From 82e03978b89938219958032efb1448cc76baa181 Mon Sep 17 00:00:00 2001 From: Saumit Date: Sat, 27 Sep 2025 02:14:26 +0530 Subject: Initial snapshot - OpenTelemetry demo 2.1.3 -f --- .../alerting/cart-service-alerting.yml | 93 ++++++++++++++++++++++ 1 file changed, 93 insertions(+) create mode 100644 src/grafana/provisioning/alerting/cart-service-alerting.yml (limited to 'src/grafana/provisioning/alerting') diff --git a/src/grafana/provisioning/alerting/cart-service-alerting.yml b/src/grafana/provisioning/alerting/cart-service-alerting.yml new file mode 100644 index 0000000..d811eca --- /dev/null +++ b/src/grafana/provisioning/alerting/cart-service-alerting.yml @@ -0,0 +1,93 @@ +# Copyright The OpenTelemetry Authors +# SPDX-License-Identifier: Apache-2.0 + +--- +apiVersion: 1 +groups: + - orgId: 1 + name: otel-demo + folder: cart + interval: 1m + rules: + - uid: des78nlna99tsf + title: CartAddItemHighLatency + condition: p95_threshold + data: + - refId: p95_duration + relativeTimeRange: + from: 600 + to: 0 + datasourceUid: webstore-metrics + model: + editorMode: code + expr: |- + histogram_quantile( + 0.95, + sum by (deployment_environment_name, service_namespace, service_name, service_instance_id, http_route, http_request_method, le) ( + rate( + http_server_request_duration_seconds_bucket{ + deployment_environment_name="", + service_namespace="opentelemetry-demo", + service_name="cart", + http_request_method="POST", + http_route="/oteldemo.CartService/AddItem" + }[5m] + ) + ) + ) + instant: true + interval: "" + intervalMs: 1000 + legendFormat: __auto + maxDataPoints: 43200 + range: false + refId: p95_duration + - refId: p95_threshold + datasourceUid: __expr__ + model: + conditions: + - evaluator: + params: + - 0.0001 + type: gt + operator: + type: and + query: + params: + - C + reducer: + params: [] + type: last + type: query + datasource: + type: __expr__ + uid: __expr__ + expression: p95_duration + intervalMs: 1000 + maxDataPoints: 43200 + refId: p95_threshold + type: threshold + dashboardUid: febljk0a32qyoa + panelId: 17 + noDataState: NoData + execErrState: Error + for: 1m + keepFiringFor: 2m + annotations: + description: |- + The 95th percentile response time for operation {{ $labels.service_namespace + }}/{{ $labels.service_name }} "{{ $labels.http_request_method }} {{ + $labels.http_route }}" has been + above xxx seconds for 2 minutes on {{ $labels.service_instance_id}}. Current + value: {{ .Value | humanizeDuration }}. + summary: |- + High P95 for {{ $labels.service_namespace }}/{{ $labels.service_name }} "{{ + $labels.http_request_method }} {{ $labels.http_route }}" + labels: + service_name: cart + service_namespace: opentelemetry-demo + severity: warning + team_name: webstore + isPaused: false + notification_settings: + receiver: grafana-default-email -- cgit v1.2.3