in data.template_file.dashboard_json : template.rendered])
+ dashboard_json = each.key
+}
diff --git a/variables.tf b/variables.tf
index 428f3dc..bf74452 100644
--- a/variables.tf
+++ b/variables.tf
@@ -260,6 +260,15 @@ variable "disable_monitoring" {
EOL
}
+variable "create_monitoring_dashboard" {
+ type = bool
+ default = false
+ description = <<-EOL
+ Optional. Determines whether to create the monitoring dashboard defined in ./dashboard.json
+ for the provisioned Cloud Run service. Defaults to false.
+EOL
+}
+
variable "enable_static_egress_ip" {
default = false
type = bool
--
GitLab