diff --git a/Makefile b/Makefile index 49522d1b..3fb044e9 100644 --- a/Makefile +++ b/Makefile @@ -34,7 +34,7 @@ ALLOY_CONFIG_FILES_IN_DOCKER = $(subst ./, /data/, $(ALLOY_CONFIG_FILES)) fmt: ## Uses Grafana Alloy to fmt the config @for c in $(ALLOY_CONFIG_FILES_IN_DOCKER); do \ echo "$$c"; \ - docker run --rm --volume "$(shell pwd):/data" -u $(shell id -u) grafana/alloy:v1.0.0 fmt -w $$c ; \ + docker run --rm --volume "$(shell pwd):/data" -u $(shell id -u) grafana/alloy:v1.1.1 fmt -w $$c ; \ done ##@ Docker compose diff --git a/docker-compose/common/compose-include/alloy.yaml b/docker-compose/common/compose-include/alloy.yaml index 104d1cc9..01a24d9d 100644 --- a/docker-compose/common/compose-include/alloy.yaml +++ b/docker-compose/common/compose-include/alloy.yaml @@ -1,7 +1,7 @@ services: alloy: depends_on: { gateway: { condition: service_healthy } } - image: ${ALLOY_IMAGE:-docker.io/grafana/alloy:v1.0.0} + image: ${ALLOY_IMAGE:-docker.io/grafana/alloy:v1.1.1} configs: - source: alloy_config_file target: /etc/alloy/config.alloy diff --git a/docker-compose/common/config/.env b/docker-compose/common/config/.env index 1d3d4b25..e531fc39 100644 --- a/docker-compose/common/config/.env +++ b/docker-compose/common/config/.env @@ -1,4 +1,4 @@ -ALLOY_IMAGE=grafana/alloy:v1.0.0 +ALLOY_IMAGE=grafana/alloy:v1.1.1 AGENT_IMAGE=grafana/agent:v0.40.3 LOKI_IMAGE=grafana/loki:3.0.0 GRAFANA_IMAGE=grafana/grafana:11.0.0 diff --git a/kubernetes/common/alloy/kustomization.yaml b/kubernetes/common/alloy/kustomization.yaml index 38fa78cf..25b9f14b 100644 --- a/kubernetes/common/alloy/kustomization.yaml +++ b/kubernetes/common/alloy/kustomization.yaml @@ -4,7 +4,7 @@ namespace: monitoring-system helmCharts: - name: alloy repo: https://grafana.github.io/helm-charts - version: 0.3.1 + version: 0.3.2 releaseName: alloy namespace: monitoring-system includeCRDs: false diff --git a/kubernetes/common/alloy/manifests/k8s-all-in-one.yaml b/kubernetes/common/alloy/manifests/k8s-all-in-one.yaml index 41a4cb43..1e2b7486 100644 --- a/kubernetes/common/alloy/manifests/k8s-all-in-one.yaml +++ b/kubernetes/common/alloy/manifests/k8s-all-in-one.yaml @@ -7,8 +7,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -21,8 +21,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -125,8 +125,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -4302,8 +4302,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4343,8 +4343,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -4383,8 +4383,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4437,7 +4437,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -4508,7 +4508,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -4524,8 +4524,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -4551,7 +4551,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -4568,17 +4568,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -4590,8 +4592,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4613,8 +4615,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/microservices-mode/logs/k8s-all-in-one.yaml b/kubernetes/microservices-mode/logs/k8s-all-in-one.yaml index 9f7a6ef3..ffd916e6 100644 --- a/kubernetes/microservices-mode/logs/k8s-all-in-one.yaml +++ b/kubernetes/microservices-mode/logs/k8s-all-in-one.yaml @@ -12,7 +12,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki namespace: logging-system --- @@ -25,8 +25,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -51,8 +51,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -155,8 +155,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -332,7 +332,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-runtime namespace: logging-system --- @@ -4721,7 +4721,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-compactor namespace: logging-system spec: @@ -4749,7 +4749,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-distributor namespace: logging-system spec: @@ -4805,7 +4805,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-index-gateway namespace: logging-system spec: @@ -4860,7 +4860,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-ingester namespace: logging-system spec: @@ -4915,7 +4915,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-querier namespace: logging-system spec: @@ -4943,7 +4943,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-query-frontend namespace: logging-system spec: @@ -4976,7 +4976,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 prometheus.io/service-monitor: "false" name: loki-distributed-query-frontend-headless namespace: logging-system @@ -4986,7 +4986,7 @@ spec: - name: http-metrics port: 3100 protocol: TCP - targetPort: http + targetPort: http-metrics - name: grpc port: 9095 protocol: TCP @@ -5011,7 +5011,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-query-scheduler namespace: logging-system spec: @@ -5047,7 +5047,7 @@ spec: - name: http-metrics port: 3100 protocol: TCP - targetPort: http + targetPort: http-metrics - name: grpc port: 9095 protocol: TCP @@ -5066,7 +5066,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-memberlist namespace: logging-system spec: @@ -5091,8 +5091,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5132,8 +5132,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -5223,7 +5223,7 @@ metadata: app.kubernetes.io/name: loki app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-distributor namespace: logging-system spec: @@ -5323,7 +5323,7 @@ metadata: app.kubernetes.io/name: loki app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-querier namespace: logging-system spec: @@ -5433,7 +5433,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-query-frontend namespace: logging-system spec: @@ -5531,7 +5531,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-query-scheduler namespace: logging-system spec: @@ -5714,7 +5714,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-bloom-compactor namespace: logging-system spec: @@ -5822,7 +5822,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-bloom-gateway namespace: logging-system spec: @@ -5931,7 +5931,7 @@ metadata: app.kubernetes.io/name: loki app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-compactor namespace: logging-system spec: @@ -6037,7 +6037,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-index-gateway namespace: logging-system spec: @@ -6141,7 +6141,7 @@ metadata: app.kubernetes.io/name: loki app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-ingester namespace: logging-system spec: @@ -6250,7 +6250,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-pattern-ingester namespace: logging-system spec: @@ -6357,7 +6357,7 @@ metadata: app.kubernetes.io/name: loki app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-ruler namespace: logging-system spec: @@ -6459,8 +6459,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -6513,7 +6513,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -6586,7 +6586,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-distributor namespace: logging-system spec: @@ -6606,7 +6606,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-ingester namespace: logging-system spec: @@ -6631,7 +6631,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-distributed-querier namespace: logging-system spec: @@ -6649,7 +6649,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -6665,8 +6665,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -6692,7 +6692,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -6709,17 +6709,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -6731,8 +6733,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -6788,8 +6790,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/microservices-mode/metrics/k8s-all-in-one.yaml b/kubernetes/microservices-mode/metrics/k8s-all-in-one.yaml index 8f00c340..d582f161 100644 --- a/kubernetes/microservices-mode/metrics/k8s-all-in-one.yaml +++ b/kubernetes/microservices-mode/metrics/k8s-all-in-one.yaml @@ -7,8 +7,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -33,8 +33,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -137,8 +137,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -4570,8 +4570,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4611,8 +4611,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -5835,8 +5835,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5889,7 +5889,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -6679,7 +6679,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -6695,8 +6695,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -6722,7 +6722,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -6739,17 +6739,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -6761,8 +6763,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -7161,8 +7163,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/microservices-mode/profiles/k8s-all-in-one.yaml b/kubernetes/microservices-mode/profiles/k8s-all-in-one.yaml index 14ffa868..f5c03a25 100644 --- a/kubernetes/microservices-mode/profiles/k8s-all-in-one.yaml +++ b/kubernetes/microservices-mode/profiles/k8s-all-in-one.yaml @@ -12,8 +12,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -36,8 +36,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system --- @@ -48,8 +48,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: profiles-system-pyroscope namespace: profiles-system rules: @@ -76,8 +76,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -178,8 +178,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: profiles-system-pyroscope namespace: profiles-system roleRef: @@ -200,8 +200,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -4537,8 +4537,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-config namespace: profiles-system --- @@ -4555,8 +4555,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-overrides-config namespace: profiles-system --- @@ -4627,8 +4627,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4668,8 +4668,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -4757,8 +4757,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-compactor namespace: profiles-system spec: @@ -4781,8 +4781,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-compactor-headless namespace: profiles-system spec: @@ -4806,8 +4806,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-distributor namespace: profiles-system spec: @@ -4830,8 +4830,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-distributor-headless namespace: profiles-system spec: @@ -4855,8 +4855,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-ingester namespace: profiles-system spec: @@ -4879,8 +4879,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-ingester-headless namespace: profiles-system spec: @@ -4903,8 +4903,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-memberlist namespace: profiles-system spec: @@ -4928,8 +4928,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-querier namespace: profiles-system spec: @@ -4952,8 +4952,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-querier-headless namespace: profiles-system spec: @@ -4977,8 +4977,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-query-frontend namespace: profiles-system spec: @@ -5001,8 +5001,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-query-frontend-headless namespace: profiles-system spec: @@ -5026,8 +5026,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-query-scheduler namespace: profiles-system spec: @@ -5050,8 +5050,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-query-scheduler-headless namespace: profiles-system spec: @@ -5075,8 +5075,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-store-gateway namespace: profiles-system spec: @@ -5099,8 +5099,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-store-gateway-headless namespace: profiles-system spec: @@ -5209,8 +5209,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-distributor namespace: profiles-system spec: @@ -5223,7 +5223,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -5251,7 +5251,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: distributor ports: @@ -5300,8 +5300,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-querier namespace: profiles-system spec: @@ -5314,7 +5314,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -5342,7 +5342,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: querier ports: @@ -5391,8 +5391,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-query-frontend namespace: profiles-system spec: @@ -5405,7 +5405,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -5433,7 +5433,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: query-frontend ports: @@ -5482,8 +5482,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-query-scheduler namespace: profiles-system spec: @@ -5496,7 +5496,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -5524,7 +5524,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: query-scheduler ports: @@ -5573,8 +5573,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5627,7 +5627,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -5699,8 +5699,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-compactor namespace: profiles-system spec: @@ -5715,7 +5715,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -5743,7 +5743,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: compactor ports: @@ -5796,8 +5796,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-ingester namespace: profiles-system spec: @@ -5812,7 +5812,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -5840,7 +5840,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: ingester ports: @@ -5890,8 +5890,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-store-gateway namespace: profiles-system spec: @@ -5906,7 +5906,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -5934,7 +5934,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: store-gateway ports: @@ -5982,7 +5982,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -5998,8 +5998,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -6025,7 +6025,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -6042,17 +6042,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -6064,8 +6066,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -6121,8 +6123,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/microservices-mode/profiles/pyroscope/kustomization.yaml b/kubernetes/microservices-mode/profiles/pyroscope/kustomization.yaml index ea76849b..9543ec52 100644 --- a/kubernetes/microservices-mode/profiles/pyroscope/kustomization.yaml +++ b/kubernetes/microservices-mode/profiles/pyroscope/kustomization.yaml @@ -2,7 +2,7 @@ apiVersion: kustomize.config.k8s.io/v1beta1 kind: Kustomization helmCharts: - name: pyroscope - version: 1.5.1 + version: 1.6.0 repo: https://grafana.github.io/helm-charts releaseName: pyroscope namespace: profiles-system diff --git a/kubernetes/microservices-mode/traces/k8s-all-in-one.yaml b/kubernetes/microservices-mode/traces/k8s-all-in-one.yaml index 3a86fff5..d363ecbf 100644 --- a/kubernetes/microservices-mode/traces/k8s-all-in-one.yaml +++ b/kubernetes/microservices-mode/traces/k8s-all-in-one.yaml @@ -36,8 +36,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -62,7 +62,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed namespace: tracing-system --- @@ -75,8 +75,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -200,8 +200,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -4975,7 +4975,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-config namespace: tracing-system --- @@ -4991,7 +4991,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-runtime namespace: tracing-system --- @@ -5151,8 +5151,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5192,8 +5192,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -5282,7 +5282,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-compactor namespace: tracing-system spec: @@ -5306,7 +5306,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-distributor namespace: tracing-system spec: @@ -5345,7 +5345,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 prometheus.io/service-monitor: "false" name: tempo-distributed-distributor-discovery namespace: tracing-system @@ -5382,7 +5382,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-gossip-ring namespace: tracing-system spec: @@ -5408,7 +5408,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-ingester namespace: tracing-system spec: @@ -5435,7 +5435,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 prometheus.io/service-monitor: "false" name: tempo-distributed-ingester-discovery namespace: tracing-system @@ -5466,7 +5466,7 @@ metadata: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-metrics-generator namespace: tracing-system spec: @@ -5494,7 +5494,7 @@ metadata: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 prometheus.io/service-monitor: "false" name: tempo-distributed-metrics-generator-discovery namespace: tracing-system @@ -5524,7 +5524,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-querier namespace: tracing-system spec: @@ -5551,7 +5551,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-query-frontend namespace: tracing-system spec: @@ -5578,7 +5578,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-query-frontend-discovery namespace: tracing-system spec: @@ -5697,7 +5697,7 @@ metadata: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-compactor namespace: tracing-system spec: @@ -5716,7 +5716,7 @@ spec: template: metadata: annotations: - checksum/config: 97a82a4cd75974b88b5a01c5ebd17709a43b32ca662368a3490a148c21694573 + checksum/config: 8d91b57c9785073fc1ca15ed620dd8ed9e926f6d7bdd014e6b32b788b59187dd logs.grafana.com/scrape: "true" profiles.grafana.com/cpu.port_name: http-metrics profiles.grafana.com/cpu.scrape: "true" @@ -5731,7 +5731,7 @@ spec: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 spec: containers: - args: @@ -5798,7 +5798,7 @@ metadata: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-distributor namespace: tracing-system spec: @@ -5813,7 +5813,7 @@ spec: template: metadata: annotations: - checksum/config: 97a82a4cd75974b88b5a01c5ebd17709a43b32ca662368a3490a148c21694573 + checksum/config: 8d91b57c9785073fc1ca15ed620dd8ed9e926f6d7bdd014e6b32b788b59187dd logs.grafana.com/scrape: "true" profiles.grafana.com/cpu.port_name: http-metrics profiles.grafana.com/cpu.scrape: "true" @@ -5828,7 +5828,7 @@ spec: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 spec: affinity: podAntiAffinity: @@ -5935,7 +5935,7 @@ metadata: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-metrics-generator namespace: tracing-system spec: @@ -5950,7 +5950,7 @@ spec: template: metadata: annotations: - checksum/config: 97a82a4cd75974b88b5a01c5ebd17709a43b32ca662368a3490a148c21694573 + checksum/config: 8d91b57c9785073fc1ca15ed620dd8ed9e926f6d7bdd014e6b32b788b59187dd logs.grafana.com/scrape: "true" profiles.grafana.com/cpu.port_name: http-metrics profiles.grafana.com/cpu.scrape: "true" @@ -5965,7 +5965,7 @@ spec: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 spec: affinity: podAntiAffinity: @@ -6063,7 +6063,7 @@ metadata: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-querier namespace: tracing-system spec: @@ -6082,7 +6082,7 @@ spec: template: metadata: annotations: - checksum/config: 97a82a4cd75974b88b5a01c5ebd17709a43b32ca662368a3490a148c21694573 + checksum/config: 8d91b57c9785073fc1ca15ed620dd8ed9e926f6d7bdd014e6b32b788b59187dd logs.grafana.com/scrape: "true" profiles.grafana.com/cpu.port_name: http-metrics profiles.grafana.com/cpu.scrape: "true" @@ -6097,7 +6097,7 @@ spec: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 spec: affinity: podAntiAffinity: @@ -6197,7 +6197,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-query-frontend namespace: tracing-system spec: @@ -6216,7 +6216,7 @@ spec: template: metadata: annotations: - checksum/config: 97a82a4cd75974b88b5a01c5ebd17709a43b32ca662368a3490a148c21694573 + checksum/config: 8d91b57c9785073fc1ca15ed620dd8ed9e926f6d7bdd014e6b32b788b59187dd logs.grafana.com/scrape: "true" profiles.grafana.com/cpu.port_name: http-metrics profiles.grafana.com/cpu.scrape: "true" @@ -6230,7 +6230,7 @@ spec: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: tempo app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 spec: affinity: podAntiAffinity: @@ -6444,8 +6444,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -6498,7 +6498,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -6572,7 +6572,7 @@ metadata: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-ingester namespace: tracing-system spec: @@ -6587,7 +6587,7 @@ spec: template: metadata: annotations: - checksum/config: 97a82a4cd75974b88b5a01c5ebd17709a43b32ca662368a3490a148c21694573 + checksum/config: 8d91b57c9785073fc1ca15ed620dd8ed9e926f6d7bdd014e6b32b788b59187dd logs.grafana.com/scrape: "true" profiles.grafana.com/cpu.port_name: http-metrics profiles.grafana.com/cpu.scrape: "true" @@ -6602,7 +6602,7 @@ spec: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 spec: affinity: podAntiAffinity: @@ -6709,7 +6709,7 @@ metadata: app.kubernetes.io/name: tempo app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 2.4.2 - helm.sh/chart: tempo-distributed-1.9.10 + helm.sh/chart: tempo-distributed-1.9.11 name: tempo-distributed-ingester namespace: tracing-system spec: @@ -6727,7 +6727,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -6743,8 +6743,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -6770,7 +6770,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -6787,17 +6787,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -6844,8 +6846,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -6901,8 +6903,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/monolithic-mode/all-in-one/k8s-all-in-one.yaml b/kubernetes/monolithic-mode/all-in-one/k8s-all-in-one.yaml index 0a3e797d..8f28db08 100644 --- a/kubernetes/monolithic-mode/all-in-one/k8s-all-in-one.yaml +++ b/kubernetes/monolithic-mode/all-in-one/k8s-all-in-one.yaml @@ -41,8 +41,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -93,8 +93,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system --- @@ -118,8 +118,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: profiles-system-pyroscope namespace: profiles-system rules: @@ -146,8 +146,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -483,8 +483,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: profiles-system-pyroscope namespace: profiles-system roleRef: @@ -505,8 +505,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -5228,8 +5228,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-config namespace: profiles-system --- @@ -5244,8 +5244,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-overrides-config namespace: profiles-system --- @@ -5547,8 +5547,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5588,8 +5588,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -5727,8 +5727,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system spec: @@ -5751,8 +5751,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 prometheus.io/service-monitor: "false" name: pyroscope-headless namespace: profiles-system @@ -5776,8 +5776,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-memberlist namespace: profiles-system spec: @@ -6153,8 +6153,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -6207,7 +6207,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -6279,8 +6279,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system spec: @@ -6295,7 +6295,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -6323,7 +6323,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: pyroscope ports: @@ -6462,8 +6462,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system spec: @@ -6594,7 +6594,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -6610,8 +6610,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -6637,7 +6637,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -6654,17 +6654,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -6711,8 +6713,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -6767,8 +6769,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system spec: @@ -6833,8 +6835,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/monolithic-mode/logs/k8s-all-in-one.yaml b/kubernetes/monolithic-mode/logs/k8s-all-in-one.yaml index 6a30f807..6e8c8e82 100644 --- a/kubernetes/monolithic-mode/logs/k8s-all-in-one.yaml +++ b/kubernetes/monolithic-mode/logs/k8s-all-in-one.yaml @@ -31,8 +31,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -57,8 +57,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -182,8 +182,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -4796,8 +4796,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4837,8 +4837,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -5133,8 +5133,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5187,7 +5187,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -5258,7 +5258,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -5274,8 +5274,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -5301,7 +5301,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -5318,17 +5318,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -5375,8 +5377,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5432,8 +5434,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/monolithic-mode/metrics/k8s-all-in-one.yaml b/kubernetes/monolithic-mode/metrics/k8s-all-in-one.yaml index 246314c6..cdd9e2ec 100644 --- a/kubernetes/monolithic-mode/metrics/k8s-all-in-one.yaml +++ b/kubernetes/monolithic-mode/metrics/k8s-all-in-one.yaml @@ -7,8 +7,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -33,8 +33,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -137,8 +137,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -4490,8 +4490,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4531,8 +4531,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -4705,8 +4705,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4759,7 +4759,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -4830,7 +4830,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -4846,8 +4846,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -4873,7 +4873,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -4890,17 +4890,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -4912,8 +4914,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4969,8 +4971,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/monolithic-mode/profiles/k8s-all-in-one.yaml b/kubernetes/monolithic-mode/profiles/k8s-all-in-one.yaml index b0d60afd..a35c9577 100644 --- a/kubernetes/monolithic-mode/profiles/k8s-all-in-one.yaml +++ b/kubernetes/monolithic-mode/profiles/k8s-all-in-one.yaml @@ -12,8 +12,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -36,8 +36,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system --- @@ -48,8 +48,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: profiles-system-pyroscope namespace: profiles-system rules: @@ -76,8 +76,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -178,8 +178,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: profiles-system-pyroscope namespace: profiles-system roleRef: @@ -200,8 +200,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -4529,8 +4529,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-config namespace: profiles-system --- @@ -4545,8 +4545,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-overrides-config namespace: profiles-system --- @@ -4617,8 +4617,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4658,8 +4658,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -4747,8 +4747,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system spec: @@ -4771,8 +4771,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 prometheus.io/service-monitor: "false" name: pyroscope-headless namespace: profiles-system @@ -4796,8 +4796,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope-memberlist namespace: profiles-system spec: @@ -4906,8 +4906,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4960,7 +4960,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -5032,8 +5032,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system spec: @@ -5048,7 +5048,7 @@ spec: template: metadata: annotations: - checksum/config: b357ed79c949078f193a9e0254cfecb7a6747996038df7d269b85c32469c9077 + checksum/config: cb025ee6893a34c1e06cdacdb1ea9623f179d7c47b0b415192a99feab0885556 profiles.grafana.com/cpu.port_name: http2 profiles.grafana.com/cpu.scrape: "true" profiles.grafana.com/goroutine.port_name: http2 @@ -5076,7 +5076,7 @@ spec: envFrom: - secretRef: name: pyroscope-env-h982fgc652 - image: grafana/pyroscope:1.5.0 + image: grafana/pyroscope:1.6.0 imagePullPolicy: IfNotPresent name: pyroscope ports: @@ -5125,8 +5125,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system spec: @@ -5144,7 +5144,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -5160,8 +5160,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -5187,7 +5187,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -5204,17 +5204,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -5226,8 +5228,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5282,8 +5284,8 @@ metadata: app.kubernetes.io/instance: pyroscope app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: pyroscope - app.kubernetes.io/version: 1.5.0 - helm.sh/chart: pyroscope-1.5.1 + app.kubernetes.io/version: 1.6.0 + helm.sh/chart: pyroscope-1.6.0 name: pyroscope namespace: profiles-system spec: @@ -5319,8 +5321,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/monolithic-mode/profiles/pyroscope/kustomization.yaml b/kubernetes/monolithic-mode/profiles/pyroscope/kustomization.yaml index a5f42009..f7627c5a 100644 --- a/kubernetes/monolithic-mode/profiles/pyroscope/kustomization.yaml +++ b/kubernetes/monolithic-mode/profiles/pyroscope/kustomization.yaml @@ -3,7 +3,7 @@ kind: Kustomization namespace: profiles-system helmCharts: - name: pyroscope - version: 1.5.1 + version: 1.6.0 repo: https://grafana.github.io/helm-charts releaseName: pyroscope namespace: profiles-system diff --git a/kubernetes/monolithic-mode/traces/k8s-all-in-one.yaml b/kubernetes/monolithic-mode/traces/k8s-all-in-one.yaml index 986368f0..e397e1e8 100644 --- a/kubernetes/monolithic-mode/traces/k8s-all-in-one.yaml +++ b/kubernetes/monolithic-mode/traces/k8s-all-in-one.yaml @@ -36,8 +36,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -75,8 +75,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -200,8 +200,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -5150,8 +5150,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5191,8 +5191,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -5551,8 +5551,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5605,7 +5605,7 @@ spec: - secretRef: name: alloy-env-7hg2fmmgdb optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -5766,7 +5766,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -5782,8 +5782,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -5809,7 +5809,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -5826,17 +5826,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -5883,8 +5885,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5969,8 +5971,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/read-write-mode/logs/k8s-all-in-one.yaml b/kubernetes/read-write-mode/logs/k8s-all-in-one.yaml index 8e43a7bd..6f9ab163 100644 --- a/kubernetes/read-write-mode/logs/k8s-all-in-one.yaml +++ b/kubernetes/read-write-mode/logs/k8s-all-in-one.yaml @@ -12,7 +12,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki namespace: logging-system --- @@ -25,8 +25,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -51,8 +51,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -154,7 +154,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-clusterrole rules: - apiGroups: @@ -176,8 +176,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -196,7 +196,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-clusterrolebinding roleRef: apiGroup: rbac.authorization.k8s.io @@ -365,7 +365,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-runtime namespace: logging-system --- @@ -4728,7 +4728,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-backend namespace: logging-system spec: @@ -4783,7 +4783,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-memberlist namespace: logging-system spec: @@ -4836,7 +4836,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-read namespace: logging-system spec: @@ -4893,7 +4893,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-write namespace: logging-system spec: @@ -4950,8 +4950,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4991,8 +4991,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -5082,7 +5082,7 @@ metadata: app.kubernetes.io/name: loki app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-read namespace: logging-system spec: @@ -5277,7 +5277,7 @@ metadata: app.kubernetes.io/name: loki app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-backend namespace: logging-system spec: @@ -5412,7 +5412,7 @@ metadata: app.kubernetes.io/name: loki app.kubernetes.io/part-of: memberlist app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-write namespace: logging-system spec: @@ -5516,8 +5516,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5570,7 +5570,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -5643,7 +5643,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-backend namespace: logging-system spec: @@ -5663,7 +5663,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-read namespace: logging-system spec: @@ -5683,7 +5683,7 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: loki app.kubernetes.io/version: 3.0.0 - helm.sh/chart: loki-6.6.1 + helm.sh/chart: loki-6.6.2 name: loki-write namespace: logging-system spec: @@ -5701,7 +5701,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -5717,8 +5717,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -5744,7 +5744,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -5761,17 +5761,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -5783,8 +5785,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5840,8 +5842,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/kubernetes/read-write-mode/metrics/k8s-all-in-one.yaml b/kubernetes/read-write-mode/metrics/k8s-all-in-one.yaml index 87b2c1e0..d484e62a 100644 --- a/kubernetes/read-write-mode/metrics/k8s-all-in-one.yaml +++ b/kubernetes/read-write-mode/metrics/k8s-all-in-one.yaml @@ -7,8 +7,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system --- @@ -21,8 +21,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy rules: - apiGroups: @@ -125,8 +125,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy roleRef: apiGroup: rbac.authorization.k8s.io @@ -4490,8 +4490,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4531,8 +4531,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy-cluster namespace: monitoring-system spec: @@ -4884,8 +4884,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -4938,7 +4938,7 @@ spec: - secretRef: name: alloy-env optional: true - image: docker.io/grafana/alloy:v1.1.0 + image: docker.io/grafana/alloy:v1.1.1 imagePullPolicy: IfNotPresent name: alloy ports: @@ -5009,7 +5009,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -5025,8 +5025,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -5052,7 +5052,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -5069,17 +5069,19 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m --- apiVersion: monitoring.coreos.com/v1 @@ -5091,8 +5093,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: @@ -5213,8 +5215,8 @@ metadata: app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: alloy app.kubernetes.io/part-of: alloy - app.kubernetes.io/version: v1.1.0 - helm.sh/chart: alloy-0.3.1 + app.kubernetes.io/version: v1.1.1 + helm.sh/chart: alloy-0.3.2 name: alloy namespace: monitoring-system spec: diff --git a/monitoring-mixins/alloy-mixin/deploy/alloy-mixin-alerts.yaml b/monitoring-mixins/alloy-mixin/deploy/alloy-mixin-alerts.yaml index 962c5e3a..79dd7b2d 100644 --- a/monitoring-mixins/alloy-mixin/deploy/alloy-mixin-alerts.yaml +++ b/monitoring-mixins/alloy-mixin/deploy/alloy-mixin-alerts.yaml @@ -1,5 +1,5 @@ groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -11,8 +11,8 @@ groups: message: Nodes report different number of peers vs. the count of observed Alloy metrics. Some Alloy metrics may be missing or the cluster is in a split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -35,7 +35,7 @@ groups: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -50,15 +50,15 @@ groups: message: Unhealthy components detected. expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 for: 5m diff --git a/monitoring-mixins/alloy-mixin/deploy/manifests/k8s-all-in-one.yaml b/monitoring-mixins/alloy-mixin/deploy/manifests/k8s-all-in-one.yaml index 4c61fdb7..dbf5b723 100644 --- a/monitoring-mixins/alloy-mixin/deploy/manifests/k8s-all-in-one.yaml +++ b/monitoring-mixins/alloy-mixin/deploy/manifests/k8s-all-in-one.yaml @@ -2847,11 +2847,11 @@ metadata: apiVersion: monitoring.coreos.com/v1 kind: PrometheusRule metadata: - name: agent-flow-mixin-alerts + name: alloy-mixin-alerts namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -2867,8 +2867,8 @@ spec: split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -2894,7 +2894,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -2911,15 +2911,17 @@ spec: expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) + > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) + > 0 for: 5m diff --git a/monitoring-mixins/alloy-mixin/deploy/prometheus-alerts.yaml b/monitoring-mixins/alloy-mixin/deploy/prometheus-alerts.yaml index 03d8cc53..dba4172d 100644 --- a/monitoring-mixins/alloy-mixin/deploy/prometheus-alerts.yaml +++ b/monitoring-mixins/alloy-mixin/deploy/prometheus-alerts.yaml @@ -6,7 +6,7 @@ metadata: namespace: monitoring-system spec: groups: - - name: clustering + - name: alloy_clustering rules: - alert: ClusterNotConverging annotations: @@ -18,8 +18,8 @@ spec: message: Nodes report different number of peers vs. the count of observed Alloy metrics. Some Alloy metrics may be missing or the cluster is in a split brain state. expr: | sum without (state) (cluster_node_peers) != - on (cluster, namespace) group_left - count by (cluster, namespace) (cluster_node_info) + on (cluster, namespace, job) group_left + count by (cluster, namespace, job) (cluster_node_info) for: 15m - alert: ClusterNodeUnhealthy annotations: @@ -42,7 +42,7 @@ spec: message: Cluster nodes are not using the same configuration file. expr: | count without (sha256) ( - max by (cluster, namespace, sha256) (alloy_config_hash and on(cluster, namespace) cluster_node_info) + max by (cluster, namespace, sha256, job) (alloy_config_hash and on(cluster, namespace) cluster_node_info) ) > 1 for: 5m - name: alloy_controller @@ -57,15 +57,15 @@ spec: message: Unhealthy components detected. expr: sum by (cluster, namespace) (alloy_component_controller_running_components{health_type!="healthy"}) > 0 for: 15m - - name: otelcol + - name: alloy_otelcol rules: - alert: OtelcolReceiverRefusedSpans annotations: message: The receiver could not push some spans to the pipeline. - expr: sum(rate(receiver_refused_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(receiver_refused_spans_ratio_total{}[1m])) > 0 for: 5m - alert: OtelcolExporterFailedSpans annotations: message: The exporter failed to send spans to their destination. - expr: sum(rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 + expr: sum by (cluster, namespace) (rate(exporter_send_failed_spans_ratio_total{}[1m])) > 0 for: 5m diff --git a/monitoring-mixins/alloy-mixin/jsonnetfile.json b/monitoring-mixins/alloy-mixin/jsonnetfile.json index d3d7271b..d46c65c9 100644 --- a/monitoring-mixins/alloy-mixin/jsonnetfile.json +++ b/monitoring-mixins/alloy-mixin/jsonnetfile.json @@ -8,7 +8,7 @@ "subdir": "operations/alloy-mixin" } }, - "version": "v1.0.0" + "version": "v1.1.1" } ], "legacyImports": true diff --git a/monitoring-mixins/alloy-mixin/jsonnetfile.lock.json b/monitoring-mixins/alloy-mixin/jsonnetfile.lock.json index 117ab0fb..d188937d 100644 --- a/monitoring-mixins/alloy-mixin/jsonnetfile.lock.json +++ b/monitoring-mixins/alloy-mixin/jsonnetfile.lock.json @@ -8,8 +8,8 @@ "subdir": "operations/alloy-mixin" } }, - "version": "acd9c2a8735f32b731c4aae61f62d93ec51c112e", - "sum": "8P4ZtEkF86ibmgFxWEuA5T7yM46pcYpG3opzale1W0U=" + "version": "2307e103dafa62bb58b70bd3efd41b91daaed22e", + "sum": "S6iPjJ1bt6s2YtjuOJDoEDlpO2IcnVs8vvkff/oEt1c=" } ], "legacyImports": false