[opentelemetry] add templating for ceph and kvm

opentelemetry/README.md

@@ -55,7 +55,13 @@ The package will deploy the OpenTelemetry Operator which works as a manager for
 - Journald events from systemd journal
 - its own metrics
 
-You can disable the collection of logs by setting `open_telemetry.LogCollector.enabled` to `false`. The same is true for disabling metrics: `open_telemetry.MetricsCollector.enabled` to `false`. 
+You can disable the collection of logs by setting `openTelemetry.logCollector.enabled` to `false`. The same is true for disabling the collection of metrics by setting `openTelemetry.metricsCollector.enabled` to `false`.
+The `logsCollector` comes with a standard set of log-processing, such as adding cluster information and common labels for Journald events.
+In addition we provide default pipelines for common log types. Currently the following log types have default configurations that can be enabled (requires `logsCollector.enabled` to `true`):
+  1. KVM: `openTelemetry.logsCollector.kvmConfig`: Logs from Kernel-based Virtual Machines (KVMs) providing insights into virtualization activities, resource usage, and system performance
+  2. Ceph:`openTelemetry.logsCollector.cephConfig`: Logs from Ceph storage systems, capturing information about cluster operations, performance metrics, and health status
+
+These default configurations provide common labels and Grok parsing for logs emitted through the respective services.
 
 Based on the backend selection the telemetry data will be exporter to the backend.
 
@@ -67,8 +73,10 @@ Greenhouse regularly performs integration tests that are bundled with **OpenTele
 
 | Name         | Description          | Type           | required           |
 | ------------ | -------------------- |---------------- | ------------------ | 
-`openTelemetry.logsCollector.enabled`    | Activates the standard configuration for logs | bool | `false`
-`openTelemetry.metricsCollector.enabled` | Activates the standard configuration for metrics | bool | `false`
+`openTelemetry.logsCollector.enabled`    | Activates the standard configuration for logs | bool | `false` |
+`openTelemetry.logsCollector.kvmConfig.enabled`    | Activates the configuration for KVM logs (requires logsCollector to be enabled) | bool | `false` |
+`openTelemetry.logsCollector.cephConfig.enabled`    | Activates the configuration for Ceph logs (requires logsCollector to be enabled) | bool | `false` |
+`openTelemetry.metricsCollector.enabled` | Activates the standard configuration for metrics | bool | `false` |
 `openTelemetry.openSearchLogs.username` | Username for OpenSearch endpoint | secret | `false` |
 `openTelemetry.openSearchLogs.password` | Password for OpenSearch endpoint | secret | `false` | 
 `openTelemetry.openSearchLogs.endpoint` | Endpoint URL for OpenSearch      | secret | `false` | 

opentelemetry/chart/Chart.yaml

@@ -4,7 +4,7 @@
 apiVersion: v2
 appVersion: v0.114.0
 name: opentelemetry-operator
-version: 0.6.1
+version: 0.7.0
 description: OpenTelemetry Operator Helm chart for Kubernetes
 icon: https://raw.githubusercontent.com/cncf/artwork/a718fa97fffec1b9fd14147682e9e3ac0c8817cb/projects/opentelemetry/icon/color/opentelemetry-icon-color.png
 type: application

opentelemetry/chart/templates/_ceph-config.tpl

@@ -0,0 +1,94 @@
+{{- define "ceph.labels" }}
+- tag_name: app.label.component
+  key: app.kubernetes.io/component
+  from: pod
+- tag_name: app.label.created-by
+  key: app.kubernetes.io/created-by
+  from: pod
+- tag_name: app.label.managed-by
+  key: app.kubernetes.io/managed-by
+  from: pod
+- tag_name: app.label.part-of
+  key: app.kubernetes.io/part-of
+  from: pod
+- tag_name: app.label.ceph-osd-id
+  key: ceph-osd-id
+  from: pod
+- tag_name: app.label.ceph_daemon_id
+  key: ceph_daemon_id
+  from: pod
+- tag_name: app.label.ceph_daemon_type
+  key: ceph_daemon_type
+  from: pod
+- tag_name: app.label.device-class
+  key: device-class
+  from: pod
+- tag_name: app.label.failure-domain
+  key: failure-domain
+  from: pod
+- tag_name: app.label.osd
+  key: osd
+  from: pod
+- tag_name: app.label.osd-store
+  key: osd-store
+  from: pod
+- tag_name: app.label.portable
+  key: portable
+  from: pod
+- tag_name: app.label.rook_cluster
+  key: rook_cluster
+  from: pod
+- tag_name: app.label.rook_io.operator-namespace
+  key: rook_io/operator-namespace
+  from: pod
+- tag_name: app.label.topology-location-host
+  key: topology-location-host
+  from: pod
+- tag_name: app.label.topology-location-region
+  key: topology-location-region
+  from: pod
+- tag_name: app.label.topology-location-region
+  key: topology-location-region
+  from: pod
+- tag_name: app.label.topology-location-root
+  key: topology-location-root
+  from: pod
+- tag_name: app.label.topology-location-zone
+  key: topology-location-zone
+  from: pod
+{{- end }}
+
+{{- define "ceph.transform" }}
+transform/ceph_rgw:
+  error_mode: ignore
+  log_statements:
+    - context: log
+      conditions:
+        - resource.attributes["app.label.component"] == "cephobjectstores.ceph.rook.io"
+      statements:
+        - merge_maps(attributes, ExtractGrokPatterns(body, "%{WORD:debug_level} %{TIMESTAMP_ISO8601:log_timestamp}(%{SPACE})?%{NOTSPACE}(%{SPACE})?%{NOTSPACE}(%{SPACE})?%{WORD}\\:(%{SPACE})?%{WORD}\\:(%{SPACE})?%{IP:client.address}(%{SPACE})?%{NOTSPACE}(%{SPACE})%{PROJECT_ID:project.id}(\\$%{NOTSPACE})?(%{SPACE})?\\[%{HTTPDATE:request.timestamp}\\] \"%{WORD:request.method} \\/(?<bucket>[a-zA-Z0-9._+-]+)?(\\/)?(%{NOTSPACE:request.path})? %{WORD:network.protocol.name}/%{NOTSPACE:network.protocol.version}\" %{NUMBER:response} %{NUMBER:content.length:int} %{NOTSPACE} \"%{GREEDYDATA:user.agent}\" %{NOTSPACE} latency=%{NUMBER:latency:float}", true, ["PROJECT_ID=([A-Za-z0-9-]+)"]),"upsert")
+        - merge_maps(attributes, ExtractGrokPatterns(body, "%{WORD:log_level}%{SPACE}%{NOTSPACE}%{SPACE}%{NOTSPACE:process.name}", true),"upsert")
+        - set(attributes["network.protocol.name"], ConvertCase(attributes["network.protocol.name"], "lower")) where cache["network.protocol.name"] != nil
+        - set(attributes["config.parsed"], "ceph_rgw") where attributes["project.id"] != nil
+        - set(attributes["config.parsed"], "ceph_rgw") where attributes["log_level"] != nil
+
+transform/ceph_osd:
+  error_mode: ignore
+  log_statements:
+    - context: log
+      conditions:
+        - resource.attributes["app.label.component"] == "cephclusters.ceph.rook.io"
+      statements:
+        - merge_maps(attributes, ExtractGrokPatterns(body, "%{WORD:osd.stats.level}%{SPACE}%{NOTSPACE:osd.stats.files}%{SPACE}%{NUMBER:osd.stats.osd.stats.size:float}%{SPACE}%{WORD}%{SPACE}%{NUMBER:osd.stats.size_unit:float}%{SPACE}%{NUMBER:osd.stats.score:float}%{SPACE}%{NUMBER:osd.stats.read_gb:float}%{SPACE}%{NUMBER:osd.stats.rn_gb:float}%{SPACE}%{NUMBER:osd.stats.rnp1_gb:float}%{SPACE}%{NUMBER:osd.stats.write_gb:float}%{SPACE}%{NUMBER:osd.stats.wnew_gb:float}%{SPACE}%{NUMBER:osd.stats.moved:float}%{SPACE}%{NUMBER:osd.stats.w_amp:float}%{SPACE}%{NUMBER:osd.stats.rd_mb_s:float}%{SPACE}%{NUMBER:osd.stats.wr_mb_s:float}%{SPACE}%{NUMBER:osd.stats.comp_sec:float}%{SPACE}%{NUMBER:osd.stats.comp_merge_cpu_sec:float}%{SPACE}%{NUMBER:osd.stats.cpmp_cnt:float}%{SPACE}%{NUMBER:osd.stats.av_sec:float}%{SPACE}%{NUMBER:osd.stats.keyin:float}%{SPACE}%{NUMBER:osd.stats.keydrop:float}%{SPACE}%{NUMBER:osd.stats.rblob_gb:float}%{SPACE}%{NUMBER:osd.stats.wblol_gb:float}", true),"upsert")
+        - merge_maps(attributes, ExtractGrokPatterns(body, "%{GREEDYDATA:osd.wall.type}\\:%{SPACE}%{NUMBER:osd.wall.writes:float}(K|M|G)?%{SPACE}writes,%{SPACE}%{NUMBER:osd.wall.syncs:float}(K|M|G)?%{SPACE}syncs,%{SPACE}%{NUMBER:osd.wall.writes_per_sync:float}%{SPACE}writes per sync, written\\:%{SPACE}%{NUMBER:osd.wall.written_gb:float}%{SPACE}(GB|MB|TB)?,%{SPACE}%{NUMBER:osd.written_mb_sec:float}", true),"upsert")
+        - merge_maps(attributes, ExtractGrokPatterns(body, "%{WORD:log_level}%{SPACE}%{NOTSPACE}%{SPACE}%{SPACE}%{NOTSPACE:process.name}", true),"upsert")
+        - set(attributes["config.parsed"], "ceph_osd") where attributes["osd.stats.level"] != nil
+        - set(attributes["config.parsed"], "ceph_osd") where attributes["osd.wall.type"] != nil
+{{- end }}
+
+{{- define "ceph.pipeline" }}
+logs/ceph:
+  receivers: [filelog/containerd]
+  processors: [k8sattributes,attributes/cluster,transform/ingress,transform/ceph_rgw,transform/ceph_osd]
+  exporters: [forward]
+{{- end }}

opentelemetry/chart/templates/_kvm-config.tpl

@@ -0,0 +1,64 @@
+{{- define "kvm.labels" }}
+
+{{- end }}
+{{- define "kvm.receiver" }}
+filelog/kvm_logs:
+  include: [ /var/log/libvirt/qemu/*.log, /var/log/openvswitch/*.log ]
+  include_file_path: true
+  start_at: beginning
+  multiline:
+    line_start_pattern: ^\d{4}-\d{2}-\d{2}
+  operators:
+    - type: regex_parser
+      regex: (?P<logtime>\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}.\d{3})
+    - type: time_parser
+      parse_from: attributes.logtime
+      layout: '%Y-%m-%dT%H:%M:%S.%L'
+      layout_type: strptime
+    - id: file-label
+      type: add
+      field: attributes["log.type"]
+      value: "files"
+{{- end }}
+{{- define "kvm.transform" }}
+transform/kvm_openvswitch:
+  error_mode: ignore
+  log_statements:
+    - context: log
+      conditions:
+        - resource.attributes["k8s.daemonset.name"] == "neutron-openvswitch-agent"
+      statements:
+        - merge_maps(attributes, ExtractGrokPatterns(body, "%{TIMESTAMP_ISO8601:logtime}%{SPACE}%{NUMBER:process.id}%{SPACE}%{WORD:log_level}%{SPACE}%{NOTSPACE:process.name}%{SPACE}\\[%{REQUEST_ID:request.id}%{SPACE}%{REQUEST_ID:request.global_id}", true, ["REQUEST_ID=([A-Za-z0-9-]+)"]), "upsert")
+        - set(attributes["config.parsed"], "kvm_openvswitch") where attributes["log_level"] != nil
+
+transform/kvm_nova_agent:
+  error_mode: ignore
+  log_statements:
+    - context: log
+      conditions:
+        - resource.attributes["k8s.daemonset.name"] == "nova-hypervisor-agents-compute-kvm"
+      statements:
+        - merge_maps(attributes, ExtractGrokPatterns(body, "%{TIMESTAMP_ISO8601:logtime}%{SPACE}%{NUMBER:process.id}%{SPACE}%{WORD:log_level}%{SPACE}%{NOTSPACE:process.name}%{SPACE}\\[%{REQUEST_ID:request.id}%{SPACE}%{REQUEST_ID:request.global_id}", true, ["REQUEST_ID=([A-Za-z0-9-]+)"]), "upsert")
+        - set(attributes["config.parsed"], "kvm_nova_agent") where attributes["log_level"] != nil
+
+transform/kvm_logs:
+  error_mode: ignore
+  log_statements:
+    - context: log
+      conditions:
+        - resource.attributes["log.type"] == "files"
+      statements:
+        - merge_maps(attributes, ExtractGrokPatterns(body, "%{TIMESTAMP_ISO8601:timestamp}%{SPACE}%{GREEDYDATA:log}",true), "upsert")
+        - set(attributes["config.parsed"], "files") where attributes["log_level"] != nil
+
+{{- end }}
+{{- define "kvm.pipeline" }}
+logs/kvm_containerd:
+  receivers: [filelog/containerd]
+  processors: [k8sattributes,attributes/cluster,transform/ingress,transform/kvm_openvswitch,transform/kvm_nova_agent]
+  exporters: [forward]
+logs/kvm_filelog:
+  receivers: [filelog/kvm_logs]
+  processors: [k8sattributes,attributes/cluster,transform/kvm_logs]
+  exporters: [forward]
+{{- end }}