apply for job 202308141030506181140 resource failed

[wuliu1516]

use_registry: false
use_deserialize_safe_module: false
dependent_distribution: true
encrypt_password: false
encrypt_module: fate_arch.common.encrypt_utils#pwdecrypt
private_key:
private_key_file:
party_id:
hook_module:
  client_authentication: fate_flow.hook.flow.client_authentication
  site_authentication: fate_flow.hook.flow.site_authentication
  permission: fate_flow.hook.flow.permission
hook_server_name:
authentication:
  client:
    switch: false
    http_app_key:
    http_secret_key:
  site:
    switch: false
permission:
  switch: false
  component: false
  dataset: false
fateflow:
  # you must set real ip address, 127.0.0.1 and 0.0.0.0 is not supported
  host: 10.2.103.192
  http_port: 9380
  grpc_port: 9360
  # when you have multiple fateflow server on one party,
  # we suggest using nginx for load balancing.
  nginx:
    host:
    http_port:
    grpc_port:
  # use random instance_id instead of {host}:{http_port}
  random_instance_id: false

  # support rollsite/nginx/fateflow as a coordination proxy
  # rollsite support fate on eggroll, use grpc protocol
  # nginx support fate on eggroll and fate on spark, use http or grpc protocol, default is http
  # fateflow support fate on eggroll and fate on spark, use http protocol, but not support exchange network mode

  # format(proxy: rollsite) means rollsite use the rollsite configuration of fate_one_eggroll and nginx use the nginx configuration of fate_one_spark
  # you also can customize the config like this(set fateflow of the opposite party as proxy):
  # proxy:
  #   name: fateflow
  #   host: xx
  #   http_port: xx
  #   grpc_port: xx
  proxy: nginx
  # support default/http/grpc
  protocol: default
database:
  name: fate_flow
  user: fate
  passwd: fate_dev
  host: 10.2.103.192
  port: 3306
  max_connections: 100
  stale_timeout: 30
zookeeper:
  hosts:
    - 127.0.0.1:2181
  use_acl: false
  user: fate
  password: fate
# engine services
default_engines:
  computing: standalone
  federation: pulsar
  storage: hdfs
fate_on_standalone:
  standalone:
    cores_per_node: 3
    nodes: 1
fate_on_spark:
  spark:
    # default use SPARK_HOME environment variable
    home: /data/projects/fate/common/spark
    cores_per_node: 4
    nodes: 3
  linkis_spark:
    cores_per_node: 3
    nodes: 2
    host: 10.2.103.192
    port: 9001
    token_code: MLSS
    python_path: /data/projects/fate/python
  hive:
    host: 127.0.0.1
    port: 10000
    auth_mechanism:
    username:
    password:
  linkis_hive:
    host: 127.0.0.1
    port: 9001
  hdfs:
    name_node: hdfs://fate-cluster
    # default /
    path_prefix:
  pulsar:
    host: 10.2.103.192
    port: 6650
    mng_port: 8080
    cluster: standalone
    # all parties should use a same tenant
    tenant: fl-tenant
    # message ttl in minutes
    topic_ttl: 5
    # default conf/pulsar_route_table.yaml
    route_table:
   # mode: replication / client, default: replication
    mode: replication
    max_message_size: 1048576
  nginx:
    host: 10.2.103.192
    http_port: 9300
    grpc_port: 9310
# external services
fateboard:
  host: 10.2.103.192
  port: 6060

enable_model_store: false
model_store_address:
  # use mysql as the model store engine
#  storage: mysql
#  database: fate_model
#  user: fate
#  password: fate
#  host: 127.0.0.1
#  port: 3306
  # other optional configs send to the engine
#  max_connections: 10
#  stale_timeout: 10

  # use tencent cos as model store engine
  storage: mysql
  name: fate_flow
  user: fate
  passwd: fate_dev
  host: 127.0.0.1
  port: 3306
  max_connections: 10
  stale_timeout: 10
  Region:
  SecretId:
  SecretKey:
  Bucket:

servings:
  hosts:
    - 10.2.103.192:8000
fatemanager:
  host: 10.2.103.192
  port: 8001
  federatedId: 0

hadoop资源

进行单边测试 10.2.103.191机器可以进行测试，10.2.103.192测试出现下面的问题，计算引擎改成spark，出现下面的问题。单独测试spark计算pi值，两台机器都可以进行计算。集群是按照fate on spark 部署