Claude
b3564737f7
yarn_client.py no longer invokes the 'yarn' binary via subprocess; it uses
httpx against /ws/v1/cluster/apps/* endpoints. This means the runtime image
no longer needs the Hadoop client installation — the only YARN-side
dependency left in the container is the config dir consumed by
spark-submit itself.
New model field:
- Job.yarn_rm_url: str | None
- PendingSubmission.yarn_rm_url: str | None (snapshotted at prepare)
prepare_submit_job snapshots Connection.yarn_rm_url into the pending
record (consistent with the existing master/deploy_mode/spark_conf
snapshot pattern); confirm_submit_job copies it onto the Job so
status/logs/kill can use it without re-looking-up the connection.
Resolution order for the RM URL at runtime:
1. Job.yarn_rm_url (preferred — survives connection edits/deletes)
2. Connection.yarn_rm_url fallback (if a future tool is added that
doesn't go through a Job)
3. YARN_RESOURCE_MANAGER_URL env var
Errors:
- YarnConfigError (HTTP 4xx semantics) when URL is missing/malformed
- YarnError for HTTP 4xx/5xx from the RM, network failures, missing
state field, or unparseable log responses
10 new tests in test_yarn_client.py cover the REST surface:
success, 404, 5xx, missing state field, env-var fallback, malformed
URL, log 404 with log-aggregation hint, kill PUT body shape, and
httpx connection-error wrapping.
122 lines
3.5 KiB
Python
122 lines
3.5 KiB
Python
# coding=utf-8
|
|
from datetime import datetime
|
|
from spark_executor.models import Connection, Job, JobStatus, PendingSubmission, SubmitResult
|
|
|
|
|
|
def test_job_roundtrip():
|
|
job = Job(
|
|
job_id="abc123",
|
|
application_id="application_17400000001",
|
|
script_path="/tmp/jobs/job_001.py",
|
|
queue="default",
|
|
submit_time=datetime(2026, 6, 24, 10, 0, 0),
|
|
connection="prod-yarn",
|
|
yarn_rm_url="http://rm:8088",
|
|
)
|
|
dumped = job.model_dump()
|
|
assert dumped["job_id"] == "abc123"
|
|
assert dumped["application_id"] == "application_17400000001"
|
|
assert dumped["connection"] == "prod-yarn"
|
|
assert dumped["yarn_rm_url"] == "http://rm:8088"
|
|
|
|
|
|
def test_job_yarn_rm_url_optional():
|
|
job = Job(
|
|
job_id="j1",
|
|
application_id="application_1",
|
|
script_path="/tmp/x.py",
|
|
queue="default",
|
|
submit_time=datetime(2026, 6, 24),
|
|
connection="dev",
|
|
)
|
|
assert job.yarn_rm_url is None
|
|
|
|
|
|
def test_job_status_default_raw():
|
|
s = JobStatus(application_id="application_1", state="RUNNING")
|
|
assert s.raw == ""
|
|
|
|
|
|
def test_submit_result_tracking_url_optional():
|
|
r = SubmitResult(job_id="j1", application_id="application_1", tracking_url=None)
|
|
assert r.tracking_url is None
|
|
|
|
|
|
def test_connection_defaults():
|
|
c = Connection(name="prod", master="yarn")
|
|
assert c.deploy_mode == "cluster"
|
|
assert c.yarn_rm_url is None
|
|
assert c.spark_conf == {}
|
|
|
|
|
|
def test_connection_with_spark_conf():
|
|
c = Connection(
|
|
name="dev",
|
|
master="spark://master:7077",
|
|
deploy_mode="client",
|
|
spark_conf={"spark.sql.shuffle.partitions": "200"},
|
|
)
|
|
assert c.spark_conf["spark.sql.shuffle.partitions"] == "200"
|
|
|
|
|
|
def test_pending_submission_defaults_to_pending_status():
|
|
p = PendingSubmission(
|
|
pending_id="p_1",
|
|
connection="prod",
|
|
master="yarn",
|
|
deploy_mode="cluster",
|
|
script_path="/tmp/j.py",
|
|
queue="default",
|
|
executor_memory="4G",
|
|
executor_cores=2,
|
|
num_executors=2,
|
|
spark_conf={},
|
|
created_at=datetime(2026, 6, 24),
|
|
)
|
|
assert p.status == "PENDING"
|
|
assert p.error is None
|
|
assert p.job_id is None
|
|
assert p.application_id is None
|
|
assert p.yarn_rm_url is None # default for connections without one set
|
|
|
|
|
|
def test_pending_submission_carries_yarn_rm_url_snapshot():
|
|
"""snapshotting yarn_rm_url lets prepare/confirm survive connection edits."""
|
|
p = PendingSubmission(
|
|
pending_id="p_x",
|
|
connection="prod",
|
|
master="yarn",
|
|
deploy_mode="cluster",
|
|
yarn_rm_url="http://rm-prod:8088",
|
|
script_path="/tmp/j.py",
|
|
queue="default",
|
|
executor_memory="4G",
|
|
executor_cores=2,
|
|
num_executors=2,
|
|
spark_conf={},
|
|
created_at=datetime(2026, 6, 24),
|
|
)
|
|
assert p.yarn_rm_url == "http://rm-prod:8088"
|
|
|
|
|
|
def test_pending_submission_can_record_outcome():
|
|
p = PendingSubmission(
|
|
pending_id="p_2",
|
|
connection="prod",
|
|
master="yarn",
|
|
deploy_mode="cluster",
|
|
script_path="/tmp/j.py",
|
|
queue="default",
|
|
executor_memory="4G",
|
|
executor_cores=2,
|
|
num_executors=2,
|
|
spark_conf={},
|
|
created_at=datetime(2026, 6, 24),
|
|
status="SUBMITTED",
|
|
job_id="j_abc",
|
|
application_id="application_17400000001",
|
|
)
|
|
assert p.status == "SUBMITTED"
|
|
assert p.job_id == "j_abc"
|
|
assert p.application_id == "application_17400000001"
|