mirror of
https://github.com/vale981/ray
synced 2025-03-10 13:26:39 -04:00
5d6bc5360d
## Why are these changes needed? - Fixes the jobs tab in the new dashboard. Previously it didn't load. - Combines the old job concept, "driver jobs" and the new job submission conception into a single concept called "jobs". Jobs tab shows information about both jobs. - Updates all job APIs: They now returns both submission jobs and driver jobs. They also contains additional data in the response including "id", "job_id", "submission_id", and "driver". They also accept either job_id or submission_id as input. - Job ID is the same as the "ray core job id" concept. It is in the form of "0100000" and is the primary id to represent jobs. - Submission ID is an ID that is generated for each ray job submission. It is in the form of "raysubmit_12345...". It is a secondary id that can be used if a client needs to provide a self-generated id. or if the job id doesn't exist (ex: if the submission job doesn't create a ray driver) This PR has 2 deprecations - The `submit_job` sdk now accepts a new kwarg `submission_id`. `job_id is deprecated. - The `ray job submit` CLI now accepts `--submission-id`. `--job-id` is deprecated. **This PR has 4 backwards incompatible changes:** - list_jobs sdk now returns a list instead of a dictionary - the `ray job list` CLI now prints a list instead of a dictionary - The `/api/jobs` endpoint returns a list instead of a dictionary - The `POST api/jobs` endpoint (submit job) now returns a json with `submission_id` field instead of `job_id`.
81 lines
2.9 KiB
Python
81 lines
2.9 KiB
Python
from enum import Enum
|
|
from typing import Any, Dict, Optional
|
|
|
|
from pydantic import BaseModel, Field
|
|
from ray.dashboard.modules.job.common import JobStatus
|
|
|
|
|
|
class DriverInfo(BaseModel):
|
|
"""A class for recording information about the driver related to the job."""
|
|
|
|
id: str = Field(..., description="The id of the driver")
|
|
node_ip_address: str = Field(
|
|
..., description="The ip address of the node the driver is running on"
|
|
)
|
|
pid: str = Field(
|
|
..., description="The pid of the worker process the driver is using."
|
|
)
|
|
# TODO(aguo): Add node_id as a field.
|
|
|
|
|
|
class JobType(str, Enum):
|
|
"""An enumeration for describing the different job types."""
|
|
|
|
#: A job that was initiated by the job submission apis
|
|
SUBMISSION = "SUBMISSION"
|
|
#: A job that was initiated by a driver script.
|
|
DRIVER = "DRIVER"
|
|
|
|
|
|
class JobDetails(BaseModel):
|
|
"""
|
|
Job data with extra details about its driver and its submission.
|
|
"""
|
|
|
|
type: JobType = Field(..., description="The type of job.")
|
|
entrypoint: Optional[str] = Field(
|
|
None, description="The entrypoint command for this job."
|
|
)
|
|
job_id: Optional[str] = Field(
|
|
None,
|
|
description="The job id. An id that is created for every job that is "
|
|
"launched in ray. This can be used to fetch data about jobs using ray "
|
|
"core apis.",
|
|
)
|
|
submission_id: Optional[str] = Field(
|
|
None,
|
|
description="A submission id is an id created for every submission job. It can "
|
|
"be used to fetch data about jobs using the job submission apis.",
|
|
)
|
|
driver_info: Optional[DriverInfo] = Field(
|
|
None,
|
|
description="The driver related to this job. For submission jobs, "
|
|
"it is the last driver launched by that job submission, "
|
|
"or None if there is no driver.",
|
|
)
|
|
|
|
# The following fields are copied from JobInfo.
|
|
# TODO(aguo): Inherit from JobInfo once it's migrated to pydantic.
|
|
status: JobStatus = Field(..., description="The status of the job.")
|
|
entrypoint: str = Field(..., description="The entrypoint command for this job.")
|
|
message: Optional[str] = Field(
|
|
None, description="A message describing the status in more detail."
|
|
)
|
|
error_type: Optional[str] = Field(
|
|
None, description="Internal error, user script error"
|
|
)
|
|
start_time: Optional[int] = Field(
|
|
None,
|
|
description="The time when the job was started. " "A Unix timestamp in ms.",
|
|
)
|
|
end_time: Optional[int] = Field(
|
|
None,
|
|
description="The time when the job moved into a terminal state. "
|
|
"A Unix timestamp in ms.",
|
|
)
|
|
metadata: Optional[Dict[str, str]] = Field(
|
|
None, description="Arbitrary user-provided metadata for the job."
|
|
)
|
|
runtime_env: Optional[Dict[str, Any]] = Field(
|
|
None, description="The runtime environment for the job."
|
|
)
|