[1,2,3]

Map tasks only accept python function tasks with 0 or 1 inputs

admin:

# For GRPC endpoints you might want to use dns:///flyte.myexample.com

endpoint: dns:///a4ad903c61##################.<http://us-west-1.elb.amazonaws.com:80|us-west-1.elb.amazonaws.com:80>

authType: Pkce

insecure: true

logger:

show-source: true

level: 0

storage:

connection:

access-key: minio

auth-type: accesskey

disable-ssl: true

endpoint: <http://a093eb##############.us-west-1.elb.amazonaws.com:9001/>

region: us-east-1

secret-key: miniostorage

type: minio

container: "my-s3-bucket"

enable-multicontainer: true

from flytekit import kwtypes, workflow
from flytekitplugins.snowflake import SnowflakeConfig, SnowflakeTask


snowflake_task_no_io = SnowflakeTask(
    name="sql.snowflake.no_io",
    inputs={},
    query_template="select * from TEST_DEV.IDENTITY.TEST_123 ;",
    output_schema_type=None,
    task_config=SnowflakeConfig(
        account="xxxxx.us-east-1",
        database="TEST_DEV",
        schema="IDENTITY",
        warehouse="DEMO_WH",
    ),
)


@workflow
def no_io_wf():
    return snowflake_task_no_io()

@task(container_image="{{.image.trainer.fqn }}:{{.image.trainer.version}}")

[images]
trainer = <http://ghcr.io/flyteorg/flytecookbook:core-latest|ghcr.io/flyteorg/flytecookbook:core-latest>
predictor = <http://ghcr.io/flyteorg/flytecookbook:pima_diabetes-d4838f0f5e39a21f845a93b9e3375a675bd75eaa|ghcr.io/flyteorg/flytecookbook:pima_diabetes-d4838f0f5e39a21f845a93b9e3375a675bd75eaa>

raise AssertionError(f"Image Config with name {name} not hound in the configuration")
AssertionError:Image Config with name trainer not found in the configuration

flyte-user-role

arg: ""

object [my_domainctw5x2vdnkvd-n0-0] terminated in the background, manually

error: "size of name exceeded length 20 : my-project.workflows.04b2ed0b-434b-4d7b-9220-90606fdc2afc.test_wf_1"

{
  project: "shelly-robotics-bidepal-robot",
  domain: "development",
  name: "my-project.workflows.04b2ed0b-434b-4d7b-9220-90606fdc2afc.test_wf_1",
  spec: {
    launch_plan: {
      project: "shelly-robotics-bidepal-robot",
      domain: "development",
      name: "my-project.workflows.04b2ed0b-434b-4d7b-9220-90606fdc2afc.test_wf_1",
      version: "0.0.1",
    },
    inputs: {
      x: 1,
    },
  },
};

floodcast_model = ContainerTask(
    name="floodcast-docker",
    input_data_dir="/input",
    output_data_dir="/output",
    inputs=kwtypes(rainfall=List[FlyteFile]),
    outputs=kwtypes(floodmaps=List[FlyteFile]),
    image="<myimage>",
    command=["/env/bin/python", "run.py"])

flytectl update launchplan ... -- version $GITSHA --activate >> --archive-old <<

EventSinkError

CreateWorkflowEvent

EventRecordingFailed: failed to record node event, caused by: EventSinkError: Error sending event, caused by [rpc error: code = Unavailable desc = upstream connect error or disconnect/reset before headers. reset reason: protocol error]

launch_plan.LaunchPlan.get_or_create(
    workflow=wf,
    name="my_wf_prod", # prod specific
    schedule=CronSchedule(schedule="1 0 * * *"),
    default_inputs={
        "execution_date": datetime.now(), # aside: this does not work. How do I provide an execution date?
    },
    fixed_inputs={
        "out_path": consts.OUT_S3_PATH_PROD # prod specific vars
    },
)

flytectl demo start

fei.sun@MacBook-Pro cookbook % pyflyte run --remote core/flyte_basics/hello_world.py my_wf


E0927 14:46:18.763713000 4366484864 <http://ssl_transport_security.cc:1495]|ssl_transport_security.cc:1495]>    Handshake failed with fatal error SSL_ERROR_SSL: error:100000f7:SSL routines:OPENSSL_internal:WRONG_VERSION_NUMBER.
E0927 14:46:18.765990000 4366484864 <http://ssl_transport_security.cc:1495]|ssl_transport_security.cc:1495]>    Handshake failed with fatal error SSL_ERROR_SSL: error:100000f7:SSL routines:OPENSSL_internal:WRONG_VERSION_NUMBER.
{"asctime": "2022-09-27 14:46:18,781", "name": "flytekit.cli", "levelname": "ERROR", "message": "Non-auth RPC error <_InactiveRpcError of RPC that terminated with:\n\tstatus = StatusCode.UNAVAILABLE\n\tdetails = \"failed to connect to all addresses\"\n\tdebug_error_string = \"{\"created\":\"@1664261178.780964000\",\"description\":\"Failed to pick subchannel\",\"file\":\"src/core/ext/filters/client_channel/client_channel.cc\",\"file_line\":3261,\"referenced_errors\":[{\"created\":\"@1664261178.780963000\",\"description\":\"failed to connect to all addresses\",\"file\":\"src/core/lib/transport/error_utils.cc\",\"file_line\":167,\"grpc_status\":14}]}\"\n>, sleeping 200ms and retrying"}
{"asctime": "2022-09-27 14:46:18,986", "name": "flytekit.cli", "levelname": "ERROR", "message": "Non-auth RPC error <_InactiveRpcError of RPC that terminated with:\n\tstatus = StatusCode.UNAVAILABLE\n\tdetails = \"failed to connect to all addresses\"\n\tdebug_error_string = \"{\"created\":\"@1664261178.985906000\",\"description\":\"Failed to pick subchannel\",\"file\":\"src/core/ext/filters/client_channel/client_channel.cc\",\"file_line\":3261,\"referenced_errors\":[{\"created\":\"@1664261178.985905000\",\"description\":\"failed to connect to all addresses\",\"file\":\"src/core/lib/transport/error_utils.cc\",\"file_line\":167,\"grpc_status\":14}]}\"\n>, sleeping 400ms and retrying"}
Traceback (most recent call last):
  File "/Users/fei.sun/Library/Python/3.8/bin//pyflyte", line 8, in <module>
    sys.exit(main())
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/click/core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/click/core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/click/core.py", line 1657, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/click/core.py", line 1657, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/click/core.py", line 1657, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/click/core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/click/core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/flytekit/clis/sdk_in_container/run.py", line 539, in _run
    remote_entity = remote.register_script(
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/flytekit/remote/remote.py", line 596, in register_script
    upload_location, md5_bytes = fast_register_single_script(
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/flytekit/tools/script_mode.py", line 113, in fast_register_single_script
    upload_location = create_upload_location_fn(content_md5=md5)
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/flytekit/clients/friendly.py", line 998, in get_upload_signed_url
    return super(SynchronousFlyteClient, self).create_upload_location(
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/flytekit/clients/raw.py", line 41, in handler
    return fn(*args, **kwargs)
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/flytekit/clients/raw.py", line 854, in create_upload_location
    return self._dataproxy_stub.CreateUploadLocation(create_upload_location_request, metadata=self._metadata)
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/grpc/_channel.py", line 946, in __call__
    return _end_unary_response_blocking(state, call, False, None)
  File "/Users/fei.sun/Library/Python/3.8/lib/python/site-packages/grpc/_channel.py", line 849, in _end_unary_response_blocking
    raise _InactiveRpcError(state)
grpc._channel._InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
	status = StatusCode.UNAVAILABLE
	details = "failed to connect to all addresses"
	debug_error_string = "{"created":"@1664261179.392327000","description":"Failed to pick subchannel","file":"src/core/ext/filters/client_channel/client_channel.cc","file_line":3261,"referenced_errors":[{"created":"@1664261179.392310000","description":"failed to connect to all addresses","file":"src/core/lib/transport/error_utils.cc","file_line":167,"grpc_status":14}]}"

Workflow[flyte-anti-fraud-ml:development:app.workflow.main_flow] failed. RuntimeExecutionError: max number of system retry attempts [31/30] exhausted. Last known status message: failed at Node[n0]. RuntimeExecutionError: failed during plugin execution, caused by: error file @[<s3://my-s3-bucket/metadata/propeller/flyte-anti-fraud-ml-development-f31c365f02c114639b00/n0/data/0/error.pb>] is too large [28775519] bytes, max allowed [10485760] bytes

max-output-size-bytes

flyte-propeller-config

kubectl edit configmap -n flyte flyte-propeller-config

flyte-propeller-config

core.yaml: |
    manager:
      pod-application: flytepropeller
      pod-template-container-name: flytepropeller
      pod-template-name: flytepropeller-template
    propeller:
      max-output-size-bytes: 52428800
      downstream-eval-duration: 30s
      enable-admin-launcher: true
      leader-election:
        enabled: true
        lease-duration: 15s
        lock-config-map:
          name: propeller-leader
          namespace: flyte
        renew-deadline: 10s
        retry-period: 2s
      limit-namespace: all
      max-workflow-retries: 3
      metadata-prefix: metadata/propeller
      metrics-prefix: flyte
      prof-port: 10254

kubectl -n flyte edit cm flyte-admin-base-config

storage.yaml: |
    storage:
      type: minio
      container: "my-s3-bucket"
      stow:
        kind: s3
        config:
          access_key_id: minio
          auth_type: accesskey
          secret_key: miniostorage
          disable_ssl: true
          endpoint: <http://minio.flyte.svc.cluster.local:9000>
          region: us-east-1
      signedUrl:
        stowConfigOverride:
          endpoint: <http://localhost:30084>
      enable-multicontainer: false
      limits:
        maxDownloadMBs: 50
  task_resource_defaults.yaml: |
    task_resources:
      defaults:
        cpu: 1
        memory: 3000Mi
        storage: 100Mi
      limits:
        cpu: 4
        gpu: 1
        memory: 3Gi
        storage: 500Mi

maxDownloadMBs

max_size_mbs

flyte-propeller-config

cache.yaml: |
    cache:
      max_size_mbs: 100
      target_gc_percent: 70

max-output-size-bytes

max-workflow-retries

RuntimeExecutionError: max number of system retry attempts [31/30] exhausted...

error file @[<s3://my-s3-bucket/metadata/propeller/flyte-anti-fraud-ml-development-f31c365f02c114639b00/n0/data/0/error.pb>] is too large [28775519] bytes, max allowed [10485760] bytes...

- kubectl -n flyte edit cm flyte-admin-base-config
- kubectl edit configmap -n flyte flyte-propeller-config
- flytectl get task-resource-attribute -p flyteexamples -d development
- flytectl update project -p flyte-anti-fraud-ml -d development --storage.cache.max_size_mbs 100
- flytectl get launchplan --project flyte-anti-fraud-ml --domain development app.workflow.main_flow --latest --execFile exec_spec.yaml
- flytectl create execution --project flyte-anti-fraud-ml --domain development --execFile exec_spec.yaml