chore: pyrscope continuous profiling for coder #43
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Emyrk
changed the title
dannykopping
approved these changes
Aug 5, 2025
| # Source: coder-observability/templates/configmap-collector.yaml | ||
| kind: ConfigMap | ||
| apiVersion: v1 | ||
| metadata: | ||
| name: collector-config | ||
| namespace: coder-observability | ||
| data: | ||
| config.river: "\n// Discover k8s nodes\ndiscovery.kubernetes \"nodes\" {\n role = \"node\"\n}\n\n// Discover k8s pods\ndiscovery.kubernetes \"pods\" {\n role = \"pod\"\n selectors {\n role = \"pod\"\n }\n}\n\ndiscovery.relabel \"pod_logs\" {\n targets = discovery.kubernetes.pods.targets\n \n rule {\n source_labels = [\"__meta_kubernetes_namespace\"]\n target_label = \"namespace\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_name\"]\n target_label = \"pod\"\n }\n // coalesce the following labels and pick the first value; we'll use this to define the \"job\" label\n rule {\n source_labels = [\"__meta_kubernetes_pod_label_app_kubernetes_io_component\", \"app\", \"__meta_kubernetes_pod_container_name\"]\n separator = \"/\"\n target_label = \"__meta_app\"\n action = \"replace\"\n regex = \"^/*([^/]+?)(?:/.*)?$\" // split by the delimiter if it exists, we only want the first one\n replacement = \"${1}\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_namespace\", \"__meta_kubernetes_pod_label_app_kubernetes_io_name\", \"__meta_app\"]\n separator = \"/\"\n target_label = \"job\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_container_name\"]\n target_label = \"container\"\n }\n rule {\n regex = \"__meta_kubernetes_pod_label_(statefulset_kubernetes_io_pod_name|controller_revision_hash)\"\n action = \"labeldrop\"\n }\n rule {\n regex = \"pod_template_generation\"\n action = \"labeldrop\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_phase\"]\n regex = \"Pending|Succeeded|Failed|Completed\"\n action = \"drop\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_node_name\"]\n action = \"replace\"\n target_label = \"node\"\n }\n rule {\n action = \"labelmap\"\n regex = \"__meta_kubernetes_pod_annotation_prometheus_io_param_(.+)\"\n replacement = \"__param_$1\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_uid\", \"__meta_kubernetes_pod_container_name\"]\n separator = \"/\"\n action = \"replace\"\n replacement = \"/var/log/pods/*$1/*.log\"\n target_label = \"__path__\"\n }\n rule {\n action = \"replace\"\n source_labels = [\"__meta_kubernetes_pod_container_id\"]\n regex = \"^(\\\\w+):\\\\/\\\\/.+$\"\n replacement = \"$1\"\n target_label = \"tmp_container_runtime\"\n }\n}\n\ndiscovery.relabel \"pod_metrics\" {\n targets = discovery.kubernetes.pods.targets\n \n rule {\n source_labels = [\"__meta_kubernetes_namespace\"]\n target_label = \"namespace\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_name\"]\n target_label = \"pod\"\n }\n // coalesce the following labels and pick the first value; we'll use this to define the \"job\" label\n rule {\n source_labels = [\"__meta_kubernetes_pod_label_app_kubernetes_io_component\", \"app\", \"__meta_kubernetes_pod_container_name\"]\n separator = \"/\"\n target_label = \"__meta_app\"\n action = \"replace\"\n regex = \"^/*([^/]+?)(?:/.*)?$\" // split by the delimiter if it exists, we only want the first one\n replacement = \"${1}\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_namespace\", \"__meta_kubernetes_pod_label_app_kubernetes_io_name\", \"__meta_app\"]\n separator = \"/\"\n target_label = \"job\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_container_name\"]\n target_label = \"container\"\n }\n rule {\n regex = \"__meta_kubernetes_pod_label_(statefulset_kubernetes_io_pod_name|controller_revision_hash)\"\n action = \"labeldrop\"\n }\n rule {\n regex = \"pod_template_generation\"\n action = \"labeldrop\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_phase\"]\n regex = \"Pending|Succeeded|Failed|Completed\"\n action = \"drop\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_node_name\"]\n action = \"replace\"\n target_label = \"node\"\n }\n rule {\n action = \"labelmap\"\n regex = \"__meta_kubernetes_pod_annotation_prometheus_io_param_(.+)\"\n replacement = \"__param_$1\"\n }\n // drop ports that do not expose Prometheus metrics, but might otherwise be exposed by a container which *also*\n // exposes an HTTP port which exposes metrics\n rule {\n source_labels = [\"__meta_kubernetes_pod_container_port_name\"]\n regex = \"grpc|http-(memberlist|console)\"\n action = \"drop\"\n }\n // adapted from the Prometheus helm chart\n // https://github.com/prometheus-community/helm-charts/blob/862870fc3c847e32479b509e511584d5283126a3/charts/prometheus/values.yaml#L1070\n rule {\n source_labels = [\"__meta_kubernetes_pod_annotation_prometheus_io_scrape\"]\n action = \"keep\"\n regex = \"true\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_annotation_prometheus_io_scheme\"]\n action = \"replace\"\n regex = \"(https?)\"\n target_label = \"__scheme__\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_annotation_prometheus_io_path\"]\n action = \"replace\"\n target_label = \"__metrics_path__\"\n regex = \"(.+)\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_annotation_prometheus_io_port\", \"__meta_kubernetes_pod_ip\"]\n action = \"replace\"\n regex = \"(\\\\d+);(([A-Fa-f0-9]{1,4}::?){1,7}[A-Fa-f0-9]{1,4})\"\n replacement = \"[$2]:$1\"\n target_label = \"__address__\"\n }\n rule {\n source_labels = [\"__meta_kubernetes_pod_annotation_prometheus_io_port\", \"__meta_kubernetes_pod_ip\"]\n action = \"replace\"\n regex = \"(\\\\d+);((([0-9]+?)(\\\\.|$)){4})\"\n replacement = \"$2:$1\"\n target_label = \"__address__\"\n }\n}\n\nlocal.file_match \"pod_logs\" {\n path_targets = discovery.relabel.pod_logs.output\n}\n\nloki.source.file \"pod_logs\" {\n targets = local.file_match.pod_logs.targets\n forward_to = [loki.process.pod_logs.receiver]\n}\n\nloki.process \"pod_logs\" {\n stage.match {\n selector = \"{tmp_container_runtime=\\\"containerd\\\"}\"\n // the cri processing stage extracts the following k/v pairs: log, stream, time, flags\n stage.cri {}\n // Set the extract flags and stream values as labels\n stage.labels {\n values = {\n flags = \"\",\n stream = \"\",\n }\n }\n }\n\n // if the label tmp_container_runtime from above is docker parse using docker\n stage.match {\n selector = \"{tmp_container_runtime=\\\"docker\\\"}\"\n // the docker processing stage extracts the following k/v pairs: log, stream, time\n stage.docker {}\n\n // Set the extract stream value as a label\n stage.labels {\n values = {\n stream = \"\",\n }\n }\n }\n\n // drop the temporary container runtime label as it is no longer needed\n stage.label_drop {\n values = [\"tmp_container_runtime\"]\n }\n\n // parse Coder logs and extract level & logger for efficient filtering\n stage.match {\n selector = \"{pod=~\\\"coder.*\\\"}\" // TODO: make configurable\n\n stage.multiline {\n firstline = \"^(?P<ts>\\\\d{4}-\\\\d{2}-\\\\d{2}\\\\s\\\\d{2}:\\\\d{2}:\\\\d{2}\\\\.\\\\d{3})\"\n max_wait_time = \"10s\"\n }\n\n stage.regex {\n expression = \"^(?P<ts>\\\\d{4}-\\\\d{2}-\\\\d{2}\\\\s\\\\d{2}:\\\\d{2}:\\\\d{2}\\\\.\\\\d{3})\\\\s\\\\[(?P<level>\\\\w+)\\\\]\\\\s\\\\s(?P<logger>[^:]+):\\\\s(?P<line>.+)\"\n }\n\n stage.timestamp {\n source = \"ts\"\n format = \"2006-01-02 15:04:05.000\"\n action_on_failure = \"fudge\" // rather have inaccurate time than drop the log line\n }\n\n stage.labels {\n values = {\n level = \"\",\n logger = \"\",\n }\n }\n }\n\n forward_to = [loki.write.loki.receiver]\n}\n\nloki.write \"loki\" {\n endpoint {\n url = \"http://loki-gateway.coder-observability.svc/loki/api/v1/push\"\n }\n}\n\nprometheus.scrape \"pods\" {\n targets = discovery.relabel.pod_metrics.output\n forward_to = [prometheus.relabel.pods.receiver]\n\n scrape_interval = \"15s\"\n scrape_timeout = \"12s\"\n}\n\n// These are metric_relabel_configs while discovery.relabel are relabel_configs.\n// See https://github.com/grafana/agent/blob/main/internal/converter/internal/prometheusconvert/prometheusconvert.go#L95-L106\nprometheus.relabel \"pods\" {\n forward_to = [prometheus.remote_write.default.receiver]\n\n // Drop kube-state-metrics' labels which clash with ours\n rule {\n source_labels = [\"__name__\", \"container\"]\n regex = \"kube_pod.+;(.+)\"\n target_label = \"container\"\n replacement = \"\"\n }\n rule {\n source_labels = [\"__name__\", \"pod\"]\n regex = \"kube_pod.+;(.+)\"\n target_label = \"pod\"\n replacement = \"\"\n }\n rule {\n source_labels = [\"__name__\", \"namespace\"]\n regex = \"kube_pod.+;(.+)\"\n target_label = \"namespace\"\n replacement = \"\"\n }\n rule {\n source_labels = [\"__name__\", \"exported_container\"]\n // don't replace an empty label\n regex = \"^kube_pod.+;(.+)$\"\n target_label = \"container\"\n replacement = \"$1\"\n }\n rule {\n source_labels = [\"__name__\", \"exported_pod\"]\n // don't replace an empty label\n regex = \"^kube_pod.+;(.+)$\"\n target_label = \"pod\"\n replacement = \"$1\"\n }\n rule {\n source_labels = [\"__name__\", \"exported_namespace\"]\n // don't replace an empty label\n regex = \"^kube_pod.+;(.+)$\"\n target_label = \"namespace\"\n replacement = \"$1\"\n }\n rule {\n regex = \"^(exported_.*|image_.*|container_id|id|uid)$\"\n action = \"labeldrop\"\n }\n}\n\ndiscovery.relabel \"cadvisor\" {\n targets = discovery.kubernetes.nodes.targets\n rule {\n replacement = \"/metrics/cadvisor\"\n target_label = \"__metrics_path__\"\n }\n}\n\nprometheus.scrape \"cadvisor\" {\n targets = discovery.relabel.cadvisor.output\n forward_to = [ prometheus.relabel.cadvisor.receiver ]\n scheme = \"https\"\n tls_config {\n insecure_skip_verify = true\n }\n bearer_token_file = \"/var/run/secrets/kubernetes.io/serviceaccount/token\"\n scrape_interval = \"15s\"\n scrape_timeout = \"12s\"\n}\n\nprometheus.relabel \"cadvisor\" {\n forward_to = [ prometheus.remote_write.default.receiver ]\n\n // Drop empty container labels, addressing https://github.com/google/cadvisor/issues/2688\n rule {\n source_labels = [\"__name__\",\"container\"]\n separator = \"@\"\n regex = \"(container_cpu_.*|container_fs_.*|container_memory_.*)@\"\n action = \"drop\"\n }\n // Drop empty image labels, addressing https://github.com/google/cadvisor/issues/2688\n rule {\n source_labels = [\"__name__\",\"image\"]\n separator = \"@\"\n regex = \"(container_cpu_.*|container_fs_.*|container_memory_.*|container_network_.*)@\"\n action = \"drop\"\n }\n // Drop irrelevant series\n rule {\n source_labels = [\"container\"]\n regex = \"^POD$\"\n action = \"drop\"\n }\n // Drop unnecessary labels\n rule {\n source_labels = [\"id\"]\n target_label = \"id\"\n replacement = \"\"\n }\n rule {\n source_labels = [\"job\"]\n target_label = \"job\"\n replacement = \"\"\n }\n rule {\n source_labels = [\"name\"]\n target_label = \"name\"\n replacement = \"\"\n }\n}\n\nprometheus.remote_write \"default\" {\n endpoint {\n url =\"http://prometheus.coder-observability.svc/api/v1/write\"\n\n // drop instance label which unnecessarily adds new series when pods are restarted, since pod IPs are dynamically assigned\n // NOTE: \"__address__\" is mapped to \"instance\", so will contain <hostname>:<port>\n write_relabel_config {\n regex = \"instance\"\n action = \"labeldrop\"\n }\n }\n}" |
There was a problem hiding this comment.
| @@ -0,0 +1,106 @@ | |||
| # Using kind to test observability | |||
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.