flow-aggregator.yml

apiVersion: v1
kind: Namespace
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator
---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator
  namespace: flow-aggregator
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  labels:
    app: flow-aggregator
  name: flow-exporter-role
  namespace: flow-aggregator
rules:
- apiGroups:
  - ""
  resourceNames:
  - flow-aggregator-ca
  resources:
  - configmaps
  verbs:
  - get
- apiGroups:
  - ""
  resourceNames:
  - flow-aggregator-client-tls
  resources:
  - secrets
  verbs:
  - get
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator-role
rules:
- apiGroups:
  - ""
  resourceNames:
  - flow-aggregator-ca
  resources:
  - configmaps
  verbs:
  - get
  - update
- apiGroups:
  - ""
  resources:
  - pods
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - configmaps
  verbs:
  - create
  - get
  - list
  - watch
- apiGroups:
  - ""
  resourceNames:
  - extension-apiserver-authentication
  resources:
  - configmaps
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resourceNames:
  - flow-aggregator-client-tls
  resources:
  - secrets
  verbs:
  - get
  - update
- apiGroups:
  - ""
  resources:
  - secrets
  verbs:
  - create
- apiGroups:
  - ""
  resourceNames:
  - flow-aggregator-configmap
  resources:
  - configmaps
  verbs:
  - update
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  labels:
    app: flow-aggregator
  name: flow-exporter-role-binding
  namespace: flow-aggregator
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: flow-exporter-role
subjects:
- kind: ServiceAccount
  name: antrea-agent
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator-cluster-id-reader
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: antrea-cluster-identity-reader
subjects:
- kind: ServiceAccount
  name: flow-aggregator
  namespace: flow-aggregator
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator-cluster-role-binding
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: flow-aggregator-role
subjects:
- kind: ServiceAccount
  name: flow-aggregator
  namespace: flow-aggregator
---
apiVersion: v1
data:
  flow-aggregator.conf: |
    # Provide the active flow record timeout as a duration string. This determines
    # how often the flow aggregator exports the active flow records to the flow
    # collector. Thus, for flows with a continuous stream of packets, a flow record
    # will be exported to the collector once the elapsed time since the last export
    # event in the flow aggregator is equal to the value of this timeout.
    # Valid time units are "ns", "us" (or "µs"), "ms", "s", "m", "h".
    activeFlowRecordTimeout: 60s

    # Provide the inactive flow record timeout as a duration string. This determines
    # how often the flow aggregator exports the inactive flow records to the flow
    # collector. A flow record is considered to be inactive if no matching record
    # has been received by the flow aggregator in the specified interval.
    # Valid time units are "ns", "us" (or "µs"), "ms", "s", "m", "h".
    inactiveFlowRecordTimeout: 90s

    # Provide the transport protocol for the flow aggregator collecting process, which is tls, tcp or udp.
    aggregatorTransportProtocol: "tls"

    # Provide an extra DNS name or IP address of flow aggregator for generating TLS certificate.
    flowAggregatorAddress: ""

    # recordContents enables configuring some fields in the flow records. Fields can
    # be excluded to reduce record size, but some features or external tooling may
    # depend on these fields.
    recordContents:
      # Determine whether source and destination Pod labels will be included in the flow records.
      podLabels: false

    # apiServer contains APIServer related configuration options.
    apiServer:
      # The port for the flow-aggregator APIServer to serve on.
      apiPort: 10348

      # Comma-separated list of Cipher Suites. If omitted, the default Go Cipher Suites will be used.
      # https://golang.org/pkg/crypto/tls/#pkg-constants
      # Note that TLS1.3 Cipher Suites cannot be added to the list. But the apiserver will always
      # prefer TLS1.3 Cipher Suites whenever possible.
      tlsCipherSuites: ""

      # TLS min version from: VersionTLS10, VersionTLS11, VersionTLS12, VersionTLS13.
      tlsMinVersion: ""

    # flowCollector contains external IPFIX or JSON collector related configuration options.
    flowCollector:
      # Enable is the switch to enable exporting flow records to external flow collector.
      enable: false

      # Provide the flow collector address as string with format <IP>:<port>[:<proto>], where proto is tcp or udp.
      # If no L4 transport proto is given, we consider tcp as default.
      address: ""

      # Provide the 32-bit Observation Domain ID which will uniquely identify this instance of the flow
      # aggregator to an external flow collector. If omitted, an Observation Domain ID will be generated
      # from the persistent cluster UUID generated by Antrea. Failing that (e.g. because the cluster UUID
      # is not available), a value will be randomly generated, which may vary across restarts of the flow
      # aggregator.
      #observationDomainID:

      # Provide format for records sent to the configured flow collector.
      # Supported formats are IPFIX and JSON.
      recordFormat: "IPFIX"

    # clickHouse contains ClickHouse related configuration options.
    clickHouse:
      # Enable is the switch to enable exporting flow records to ClickHouse.
      enable: false

      # Database is the name of database where Antrea "flows" table is created.
      database: "default"

      # DatabaseURL is the url to the database. Provide the database URL as a string with format
      # <Protocol>://<ClickHouse server FQDN or IP>:<ClickHouse port>. The protocol has to be
      # one of the following: "tcp", "tls", "http", "https". When "tls" or "https" is used, tls
      # will be enabled.
      databaseURL: "tcp://clickhouse-clickhouse.flow-visibility.svc:9000"

      # TLS configuration options, when using TLS to connect to the ClickHouse service.
      tls:
        # InsecureSkipVerify determines whether to skip the verification of the server's certificate chain and host name.
        # Default is false.
        insecureSkipVerify: false

        # CACert indicates whether to use custom CA certificate. Default root CAs will be used if this field is false.
        # If true, a Secret named "clickhouse-ca" must be provided with the following keys:
        # ca.crt: <CA certificate>
        caCert: false

      # Debug enables debug logs from ClickHouse sql driver.
      debug: false

      # Compress enables lz4 compression when committing flow records.
      compress: true

      # CommitInterval is the periodical interval between batch commit of flow records to DB.
      # Valid time units are "ns", "us" (or "µs"), "ms", "s", "m", "h".
      # The minimum interval is 1s based on ClickHouse documentation for best performance.
      commitInterval: "8s"

    # s3Uploader contains configuration options for uploading flow records to AWS S3.
    s3Uploader:
      # Enable is the switch to enable exporting flow records to AWS S3.
      # At the moment, the flow aggregator will look for the "standard" environment variables to
      # authenticate to AWS. These can be static credentials (AWS_ACCESS_KEY_ID,
      # AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN) or a Web Identity Token
      # (AWS_WEB_IDENTITY_TOKEN_FILE).
      enable: false

      # BucketName is the name of the S3 bucket to which flow records will be uploaded. If this
      # field is empty, initialization will fail.
      bucketName: ""

      # BucketPrefix is the prefix ("folder") under which flow records will be uploaded. If this
      # is omitted, flow records will be uploaded to the root of the bucket.
      bucketPrefix: ""

      # Region is used as a "hint" to get the region in which the provided bucket is located.
      # An error will occur if the bucket does not exist in the AWS partition the region hint
      # belongs to. If region is omitted, the value of the AWS_REGION environment variable will
      # be used, and if it is missing, we will default to "us-west-2".
      region: "us-west-2"

      # RecordFormat defines the format of the flow records uploaded to S3. Only "CSV" is
      # supported at the moment.
      recordFormat: "CSV"

      # Compress enables gzip compression when uploading files to S3. Defaults to true.
      compress: true

      # MaxRecordsPerFile is the maximum number of records per file uploaded. It is not recommended
      # to change this value.
      maxRecordsPerFile: 1e+06

      # UploadInterval is the duration between each file upload to S3.
      uploadInterval: "60s"

    # FlowLogger contains configuration options for writing flow records to a local log file.
    flowLogger:
      # Enable is the switch to enable writing flow records to a local log file.
      enable: false

      # Path is the path to the local log file.
      path: "/tmp/antrea-flows.log"

      # MaxSize is the maximum size in MB of a log file before it gets rotated.
      maxSize: 100

      # MaxBackups is the maximum number of old log files to retain. If set to 0, all log files will be
      # retained (unless MaxAge causes them to be deleted).
      maxBackups: 3

      # MaxAge is the maximum number of days to retain old log files based on the timestamp encoded in
      # their filename. The default (0) is not to remove old log files based on age.
      maxAge: 0

      # Compress enables gzip compression on rotated files.
      compress: true

      # RecordFormat defines the format of the flow records logged to file. Only "CSV" is supported at
      # the moment.
      recordFormat: "CSV"

      # Filters can be used to select which flow records to log to file. The provided filters are OR-ed
      # to determine whether a specific flow should be logged.
      filters:
        []

      # PrettyPrint enables conversion of some numeric fields to a more meaningful string
      # representation.
      prettyPrint: true
kind: ConfigMap
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator-configmap
  namespace: flow-aggregator
---
apiVersion: v1
kind: Secret
metadata:
  labels:
    app: flow-aggregator
  name: clickhouse-secret
  namespace: flow-aggregator
stringData:
  password: clickhouse_operator_password
  username: clickhouse_operator
type: Opaque
---
apiVersion: v1
kind: Secret
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator-aws-credentials
  namespace: flow-aggregator
stringData:
  aws_access_key_id: changeme
  aws_secret_access_key: changeme
  aws_session_token: ""
type: Opaque
---
apiVersion: v1
kind: Service
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator
  namespace: flow-aggregator
spec:
  ports:
  - name: ipfix-udp
    port: 4739
    protocol: UDP
    targetPort: 4739
  - name: ipfix-tcp
    port: 4739
    protocol: TCP
    targetPort: 4739
  selector:
    app: flow-aggregator
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: flow-aggregator
  name: flow-aggregator
  namespace: flow-aggregator
spec:
  replicas: 1
  selector:
    matchLabels:
      app: flow-aggregator
  template:
    metadata:
      labels:
        app: flow-aggregator
    spec:
      containers:
      - args:
        - --config
        - /etc/flow-aggregator/flow-aggregator.conf
        - --logtostderr=false
        - --log_dir=/var/log/antrea/flow-aggregator
        - --alsologtostderr
        - --log_file_max_size=100
        - --log_file_max_num=4
        env:
        - name: POD_NAME
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
        - name: POD_NAMESPACE
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
        - name: CH_USERNAME
          valueFrom:
            secretKeyRef:
              key: username
              name: clickhouse-secret
        - name: CH_PASSWORD
          valueFrom:
            secretKeyRef:
              key: password
              name: clickhouse-secret
        - name: FA_CONFIG_MAP_NAME
          value: flow-aggregator-configmap
        - name: AWS_ACCESS_KEY_ID
          valueFrom:
            secretKeyRef:
              key: aws_access_key_id
              name: flow-aggregator-aws-credentials
        - name: AWS_SECRET_ACCESS_KEY
          valueFrom:
            secretKeyRef:
              key: aws_secret_access_key
              name: flow-aggregator-aws-credentials
        - name: AWS_SESSION_TOKEN
          valueFrom:
            secretKeyRef:
              key: aws_session_token
              name: flow-aggregator-aws-credentials
        image: antrea/flow-aggregator:latest
        imagePullPolicy: IfNotPresent
        name: flow-aggregator
        ports:
        - containerPort: 4739
        volumeMounts:
        - mountPath: /etc/flow-aggregator
          name: flow-aggregator-config
          readOnly: true
        - mountPath: /var/log/antrea/flow-aggregator
          name: host-var-log-antrea-flow-aggregator
        - mountPath: /etc/flow-aggregator/certs
          name: clickhouse-ca
      nodeSelector:
        kubernetes.io/arch: amd64
        kubernetes.io/os: linux
      serviceAccountName: flow-aggregator
      volumes:
      - configMap:
          name: flow-aggregator-configmap
        name: flow-aggregator-config
      - hostPath:
          path: /var/log/antrea/flow-aggregator
          type: DirectoryOrCreate
        name: host-var-log-antrea-flow-aggregator
      - name: clickhouse-ca
        secret:
          defaultMode: 256
          optional: true
          secretName: clickhouse-ca