From f2a309f91dbdb5b07871a1c32a2e9a2ae4f1fe02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Miko=C5=82aj=20=C5=9Awi=C4=85tek?= Date: Wed, 4 Oct 2023 15:11:04 +0200 Subject: [PATCH] feat(metrics): allow overriding metrics collector configuration (cherry picked from commit 5dc06a5ef0c8c210aac9eae6417b596ae4c85cb3) --- .changelog/3314.added.txt | 1 + deploy/helm/sumologic/README.md | 2 + .../otelcol/opentelemetrycollector.yaml | 11 +- deploy/helm/sumologic/values.yaml | 19 + .../metrics_collector_otc/basic.output.yaml | 328 +++--- .../metrics_collector_otc/custom.input.yaml | 5 + .../metrics_collector_otc/custom.output.yaml | 1017 +---------------- 7 files changed, 256 insertions(+), 1127 deletions(-) create mode 100644 .changelog/3314.added.txt diff --git a/.changelog/3314.added.txt b/.changelog/3314.added.txt new file mode 100644 index 0000000000..feb0236bae --- /dev/null +++ b/.changelog/3314.added.txt @@ -0,0 +1 @@ +feat(metrics): allow overriding metrics collector configuration \ No newline at end of file diff --git a/deploy/helm/sumologic/README.md b/deploy/helm/sumologic/README.md index b3cf13104b..8f871b3cd0 100644 --- a/deploy/helm/sumologic/README.md +++ b/deploy/helm/sumologic/README.md @@ -142,6 +142,8 @@ The following table lists the configurable parameters of the Sumo Logic chart an | `sumologic.metrics.collector.otelcol.cAdvisor.enabled` | Enable collection of cAdvisor metrics. | `true` | | `sumologic.metrics.collector.otelcol.annotatedPods.enabled` | Enable collection of metrics from Pods annotated with prometheus.io/\* keys. See [docs/collecting-application-metrics.md](/docs/collecting-application-metrics.md#application-metrics-are-exposed-one-endpoint-scenario) for more information. | `true` | | `sumologic.metrics.collector.otelcol.allocationStrategy` | Allocation strategy for the scrape target allocator. Valid values are: least-weighted and consistent-hashing. See: https://github.com/open-telemetry/opentelemetry-operator/blob/main/docs/api.md#opentelemetrycollectorspectargetallocator | `least-weighted` | +| `sumologic.metrics.collector.otelcol.config.merge` | Configuration for otelcol metrics collector, merged with defaults. See also https://github.com/SumoLogic/sumologic-otel-collector/blob/main/docs/configuration.md. | {} | +| `sumologic.metrics.collector.otelcol.config.override` | Configuration for otelcol metrics collector, replaces defaults. See also https://github.com/SumoLogic/sumologic-otel-collector/blob/main/docs/configuration.md. | {} | | `sumologic.metrics.dropHistogramBuckets` | Drop buckets from select high-cardinality histogram metrics, leaving only the sum and count components. | `true` | | `sumologic.metrics.sourceType` | The type of the Sumo Logic source being used for metrics ingestion. Can be `http` or `otlp`. | `http` | | `sumologic.traces.enabled` | Set the enabled flag to true to enable tracing ingestion. _Tracing must be enabled for the account first. Please contact your Sumo representative for activation details_ | `true` | diff --git a/deploy/helm/sumologic/templates/metrics/collector/otelcol/opentelemetrycollector.yaml b/deploy/helm/sumologic/templates/metrics/collector/otelcol/opentelemetrycollector.yaml index 1a7292650b..aa5a39f5c8 100644 --- a/deploy/helm/sumologic/templates/metrics/collector/otelcol/opentelemetrycollector.yaml +++ b/deploy/helm/sumologic/templates/metrics/collector/otelcol/opentelemetrycollector.yaml @@ -1,4 +1,13 @@ {{- if and (eq (include "metrics.otelcol.enabled" .) "true") .Values.sumologic.metrics.collector.otelcol.enabled }} +{{ $baseConfig := (tpl (.Files.Get "conf/metrics/collector/otelcol/config.yaml") .) | fromYaml }} +{{ $mergeConfig := .Values.sumologic.metrics.collector.otelcol.config.merge }} +{{ $overrideConfig := .Values.sumologic.metrics.collector.otelcol.config.override }} +{{ $finalConfig := "" }} +{{ if $overrideConfig }} +{{ $finalConfig = $overrideConfig }} +{{ else }} +{{ $finalConfig = mergeOverwrite $baseConfig $mergeConfig }} +{{ end }} apiVersion: opentelemetry.io/v1alpha1 kind: OpenTelemetryCollector metadata: @@ -98,5 +107,5 @@ spec: - name: file-storage mountPath: /var/lib/storage/otc config: | -{{- (tpl (.Files.Get "conf/metrics/collector/otelcol/config.yaml") .) | nindent 4 }} +{{- $finalConfig | toYaml | nindent 4 }} {{- end }} diff --git a/deploy/helm/sumologic/values.yaml b/deploy/helm/sumologic/values.yaml index 15c8b29c44..ac75f4cfe9 100644 --- a/deploy/helm/sumologic/values.yaml +++ b/deploy/helm/sumologic/values.yaml @@ -548,6 +548,25 @@ sumologic: ## See: https://github.com/open-telemetry/opentelemetry-operator/blob/main/docs/api.md#opentelemetrycollectorspectargetallocator # allocationStrategy: least-weighted + config: + ## Directly alter the OT configuration. The value of this key should be a dictionary, that will + ## be directly merged with the generated configuration, overriding existing values. + ## For example: + # override: + # processors: + # batch: + # send_batch_size: 512 + ## will change the batch size of the pipeline. + ## + ## WARNING: This field is not subject to backwards-compatibility guarantees offered by the rest + ## of this chart. It involves implementation details that may change even in minor versions. + ## Use with caution, and consider opening an issue, so your customization can be added in a safer way. + merge: {} + ## Completely override existing config and replace it with the contents of this value. + ## The value of this key should be a dictionary, that will replace the normal configuration. + ## This is an advanced feature, use with caution, and review the generated configuration first. + override: {} + ## Default metric filters for Sumo Apps enableDefaultFilters: false diff --git a/tests/helm/testdata/goldenfile/metrics_collector_otc/basic.output.yaml b/tests/helm/testdata/goldenfile/metrics_collector_otc/basic.output.yaml index bcebf2c2ad..b59b37d550 100644 --- a/tests/helm/testdata/goldenfile/metrics_collector_otc/basic.output.yaml +++ b/tests/helm/testdata/goldenfile/metrics_collector_otc/basic.output.yaml @@ -66,204 +66,196 @@ spec: config: | exporters: otlphttp: + disable_keep_alives: true endpoint: http://${METADATA_METRICS_SVC}.${NAMESPACE}.svc.cluster.local.:4318 sending_queue: - queue_size: 10000 num_consumers: 10 + queue_size: 10000 storage: file_storage - # this improves load balancing at the cost of more network traffic - disable_keep_alives: true - extensions: - health_check: {} - pprof: {} file_storage: - directory: /var/lib/storage/otc - timeout: 10s compaction: - on_rebound: true directory: /tmp - - + on_rebound: true + directory: /var/lib/storage/otc + timeout: 10s + health_check: {} + pprof: {} processors: batch: send_batch_max_size: 2000 send_batch_size: 1000 timeout: 1s - + filter/drop_unnecessary_metrics: + error_mode: ignore + metrics: + metric: + - resource.attributes["service.name"] != "pod-annotations" and IsMatch(name, + "scrape_.*") + - IsMatch(name, "^(apiserver_request_duration_seconds|coredns_dns_request_duration_seconds|kubelet_runtime_operations_duration_seconds)$") transform/drop_unnecessary_attributes: error_mode: ignore metric_statements: - - context: resource - statements: - - delete_key(attributes, "http.scheme") - - delete_key(attributes, "net.host.name") - - delete_key(attributes, "net.host.port") - - delete_key(attributes, "service.instance.id") - # prometheus receiver adds these automatically - # we drop them to make the rest of our pipeline easier to reason about - # after the collector and metadata are merged, consider using them instead of k8sattributes processor - - delete_matching_keys(attributes, "k8s.*") + - context: resource + statements: + - delete_key(attributes, "http.scheme") + - delete_key(attributes, "net.host.name") + - delete_key(attributes, "net.host.port") + - delete_key(attributes, "service.instance.id") + - delete_matching_keys(attributes, "k8s.*") transform/extract_sum_count_from_histograms: error_mode: ignore metric_statements: - - context: metric - statements: - - extract_sum_metric(true) where IsMatch(name, "^(apiserver_request_duration_seconds|coredns_dns_request_duration_seconds|kubelet_runtime_operations_duration_seconds)$") - - extract_count_metric(true) where IsMatch(name, "^(apiserver_request_duration_seconds|coredns_dns_request_duration_seconds|kubelet_runtime_operations_duration_seconds)$") - filter/drop_unnecessary_metrics: - error_mode: ignore - metrics: - metric: - # we let the metrics from annotations ("kubernetes-pods") through as they are - - resource.attributes["service.name"] != "pod-annotations" and IsMatch(name, "scrape_.*") - # drop histograms we've extracted sums and counts from, but don't want the full thing - - IsMatch(name, "^(apiserver_request_duration_seconds|coredns_dns_request_duration_seconds|kubelet_runtime_operations_duration_seconds)$") - + - context: metric + statements: + - extract_sum_metric(true) where IsMatch(name, "^(apiserver_request_duration_seconds|coredns_dns_request_duration_seconds|kubelet_runtime_operations_duration_seconds)$") + - extract_count_metric(true) where IsMatch(name, "^(apiserver_request_duration_seconds|coredns_dns_request_duration_seconds|kubelet_runtime_operations_duration_seconds)$") receivers: prometheus: config: global: scrape_interval: 30s scrape_configs: - ## scraping metrics basing on annotations: - ## - prometheus.io/scrape: true - to scrape metrics from the pod - ## - prometheus.io/path: /metrics - path which the metric should be scrape from - ## - prometheus.io/port: 9113 - port which the metric should be scrape from - ## rel: https://github.com/prometheus-operator/kube-prometheus/pull/16#issuecomment-424318647 - - job_name: "pod-annotations" - kubernetes_sd_configs: - - role: pod - relabel_configs: - - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape] - action: keep - regex: true - - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path] - action: replace - target_label: __metrics_path__ - regex: (.+) - - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port] - action: replace - regex: ([^:]+)(?::\d+)?;(\d+) - replacement: $1:$2 - target_label: __address__ - - source_labels: [__metrics_path__] - separator: ; - regex: (.*) - target_label: endpoint - replacement: $1 - action: replace - - source_labels: [__meta_kubernetes_namespace] - action: replace - target_label: namespace - - action: labelmap - regex: __meta_kubernetes_pod_label_(.+) - - source_labels: [__meta_kubernetes_pod_name] - separator: ; - regex: (.*) - target_label: pod - replacement: $1 - action: replace - ## These scrape configs are for kubelet metrics - ## Prometheus operator does this by manually maintaining a Service with Endpoints for all Nodes - ## We don't have that capability, so we need to use a static configuration - - job_name: kubelet - scheme: https - authorization: - credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token - tls_config: - ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt - insecure_skip_verify: true - honor_labels: true - kubernetes_sd_configs: - - role: node - metric_relabel_configs: - - action: keep - regex: (?:kubelet_docker_operations_errors(?:|_total)|kubelet_(?:docker|runtime)_operations_duration_seconds_(?:count|sum)|kubelet_running_(?:container|pod)(?:_count|s)|kubelet_(:?docker|runtime)_operations_latency_microseconds(?:|_count|_sum)) - source_labels: [__name__] - - action: labeldrop - regex: id - relabel_configs: - - source_labels: - - __meta_kubernetes_node_name - target_label: node - - target_label: endpoint - replacement: https-metrics - - source_labels: - - __metrics_path__ - target_label: metrics_path - action: replace - - source_labels: - - __address__ - target_label: instance - action: replace - - job_name: cadvisor - scheme: https - authorization: - credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token - tls_config: - ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt - insecure_skip_verify: true - honor_labels: true - metrics_path: /metrics/cadvisor - kubernetes_sd_configs: - - role: node - metric_relabel_configs: - - action: replace - regex: .* - replacement: kubelet - source_labels: [__name__] - target_label: job - - action: keep - regex: (?:container_cpu_usage_seconds_total|container_memory_working_set_bytes|container_fs_usage_bytes|container_fs_limit_bytes|container_cpu_cfs_throttled_seconds_total|container_network_receive_bytes_total|container_network_transmit_bytes_total) - source_labels: [__name__] - ## Drop container metrics with container tag set to an empty string: - ## these are the pod aggregated container metrics which can be aggregated - ## in Sumo anyway. There's also some cgroup-specific time series we also - ## do not need. - - action: drop - source_labels: [__name__, container] - regex: (?:container_cpu_usage_seconds_total|container_memory_working_set_bytes|container_fs_usage_bytes|container_fs_limit_bytes);$ - - action: labelmap - regex: container_name - replacement: container - - action: drop - source_labels: [container] # partially copied from what operator generates - regex: POD - - action: labeldrop - regex: (id|name) - relabel_configs: - - target_label: endpoint - replacement: https-metrics - - source_labels: - - __metrics_path__ - target_label: metrics_path - action: replace - - source_labels: - - __address__ - target_label: instance - action: replace + - job_name: pod-annotations + kubernetes_sd_configs: + - role: pod + relabel_configs: + - action: keep + regex: true + source_labels: + - __meta_kubernetes_pod_annotation_prometheus_io_scrape + - action: replace + regex: (.+) + source_labels: + - __meta_kubernetes_pod_annotation_prometheus_io_path + target_label: __metrics_path__ + - action: replace + regex: ([^:]+)(?::\d+)?;(\d+) + replacement: $1:$2 + source_labels: + - __address__ + - __meta_kubernetes_pod_annotation_prometheus_io_port + target_label: __address__ + - action: replace + regex: (.*) + replacement: $1 + separator: ; + source_labels: + - __metrics_path__ + target_label: endpoint + - action: replace + source_labels: + - __meta_kubernetes_namespace + target_label: namespace + - action: labelmap + regex: __meta_kubernetes_pod_label_(.+) + - action: replace + regex: (.*) + replacement: $1 + separator: ; + source_labels: + - __meta_kubernetes_pod_name + target_label: pod + - authorization: + credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token + honor_labels: true + job_name: kubelet + kubernetes_sd_configs: + - role: node + metric_relabel_configs: + - action: keep + regex: (?:kubelet_docker_operations_errors(?:|_total)|kubelet_(?:docker|runtime)_operations_duration_seconds_(?:count|sum)|kubelet_running_(?:container|pod)(?:_count|s)|kubelet_(:?docker|runtime)_operations_latency_microseconds(?:|_count|_sum)) + source_labels: + - __name__ + - action: labeldrop + regex: id + relabel_configs: + - source_labels: + - __meta_kubernetes_node_name + target_label: node + - replacement: https-metrics + target_label: endpoint + - action: replace + source_labels: + - __metrics_path__ + target_label: metrics_path + - action: replace + source_labels: + - __address__ + target_label: instance + scheme: https + tls_config: + ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecure_skip_verify: true + - authorization: + credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token + honor_labels: true + job_name: cadvisor + kubernetes_sd_configs: + - role: node + metric_relabel_configs: + - action: replace + regex: .* + replacement: kubelet + source_labels: + - __name__ + target_label: job + - action: keep + regex: (?:container_cpu_usage_seconds_total|container_memory_working_set_bytes|container_fs_usage_bytes|container_fs_limit_bytes|container_cpu_cfs_throttled_seconds_total|container_network_receive_bytes_total|container_network_transmit_bytes_total) + source_labels: + - __name__ + - action: drop + regex: (?:container_cpu_usage_seconds_total|container_memory_working_set_bytes|container_fs_usage_bytes|container_fs_limit_bytes);$ + source_labels: + - __name__ + - container + - action: labelmap + regex: container_name + replacement: container + - action: drop + regex: POD + source_labels: + - container + - action: labeldrop + regex: (id|name) + metrics_path: /metrics/cadvisor + relabel_configs: + - replacement: https-metrics + target_label: endpoint + - action: replace + source_labels: + - __metrics_path__ + target_label: metrics_path + - action: replace + source_labels: + - __address__ + target_label: instance + scheme: https + tls_config: + ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecure_skip_verify: true target_allocator: + collector_id: ${POD_NAME} endpoint: http://RELEASE-NAME-sumologic-metrics-targetallocator interval: 30s - collector_id: ${POD_NAME} - service: - telemetry: - logs: - level: info - metrics: - address: 0.0.0.0:8888 # this is the default, but setting it explicitly lets the operator add it automatically extensions: - - health_check - - pprof - - file_storage + - health_check + - pprof + - file_storage pipelines: metrics: - exporters: [otlphttp] + exporters: + - otlphttp processors: - - batch - - transform/extract_sum_count_from_histograms - - filter/drop_unnecessary_metrics - - transform/drop_unnecessary_attributes - receivers: [prometheus] + - batch + - transform/extract_sum_count_from_histograms + - filter/drop_unnecessary_metrics + - transform/drop_unnecessary_attributes + receivers: + - prometheus + telemetry: + logs: + level: info + metrics: + address: 0.0.0.0:8888 diff --git a/tests/helm/testdata/goldenfile/metrics_collector_otc/custom.input.yaml b/tests/helm/testdata/goldenfile/metrics_collector_otc/custom.input.yaml index 9f55595179..e4f8745574 100644 --- a/tests/helm/testdata/goldenfile/metrics_collector_otc/custom.input.yaml +++ b/tests/helm/testdata/goldenfile/metrics_collector_otc/custom.input.yaml @@ -43,6 +43,11 @@ sumologic: annotatedPods: enabled: false allocationStrategy: consistent-hashing + config: + merge: + processors: + batch: + send_batch_size: 5000 enableDefaultFilters: true dropHistogramBuckets: false diff --git a/tests/helm/testdata/goldenfile/metrics_collector_otc/custom.output.yaml b/tests/helm/testdata/goldenfile/metrics_collector_otc/custom.output.yaml index 8e060ba16d..d250528eab 100644 --- a/tests/helm/testdata/goldenfile/metrics_collector_otc/custom.output.yaml +++ b/tests/helm/testdata/goldenfile/metrics_collector_otc/custom.output.yaml @@ -85,966 +85,66 @@ spec: config: | exporters: otlphttp: + disable_keep_alives: true endpoint: http://${METADATA_METRICS_SVC}.${NAMESPACE}.svc.cluster.local.:4318 sending_queue: - queue_size: 10000 num_consumers: 10 + queue_size: 10000 storage: file_storage - # this improves load balancing at the cost of more network traffic - disable_keep_alives: true - extensions: - health_check: {} - pprof: {} file_storage: - directory: /var/lib/storage/otc - timeout: 10s compaction: - on_rebound: true directory: /tmp - - + on_rebound: true + directory: /var/lib/storage/otc + timeout: 10s + health_check: {} + pprof: {} processors: batch: send_batch_max_size: 2000 - send_batch_size: 1000 + send_batch_size: 5000 timeout: 1s - - transform/drop_unnecessary_attributes: - error_mode: ignore - metric_statements: - - context: resource - statements: - - delete_key(attributes, "http.scheme") - - delete_key(attributes, "net.host.name") - - delete_key(attributes, "net.host.port") - - delete_key(attributes, "service.instance.id") - # prometheus receiver adds these automatically - # we drop them to make the rest of our pipeline easier to reason about - # after the collector and metadata are merged, consider using them instead of k8sattributes processor - - delete_matching_keys(attributes, "k8s.*") - filter/drop_unnecessary_metrics: + filter/app_metrics: error_mode: ignore metrics: metric: - # we let the metrics from annotations ("kubernetes-pods") through as they are - - resource.attributes["service.name"] != "pod-annotations" and IsMatch(name, "scrape_.*") - - filter/app_metrics: + - IsMatch(name, "nginx_ingress_.*") and not IsMatch(name, "(?:nginx_ingress_controller_ingress_resources_total|nginx_ingress_controller_nginx_(last_reload_(milliseconds|status)|reload(s|_errors)_total)|nginx_ingress_controller_virtualserver(|route)_resources_total|nginx_ingress_nginx_connections_(accepted|active|handled|reading|waiting|writing)|nginx_ingress_nginx_http_requests_total|nginx_ingress_nginxplus_(connections_(accepted|active|dropped|idle)|http_requests_(current|total)|resolver_(addr|formerr|name|noerror|notimp|nxdomain|refused|servfail|srv|timedout|unknown)|ssl_(handshakes_failed|session_reuses)|stream_server_zone_(connections|received|sent)|stream_upstream_server_(active|connect_time|fails|health_checks_fails|health_checks_unhealthy|received|response_time|sent|unavail|state)|(location|server)_zone_(discarded|received|requests|responses|sent|processing)|upstream_server_(fails|header_time|health_checks_fails|health_checks_unhealthy|received|sent|unavail|response_time|responses|requests)))") + - IsMatch(name, "nginx_.*") and not IsMatch(name, "(?:nginx_(accepts|active|handled|reading|requests|waiting|writing)|nginx_plus_api_connections_(accepted|active|dropped|idle)|nginx_plus_api_http_caches_(cold|hit_bytes|max_size|miss_bytes|size|updating_bytes)|nginx_plus_api_http_location_zones_(discarded|received|requests|sent)|nginx_plus_api_http_location_zones_responses_(1xx|2xx|3xx|4xx|5xx|total)|nginx_plus_api_http_requests_(current|total)|nginx_plus_api_http_server_zones_(discarded|processing|received|requests|sent)|nginx_plus_api_http_server_zones_responses_(1xx|2xx|3xx|4xx|5xx|total)|nginx_plus_api_http_upstream_peers_(backup|downtime|fails|healthchecks_fails|healthchecks_unhealthy|received|requests|sent|unavail|response_time)|nginx_plus_api_http_upstream_peers_responses_(1xx|2xx|3xx|4xx|5xx|total)|nginx_plus_api_resolver_zones_(addr|formerr|name|noerror|notimp|nxdomain|refused|servfail|srv|timedout)|nginx_plus_api_ssl_(handshakes_failed|session_reuses)|nginx_plus_api_stream_server_zones_(connections|received|sent)|nginx_plus_api_stream_upstream_peers_(active|backup|connect_time|downtime|fails|healthchecks_fails|healthchecks_last_passed|healthchecks_unhealthy|received|response_time|sent|unavail))") + - IsMatch(name, "redis_.*") and not IsMatch(name, "(?:redis_((blocked_|)clients|cluster_enabled|cmdstat_calls|connected_slaves|(evicted|expired|tracking_total)_keys|instantaneous_ops_per_sec|keyspace_(hitrate|hits|misses)|(master|slave)_repl_offset|maxmemory|mem_fragmentation_(bytes|ratio)|rdb_changes_since_last_save|rejected_connections|total_commands_processed|total_net_(input|output)_bytes|uptime|used_(cpu_(sys|user)|memory(_overhead|_rss|_startup|))))") + - IsMatch(name, "java_.*") and not IsMatch(name, "(?:java_lang_(ClassLoading_(TotalL|Unl|L)oadedClassCount|Compilation_TotalCompilationTime|GarbageCollector_(Collection(Count|Time)|LastGcInfo_(GcThreadCount|duration|(memoryU|u)sage(After|Before)Gc_.*_used))|MemoryPool_(CollectionUsage(ThresholdSupported|_committed|_max|_used)|(Peak|)Usage_(committed|max|used)|UsageThresholdSupported)|Memory_((Non|)HeapMemoryUsage_(committed|max|used)|ObjectPendingFinalizationCount)|OperatingSystem_(AvailableProcessors|(CommittedVirtual|(Free|Total)(Physical|))MemorySize|(Free|Total)SwapSpaceSize|(Max|Open)FileDescriptorCount|ProcessCpu(Load|Time)|System(CpuLoad|LoadAverage))|Runtime_(BootClassPathSupported|Pid|Uptime|StartTime)|Threading_(CurrentThread(AllocatedBytes|(Cpu|User)Time)|(Daemon|Peak|TotalStarted|)ThreadCount|(ObjectMonitor|Synchronizer)UsageSupported|Thread(AllocatedMemory.*|ContentionMonitoring.*|CpuTime.*))))") + - IsMatch(name, "kafka_.*") and not IsMatch(name, "(?:kafka_(broker_.*|controller_.*|java_lang_.*|partition_.*|purgatory_.*|network_.*|replica_.*|request_.*|topic_.*|topics_.*|zookeeper_.*))") + - IsMatch(name, "mysql_.*") and not IsMatch(name, "(?:mysql_((uptime|connection_errors_.*|queries|slow_queries|questions|table_open_cache_.*|table_locks_.*|commands_.*|select_.*|sort_.*|mysqlx_connections_.*|mysqlx_worker_.*|connections|aborted_.*|locked_connects|bytes_.*|qcache_.*|threads_.*|opened_.*|created_tmp_.*)|innodb_(buffer_pool_.*|data_.*|rows_.*|row_lock_.*|log_waits)|perf_schema_(events_statements_.*|table_io_waits_.*|index_io_waits_.*|read.*|write.*)))") + - IsMatch(name, "postgresql_.*") and not IsMatch(name, "(?:postgresql_(blks_(hit|read)|buffers_(backend|checkpoint|clean)|checkpoints_(req|timed)|db_size|deadlocks|flush_lag|heap_blks_(hit|read)|idx_blks_(hit|read)|idx_scan|idx_tup_(fetch|read)|index_size|n_dead_tup|n_live_tup|n_tup_(upd|ins|del|hot_upd)|num_locks|numbackends|replay_lag|replication_(delay|lag)|seq_scan|seq_tup_read|stat_ssl_compression_count|table_size|tidx_blks_(hit|read)|toast_blks_(hit|read)|tup_(deleted|fetched|inserted|returned|updated)|write_lag|xact_(commit|rollback)))") + - IsMatch(name, "apache_.*") and not IsMatch(name, "(?:apache_((BusyWorkers|BytesPerReq|BytesPerSec|CPUChildrenSystem|CPUChildrenUser|CPULoad|CPUSystem|CPUUser|DurationPerReq|IdleWorkers|Load1|Load15|Load5|ParentServerConfigGeneration|ParentServerMPMGeneration|ReqPerSec|ServerUptimeSeconds|TotalAccesses|TotalDuration|TotalkBytes|Uptime)|(scboard_(closing|dnslookup|finishing|idle_cleanup|keepalive|logging|open|reading|sending|starting|waiting))))") + - IsMatch(name, "sqlserver_.*") and not IsMatch(name, "(?:sqlserver_(cpu_sqlserver_process_cpu|database_io_(read_(bytes|latency_ms)|write_(bytes|latency_ms))|memory_clerks_size_kb|performance_value|server_properties_server_memory|volume_space_(total_space_bytes|used_space_bytes)))") + - IsMatch(name, "haproxy_.*") and not IsMatch(name, "(?:haproxy_(active_servers|backup_servers|bin|bout|chkfail|ctime|dreq|dresp|econ|ereq|eresp|http_response_(1xx|2xx|3xx|4xx|5xx|other)|qcur|qmax|qtime|rate|rtime|scur|slim|smax|ttime|weight|wredis|wretr))") + - IsMatch(name, "cassandra_.*") and not IsMatch(name, "(?:cassandra_(CacheMetrics_ChunkCache_OneMinuteRate|ClientMetrics_(connectedNativeClients_Value|RequestDiscarded_OneMinuteRate)|CommitLogMetrics_(CompletedTasks_Value|PendingTasks_Value)|DroppedMessageMetrics_Dropped_OneMinuteRate|java_(GarbageCollector_(ConcurrentMarkSweep|ParNew)_(CollectionCount|CollectionTime|LastGcInfo_duration|LastGcInfo_GcThreadCount|LastGcInfo_memoryUsageAfterGc_.*_used|LastGcInfo_memoryUsageBeforeGc_.*_used)|Memory_HeapMemoryUsage_used|OperatingSystem_(AvailableProcessors|FreePhysicalMemorySize|SystemCpuLoad|TotalPhysicalMemorySize|TotalSwapSpaceSize))|Net_FailureDetector_(DownEndpointCount|UpEndpointCount)|TableMetrics_(AllMemtablesHeapSize_Value|AllMemtablesLiveDataSize_Value|CompactionBytesWritten_Count|EstimatedPartitionCount_Value|KeyCacheHitRate_Value|LiveSSTableCount_Value|MemtableColumnsCount_Value|MemtableLiveDataSize_Value|MemtableOffHeapSize_Value|MemtableOnHeapSize_Value|MemtableSwitchCount_Count|PendingCompactions_Value|PendingFlushes_Count|PercentRepaired_Value|RangeLatency_Count|ReadLatency_50thPercentile|ReadLatency_Max|ReadLatency_OneMinuteRate|RowCacheHit_Count|RowCacheMiss_Count|SSTablesPerReadHistogram_50thPercentile|SSTablesPerReadHistogram_99thPercentile|SSTablesPerReadHistogram_Count|SSTablesPerReadHistogram_Max|TombstoneScannedHistogram_50thPercentile|TombstoneScannedHistogram_99thPercentile|TombstoneScannedHistogram_Max|TotalDiskSpaceUsed_Count|WaitingOnFreeMemtableSpace_Max|WriteLatency_50thPercentile|WriteLatency_99thPercentile|WriteLatency_Max|WriteLatency_OneMinuteRate)|ThreadPoolMetrics_(internal_(Count|Value)|request_(Count|Value)|transport_(Count|Value))))") + - IsMatch(name, "mongodb_.*") and not IsMatch(name, "(?:mongodb_(active_(reads|writes)|commands_per_sec|connections_current|db_stats_storage_size|deletes_per_sec|document_.*|flushes_per_sec|getmores_per_sec|inserts_per_sec|net_.*_bytes_count|open_connections|page_faults|percent_cache_(dirty|used)|queries_per_sec|queued_(reads|writes)|repl_((commands|deletes|getmores|inserts|oplog|queries|updates)_per_sec|queries|oplog_window_sec)|resident_megabytes|updates_per_sec|uptime_ns|vsize_megabytes|wtcache_bytes_read_into))") + - IsMatch(name, "rabbitmq_.*") and not IsMatch(name, "(?:rabbitmq_(exchange_messages_publish_(in_rate|in|out_rate|out)|node_(disk_free_limit|disk_free|mem_(limit|used)|uptime|fd_used|mnesia_(disk_tx_count|ram_tx_count)|gc_num_rate)|overview_(clustering_listerners|connections|exchanges|consumers|queues|messages_(delivered|published|unacked))|queue_(consumers|memory|slave_nodes|messages_(publish_rate|deliver_rate|memory|max_time|unack))))") + - IsMatch(name, "tomcat_.*") and not IsMatch(name, "(?:tomcat_(connector_(bytes_(received|sent)|current_(thread_(busy|count)|threads_busy)|error_count|max_threads|max_time|processing_time|request_count)|jmx_(jvm_memory_(HeapMemoryUsage_(max|used)|NonHeapMemoryUsage_(max|used))|OperatingSystem_(FreePhysicalMemorySize|FreeSwapSpaceSize|SystemCpuLoad|TotalPhysicalMemorySize|TotalSwapSpaceSize)|Servlet_processingTime)|jvm_memory_(free|max|total)|jvm_memorypool_(bytes_(received|sent)|current_thread_count|current_threads_busy|error_count|max_threads|max_time|max|processing_time|request_count|used)))") + - IsMatch(name, "varnish_.*") and not IsMatch(name, "(?:varnish_(backend_(busy|conn|fail|recycle|req|retry|reuse|unhealthy)|bans_(completed|deleted|dups|lurker_(contention|obj_killed|tests_tested|tested|)|obj_killed|obj|persisted_(bytes|fragmentation))|bans|boot_.*_.*_(bodybytes|hdrbytes)|cache_(hit_grace|hitpass|miss|hit)|client_(req_400|req_417|req|resp_500)|n_(backend|expired|lru_nuked|vcl_avail)|pools|s0_g_(bytes|space)|s_(fetch|pipe_(in|out)|req_(bodybytes|hdrbytes)|resp_(bodybytes|hdrbytes)|sess)|sess_(closed_err|closed|conn|drop|dropped|fail|queued)|thread_queue_len|threads_(created|destroyed|failed|limited)|threads|uptime|vmods))") + - IsMatch(name, "memcached_.*") and not IsMatch(name, "(?:memcached_(accepting_conns|auth_(cmds|errors)|bytes_(read|written)|bytes|cas_*|cmd_.*|conn_yields|connection_structures|curr_(connections|items)|decr_.*|delete_.*|evictions|get_(hits|misses)|hash_(bytes|is_expanding)|incr_.*|limit_maxbytes|listen_disabled_num|reclaimed|threads|total_(connections|items)|uptime))") + - IsMatch(name, "elasticsearch_.*") and not IsMatch(name, "(?:elasticsearch_(cluster_health_(active_(primary_shards|shards)|delayed_unassigned_shards|indices_status_code|initializing_shards|number_of_(data_nodes|nodes|pending_tasks)|relocating_shards|unassigned_shards)|clusterstats_(indices_fielddata_evictions|nodes_jvm_mem_heap_used_in_bytes)|fs_total_(free_in_bytes|total_in_bytes)|indices_(flush_(total|total_time_in_millis)|get_(exists_time_in_millis|exists_total|missing_time_in_millis|missing_total|time_in_millis|total)|indexing_delete_time_in_millis|indexing_delete_total|indexing_index_time_in_millis|indexing_index_total|merges_total_time_in_millis|search_query_time_in_millis|search_query_total|segments_fixed_bit_set_memory_in_bytes|segments_terms_memory_in_bytes|stats_primaries_(docs_count|indexing_index_time_in_millis|query_cache_cache_size|query_cache_evictions|segments_doc_values_memory_in_bytes|segments_index_writer_memory_in_bytes|segments_memory_in_bytes)|stats_total___(fielddata_memory_size_in_bytes|indexing_index_total|merges_total)|stats_total_(docs_count|fielddata_memory_size_in_bytes|flush_total_time_in_millis|indexing_delete_total|indexing_index_time_in_millis|indexing_index_total|merges_total_docs|merges_total_size_in_bytes|merges_total_time_in_millis|query_cache_evictions|refresh_total|refresh_total_time_in_millis|search_fetch_time_in_millis|search_fetch_total|search_query_time_in_millis|search_query_total|segments_fixed_bit_set_memory_in_bytes|segments_index_writer_memory_in_bytes|segments_memory_in_bytes|segments_terms_memory_in_bytes|store_size_in_bytes|translog_operations|translog_size_in_bytes))|jvm_(gc_collectors_.*_collection_time_in_millis|mem_heap_committed_in_bytes|mem_heap_used_in_bytes|mem_heap_used_percent)|os_cpu_(load_average_5m|percent)|process_open_file_descriptors|thread_pool_(analyze_completed|analyze_threads|get_rejected|search_queue)|transport_(rx_size_in_bytes|tx_size_in_bytes)))") + - IsMatch(name, "activemq_.*") and not IsMatch(name, "(?:activemq_(topic_.*|queue_.*|.*_QueueSize|broker_(AverageMessageSize|CurrentConnectionsCount|MemoryLimit|StoreLimit|TempLimit|TotalConnectionsCount|TotalConsumerCount|TotalDequeueCount|TotalEnqueueCount|TotalMessageCount|TotalProducerCount|UptimeMillis)|jvm_memory_(HeapMemoryUsage_max|HeapMemoryUsage_used|NonHeapMemoryUsage_used)|jvm_runtime_Uptime|OperatingSystem_(FreePhysicalMemorySize|SystemCpuLoad|TotalPhysicalMemorySize)))") + - IsMatch(name, "couchbase_.*") and not IsMatch(name, "(?:couchbase_(node_.*|bucket_(ep_.*|vb_.*|delete_.*|cmd.*|bytes_.*|item_count|curr_connections|ops_per_sec|disk_write_queue|mem_.*|cas_hits|ops|curr_items|cpu_utilization_rate|swap_used|disk_used|rest_requests|hibernated_waked|xdc_ops)))") + - IsMatch(name, "squid_.*") and not IsMatch(name, "(?:squid_(uptime|cache(Ip(Entries|Requests|Hits)|Fqdn(Entries|Requests|Misses|NegativeHits)|Dns(Requests|Replies|SvcTime5)|Sys(PageFaults|NumReads)|Current(FileDescrCnt|UnusedFDescrCnt|ResFileDescrCnt)|Server(Requests|InKb|OutKb)|Http(AllSvcTime5|Errors|InKb|OutKb|AllSvcTime1)|Mem(MaxSize|Usage)|NumObjCount|CpuTime|MaxResSize|ProtoClientHttpRequests|Clients)))") + filter/drop_unnecessary_metrics: error_mode: ignore metrics: metric: - ## Nginx ingress controller metrics - ## rel: https://docs.nginx.com/nginx-ingress-controller/logging-and-monitoring/prometheus/#available-metrics - ## nginx_ingress_controller_ingress_resources_total - ## nginx_ingress_controller_nginx_last_reload_milliseconds - ## nginx_ingress_controller_nginx_last_reload_status - ## nginx_ingress_controller_nginx_reload_errors_total - ## nginx_ingress_controller_nginx_reloads_total - ## nginx_ingress_controller_virtualserver_resources_total - ## nginx_ingress_controller_virtualserverroute_resources_total - ## nginx_ingress_nginx_connections_accepted - ## nginx_ingress_nginx_connections_active - ## nginx_ingress_nginx_connections_handled - ## nginx_ingress_nginx_connections_reading - ## nginx_ingress_nginx_connections_waiting - ## nginx_ingress_nginx_connections_writing - ## nginx_ingress_nginx_http_requests_total - ## nginx_ingress_nginxplus_connections_accepted - ## nginx_ingress_nginxplus_connections_active - ## nginx_ingress_nginxplus_connections_dropped - ## nginx_ingress_nginxplus_connections_idle - ## nginx_ingress_nginxplus_http_requests_current - ## nginx_ingress_nginxplus_http_requests_total - ## nginx_ingress_nginxplus_resolver_addr - ## nginx_ingress_nginxplus_resolver_formerr - ## nginx_ingress_nginxplus_resolver_name - ## nginx_ingress_nginxplus_resolver_noerror - ## nginx_ingress_nginxplus_resolver_notimp - ## nginx_ingress_nginxplus_resolver_nxdomain - ## nginx_ingress_nginxplus_resolver_refused - ## nginx_ingress_nginxplus_resolver_servfail - ## nginx_ingress_nginxplus_resolver_srv - ## nginx_ingress_nginxplus_resolver_timedout - ## nginx_ingress_nginxplus_resolver_unknown - ## nginx_ingress_nginxplus_ssl_handshakes_failed - ## nginx_ingress_nginxplus_ssl_session_reuses - ## nginx_ingress_nginxplus_stream_server_zone_connections - ## nginx_ingress_nginxplus_stream_server_zone_received - ## nginx_ingress_nginxplus_stream_server_zone_sent - ## nginx_ingress_nginxplus_stream_upstream_server_active - ## nginx_ingress_nginxplus_stream_upstream_server_connect_time - ## nginx_ingress_nginxplus_stream_upstream_server_fails - ## nginx_ingress_nginxplus_stream_upstream_server_health_checks_fails - ## nginx_ingress_nginxplus_stream_upstream_server_health_checks_unhealthy - ## nginx_ingress_nginxplus_stream_upstream_server_received - ## nginx_ingress_nginxplus_stream_upstream_server_response_time - ## nginx_ingress_nginxplus_stream_upstream_server_sent - ## nginx_ingress_nginxplus_stream_upstream_server_unavail - ## nginx_ingress_nginxplus_stream_upstream_server_state - ## nginx_ingress_nginxplus_location_zone_discarded - ## nginx_ingress_nginxplus_location_zone_received - ## nginx_ingress_nginxplus_location_zone_requests - ## nginx_ingress_nginxplus_location_zone_responses - ## nginx_ingress_nginxplus_location_zone_sent - ## nginx_ingress_nginxplus_server_zone_discarded - ## nginx_ingress_nginxplus_server_zone_processing - ## nginx_ingress_nginxplus_server_zone_received - ## nginx_ingress_nginxplus_server_zone_requests - ## nginx_ingress_nginxplus_server_zone_responses - ## nginx_ingress_nginxplus_server_zone_sent - ## nginx_ingress_nginxplus_upstream_server_fails - ## nginx_ingress_nginxplus_upstream_server_header_time - ## nginx_ingress_nginxplus_upstream_server_health_checks_fails - ## nginx_ingress_nginxplus_upstream_server_health_checks_unhealthy - ## nginx_ingress_nginxplus_upstream_server_received - ## nginx_ingress_nginxplus_upstream_server_sent - ## nginx_ingress_nginxplus_upstream_server_unavail - ## nginx_ingress_nginxplus_upstream_server_response_time - ## nginx_ingress_nginxplus_upstream_server_responses - ## nginx_ingress_nginxplus_upstream_server_requests - - IsMatch(name, "nginx_ingress_.*") and not IsMatch(name, "(?:nginx_ingress_controller_ingress_resources_total|nginx_ingress_controller_nginx_(last_reload_(milliseconds|status)|reload(s|_errors)_total)|nginx_ingress_controller_virtualserver(|route)_resources_total|nginx_ingress_nginx_connections_(accepted|active|handled|reading|waiting|writing)|nginx_ingress_nginx_http_requests_total|nginx_ingress_nginxplus_(connections_(accepted|active|dropped|idle)|http_requests_(current|total)|resolver_(addr|formerr|name|noerror|notimp|nxdomain|refused|servfail|srv|timedout|unknown)|ssl_(handshakes_failed|session_reuses)|stream_server_zone_(connections|received|sent)|stream_upstream_server_(active|connect_time|fails|health_checks_fails|health_checks_unhealthy|received|response_time|sent|unavail|state)|(location|server)_zone_(discarded|received|requests|responses|sent|processing)|upstream_server_(fails|header_time|health_checks_fails|health_checks_unhealthy|received|sent|unavail|response_time|responses|requests)))") - ## Nginx telegraf metrics - ## nginx_accepts - ## nginx_active - ## nginx_handled - ## nginx_reading - ## nginx_requests - ## nginx_waiting - ## nginx_writing - ## **************** Nginx Plus telegraf metrics - ## nginx_plus_api_connections_accepted - ## nginx_plus_api_connections_active - ## nginx_plus_api_connections_dropped - ## nginx_plus_api_connections_idle - ## nginx_plus_api_http_caches_cold - ## nginx_plus_api_http_caches_hit_bytes - ## nginx_plus_api_http_caches_max_size - ## nginx_plus_api_http_caches_miss_bytes - ## nginx_plus_api_http_caches_size - ## nginx_plus_api_http_caches_updating_bytes - ## nginx_plus_api_http_location_zones_discarded - ## nginx_plus_api_http_location_zones_received - ## nginx_plus_api_http_location_zones_requests - ## nginx_plus_api_http_location_zones_responses_1xx - ## nginx_plus_api_http_location_zones_responses_2xx - ## nginx_plus_api_http_location_zones_responses_3xx - ## nginx_plus_api_http_location_zones_responses_4xx - ## nginx_plus_api_http_location_zones_responses_5xx - ## nginx_plus_api_http_location_zones_responses_total - ## nginx_plus_api_http_location_zones_sent - ## nginx_plus_api_http_requests_current - ## nginx_plus_api_http_requests_total - ## nginx_plus_api_http_server_zones_discarded - ## nginx_plus_api_http_server_zones_processing - ## nginx_plus_api_http_server_zones_received - ## nginx_plus_api_http_server_zones_requests - ## nginx_plus_api_http_server_zones_responses_1xx - ## nginx_plus_api_http_server_zones_responses_2xx - ## nginx_plus_api_http_server_zones_responses_3xx - ## nginx_plus_api_http_server_zones_responses_4xx - ## nginx_plus_api_http_server_zones_responses_5xx - ## nginx_plus_api_http_server_zones_responses_total - ## nginx_plus_api_http_server_zones_sent - ## nginx_plus_api_http_upstream_peers_backup - ## nginx_plus_api_http_upstream_peers_downtime - ## nginx_plus_api_http_upstream_peers_fails - ## nginx_plus_api_http_upstream_peers_healthchecks_fails - ## nginx_plus_api_http_upstream_peers_healthchecks_unhealthy - ## nginx_plus_api_http_upstream_peers_received - ## nginx_plus_api_http_upstream_peers_requests - ## nginx_plus_api_http_upstream_peers_response_time - ## nginx_plus_api_http_upstream_peers_responses_1xx - ## nginx_plus_api_http_upstream_peers_responses_2xx - ## nginx_plus_api_http_upstream_peers_responses_3xx - ## nginx_plus_api_http_upstream_peers_responses_4xx - ## nginx_plus_api_http_upstream_peers_responses_5xx - ## nginx_plus_api_http_upstream_peers_responses_total - ## nginx_plus_api_http_upstream_peers_sent - ## nginx_plus_api_http_upstream_peers_unavail - ## nginx_plus_api_resolver_zones_addr - ## nginx_plus_api_resolver_zones_formerr - ## nginx_plus_api_resolver_zones_name - ## nginx_plus_api_resolver_zones_noerror - ## nginx_plus_api_resolver_zones_notimp - ## nginx_plus_api_resolver_zones_nxdomain - ## nginx_plus_api_resolver_zones_refused - ## nginx_plus_api_resolver_zones_servfail - ## nginx_plus_api_resolver_zones_srv - ## nginx_plus_api_resolver_zones_timedout - ## nginx_plus_api_ssl_handshakes_failed - ## nginx_plus_api_ssl_session_reuses - ## nginx_plus_api_stream_server_zones_connections - ## nginx_plus_api_stream_server_zones_received - ## nginx_plus_api_stream_server_zones_sent - ## nginx_plus_api_stream_upstream_peers_active - ## nginx_plus_api_stream_upstream_peers_backup - ## nginx_plus_api_stream_upstream_peers_connect_time - ## nginx_plus_api_stream_upstream_peers_downtime - ## nginx_plus_api_stream_upstream_peers_fails - ## nginx_plus_api_stream_upstream_peers_healthchecks_fails - ## nginx_plus_api_stream_upstream_peers_healthchecks_last_passed - ## nginx_plus_api_stream_upstream_peers_healthchecks_unhealthy - ## nginx_plus_api_stream_upstream_peers_received - ## nginx_plus_api_stream_upstream_peers_response_time - ## nginx_plus_api_stream_upstream_peers_sent - ## nginx_plus_api_stream_upstream_peers_unavail - - IsMatch(name, "nginx_.*") and not IsMatch(name, "(?:nginx_(accepts|active|handled|reading|requests|waiting|writing)|nginx_plus_api_connections_(accepted|active|dropped|idle)|nginx_plus_api_http_caches_(cold|hit_bytes|max_size|miss_bytes|size|updating_bytes)|nginx_plus_api_http_location_zones_(discarded|received|requests|sent)|nginx_plus_api_http_location_zones_responses_(1xx|2xx|3xx|4xx|5xx|total)|nginx_plus_api_http_requests_(current|total)|nginx_plus_api_http_server_zones_(discarded|processing|received|requests|sent)|nginx_plus_api_http_server_zones_responses_(1xx|2xx|3xx|4xx|5xx|total)|nginx_plus_api_http_upstream_peers_(backup|downtime|fails|healthchecks_fails|healthchecks_unhealthy|received|requests|sent|unavail|response_time)|nginx_plus_api_http_upstream_peers_responses_(1xx|2xx|3xx|4xx|5xx|total)|nginx_plus_api_resolver_zones_(addr|formerr|name|noerror|notimp|nxdomain|refused|servfail|srv|timedout)|nginx_plus_api_ssl_(handshakes_failed|session_reuses)|nginx_plus_api_stream_server_zones_(connections|received|sent)|nginx_plus_api_stream_upstream_peers_(active|backup|connect_time|downtime|fails|healthchecks_fails|healthchecks_last_passed|healthchecks_unhealthy|received|response_time|sent|unavail))") - ## Redis metrics - ## redis_blocked_clients - ## redis_clients - ## redis_cluster_enabled - ## redis_cmdstat_calls - ## redis_connected_slaves - ## redis_evicted_keys - ## redis_expired_keys - ## redis_instantaneous_ops_per_sec - ## redis_keyspace_hitrate - ## redis_keyspace_hits - ## redis_keyspace_misses - ## redis_master_repl_offset - ## redis_maxmemory - ## redis_mem_fragmentation_bytes - ## redis_mem_fragmentation_ratio - ## redis_rdb_changes_since_last_save - ## redis_rejected_connections - ## redis_slave_repl_offset - ## redis_total_commands_processed - ## redis_total_net_input_bytes - ## redis_total_net_output_bytes - ## redis_tracking_total_keys - ## redis_uptime - ## redis_used_cpu_sys - ## redis_used_cpu_user - ## redis_used_memory - ## redis_used_memory_overhead - ## redis_used_memory_rss - ## redis_used_memory_startup - - IsMatch(name, "redis_.*") and not IsMatch(name, "(?:redis_((blocked_|)clients|cluster_enabled|cmdstat_calls|connected_slaves|(evicted|expired|tracking_total)_keys|instantaneous_ops_per_sec|keyspace_(hitrate|hits|misses)|(master|slave)_repl_offset|maxmemory|mem_fragmentation_(bytes|ratio)|rdb_changes_since_last_save|rejected_connections|total_commands_processed|total_net_(input|output)_bytes|uptime|used_(cpu_(sys|user)|memory(_overhead|_rss|_startup|))))") - ## JMX Metrics - ## java_lang_ClassLoading_LoadedClassCount - ## java_lang_ClassLoading_TotalLoadedClassCount - ## java_lang_ClassLoading_UnloadedClassCount - ## java_lang_Compilation_TotalCompilationTime - ## java_lang_GarbageCollector_CollectionCount - ## java_lang_GarbageCollector_CollectionTime - ## java_lang_GarbageCollector_LastGcInfo_GcThreadCount # unavailable for adoptopenjdk-openj9 - ## java_lang_GarbageCollector_LastGcInfo_duration # unavailable for adoptopenjdk-openj9 - ## java_lang_GarbageCollector_LastGcInfo_memoryUsageAfterGc_*_used - ## java_lang_GarbageCollector_LastGcInfo_memoryUsageBeforeGc_*_used - ## java_lang_GarbageCollector_LastGcInfo_usageAfterGc_*_used # only for adoptopenjdk-openj9 - ## java_lang_GarbageCollector_LastGcInfo_usageBeforeGc_*_used # only for adoptopenjdk-openj9 - ## java_lang_MemoryPool_CollectionUsageThresholdSupported - ## java_lang_MemoryPool_CollectionUsage_committed - ## java_lang_MemoryPool_CollectionUsage_max - ## java_lang_MemoryPool_CollectionUsage_used - ## java_lang_MemoryPool_PeakUsage_committed - ## java_lang_MemoryPool_PeakUsage_max - ## java_lang_MemoryPool_PeakUsage_used - ## java_lang_MemoryPool_UsageThresholdSupported - ## java_lang_MemoryPool_Usage_committed - ## java_lang_MemoryPool_Usage_max - ## java_lang_MemoryPool_Usage_used - ## java_lang_Memory_HeapMemoryUsage_committed - ## java_lang_Memory_HeapMemoryUsage_max - ## java_lang_Memory_HeapMemoryUsage_used - ## java_lang_Memory_NonHeapMemoryUsage_committed - ## java_lang_Memory_NonHeapMemoryUsage_max - ## java_lang_Memory_NonHeapMemoryUsage_used - ## java_lang_Memory_ObjectPendingFinalizationCount - ## java_lang_OperatingSystem_AvailableProcessors - ## java_lang_OperatingSystem_CommittedVirtualMemorySize - ## java_lang_OperatingSystem_FreeMemorySize # Added in jdk14 - ## java_lang_OperatingSystem_FreePhysicalMemorySize - ## java_lang_OperatingSystem_FreeSwapSpaceSize - ## java_lang_OperatingSystem_MaxFileDescriptorCount - ## java_lang_OperatingSystem_OpenFileDescriptorCount - ## java_lang_OperatingSystem_ProcessCpuLoad - ## java_lang_OperatingSystem_ProcessCpuTime - ## java_lang_OperatingSystem_SystemCpuLoad - ## java_lang_OperatingSystem_SystemLoadAverage - ## java_lang_OperatingSystem_TotalMemorySize # Added in jdk14 - ## java_lang_OperatingSystem_TotalPhysicalMemorySize - ## java_lang_OperatingSystem_TotalSwapSpaceSize - ## java_lang_Runtime_BootClassPathSupported - ## java_lang_Runtime_Pid # not available for jdk8 - ## java_lang_Runtime_Uptime - ## java_lang_Runtime_StartTime - ## java_lang_Threading_CurrentThreadAllocatedBytes # Added in jdk14 - ## java_lang_Threading_CurrentThreadCpuTime - ## java_lang_Threading_CurrentThreadUserTime - ## java_lang_Threading_DaemonThreadCount - ## java_lang_Threading_ObjectMonitorUsageSupported - ## java_lang_Threading_PeakThreadCount - ## java_lang_Threading_SynchronizerUsageSupported - ## java_lang_Threading_ThreadAllocatedMemory* # Not available for adoptopenjdk-openj9 - ## java_lang_Threading_ThreadContentionMonitoring* - ## java_lang_Threading_ThreadCount - ## java_lang_Threading_ThreadCpuTime* - ## java_lang_Threading_TotalStartedThreadCount - - IsMatch(name, "java_.*") and not IsMatch(name, "(?:java_lang_(ClassLoading_(TotalL|Unl|L)oadedClassCount|Compilation_TotalCompilationTime|GarbageCollector_(Collection(Count|Time)|LastGcInfo_(GcThreadCount|duration|(memoryU|u)sage(After|Before)Gc_.*_used))|MemoryPool_(CollectionUsage(ThresholdSupported|_committed|_max|_used)|(Peak|)Usage_(committed|max|used)|UsageThresholdSupported)|Memory_((Non|)HeapMemoryUsage_(committed|max|used)|ObjectPendingFinalizationCount)|OperatingSystem_(AvailableProcessors|(CommittedVirtual|(Free|Total)(Physical|))MemorySize|(Free|Total)SwapSpaceSize|(Max|Open)FileDescriptorCount|ProcessCpu(Load|Time)|System(CpuLoad|LoadAverage))|Runtime_(BootClassPathSupported|Pid|Uptime|StartTime)|Threading_(CurrentThread(AllocatedBytes|(Cpu|User)Time)|(Daemon|Peak|TotalStarted|)ThreadCount|(ObjectMonitor|Synchronizer)UsageSupported|Thread(AllocatedMemory.*|ContentionMonitoring.*|CpuTime.*))))") - ## Kafka Metrics - ## List of Metrics are on following dochub page: - ## https://help.sumologic.com/docs/integrations/containers-orchestration/kafka/#kafka-metrics - ## Metrics follow following format: - ## kafka_broker_* - ## kafka_controller_* - ## kafka_java_lang_* - ## kafka_partition_* - ## kafka_purgatory_* - ## kafka_network_* - ## kafka_replica_* - ## kafka_request_* - ## kafka_topic_* - ## kafka_topics_* - ## kafka_zookeeper_* - - IsMatch(name, "kafka_.*") and not IsMatch(name, "(?:kafka_(broker_.*|controller_.*|java_lang_.*|partition_.*|purgatory_.*|network_.*|replica_.*|request_.*|topic_.*|topics_.*|zookeeper_.*))") - ## MySQL Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/v1.18.1/plugins/inputs/mysql#metrics - ## Metrics follow following format: - ## mysql_uptime - ## mysql_connection_errors_* - ## mysql_queries - ## mysql_slow_queries - ## mysql_questions - ## mysql_table_open_cache_* - ## mysql_table_locks_* - ## mysql_commands_* - ## mysql_select_* - ## mysql_sort_* - ## mysql_mysqlx_connections_* - ## mysql_mysqlx_worker_* - ## mysql_connections - ## mysql_aborted_* - ## mysql_locked_connects - ## mysql_bytes_* - ## mysql_qcache_* - ## mysql_threads_* - ## mysql_opened_* - ## mysql_created_tmp_* - ## mysql_innodb_buffer_pool_* - ## mysql_innodb_data_* - ## mysql_innodb_rows_* - ## mysql_innodb_row_lock_* - ## mysql_innodb_log_waits - ## mysql_perf_schema_events_statements_* - ## mysql_perf_schema_table_io_waits_* - ## mysql_perf_schema_index_io_waits_* - ## mysql_perf_schema_read* - ## mysql_perf_schema_write* - - IsMatch(name, "mysql_.*") and not IsMatch(name, "(?:mysql_((uptime|connection_errors_.*|queries|slow_queries|questions|table_open_cache_.*|table_locks_.*|commands_.*|select_.*|sort_.*|mysqlx_connections_.*|mysqlx_worker_.*|connections|aborted_.*|locked_connects|bytes_.*|qcache_.*|threads_.*|opened_.*|created_tmp_.*)|innodb_(buffer_pool_.*|data_.*|rows_.*|row_lock_.*|log_waits)|perf_schema_(events_statements_.*|table_io_waits_.*|index_io_waits_.*|read.*|write.*)))") - ## PostgreSQL Telegraf Metrics - ## List of Metrics are on following dochub page: - ## https://help.sumologic.com/docs/integrations/databases/postgresql/#postgresql-metrics - ## Metrics follow following format: - ## postgresql_blks_hit - ## postgresql_blks_read - ## postgresql_buffers_backend - ## postgresql_buffers_checkpoint - ## postgresql_buffers_clean - ## postgresql_checkpoints_req - ## postgresql_checkpoints_timed - ## postgresql_db_size - ## postgresql_deadlocks - ## postgresql_flush_lag - ## postgresql_heap_blks_hit - ## postgresql_heap_blks_read - ## postgresql_idx_blks_hit - ## postgresql_idx_blks_read - ## postgresql_idx_scan - ## postgresql_idx_tup_fetch - ## postgresql_idx_tup_read - ## postgresql_index_size - ## postgresql_n_dead_tup - ## postgresql_n_live_tup - ## postgresql_n_tup_del - ## postgresql_n_tup_hot_upd - ## postgresql_n_tup_ins - ## postgresql_n_tup_upd - ## postgresql_num_locks - ## postgresql_numbackends - ## postgresql_replay_lag - ## postgresql_replication_delay - ## postgresql_replication_lag - ## postgresql_seq_scan - ## postgresql_seq_tup_read - ## postgresql_stat_ssl_compression_count - ## postgresql_table_size - ## postgresql_tup_deleted - ## postgresql_tup_fetched - ## postgresql_tup_inserted - ## postgresql_tup_returned - ## postgresql_tup_updated - ## postgresql_write_lag - ## postgresql_xact_commit - ## postgresql_xact_rollback - ## postgresql_toast_blks_read - ## postgresql_toast_blks_hit - ## postgresql_tidx_blks_read - ## postgresql_tidx_blks_hit - - IsMatch(name, "postgresql_.*") and not IsMatch(name, "(?:postgresql_(blks_(hit|read)|buffers_(backend|checkpoint|clean)|checkpoints_(req|timed)|db_size|deadlocks|flush_lag|heap_blks_(hit|read)|idx_blks_(hit|read)|idx_scan|idx_tup_(fetch|read)|index_size|n_dead_tup|n_live_tup|n_tup_(upd|ins|del|hot_upd)|num_locks|numbackends|replay_lag|replication_(delay|lag)|seq_scan|seq_tup_read|stat_ssl_compression_count|table_size|tidx_blks_(hit|read)|toast_blks_(hit|read)|tup_(deleted|fetched|inserted|returned|updated)|write_lag|xact_(commit|rollback)))") - ## Apache Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/v1.18.2/plugins/inputs/apache - ## Metrics follow following format: - ## apache_BusyWorkers - ## apache_BytesPerReq - ## apache_BytesPerSec - ## apache_CPUChildrenSystem - ## apache_CPUChildrenUser - ## apache_CPULoad - ## apache_CPUSystem - ## apache_CPUUser - ## apache_DurationPerReq - ## apache_IdleWorkers - ## apache_Load1 - ## apache_Load5 - ## apache_Load15 - ## apache_ParentServerConfigGeneration - ## apache_ParentServerMPMGeneration - ## apache_ReqPerSec - ## apache_ServerUptimeSeconds - ## apache_TotalAccesses - ## apache_TotalDuration - ## apache_TotalkBytes - ## apache_Uptime - ## apache_scboard_closing - ## apache_scboard_dnslookup - ## apache_scboard_finishing - ## apache_scboard_idle_cleanup - ## apache_scboard_keepalive - ## apache_scboard_logging - ## apache_scboard_open - ## apache_scboard_reading - ## apache_scboard_sending - ## apache_scboard_starting - ## apache_scboard_waiting - - IsMatch(name, "apache_.*") and not IsMatch(name, "(?:apache_((BusyWorkers|BytesPerReq|BytesPerSec|CPUChildrenSystem|CPUChildrenUser|CPULoad|CPUSystem|CPUUser|DurationPerReq|IdleWorkers|Load1|Load15|Load5|ParentServerConfigGeneration|ParentServerMPMGeneration|ReqPerSec|ServerUptimeSeconds|TotalAccesses|TotalDuration|TotalkBytes|Uptime)|(scboard_(closing|dnslookup|finishing|idle_cleanup|keepalive|logging|open|reading|sending|starting|waiting))))") - ## SQLServer Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/v1.18.2/plugins/inputs/sqlserver - ## Metrics follow following format: - ## sqlserver_cpu_sqlserver_process_cpu - ## sqlserver_database_io_read_bytes - ## sqlserver_database_io_read_latency_ms - ## sqlserver_database_io_write_bytes - ## sqlserver_database_io_write_latency_ms - ## sqlserver_memory_clerks_size_kb - ## sqlserver_performance_value - ## sqlserver_server_properties_server_memory - ## sqlserver_volume_space_total_space_bytes - ## sqlserver_volume_space_used_space_bytes - - IsMatch(name, "sqlserver_.*") and not IsMatch(name, "(?:sqlserver_(cpu_sqlserver_process_cpu|database_io_(read_(bytes|latency_ms)|write_(bytes|latency_ms))|memory_clerks_size_kb|performance_value|server_properties_server_memory|volume_space_(total_space_bytes|used_space_bytes)))") - ## Haproxy Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/v1.18.2/plugins/inputs/haproxy - ## Metrics follow following format: - ## haproxy_active_servers - ## haproxy_backup_servers - ## haproxy_bin - ## haproxy_bout - ## haproxy_chkfail - ## haproxy_ctime - ## haproxy_dreq - ## haproxy_dresp - ## haproxy_econ - ## haproxy_ereq - ## haproxy_eresp - ## haproxy_http_response_* - ## haproxy_qcur - ## haproxy_qmax - ## haproxy_qtime - ## haproxy_rate - ## haproxy_rtime - ## haproxy_scur - ## haproxy_slim - ## haproxy_smax - ## haproxy_ttime - ## haproxy_weight - ## haproxy_wredis - ## haproxy_wretr - - IsMatch(name, "haproxy_.*") and not IsMatch(name, "(?:haproxy_(active_servers|backup_servers|bin|bout|chkfail|ctime|dreq|dresp|econ|ereq|eresp|http_response_(1xx|2xx|3xx|4xx|5xx|other)|qcur|qmax|qtime|rate|rtime|scur|slim|smax|ttime|weight|wredis|wretr))") - ## Cassandra Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/v1.18.2/plugins/inputs/cassandra - ## cassandra_CacheMetrics_ChunkCache_OneMinuteRate - ## cassandra_ClientMetrics_connectedNativeClients_Value - ## cassandra_ClientMetrics_RequestDiscarded_OneMinuteRate - ## cassandra_CommitLogMetrics_CompletedTasks_Value - ## cassandra_CommitLogMetrics_PendingTasks_Value - ## cassandra_DroppedMessageMetrics_Dropped_OneMinuteRate - ## cassandra_java_GarbageCollector_*_CollectionCount - ## cassandra_java_GarbageCollector_*_CollectionTime - ## cassandra_java_GarbageCollector_*_LastGcInfo_duration - ## cassandra_java_GarbageCollector_*_LastGcInfo_GcThreadCount - ## cassandra_java_GarbageCollector_*_LastGcInfo_memoryUsageAfterGc_*_used - ## cassandra_java_GarbageCollector_*_LastGcInfo_memoryUsageBeforeGc_*_used - ## cassandra_java_Memory_HeapMemoryUsage_used - ## cassandra_java_OperatingSystem_AvailableProcessors - ## cassandra_java_OperatingSystem_FreePhysicalMemorySize - ## cassandra_java_OperatingSystem_SystemCpuLoad - ## cassandra_java_OperatingSystem_TotalPhysicalMemorySize - ## cassandra_java_OperatingSystem_TotalSwapSpaceSize - ## cassandra_Net_FailureDetector_DownEndpointCount - ## cassandra_Net_FailureDetector_UpEndpointCount - ## cassandra_TableMetrics_AllMemtablesHeapSize_Value - ## cassandra_TableMetrics_AllMemtablesLiveDataSize_Value - ## cassandra_TableMetrics_CompactionBytesWritten_Count - ## cassandra_TableMetrics_EstimatedPartitionCount_Value - ## cassandra_TableMetrics_KeyCacheHitRate_Value - ## cassandra_TableMetrics_LiveSSTableCount_Value - ## cassandra_TableMetrics_MemtableColumnsCount_Value - ## cassandra_TableMetrics_MemtableLiveDataSize_Value - ## cassandra_TableMetrics_MemtableOffHeapSize_Value - ## cassandra_TableMetrics_MemtableOnHeapSize_Value - ## cassandra_TableMetrics_MemtableSwitchCount_Count - ## cassandra_TableMetrics_PendingCompactions_Value - ## cassandra_TableMetrics_PendingFlushes_Count - ## cassandra_TableMetrics_PercentRepaired_Value - ## cassandra_TableMetrics_RangeLatency_Count - ## cassandra_TableMetrics_ReadLatency_50thPercentile - ## cassandra_TableMetrics_ReadLatency_Max - ## cassandra_TableMetrics_ReadLatency_OneMinuteRate - ## cassandra_TableMetrics_RowCacheHit_Count - ## cassandra_TableMetrics_RowCacheMiss_Count - ## cassandra_TableMetrics_SSTablesPerReadHistogram_50thPercentile - ## cassandra_TableMetrics_SSTablesPerReadHistogram_99thPercentile - ## cassandra_TableMetrics_SSTablesPerReadHistogram_Count - ## cassandra_TableMetrics_SSTablesPerReadHistogram_Max - ## cassandra_TableMetrics_TombstoneScannedHistogram_50thPercentile - ## cassandra_TableMetrics_TombstoneScannedHistogram_99thPercentile - ## cassandra_TableMetrics_TombstoneScannedHistogram_Max - ## cassandra_TableMetrics_TotalDiskSpaceUsed_Count - ## cassandra_TableMetrics_WaitingOnFreeMemtableSpace_Max - ## cassandra_TableMetrics_WriteLatency_50thPercentile - ## cassandra_TableMetrics_WriteLatency_99thPercentile - ## cassandra_TableMetrics_WriteLatency_Max - ## cassandra_TableMetrics_WriteLatency_OneMinuteRate - ## cassandra_ThreadPoolMetrics_internal_Count - ## cassandra_ThreadPoolMetrics_internal_Value - ## cassandra_ThreadPoolMetrics_request_Count - ## cassandra_ThreadPoolMetrics_request_Value - ## cassandra_ThreadPoolMetrics_transport_Count - ## cassandra_ThreadPoolMetrics_transport_Value - - IsMatch(name, "cassandra_.*") and not IsMatch(name, "(?:cassandra_(CacheMetrics_ChunkCache_OneMinuteRate|ClientMetrics_(connectedNativeClients_Value|RequestDiscarded_OneMinuteRate)|CommitLogMetrics_(CompletedTasks_Value|PendingTasks_Value)|DroppedMessageMetrics_Dropped_OneMinuteRate|java_(GarbageCollector_(ConcurrentMarkSweep|ParNew)_(CollectionCount|CollectionTime|LastGcInfo_duration|LastGcInfo_GcThreadCount|LastGcInfo_memoryUsageAfterGc_.*_used|LastGcInfo_memoryUsageBeforeGc_.*_used)|Memory_HeapMemoryUsage_used|OperatingSystem_(AvailableProcessors|FreePhysicalMemorySize|SystemCpuLoad|TotalPhysicalMemorySize|TotalSwapSpaceSize))|Net_FailureDetector_(DownEndpointCount|UpEndpointCount)|TableMetrics_(AllMemtablesHeapSize_Value|AllMemtablesLiveDataSize_Value|CompactionBytesWritten_Count|EstimatedPartitionCount_Value|KeyCacheHitRate_Value|LiveSSTableCount_Value|MemtableColumnsCount_Value|MemtableLiveDataSize_Value|MemtableOffHeapSize_Value|MemtableOnHeapSize_Value|MemtableSwitchCount_Count|PendingCompactions_Value|PendingFlushes_Count|PercentRepaired_Value|RangeLatency_Count|ReadLatency_50thPercentile|ReadLatency_Max|ReadLatency_OneMinuteRate|RowCacheHit_Count|RowCacheMiss_Count|SSTablesPerReadHistogram_50thPercentile|SSTablesPerReadHistogram_99thPercentile|SSTablesPerReadHistogram_Count|SSTablesPerReadHistogram_Max|TombstoneScannedHistogram_50thPercentile|TombstoneScannedHistogram_99thPercentile|TombstoneScannedHistogram_Max|TotalDiskSpaceUsed_Count|WaitingOnFreeMemtableSpace_Max|WriteLatency_50thPercentile|WriteLatency_99thPercentile|WriteLatency_Max|WriteLatency_OneMinuteRate)|ThreadPoolMetrics_(internal_(Count|Value)|request_(Count|Value)|transport_(Count|Value))))") - ## MongoDB Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/master/plugins/inputs/mongodb - ## Metrics follow following format: - ## mongodb_active_reads - ## mongodb_active_writes - ## mongodb_commands_per_sec - ## mongodb_connections_current - ## mongodb_db_stats_storage_size - ## mongodb_deletes_per_sec - ## mongodb_document_* - ## mongodb_flushes_per_sec - ## mongodb_getmores_per_sec - ## mongodb_inserts_per_sec - ## mongodb_net_*_bytes_count - ## mongodb_open_connections - ## mongodb_page_faults - ## mongodb_percent_cache_dirty - ## mongodb_percent_cache_used - ## mongodb_queries_per_sec - ## mongodb_queued_reads - ## mongodb_queued_writes - ## mongodb_repl_queries - ## mongodb_repl_commands_per_sec - ## mongodb_repl_deletes_per_sec - ## mongodb_repl_getmores_per_sec - ## mongodb_repl_inserts_per_sec - ## mongodb_repl_oplog_window_sec - ## mongodb_repl_queries_per_sec - ## mongodb_repl_updates_per_sec - ## mongodb_resident_megabytes - ## mongodb_updates_per_sec - ## mongodb_uptime_ns - ## mongodb_vsize_megabytes - ## mongodb_wtcache_bytes_read_into - - IsMatch(name, "mongodb_.*") and not IsMatch(name, "(?:mongodb_(active_(reads|writes)|commands_per_sec|connections_current|db_stats_storage_size|deletes_per_sec|document_.*|flushes_per_sec|getmores_per_sec|inserts_per_sec|net_.*_bytes_count|open_connections|page_faults|percent_cache_(dirty|used)|queries_per_sec|queued_(reads|writes)|repl_((commands|deletes|getmores|inserts|oplog|queries|updates)_per_sec|queries|oplog_window_sec)|resident_megabytes|updates_per_sec|uptime_ns|vsize_megabytes|wtcache_bytes_read_into))") - ## Rabbitmq Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/master/plugins/inputs/rabbitmq - ## Metrics follow following format: - ## rabbitmq_exchange_messages_publish_in - ## rabbitmq_exchange_messages_publish_in_rate - ## rabbitmq_exchange_messages_publish_out - ## rabbitmq_exchange_messages_publish_out_rate - ## rabbitmq_node_disk_free - ## rabbitmq_node_disk_free_limit - ## rabbitmq_node_fd_used - ## rabbitmq_node_gc_num_rate - ## rabbitmq_node_mem_limit - ## rabbitmq_node_mem_used - ## rabbitmq_node_mnesia_disk_tx_count - ## rabbitmq_node_mnesia_ram_tx_count - ## rabbitmq_node_uptime - ## rabbitmq_overview_clustering_listerners - ## rabbitmq_overview_connections - ## rabbitmq_overview_consumers - ## rabbitmq_overview_exchanges - ## rabbitmq_overview_messages_delivered - ## rabbitmq_overview_messages_published - ## rabbitmq_overview_messages_unacked - ## rabbitmq_overview_queues - ## rabbitmq_queue_consumers - ## rabbitmq_queue_memory - ## rabbitmq_queue_messages_deliver_rate - ## rabbitmq_queue_messages_max_time - ## rabbitmq_queue_messages_memory - ## rabbitmq_queue_messages_publish_rate - ## rabbitmq_queue_messages_unack - ## rabbitmq_queue_slave_nodes - - IsMatch(name, "rabbitmq_.*") and not IsMatch(name, "(?:rabbitmq_(exchange_messages_publish_(in_rate|in|out_rate|out)|node_(disk_free_limit|disk_free|mem_(limit|used)|uptime|fd_used|mnesia_(disk_tx_count|ram_tx_count)|gc_num_rate)|overview_(clustering_listerners|connections|exchanges|consumers|queues|messages_(delivered|published|unacked))|queue_(consumers|memory|slave_nodes|messages_(publish_rate|deliver_rate|memory|max_time|unack))))") - ## Tomcat Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/master/plugins/inputs/tomcat - ## Metrics follow following format: - ## tomcat_connector_bytes_received - ## tomcat_connector_bytes_sent - ## tomcat_connector_current_thread_busy - ## tomcat_connector_current_thread_count - ## tomcat_connector_current_threads_busy - ## tomcat_connector_error_count - ## tomcat_connector_max_threads - ## tomcat_connector_max_time - ## tomcat_connector_processing_time - ## tomcat_connector_request_count - ## tomcat_jmx_jvm_memory_HeapMemoryUsage_max - ## tomcat_jmx_jvm_memory_HeapMemoryUsage_used - ## tomcat_jmx_jvm_memory_NonHeapMemoryUsage_max - ## tomcat_jmx_jvm_memory_NonHeapMemoryUsage_used - ## tomcat_jmx_OperatingSystem_FreePhysicalMemorySize - ## tomcat_jmx_OperatingSystem_FreeSwapSpaceSize - ## tomcat_jmx_OperatingSystem_SystemCpuLoad - ## tomcat_jmx_OperatingSystem_TotalPhysicalMemorySize - ## tomcat_jmx_OperatingSystem_TotalSwapSpaceSize - ## tomcat_jmx_Servlet_processingTime - ## tomcat_jvm_memory_free - ## tomcat_jvm_memory_max - ## tomcat_jvm_memory_total - ## tomcat_jvm_memorypool_bytes_received - ## tomcat_jvm_memorypool_bytes_sent - ## tomcat_jvm_memorypool_current_thread_count - ## tomcat_jvm_memorypool_current_threads_busy - ## tomcat_jvm_memorypool_error_count - ## tomcat_jvm_memorypool_max - ## tomcat_jvm_memorypool_max_threads - ## tomcat_jvm_memorypool_max_time - ## tomcat_jvm_memorypool_processing_time - ## tomcat_jvm_memorypool_request_count - ## tomcat_jvm_memorypool_used - - IsMatch(name, "tomcat_.*") and not IsMatch(name, "(?:tomcat_(connector_(bytes_(received|sent)|current_(thread_(busy|count)|threads_busy)|error_count|max_threads|max_time|processing_time|request_count)|jmx_(jvm_memory_(HeapMemoryUsage_(max|used)|NonHeapMemoryUsage_(max|used))|OperatingSystem_(FreePhysicalMemorySize|FreeSwapSpaceSize|SystemCpuLoad|TotalPhysicalMemorySize|TotalSwapSpaceSize)|Servlet_processingTime)|jvm_memory_(free|max|total)|jvm_memorypool_(bytes_(received|sent)|current_thread_count|current_threads_busy|error_count|max_threads|max_time|max|processing_time|request_count|used)))") - ## Varnish Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/master/plugins/inputs/varnish - ## Metrics follow following format: - ## varnish_backend_busy - ## varnish_backend_conn - ## varnish_backend_fail - ## varnish_backend_recycle - ## varnish_backend_req - ## varnish_backend_retry - ## varnish_backend_reuse - ## varnish_backend_unhealthy - ## varnish_bans - ## varnish_bans_completed - ## varnish_bans_deleted - ## varnish_bans_dups - ## varnish_bans_lurker_contention - ## varnish_bans_lurker_obj_killed - ## varnish_bans_lurker_tested - ## varnish_bans_lurker_tests_tested - ## varnish_bans_obj - ## varnish_bans_obj_killed - ## varnish_bans_persisted_bytes - ## varnish_bans_persisted_fragmentation - ## varnish_boot_*_*_bodybytes - ## varnish_boot_*_*_hdrbytes - ## varnish_boot_*_bereq_bodybytes - ## varnish_boot_*_bereq_hdrbytes - ## varnish_cache_hit - ## varnish_cache_hit_grace - ## varnish_cache_hitpass - ## varnish_cache_miss - ## varnish_client_req - ## varnish_client_req_400 - ## varnish_client_req_417 - ## varnish_client_resp_500 - ## varnish_n_backend - ## varnish_n_expired - ## varnish_n_lru_nuked - ## varnish_n_vcl_avail - ## varnish_pools - ## varnish_s0_g_bytes - ## varnish_s0_g_space - ## varnish_s_fetch - ## varnish_s_pipe_in - ## varnish_s_pipe_out - ## varnish_s_req_bodybytes - ## varnish_s_req_hdrbytes - ## varnish_s_resp_bodybytes - ## varnish_s_resp_hdrbytes - ## varnish_s_sess - ## varnish_sess_closed - ## varnish_sess_closed_err - ## varnish_sess_conn - ## varnish_sess_drop - ## varnish_sess_dropped - ## varnish_sess_fail - ## varnish_sess_queued - ## varnish_thread_queue_len - ## varnish_threads - ## varnish_threads_created - ## varnish_threads_destroyed - ## varnish_threads_failed - ## varnish_threads_limited - ## varnish_uptime - ## varnish_vmods - - IsMatch(name, "varnish_.*") and not IsMatch(name, "(?:varnish_(backend_(busy|conn|fail|recycle|req|retry|reuse|unhealthy)|bans_(completed|deleted|dups|lurker_(contention|obj_killed|tests_tested|tested|)|obj_killed|obj|persisted_(bytes|fragmentation))|bans|boot_.*_.*_(bodybytes|hdrbytes)|cache_(hit_grace|hitpass|miss|hit)|client_(req_400|req_417|req|resp_500)|n_(backend|expired|lru_nuked|vcl_avail)|pools|s0_g_(bytes|space)|s_(fetch|pipe_(in|out)|req_(bodybytes|hdrbytes)|resp_(bodybytes|hdrbytes)|sess)|sess_(closed_err|closed|conn|drop|dropped|fail|queued)|thread_queue_len|threads_(created|destroyed|failed|limited)|threads|uptime|vmods))") - ## Memcached Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/master/plugins/inputs/memcache - ## Metrics follow following format: - ## memcached_accepting_conns - ## memcached_auth_cmds - ## memcached_auth_errors - ## memcached_bytes - ## memcached_bytes_read - ## memcached_bytes_written - ## memcached_cas_* - ## memcached_cas_* - ## memcached_cmd_* - ## memcached_cmd_flush - ## memcached_cmd_get - ## memcached_cmd_set - ## memcached_cmd_touch - ## memcached_conn_yields - ## memcached_connection_structures - ## memcached_curr_connections - ## memcached_curr_items - ## memcached_decr_* - ## memcached_delete_* - ## memcached_evictions - ## memcached_get_hits - ## memcached_get_misses - ## memcached_hash_bytes - ## memcached_hash_is_expanding - ## memcached_incr_* - ## memcached_limit_maxbytes - ## memcached_listen_disabled_num - ## memcached_reclaimed - ## memcached_threads - ## memcached_total_connections - ## memcached_total_items - ## memcached_uptime - - IsMatch(name, "memcached_.*") and not IsMatch(name, "(?:memcached_(accepting_conns|auth_(cmds|errors)|bytes_(read|written)|bytes|cas_*|cmd_.*|conn_yields|connection_structures|curr_(connections|items)|decr_.*|delete_.*|evictions|get_(hits|misses)|hash_(bytes|is_expanding)|incr_.*|limit_maxbytes|listen_disabled_num|reclaimed|threads|total_(connections|items)|uptime))") - ## Elasticsearch Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/master/plugins/inputs/elasticsearch - ## elasticsearch_cluster_health_active_primary_shards - ## elasticsearch_cluster_health_active_shards - ## elasticsearch_cluster_health_delayed_unassigned_shards - ## elasticsearch_cluster_health_indices_status_code - ## elasticsearch_cluster_health_initializing_shards - ## elasticsearch_cluster_health_number_of_data_nodes - ## elasticsearch_cluster_health_number_of_nodes - ## elasticsearch_cluster_health_number_of_pending_tasks - ## elasticsearch_cluster_health_relocating_shards - ## elasticsearch_cluster_health_unassigned_shards - ## elasticsearch_clusterstats_indices_fielddata_evictions - ## elasticsearch_clusterstats_nodes_jvm_mem_heap_used_in_bytes - ## elasticsearch_fs_total_free_in_bytes - ## elasticsearch_fs_total_total_in_bytes - ## elasticsearch_indices_flush_total - ## elasticsearch_indices_flush_total_time_in_millis - ## elasticsearch_indices_get_exists_time_in_millis - ## elasticsearch_indices_get_exists_total - ## elasticsearch_indices_get_missing_time_in_millis - ## elasticsearch_indices_get_missing_total - ## elasticsearch_indices_get_time_in_millis - ## elasticsearch_indices_get_total - ## elasticsearch_indices_indexing_delete_time_in_millis - ## elasticsearch_indices_indexing_delete_total - ## elasticsearch_indices_indexing_index_time_in_millis - ## elasticsearch_indices_indexing_index_total - ## elasticsearch_indices_merges_total_time_in_millis - ## elasticsearch_indices_search_query_time_in_millis - ## elasticsearch_indices_search_query_total - ## elasticsearch_indices_segments_fixed_bit_set_memory_in_bytes - ## elasticsearch_indices_segments_terms_memory_in_bytes - ## elasticsearch_indices_stats_primaries_docs_count - ## elasticsearch_indices_stats_primaries_indexing_index_time_in_millis - ## elasticsearch_indices_stats_primaries_query_cache_cache_size - ## elasticsearch_indices_stats_primaries_query_cache_evictions - ## elasticsearch_indices_stats_primaries_segments_doc_values_memory_in_bytes - ## elasticsearch_indices_stats_primaries_segments_index_writer_memory_in_bytes - ## elasticsearch_indices_stats_primaries_segments_memory_in_bytes - ## elasticsearch_indices_stats_total___fielddata_memory_size_in_bytes - ## elasticsearch_indices_stats_total___indexing_index_total - ## elasticsearch_indices_stats_total___merges_total - ## elasticsearch_indices_stats_total_docs_count - ## elasticsearch_indices_stats_total_fielddata_memory_size_in_bytes - ## elasticsearch_indices_stats_total_flush_total_time_in_millis - ## elasticsearch_indices_stats_total_indexing_delete_total - ## elasticsearch_indices_stats_total_indexing_index_time_in_millis - ## elasticsearch_indices_stats_total_indexing_index_total - ## elasticsearch_indices_stats_total_merges_total_docs - ## elasticsearch_indices_stats_total_merges_total_size_in_bytes - ## elasticsearch_indices_stats_total_merges_total_time_in_millis - ## elasticsearch_indices_stats_total_query_cache_evictions - ## elasticsearch_indices_stats_total_refresh_total - ## elasticsearch_indices_stats_total_refresh_total_time_in_millis - ## elasticsearch_indices_stats_total_search_fetch_time_in_millis - ## elasticsearch_indices_stats_total_search_fetch_total - ## elasticsearch_indices_stats_total_search_query_time_in_millis - ## elasticsearch_indices_stats_total_search_query_total - ## elasticsearch_indices_stats_total_segments_fixed_bit_set_memory_in_bytes - ## elasticsearch_indices_stats_total_segments_index_writer_memory_in_bytes - ## elasticsearch_indices_stats_total_segments_memory_in_bytes - ## elasticsearch_indices_stats_total_segments_terms_memory_in_bytes - ## elasticsearch_indices_stats_total_store_size_in_bytes - ## elasticsearch_indices_stats_total_translog_operations - ## elasticsearch_indices_stats_total_translog_size_in_bytes - ## elasticsearch_jvm_gc_collectors_*_collection_time_in_millis - ## elasticsearch_jvm_mem_heap_committed_in_bytes - ## elasticsearch_jvm_mem_heap_used_in_bytes - ## elasticsearch_jvm_mem_heap_used_percent - ## elasticsearch_os_cpu_load_average_5m - ## elasticsearch_os_cpu_percent - ## elasticsearch_process_open_file_descriptors - ## elasticsearch_thread_pool_analyze_completed - ## elasticsearch_thread_pool_analyze_threads - ## elasticsearch_thread_pool_get_rejected - ## elasticsearch_thread_pool_search_queue - ## elasticsearch_transport_rx_size_in_bytes - ## elasticsearch_transport_tx_size_in_bytes - - IsMatch(name, "elasticsearch_.*") and not IsMatch(name, "(?:elasticsearch_(cluster_health_(active_(primary_shards|shards)|delayed_unassigned_shards|indices_status_code|initializing_shards|number_of_(data_nodes|nodes|pending_tasks)|relocating_shards|unassigned_shards)|clusterstats_(indices_fielddata_evictions|nodes_jvm_mem_heap_used_in_bytes)|fs_total_(free_in_bytes|total_in_bytes)|indices_(flush_(total|total_time_in_millis)|get_(exists_time_in_millis|exists_total|missing_time_in_millis|missing_total|time_in_millis|total)|indexing_delete_time_in_millis|indexing_delete_total|indexing_index_time_in_millis|indexing_index_total|merges_total_time_in_millis|search_query_time_in_millis|search_query_total|segments_fixed_bit_set_memory_in_bytes|segments_terms_memory_in_bytes|stats_primaries_(docs_count|indexing_index_time_in_millis|query_cache_cache_size|query_cache_evictions|segments_doc_values_memory_in_bytes|segments_index_writer_memory_in_bytes|segments_memory_in_bytes)|stats_total___(fielddata_memory_size_in_bytes|indexing_index_total|merges_total)|stats_total_(docs_count|fielddata_memory_size_in_bytes|flush_total_time_in_millis|indexing_delete_total|indexing_index_time_in_millis|indexing_index_total|merges_total_docs|merges_total_size_in_bytes|merges_total_time_in_millis|query_cache_evictions|refresh_total|refresh_total_time_in_millis|search_fetch_time_in_millis|search_fetch_total|search_query_time_in_millis|search_query_total|segments_fixed_bit_set_memory_in_bytes|segments_index_writer_memory_in_bytes|segments_memory_in_bytes|segments_terms_memory_in_bytes|store_size_in_bytes|translog_operations|translog_size_in_bytes))|jvm_(gc_collectors_.*_collection_time_in_millis|mem_heap_committed_in_bytes|mem_heap_used_in_bytes|mem_heap_used_percent)|os_cpu_(load_average_5m|percent)|process_open_file_descriptors|thread_pool_(analyze_completed|analyze_threads|get_rejected|search_queue)|transport_(rx_size_in_bytes|tx_size_in_bytes)))") - ## Activemq Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/master/plugins/inputs/activemq - ## activemq_queue_* - ## activemq_topic_* - ## activemq_*_QueueSize - ## activemq_broker_AverageMessageSize - ## activemq_broker_CurrentConnectionsCount - ## activemq_broker_MemoryLimit - ## activemq_broker_StoreLimit - ## activemq_broker_TempLimit - ## activemq_broker_TotalConnectionsCount - ## activemq_broker_TotalConsumerCount - ## activemq_broker_TotalDequeueCount - ## activemq_broker_TotalEnqueueCount - ## activemq_broker_TotalMessageCount - ## activemq_broker_TotalProducerCount - ## activemq_broker_UptimeMillis - ## activemq_jvm_memory_HeapMemoryUsage_max - ## activemq_jvm_memory_HeapMemoryUsage_used - ## activemq_jvm_memory_NonHeapMemoryUsage_used - ## activemq_jvm_runtime_Uptime - ## activemq_OperatingSystem_FreePhysicalMemorySize - ## activemq_OperatingSystem_SystemCpuLoad - ## activemq_OperatingSystem_TotalPhysicalMemorySize - - IsMatch(name, "activemq_.*") and not IsMatch(name, "(?:activemq_(topic_.*|queue_.*|.*_QueueSize|broker_(AverageMessageSize|CurrentConnectionsCount|MemoryLimit|StoreLimit|TempLimit|TotalConnectionsCount|TotalConsumerCount|TotalDequeueCount|TotalEnqueueCount|TotalMessageCount|TotalProducerCount|UptimeMillis)|jvm_memory_(HeapMemoryUsage_max|HeapMemoryUsage_used|NonHeapMemoryUsage_used)|jvm_runtime_Uptime|OperatingSystem_(FreePhysicalMemorySize|SystemCpuLoad|TotalPhysicalMemorySize)))") - ## Couchbase Telegraf Metrics - ## List of Metrics are on following github page: - ## https://github.com/influxdata/telegraf/tree/master/plugins/inputs/couchbase - ## couchbase_node_memory_free - ## couchbase_node_memory_total - ## couchbase_bucket_item_count - ## couchbase_bucket_curr_connections - ## couchbase_bucket_ops_per_sec - ## couchbase_bucket_ep_num_value_ejects - ## couchbase_bucket_disk_write_queue - ## couchbase_bucket_ep_oom_errors - ## couchbase_bucket_delete_misses - ## couchbase_bucket_delete_hits - ## couchbase_bucket_bytes_read - ## couchbase_bucket_bytes_written - ## couchbase_bucket_cmd_get - ## couchbase_bucket_cmd_set - ## couchbase_bucket_cas_hits - ## couchbase_bucket_ops - ## couchbase_bucket_curr_items - ## couchbase_bucket_mem_actual_free - ## couchbase_bucket_cpu_utilization_rate - ## couchbase_bucket_swap_used - ## couchbase_bucket_disk_used - ## couchbase_bucket_rest_requests - ## couchbase_bucket_hibernated_waked - ## couchbase_bucket_mem_used - ## couchbase_bucket_xdc_ops - ## couchbase_bucket_ep_mem_low_wat - ## couchbase_bucket_ep_mem_high_wat - ## couchbase_bucket_ep_ops_update - ## couchbase_bucket_ep_tmp_oom_errors - ## couchbase_bucket_ep_dcp_replica_count - ## couchbase_bucket_ep_dcp_replica_producer_count - ## couchbase_bucket_ep_dcp_xdcr_producer_count - ## couchbase_bucket_ep_dcp_replica_items_remaining - ## couchbase_bucket_ep_dcp_xdcr_items_remaining - ## couchbase_bucket_ep_dcp_replica_items_sent - ## couchbase_bucket_ep_dcp_xdcr_items_sent - ## couchbase_bucket_ep_dcp_replica_total_bytes - ## couchbase_bucket_ep_dcp_xdcr_total_bytes - ## couchbase_bucket_ep_num_ops_get_meta - ## couchbase_bucket_ep_num_ops_set_meta - ## couchbase_bucket_ep_num_ops_del_meta - ## couchbase_bucket_ep_dcp_xdcr_count - ## couchbase_bucket_ep_resident_items_rate - ## couchbase_bucket_vb_active_queue_size - ## couchbase_bucket_vb_replica_queue_size - ## couchbase_bucket_vb_pending_queue_size - ## couchbase_bucket_vb_active_queue_fill - ## couchbase_bucket_vb_replica_queue_fill - ## couchbase_bucket_vb_pending_queue_fill - ## couchbase_bucket_vb_avg_active_queue_age - ## couchbase_bucket_vb_avg_replica_queue_age - ## couchbase_bucket_vb_avg_pending_queue_age - ## couchbase_bucket_vb_active_num - ## couchbase_bucket_vb_replica_num - ## couchbase_bucket_vb_pending_num - ## couchbase_bucket_vb_pending_curr_items - ## couchbase_bucket_vb_active_resident_items_ratio - - IsMatch(name, "couchbase_.*") and not IsMatch(name, "(?:couchbase_(node_.*|bucket_(ep_.*|vb_.*|delete_.*|cmd.*|bytes_.*|item_count|curr_connections|ops_per_sec|disk_write_queue|mem_.*|cas_hits|ops|curr_items|cpu_utilization_rate|swap_used|disk_used|rest_requests|hibernated_waked|xdc_ops)))") - ## SquidProxy Telegraf Metrics - ## List of Metrics are on following github page: - ## https://wiki.squid-cache.org/Features/Snmp - ## squid_cacheIpEntries - ## squid_cacheIpRequests - ## squid_cacheIpHits - ## squid_cacheFqdnEntries - ## squid_cacheFqdnRequests - ## squid_cacheFqdnMisses - ## squid_cacheFqdnNegativeHits - ## squid_cacheDnsRequests - ## squid_cacheDnsReplies - ## squid_cacheDnsSvcTime5 - ## squid_cacheSysPageFaults - ## squid_cacheSysNumReads - ## squid_cacheCurrentFileDescrCnt - ## squid_cacheCurrentUnusedFDescrCnt - ## squid_cacheCurrentResFileDescrCnt - ## squid_cacheServerRequests - ## squid_cacheServerInKb - ## squid_cacheServerOutKb - ## squid_cacheHttpAllSvcTime5 - ## squid_cacheHttpErrors - ## squid_cacheHttpInKb - ## squid_cacheHttpOutKb - ## squid_cacheHttpAllSvcTime1 - ## squid_cacheMemMaxSize - ## squid_cacheMemUsage - ## squid_cacheNumObjCount - ## squid_cacheCpuTime - ## squid_cacheMaxResSize - ## squid_cacheProtoClientHttpRequests - ## squid_cacheClients - ## squid_uptime - - IsMatch(name, "squid_.*") and not IsMatch(name, "(?:squid_(uptime|cache(Ip(Entries|Requests|Hits)|Fqdn(Entries|Requests|Misses|NegativeHits)|Dns(Requests|Replies|SvcTime5)|Sys(PageFaults|NumReads)|Current(FileDescrCnt|UnusedFDescrCnt|ResFileDescrCnt)|Server(Requests|InKb|OutKb)|Http(AllSvcTime5|Errors|InKb|OutKb|AllSvcTime1)|Mem(MaxSize|Usage)|NumObjCount|CpuTime|MaxResSize|ProtoClientHttpRequests|Clients)))") - + - resource.attributes["service.name"] != "pod-annotations" and IsMatch(name, + "scrape_.*") + transform/drop_unnecessary_attributes: + error_mode: ignore + metric_statements: + - context: resource + statements: + - delete_key(attributes, "http.scheme") + - delete_key(attributes, "net.host.name") + - delete_key(attributes, "net.host.port") + - delete_key(attributes, "service.instance.id") + - delete_matching_keys(attributes, "k8s.*") receivers: prometheus: config: @@ -1052,26 +152,27 @@ spec: scrape_interval: 60s scrape_configs: [] target_allocator: + collector_id: ${POD_NAME} endpoint: http://RELEASE-NAME-sumologic-metrics-targetallocator interval: 30s - collector_id: ${POD_NAME} - service: - telemetry: - logs: - level: info - metrics: - address: 0.0.0.0:8888 # this is the default, but setting it explicitly lets the operator add it automatically extensions: - - health_check - - pprof - - file_storage + - health_check + - pprof + - file_storage pipelines: metrics: - exporters: [otlphttp] + exporters: + - otlphttp processors: - - batch - - filter/drop_unnecessary_metrics - - transform/drop_unnecessary_attributes - - filter/app_metrics - receivers: [prometheus] + - batch + - filter/drop_unnecessary_metrics + - transform/drop_unnecessary_attributes + - filter/app_metrics + receivers: + - prometheus + telemetry: + logs: + level: info + metrics: + address: 0.0.0.0:8888