Skip to content

fix(dashboards): deduplicate container queries #1130

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 4, 2025
Merged

fix(dashboards): deduplicate container queries #1130

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7bd9fb1
fix(dashboards): deduplicate container queries
skl Oct 30, 2025
a7cb233
fix: make dev-reload should regenerate all assets
skl Oct 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ dev-port-forward:
kubectl --context kind-kubernetes-mixin wait --for=condition=Ready pods -l app=lgtm --timeout=300s
kubectl --context kind-kubernetes-mixin port-forward service/lgtm 3000:3000 4317:4317 4318:4318 9090:9090

dev-reload: clean-alerts clean-rules generate lint
dev-reload: clean-dashboards clean-alerts clean-rules generate lint
@cp -v prometheus_alerts.yaml scripts/provisioning/prometheus/ && \
cp -v prometheus_rules.yaml scripts/provisioning/prometheus/ && \
kubectl --context kind-kubernetes-mixin apply -f scripts/lgtm.yaml && \
Expand Down
16 changes: 8 additions & 8 deletions dashboards/resources/cluster.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,7 +129,7 @@ local var = g.dashboard.variable;
+ tsPanel.queryOptions.withTargets([
prometheus.new(
'${datasource}',
'sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config
'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster"})) by (namespace)' % $._config
)
+ prometheus.withLegendFormat('__auto'),
]),
Expand All @@ -144,23 +144,23 @@ local var = g.dashboard.variable;
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster"})) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(namespace_cpu:kube_pod_container_resource_requests:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster"})) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(namespace_cpu:kube_pod_container_resource_limits:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster"})) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
])
Expand Down Expand Up @@ -246,7 +246,7 @@ local var = g.dashboard.variable;
+ tsPanel.queryOptions.withTargets([
prometheus.new(
'${datasource}',
'sum(container_memory_rss{%(cadvisorSelector)s, %(clusterLabel)s="$cluster", container!=""}) by (namespace)' % $._config
'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_rss{%(cadvisorSelector)s, %(clusterLabel)s="$cluster", container!=""})) by (namespace)' % $._config
)
+ prometheus.withLegendFormat('__auto'),
]),
Expand All @@ -261,23 +261,23 @@ local var = g.dashboard.variable;
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(container_memory_rss{%(cadvisorSelector)s, %(clusterLabel)s="$cluster", container!=""}) by (namespace)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_rss{%(cadvisorSelector)s, %(clusterLabel)s="$cluster", container!=""})) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(namespace_memory:kube_pod_container_resource_requests:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(container_memory_rss{%(cadvisorSelector)s, %(clusterLabel)s="$cluster", container!=""}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_rss{%(cadvisorSelector)s, %(clusterLabel)s="$cluster", container!=""})) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(namespace_memory:kube_pod_container_resource_limits:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),

prometheus.new('${datasource}', 'sum(container_memory_rss{%(cadvisorSelector)s, %(clusterLabel)s="$cluster", container!=""}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_rss{%(cadvisorSelector)s, %(clusterLabel)s="$cluster", container!=""})) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{%(clusterLabel)s="$cluster"}) by (namespace)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
])
Expand Down
16 changes: 8 additions & 8 deletions dashboards/resources/multi-cluster.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,27 +99,27 @@ local var = g.dashboard.variable;
cpuUsage: [
tsPanel.new('CPU Usage')
+ tsPanel.queryOptions.withTargets([
prometheus.new('${datasource}', 'sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m) by (%(clusterLabel)s)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m)) by (%(clusterLabel)s)' % $._config)
+ prometheus.withLegendFormat('__auto'),
]),
],

cpuQuota: [
g.panel.table.new('CPU Quota')
+ g.panel.table.queryOptions.withTargets([
prometheus.new('${datasource}', 'sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m) by (%(clusterLabel)s)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m)) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
prometheus.new('${datasource}', 'sum(kube_pod_container_resource_requests{%(kubeStateMetricsSelector)s, resource="cpu"}) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
prometheus.new('${datasource}', 'sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m) by (%(clusterLabel)s) / sum(kube_pod_container_resource_requests{%(kubeStateMetricsSelector)s, resource="cpu"}) by (%(clusterLabel)s)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m)) by (%(clusterLabel)s) / sum(kube_pod_container_resource_requests{%(kubeStateMetricsSelector)s, resource="cpu"}) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
prometheus.new('${datasource}', 'sum(kube_pod_container_resource_limits{%(kubeStateMetricsSelector)s, resource="cpu"}) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
prometheus.new('${datasource}', 'sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m) by (%(clusterLabel)s) / sum(kube_pod_container_resource_limits{%(kubeStateMetricsSelector)s, resource="cpu"}) by (%(clusterLabel)s)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m)) by (%(clusterLabel)s) / sum(kube_pod_container_resource_limits{%(kubeStateMetricsSelector)s, resource="cpu"}) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
])
Expand Down Expand Up @@ -197,7 +197,7 @@ local var = g.dashboard.variable;
+ tsPanel.standardOptions.withUnit('bytes')
+ tsPanel.queryOptions.withTargets([
// Not using container_memory_usage_bytes here because that includes page cache
prometheus.new('${datasource}', 'sum(container_memory_rss{%(cadvisorSelector)s, container!=""}) by (%(clusterLabel)s)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_rss{%(cadvisorSelector)s, container!=""})) by (%(clusterLabel)s)' % $._config)
+ prometheus.withLegendFormat('__auto'),
]),
],
Expand All @@ -206,19 +206,19 @@ local var = g.dashboard.variable;
g.panel.table.new('Memory Requests by Cluster')
+ g.panel.table.standardOptions.withUnit('bytes')
+ g.panel.table.queryOptions.withTargets([
prometheus.new('${datasource}', 'sum(container_memory_rss{%(cadvisorSelector)s, container!=""}) by (%(clusterLabel)s)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_rss{%(cadvisorSelector)s, container!=""})) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
prometheus.new('${datasource}', 'sum(kube_pod_container_resource_requests{%(kubeStateMetricsSelector)s, resource="memory"}) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
prometheus.new('${datasource}', 'sum(container_memory_rss{%(cadvisorSelector)s, container!=""}) by (%(clusterLabel)s) / sum(kube_pod_container_resource_requests{%(kubeStateMetricsSelector)s, resource="memory"}) by (%(clusterLabel)s)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_rss{%(cadvisorSelector)s, container!=""})) by (%(clusterLabel)s) / sum(kube_pod_container_resource_requests{%(kubeStateMetricsSelector)s, resource="memory"}) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
prometheus.new('${datasource}', 'sum(kube_pod_container_resource_limits{%(kubeStateMetricsSelector)s, resource="memory"}) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
prometheus.new('${datasource}', 'sum(container_memory_rss{%(cadvisorSelector)s, container!=""}) by (%(clusterLabel)s) / sum(kube_pod_container_resource_limits{%(kubeStateMetricsSelector)s, resource="memory"}) by (%(clusterLabel)s)' % $._config)
prometheus.new('${datasource}', 'sum(max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_rss{%(cadvisorSelector)s, container!=""})) by (%(clusterLabel)s) / sum(kube_pod_container_resource_limits{%(kubeStateMetricsSelector)s, resource="memory"}) by (%(clusterLabel)s)' % $._config)
+ prometheus.withInstant(true)
+ prometheus.withFormat('table'),
])
Expand Down
Loading