deploy/test-oas/conf/config.yaml

env:
  java:
    opts:
      all: "-Dsource.pb.enable=true -Dsource.pb.kafka.brokers=kafka.observe.svc.cluster.local:9092 -Dsource.pb.kafka.topics=otelproto -DMYSQL_DSN=jdbc:mysql://mysql.observe.svc.cluster.local:3306/observe -DtraceURL.tableName=otel.otel_traces_url_local"
      #all: "-DKAFKA_BROKERS=kafka.observe.svc.cluster.local:9092 -DKAFKA_TOPIC=otelproto -DMYSQL_DSN=jdbc:mysql://mysql.observe.svc.cluster.local:3306/observe -Di6000.kafka.bootstrap-server=kafka.observe.svc.cluster.local:9092 -Di6000.kafka.topic=i6000_trace -Di6000.include_app_names=SPRING,OBSERVE -DtraceURL.tableName=otel.otel_traces_url_local"
#==============================================================================
# Common
#==============================================================================

jobmanager:
  # The host interface the JobManager will bind to. By default, this is localhost, and will prevent
  # the JobManager from communicating outside the machine/container it is running on.
  # On YARN this setting will be ignored if it is set to 'localhost', defaulting to 0.0.0.0.
  # On Kubernetes this setting will be ignored, defaulting to 0.0.0.0.
  #
  # To enable this, set the bind-host address to one that has access to an outside facing network
  # interface, such as 0.0.0.0.
  bind-host: localhost
  rpc:
    # The external address of the host on which the JobManager runs and can be
    # reached by the TaskManagers and any clients which want to connect. This setting
    # is only used in Standalone mode and may be overwritten on the JobManager side
    # by specifying the --host <hostname> parameter of the bin/jobmanager.sh executable.
    # In high availability mode, if you use the bin/start-cluster.sh script and setup
    # the conf/masters file, this will be taken care of automatically. Yarn
    # automatically configure the host name based on the hostname of the node where the
    # JobManager runs.
    address: localhost
    # The RPC port where the JobManager is reachable.
    port: 6123
  memory:
    process:
      # The total process memory size for the JobManager.
      # Note this accounts for all memory usage within the JobManager process, including JVM metaspace and other overhead.
      size: 1600m
  execution:
    # The failover strategy, i.e., how the job computation recovers from task failures.
    # Only restart tasks that may have been affected by the task failure, which typically includes
    # downstream tasks and potentially upstream tasks if their produced data is no longer available for consumption.
    failover-strategy: region

taskmanager:
  # The host interface the TaskManager will bind to. By default, this is localhost, and will prevent
  # the TaskManager from communicating outside the machine/container it is running on.
  # On YARN this setting will be ignored if it is set to 'localhost', defaulting to 0.0.0.0.
  # On Kubernetes this setting will be ignored, defaulting to 0.0.0.0.
  #
  # To enable this, set the bind-host address to one that has access to an outside facing network
  # interface, such as 0.0.0.0.
  bind-host: localhost
  # The address of the host on which the TaskManager runs and can be reached by the JobManager and
  # other TaskManagers. If not specified, the TaskManager will try different strategies to identify
  # the address.
  #
  # Note this address needs to be reachable by the JobManager and forward traffic to one of
  # the interfaces the TaskManager is bound to (see 'taskmanager.bind-host').
  #
  # Note also that unless all TaskManagers are running on the same machine, this address needs to be
  # configured separately for each TaskManager.
  host: localhost
  # The number of task slots that each TaskManager offers. Each slot runs one parallel pipeline.
  numberOfTaskSlots: 2
  memory:
    task:
      off-heap:
        size: 256m
    network: 
      fraction: 0.2
    process:
      # The total process memory size for the TaskManager.
      #
      # Note this accounts for all memory usage within the TaskManager process, including JVM metaspace and other overhead.
      # To exclude JVM metaspace and overhead, please, use total Flink memory size instead of 'taskmanager.memory.process.size'.
      # It is not recommended to set both 'taskmanager.memory.process.size' and Flink memory.
      size: 4gb

parallelism:
  # The parallelism used for programs that did not specify and other parallelism.
  default: 3

# # The default file system scheme and authority.
# # By default file paths without scheme are interpreted relative to the local
# # root file system 'file:///'. Use this to override the default and interpret
# # relative paths relative to a different file system,
# # for example 'hdfs://mynamenode:12345'
# fs:
#   default-scheme: hdfs://mynamenode:12345

#==============================================================================
# High Availability
#==============================================================================

# high-availability:
#   # The high-availability mode. Possible options are 'NONE' or 'zookeeper'.
#   type: zookeeper
#   # The path where metadata for master recovery is persisted. While ZooKeeper stores
#   # the small ground truth for checkpoint and leader election, this location stores
#   # the larger objects, like persisted dataflow graphs.
#   #
#   # Must be a durable file system that is accessible from all nodes
#   # (like HDFS, S3, Ceph, nfs, ...)
#   storageDir: hdfs:///flink/ha/
#   zookeeper:
#     # The list of ZooKeeper quorum peers that coordinate the high-availability
#     # setup. This must be a list of the form:
#     # "host1:clientPort,host2:clientPort,..." (default clientPort: 2181)
#     quorum: localhost:2181
#     client:
#       # ACL options are based on https://zookeeper.apache.org/doc/r3.1.2/zookeeperProgrammers.html#sc_BuiltinACLSchemes
#       # It can be either "creator" (ZOO_CREATE_ALL_ACL) or "open" (ZOO_OPEN_ACL_UNSAFE)
#       # The default value is "open" and it can be changed to "creator" if ZK security is enabled
#       acl: open

#==============================================================================
# Fault tolerance and checkpointing
#==============================================================================

# The backend that will be used to store operator state checkpoints if
# checkpointing is enabled. Checkpointing is enabled when execution.checkpointing.interval > 0.

# # Execution checkpointing related parameters. Please refer to CheckpointConfig and ExecutionCheckpointingOptions for more details.
# execution:
#   checkpointing:
#     interval: 3min
#     externalized-checkpoint-retention: [DELETE_ON_CANCELLATION, RETAIN_ON_CANCELLATION]
#     max-concurrent-checkpoints: 1
#     min-pause: 0
#     mode: [EXACTLY_ONCE, AT_LEAST_ONCE]
#     timeout: 10min
#     tolerable-failed-checkpoints: 0
#     unaligned: false

# state:
#   backend:
#     # Supported backends are 'hashmap', 'rocksdb', or the
#     # <class-name-of-factory>.
#     type: hashmap
#     # Flag to enable/disable incremental checkpoints for backends that
#     # support incremental checkpoints (like the RocksDB state backend).
#     incremental: false
#   checkpoints:
#       # Directory for checkpoints filesystem, when using any of the default bundled
#       # state backends.
#       dir: hdfs://namenode-host:port/flink-checkpoints
#   savepoints:
#       # Default target directory for savepoints, optional.
#       dir: hdfs://namenode-host:port/flink-savepoints

#==============================================================================
# Rest & web frontend
#==============================================================================

rest:
  # The address to which the REST client will connect to
  address: localhost
  # The address that the REST & web server binds to
  # By default, this is localhost, which prevents the REST & web server from
  # being able to communicate outside of the machine/container it is running on.
  #
  # To enable this, set the bind address to one that has access to outside-facing
  # network interface, such as 0.0.0.0.
  bind-address: localhost
  # # The port to which the REST client connects to. If rest.bind-port has
  # # not been specified, then the server will bind to this port as well.
  # port: 8081
  # # Port range for the REST and web server to bind to.
  # bind-port: 8080-8090

# web:
#   submit:
#     # Flag to specify whether job submission is enabled from the web-based
#     # runtime monitor. Uncomment to disable.
#     enable: false
#   cancel:
#     # Flag to specify whether job cancellation is enabled from the web-based
#     # runtime monitor. Uncomment to disable.
#     enable: false

#==============================================================================
# Advanced
#==============================================================================

# io:
#   tmp:
#     # Override the directories for temporary files. If not specified, the
#     # system-specific Java temporary directory (java.io.tmpdir property) is taken.
#     #
#     # For framework setups on Yarn, Flink will automatically pick up the
#     # containers' temp directories without any need for configuration.
#     #
#     # Add a delimited list for multiple directories, using the system directory
#     # delimiter (colon ':' on unix) or a comma, e.g.:
#     # /data1/tmp:/data2/tmp:/data3/tmp
#     #
#     # Note: Each directory entry is read from and written to by a different I/O
#     # thread. You can include the same directory multiple times in order to create
#     # multiple I/O threads against that directory. This is for example relevant for
#     # high-throughput RAIDs.
#     dirs: /tmp

# classloader:
#   resolve:
#     # The classloading resolve order. Possible values are 'child-first' (Flink's default)
#     # and 'parent-first' (Java's default).
#     #
#     # Child first classloading allows users to use different dependency/library
#     # versions in their application than those in the classpath. Switching back
#     # to 'parent-first' may help with debugging dependency issues.
#     order: child-first

# The amount of memory going to the network stack. These numbers usually need
# no tuning. Adjusting them may be necessary in case of an "Insufficient number
# of network buffers" error. The default min is 64MB, the default max is 1GB.
#
# taskmanager:
#   memory:
#     network:
#       fraction: 0.1
#       min: 64mb
#       max: 1gb

#==============================================================================
# Flink Cluster Security Configuration
#==============================================================================

# Kerberos authentication for various components - Hadoop, ZooKeeper, and connectors -
# may be enabled in four steps:
# 1. configure the local krb5.conf file
# 2. provide Kerberos credentials (either a keytab or a ticket cache w/ kinit)
# 3. make the credentials available to various JAAS login contexts
# 4. configure the connector to use JAAS/SASL

# # The below configure how Kerberos credentials are provided. A keytab will be used instead of
# # a ticket cache if the keytab path and principal are set.
# security:
#   kerberos:
#     login:
#       use-ticket-cache: true
#       keytab: /path/to/kerberos/keytab
#       principal: flink-user
#       # The configuration below defines which JAAS login contexts
#       contexts: Client,KafkaClient

#==============================================================================
# ZK Security Configuration
#==============================================================================

# zookeeper:
#   sasl:
#     # Below configurations are applicable if ZK ensemble is configured for security
#     #
#     # Override below configuration to provide custom ZK service name if configured
#     # zookeeper.sasl.service-name: zookeeper
#     #
#     # The configuration below must match one of the values set in "security.kerberos.login.contexts"
#     login-context-name: Client

#==============================================================================
# HistoryServer
#==============================================================================

# The HistoryServer is started and stopped via bin/historyserver.sh (start|stop)
#
# jobmanager:
#   archive:
#     fs:
#       # Directory to upload completed jobs to. Add this directory to the list of
#       # monitored directories of the HistoryServer as well (see below).
#       dir: hdfs:///completed-jobs/

# historyserver:
#   web:
#     # The address under which the web-based HistoryServer listens.
#     address: 0.0.0.0
#     # The port under which the web-based HistoryServer listens.
#     port: 8082
#   archive:
#     fs:
#       # Comma separated list of directories to monitor for completed jobs.
#       dir: hdfs:///completed-jobs/
#       # Interval in milliseconds for refreshing the monitored directories.
#       fs.refresh-interval: 10000


metrics:
  reporter: 
    prom:
      port: 9249
      factory:
        class: org.apache.flink.metrics.prometheus.PrometheusReporterFactory
      scope:
        variables:
          additional: 
            biz: ob-agent-stream


kubernetes:
  #rest-service:
  #  exposed:
  #    type: NodePort
  pod-template-file:
    taskmanager: ./conf/taskmanager-pod-template.yaml
  jobmanager:
    cpu:
      amount: 2.0
  taskmanager:
    cpu:
      amount: 4.0
    annotations: 
      prometheus.io/scrape: true
      prometheus.io/port: 9249
      prometheus.io/path: /

pipeline:
  serialization-config:
    - io.opentelemetry.proto.collector.trace.v1.ExportTraceServiceRequest: 
        type: kryo 
        kryo-type: registered
        class: com.twitter.chill.protobuf.ProtobufSerializer