Skip to content

fixes #6486

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
kanwarujjaval merged 3 commits into from
Jul 29, 2025
Merged

fixes #6486

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
57dfa41
dashfixes
kanwarujjaval Jul 29, 2025
2c9588e
feat: add kube-state-metrics and node-exporter for Kubernetes infrast…
kanwarujjaval Jul 29, 2025
515d2d3
Merge branch 'newarchitecture' of github.com:Countly/countly-server i…
kanwarujjaval Jul 29, 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
161 changes: 158 additions & 3 deletions k8s-production/observability-stack/alloy.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ rules:
resources:
- nodes
- nodes/proxy
- nodes/metrics
- services
- endpoints
- pods
Expand All @@ -21,6 +22,11 @@ rules:
resources:
- configmaps
verbs: ["get"]
- apiGroups: ["metrics.k8s.io"]
resources:
- nodes
- pods
verbs: ["get", "list"]
- apiGroups: ["apps"]
resources:
- daemonsets
Expand Down Expand Up @@ -152,7 +158,7 @@ data:
values = {
traceID = "trace_id",
spanID = "span_id",
level = null,
level = "level",
}
}

Expand Down Expand Up @@ -192,7 +198,7 @@ data:
send = false
}

send_exemplars = true
send_exemplars = false
send_native_histograms = false
}

Expand Down Expand Up @@ -336,6 +342,151 @@ data:
job_name = "alloy-internal"
scrape_interval = "30s"
}

// ===== Kubernetes Infrastructure Monitoring =====

// kube-state-metrics discovery
discovery.kubernetes "kube_state_metrics" {
role = "service"
namespaces {
names = ["countly-observability"]
}
}

discovery.relabel "kube_state_metrics" {
targets = discovery.kubernetes.kube_state_metrics.targets

rule {
source_labels = ["__meta_kubernetes_service_name"]
regex = "kube-state-metrics"
action = "keep"
}

rule {
source_labels = ["__meta_kubernetes_service_port_name"]
regex = "http-metrics"
action = "keep"
}

rule {
source_labels = ["__address__"]
target_label = "__address__"
replacement = "${1}:8080"
regex = "([^:]+)(?::\\d+)?"
}
}

prometheus.scrape "kube_state_metrics" {
targets = discovery.relabel.kube_state_metrics.output
forward_to = [prometheus.remote_write.default.receiver]
job_name = "kube-state-metrics"
scrape_interval = "30s"
scrape_timeout = "10s"
honor_labels = true
}

// node-exporter discovery
discovery.kubernetes "node_exporter" {
role = "pod"
namespaces {
names = ["countly-observability"]
}
}

discovery.relabel "node_exporter" {
targets = discovery.kubernetes.node_exporter.targets

rule {
source_labels = ["__meta_kubernetes_pod_label_app"]
regex = "node-exporter"
action = "keep"
}

rule {
source_labels = ["__meta_kubernetes_pod_container_port_name"]
regex = "http-metrics"
action = "keep"
}

rule {
source_labels = ["__meta_kubernetes_pod_node_name"]
target_label = "node"
}

rule {
source_labels = ["__meta_kubernetes_pod_host_ip"]
target_label = "__address__"
replacement = "${1}:9100"
}
}

prometheus.scrape "node_exporter" {
targets = discovery.relabel.node_exporter.output
forward_to = [prometheus.remote_write.default.receiver]
job_name = "node-exporter"
scrape_interval = "30s"
scrape_timeout = "29s"

// Limit metrics to reduce timeout issues
metric_relabel_configs = [
// Drop detailed filesystem metrics for docker/k8s internal mounts
{
source_labels = ["__name__", "mountpoint"]
regex = "node_filesystem.*;/var/lib/docker/.*"
action = "drop"
},
{
source_labels = ["__name__", "mountpoint"]
regex = "node_filesystem.*;/var/lib/kubelet/.*"
action = "drop"
}
]
}

// cAdvisor metrics from kubelet
discovery.kubernetes "kubelet" {
role = "node"
}

discovery.relabel "kubelet_cadvisor" {
targets = discovery.kubernetes.kubelet.targets

rule {
source_labels = ["__address__"]
regex = "([^:]+):?(\\d+)?"
target_label = "__address__"
replacement = "${1}:10250"
}

rule {
source_labels = ["__meta_kubernetes_node_name"]
target_label = "node"
}

rule {
target_label = "__metrics_path__"
replacement = "/metrics/cadvisor"
}

rule {
target_label = "__scheme__"
replacement = "https"
}
}

prometheus.scrape "kubelet_cadvisor" {
targets = discovery.relabel.kubelet_cadvisor.output
forward_to = [prometheus.remote_write.default.receiver]
job_name = "kubelet-cadvisor"
scrape_interval = "30s"
scrape_timeout = "10s"

tls_config {
insecure_skip_verify = true
}

bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
}

//////////////////////////////////////////////////////////////
// === Profiles pipeline (Pyroscope Push API) ================
Expand Down Expand Up @@ -455,6 +606,8 @@ spec:
- name: varlibdockercontainers
mountPath: /var/lib/docker/containers
readOnly: true
- name: alloy-storage
mountPath: /tmp/alloy
resources:
requests:
cpu: 200m
Expand Down Expand Up @@ -483,4 +636,6 @@ spec:
path: /var/log
- name: varlibdockercontainers
hostPath:
path: /var/lib/docker/containers
path: /var/lib/docker/containers
- name: alloy-storage
emptyDir: {}
59 changes: 16 additions & 43 deletions k8s-production/observability-stack/dashboards-manual/01-countly-platform-overview.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,18 +124,9 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(rate(countly_http_server_duration_milliseconds_count{http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[$__rate_interval])) by (service_name)",
"expr": "sum(rate(countly_http_server_duration_milliseconds_count{service_name=~\"$service_name\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[${__rate_interval}])) by (service_name)",
"legendFormat": "{{service_name}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(rate(http_server_request_duration_seconds_count{job=\"countly-frontend\"}[$__rate_interval]))",
"legendFormat": "countly-frontend",
"refId": "B"
}
],
"title": "🔄 Request Rate (req/s)",
Expand Down Expand Up @@ -226,18 +217,9 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "histogram_quantile(0.95, sum(rate(countly_http_server_duration_milliseconds_bucket{http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[$__rate_interval])) by (service_name, le))",
"expr": "histogram_quantile(0.95, sum(rate(countly_http_server_duration_milliseconds_bucket{service_name=~\"$service_name\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[${__rate_interval}])) by (service_name, le))",
"legendFormat": "{{service_name}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "histogram_quantile(0.95, sum(rate(http_server_request_duration_seconds_bucket{job=\"countly-frontend\"}[$__rate_interval])) by (le)) * 1000",
"legendFormat": "countly-frontend",
"refId": "B"
}
],
"title": "⏱️ Response Time P95 (ms)",
Expand Down Expand Up @@ -330,18 +312,9 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(rate(countly_http_server_duration_milliseconds_count{http_status_code=~\"5..\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[$__rate_interval])) by (service_name) / sum(rate(countly_http_server_duration_milliseconds_count{http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[$__rate_interval])) by (service_name)",
"expr": "sum(rate(countly_http_server_duration_milliseconds_count{service_name=~\"$service_name\",http_status_code=~\"5..\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[${__rate_interval}])) by (service_name) / sum(rate(countly_http_server_duration_milliseconds_count{service_name=~\"$service_name\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[${__rate_interval}])) by (service_name)",
"legendFormat": "{{service_name}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(rate(http_server_request_duration_seconds_count{job=\"countly-frontend\",http_response_status_code=~\"5..\"}[$__rate_interval])) / sum(rate(http_server_request_duration_seconds_count{job=\"countly-frontend\"}[$__rate_interval]))",
"legendFormat": "countly-frontend",
"refId": "B"
}
],
"title": "💥 Error Rate (5xx)",
Expand Down Expand Up @@ -432,7 +405,7 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "increase(process_memory_usage_bytes[30s]) / 6",
"expr": "process_memory_usage_bytes{service_name=~\"$service_name\"} / 1024 / 1024 / 1024",
"legendFormat": "{{service_name}}",
"refId": "A"
}
Expand Down Expand Up @@ -606,7 +579,7 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "up{job=~\"countly.*\"}",
"expr": "count by (service_name) (countly_http_server_duration_milliseconds_count{service_name=~\"$service_name\"}) > 0",
"format": "table",
"instant": true,
"legendFormat": "",
Expand All @@ -617,7 +590,7 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "increase(process_memory_usage_bytes[30s]) / 6",
"expr": "process_memory_usage_bytes{service_name=~\"$service_name\"} / 1024 / 1024 / 1024",
"format": "table",
"instant": true,
"legendFormat": "",
Expand All @@ -628,7 +601,7 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(rate(countly_http_server_duration_milliseconds_count{http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[$__rate_interval])) by (service_name)",
"expr": "sum(rate(countly_http_server_duration_milliseconds_count{service_name=~\"$service_name\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[${__rate_interval}])) by (service_name)",
"format": "table",
"instant": true,
"legendFormat": "",
Expand All @@ -639,7 +612,7 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(rate(countly_http_server_duration_milliseconds_count{http_status_code=~\"5..\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[$__rate_interval])) by (service_name) / sum(rate(countly_http_server_duration_milliseconds_count{http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[$__rate_interval])) by (service_name)",
"expr": "sum(rate(countly_http_server_duration_milliseconds_count{service_name=~\"$service_name\",http_status_code=~\"5..\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[${__rate_interval}])) by (service_name) / sum(rate(countly_http_server_duration_milliseconds_count{service_name=~\"$service_name\",http_route!~\".*/(v1|v2)/(traces|metrics|logs).*\"}[${__rate_interval}])) by (service_name)",
"format": "table",
"instant": true,
"legendFormat": "",
Expand Down Expand Up @@ -863,7 +836,7 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "rate(otelcol_receiver_accepted_spans_total[$__rate_interval])",
"expr": "rate(otelcol_receiver_accepted_spans_total[${__rate_interval}])",
"legendFormat": "Spans/sec",
"refId": "A"
},
Expand All @@ -872,7 +845,7 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "rate(otelcol_receiver_accepted_metric_points_total[$__rate_interval])",
"expr": "rate(otelcol_receiver_accepted_metric_points_total[${__rate_interval}])",
"legendFormat": "Metrics/sec",
"refId": "B"
}
Expand Down Expand Up @@ -957,7 +930,7 @@
"type": "loki",
"uid": "loki"
},
"expr": "sum(rate({namespace=\"countly\"}[$__rate_interval])) by (app)",
"expr": "sum(rate({namespace=\"countly\"}[${__rate_interval}])) by (app)",
"legendFormat": "{{app}}",
"refId": "A"
}
Expand Down Expand Up @@ -1042,7 +1015,7 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "rate(pyroscope_receive_http_request_duration_seconds_count[$__rate_interval])",
"expr": "rate(pyroscope_receive_http_request_duration_seconds_count[${__rate_interval}])",
"legendFormat": "Profiles/sec",
"refId": "A"
}
Expand Down Expand Up @@ -1143,19 +1116,19 @@
"type": "prometheus",
"uid": "prometheus"
},
"definition": "label_values(up{job=~\"countly.*\"}, job)",
"definition": "label_values(countly_http_server_duration_milliseconds_count, service_name)",
"hide": 0,
"includeAll": true,
"label": "Service",
"multi": true,
"name": "service",
"name": "service_name",
"options": [],
"query": {
"query": "label_values(up{job=~\"countly.*\"}, job)",
"query": "label_values(countly_http_server_duration_milliseconds_count, service_name)",
"refId": "StandardVariableQuery"
},
"refresh": 2,
"regex": "",
"regex": "/^countly-.*/",
"skipUrlSync": false,
"sort": 1,
"type": "query"
Expand Down
Loading
Loading