Claude
ad557b5984
Add per-Connection ssl_verify / ssl_ca_bundle plus global defaults so CDH 5 / on-prem clusters with self-signed certs or custom CA bundles can be queried without patching code. - Connection gets ssl_verify (bool|None) and ssl_ca_bundle (str|None) - Settings gets ssl_verify_default and ssl_ca_bundle_default - New YarnClientConfig dataclass carries the resolved verify= value - _request passes verify= through to httpx.request - All public yarn_client functions now take YarnClientConfig instead of a bare yarn_rm_url string; tool call sites resolve the Connection - SaveConnectionRequest exposes the two new fields Tests cover per-connection CA bundle, per-connection verify=False, global default fallback, and connection-not-found error.
326 lines
12 KiB
Python
326 lines
12 KiB
Python
# coding=utf-8
|
|
from unittest.mock import patch
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from common import config
|
|
from spark_executor.models import Connection
|
|
from spark_executor.core.yarn_client import (
|
|
YarnConfigError,
|
|
YarnError,
|
|
YarnClientConfig,
|
|
get_application_logs,
|
|
get_application_status,
|
|
kill_application,
|
|
)
|
|
|
|
|
|
RM = "http://rm:8088"
|
|
HTTPS_RM = "https://rm:8088"
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _restore_settings():
|
|
"""Each test gets a clean copy of `settings` so env-var-style overrides
|
|
in one test don't leak into the next."""
|
|
snapshot = config.Settings(
|
|
data_dir=config.settings.data_dir,
|
|
jobs_dir=config.settings.jobs_dir,
|
|
yarn_resource_manager_url=config.settings.yarn_resource_manager_url,
|
|
log_level=config.settings.log_level,
|
|
ssl_verify_default=config.settings.ssl_verify_default,
|
|
ssl_ca_bundle_default=config.settings.ssl_ca_bundle_default,
|
|
)
|
|
yield
|
|
config.settings.data_dir = snapshot.data_dir
|
|
config.settings.jobs_dir = snapshot.jobs_dir
|
|
config.settings.yarn_resource_manager_url = snapshot.yarn_resource_manager_url
|
|
config.settings.log_level = snapshot.log_level
|
|
config.settings.ssl_verify_default = snapshot.ssl_verify_default
|
|
config.settings.ssl_ca_bundle_default = snapshot.ssl_ca_bundle_default
|
|
|
|
|
|
def _resp(status: int, *, json_data=None, text: str | None = None) -> httpx.Response:
|
|
if json_data is not None:
|
|
return httpx.Response(status, json=json_data)
|
|
return httpx.Response(status, text=text or "")
|
|
|
|
|
|
# --- get_application_status ---
|
|
|
|
def test_status_parses_app_state():
|
|
fake = _resp(200, json_data={"app": {"id": "application_1", "state": "RUNNING"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
state, raw = get_application_status("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
assert state == "RUNNING"
|
|
assert "RUNNING" in raw
|
|
args = m.call_args.args
|
|
assert args == ("GET", f"{RM}/ws/v1/cluster/apps/application_1")
|
|
assert m.call_args.kwargs["verify"] is True
|
|
|
|
|
|
def test_status_raises_on_404():
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=_resp(404)):
|
|
with pytest.raises(YarnError, match="not found"):
|
|
get_application_status("application_x", YarnClientConfig(yarn_rm_url=RM))
|
|
|
|
|
|
def test_status_raises_on_5xx():
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request",
|
|
return_value=_resp(503, text="upstream down"),
|
|
):
|
|
with pytest.raises(YarnError, match="503"):
|
|
get_application_status("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
|
|
|
|
def test_status_raises_when_state_field_missing():
|
|
fake = _resp(200, json_data={"app": {"id": "application_1"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake):
|
|
with pytest.raises(YarnError, match="Could not parse YARN state"):
|
|
get_application_status("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
|
|
|
|
def test_status_requires_rm_url():
|
|
config.settings.yarn_resource_manager_url = None
|
|
with pytest.raises(YarnConfigError):
|
|
get_application_status("application_1", YarnClientConfig(yarn_rm_url=None))
|
|
|
|
|
|
def test_status_falls_back_to_settings_yarn_rm_url():
|
|
config.settings.yarn_resource_manager_url = "http://env-rm:8088"
|
|
fake = _resp(200, json_data={"app": {"state": "FINISHED"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
state, _ = get_application_status("application_1", YarnClientConfig(yarn_rm_url=None))
|
|
assert state == "FINISHED"
|
|
assert "env-rm:8088" in m.call_args.args[1]
|
|
|
|
|
|
def test_status_rejects_non_http_url():
|
|
with pytest.raises(YarnConfigError, match="must start with"):
|
|
get_application_status("application_1", YarnClientConfig(yarn_rm_url="rm:8088"))
|
|
|
|
|
|
# --- get_application_logs ---
|
|
|
|
def test_logs_returns_text_on_h3_aggregated_endpoint():
|
|
fake = _resp(200, text="log line 1\nlog line 2\n")
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
out = get_application_logs("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
assert out == "log line 1\nlog line 2\n"
|
|
assert m.call_args.args == (
|
|
"GET",
|
|
f"{RM}/ws/v1/cluster/apps/application_1/aggregated-logs",
|
|
)
|
|
assert m.call_args.kwargs["verify"] is True
|
|
|
|
|
|
def test_logs_falls_back_to_nodemanager_on_404():
|
|
responses = [
|
|
_resp(404), # aggregated-logs H3 endpoint missing
|
|
_resp(200, json_data={"appAttempts": {"appAttempt": [{"id": "attempt_1"}]}}),
|
|
_resp(
|
|
200,
|
|
json_data={
|
|
"containers": {
|
|
"container": [
|
|
{
|
|
"id": "container_1",
|
|
"user": "hdfs",
|
|
"nodeHttpAddress": "nm1:8042",
|
|
}
|
|
]
|
|
}
|
|
},
|
|
),
|
|
_resp(200, text="container log content"),
|
|
]
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request", side_effect=responses
|
|
) as m:
|
|
out = get_application_logs("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
assert "container_1" in out
|
|
assert "container log content" in out
|
|
calls = m.call_args_list
|
|
assert calls[0].args == (
|
|
"GET",
|
|
f"{RM}/ws/v1/cluster/apps/application_1/aggregated-logs",
|
|
)
|
|
assert calls[1].args == ("GET", f"{RM}/ws/v1/cluster/apps/application_1/appattempts")
|
|
assert calls[2].args == (
|
|
"GET",
|
|
f"{RM}/ws/v1/cluster/apps/application_1/appattempts/attempt_1/containers",
|
|
)
|
|
assert calls[3].args == (
|
|
"GET",
|
|
"http://nm1:8042/node/containerlogs/container_1/hdfs/",
|
|
)
|
|
|
|
|
|
def test_logs_raises_on_404_when_nm_also_empty():
|
|
responses = [
|
|
_resp(404), # aggregated-logs H3 endpoint missing
|
|
_resp(200, json_data={"appAttempts": {"appAttempt": []}}),
|
|
]
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request", side_effect=responses
|
|
):
|
|
with pytest.raises(YarnError, match="log-aggregation-enable"):
|
|
get_application_logs("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
|
|
|
|
def test_logs_handles_multiple_containers():
|
|
responses = [
|
|
_resp(404), # aggregated-logs H3 endpoint missing
|
|
_resp(200, json_data={"appAttempts": {"appAttempt": [{"id": "attempt_1"}]}}),
|
|
_resp(
|
|
200,
|
|
json_data={
|
|
"containers": {
|
|
"container": [
|
|
{
|
|
"id": "container_1",
|
|
"user": "hdfs",
|
|
"nodeHttpAddress": "nm1:8042",
|
|
},
|
|
{
|
|
"id": "container_2",
|
|
"user": "hdfs",
|
|
"nodeHttpAddress": "nm2:8042",
|
|
},
|
|
]
|
|
}
|
|
},
|
|
),
|
|
_resp(200, text="log one"),
|
|
_resp(200, text="log two"),
|
|
]
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request", side_effect=responses
|
|
) as m:
|
|
out = get_application_logs("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
assert "log one" in out
|
|
assert "log two" in out
|
|
assert out.index("log one") < out.index("log two")
|
|
calls = m.call_args_list
|
|
assert calls[3].args == (
|
|
"GET",
|
|
"http://nm1:8042/node/containerlogs/container_1/hdfs/",
|
|
)
|
|
assert calls[4].args == (
|
|
"GET",
|
|
"http://nm2:8042/node/containerlogs/container_2/hdfs/",
|
|
)
|
|
|
|
|
|
def test_logs_5xx_on_aggregated_endpoint_raises_immediately():
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request",
|
|
return_value=_resp(500, text="boom"),
|
|
) as m:
|
|
with pytest.raises(YarnError, match="500"):
|
|
get_application_logs("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
assert m.call_count == 1
|
|
|
|
|
|
# --- kill_application ---
|
|
|
|
def test_kill_sends_put_with_killed_state():
|
|
fake = _resp(200, json_data={"app": {"state": "KILLED"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
kill_application("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
args = m.call_args.args
|
|
assert args == ("PUT", f"{RM}/ws/v1/cluster/apps/application_1/state")
|
|
assert m.call_args.kwargs["json"] == {"state": "KILLED"}
|
|
assert m.call_args.kwargs["verify"] is True
|
|
|
|
|
|
def test_kill_raises_on_5xx():
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request",
|
|
return_value=_resp(403, text="forbidden"),
|
|
):
|
|
with pytest.raises(YarnError, match="403"):
|
|
kill_application("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
|
|
|
|
# --- connection errors ---
|
|
|
|
def test_status_wraps_httpx_errors_as_yarn_error():
|
|
with patch(
|
|
"spark_executor.core.yarn_client.httpx.request",
|
|
side_effect=httpx.ConnectError("connection refused"),
|
|
):
|
|
with pytest.raises(YarnError, match="connection failed"):
|
|
get_application_status("application_1", YarnClientConfig(yarn_rm_url=RM))
|
|
|
|
|
|
# --- SSL/TLS configuration ---
|
|
|
|
def test_request_passes_ssl_verify_true():
|
|
config.settings.ssl_verify_default = True
|
|
fake = _resp(200, json_data={"app": {"state": "RUNNING"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
get_application_status(
|
|
"application_1",
|
|
YarnClientConfig(yarn_rm_url=RM, ssl_verify=True),
|
|
)
|
|
assert m.call_args.kwargs["verify"] is True
|
|
|
|
|
|
def test_request_passes_ssl_ca_bundle_path():
|
|
fake = _resp(200, json_data={"app": {"state": "RUNNING"}})
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
get_application_status(
|
|
"application_1",
|
|
YarnClientConfig(
|
|
yarn_rm_url=HTTPS_RM,
|
|
ssl_ca_bundle="/path/to/ca.crt",
|
|
),
|
|
)
|
|
assert m.call_args.kwargs["verify"] == "/path/to/ca.crt"
|
|
|
|
|
|
def test_request_uses_global_ssl_default_when_connection_unset():
|
|
config.settings.ssl_verify_default = True
|
|
config.settings.ssl_ca_bundle_default = "/global/ca.crt"
|
|
config.settings.yarn_resource_manager_url = "https://rm:8088"
|
|
fake = _resp(200, json_data={"app": {"state": "RUNNING"}})
|
|
conn = Connection(name="prod", master="yarn", ssl_verify=None, ssl_ca_bundle=None)
|
|
cfg = YarnClientConfig.from_connection(conn)
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
get_application_status("application_1", cfg)
|
|
assert m.call_args.kwargs["verify"] == "/global/ca.crt"
|
|
|
|
|
|
def test_request_per_connection_ssl_overrides_global():
|
|
config.settings.ssl_verify_default = True
|
|
config.settings.ssl_ca_bundle_default = "/global/ca.crt"
|
|
config.settings.yarn_resource_manager_url = "https://rm:8088"
|
|
fake = _resp(200, json_data={"app": {"state": "RUNNING"}})
|
|
conn = Connection(
|
|
name="prod",
|
|
master="yarn",
|
|
ssl_verify=False,
|
|
ssl_ca_bundle="/conn/ca.crt",
|
|
)
|
|
cfg = YarnClientConfig.from_connection(conn)
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
get_application_status("application_1", cfg)
|
|
assert m.call_args.kwargs["verify"] == "/conn/ca.crt"
|
|
|
|
|
|
def test_ssl_verify_false_without_ca_bundle_uses_global_default():
|
|
"""If a connection only sets ssl_verify=False and no CA bundle is
|
|
configured globally, httpx should skip certificate verification."""
|
|
config.settings.ssl_verify_default = True
|
|
config.settings.ssl_ca_bundle_default = None
|
|
config.settings.yarn_resource_manager_url = "https://rm:8088"
|
|
fake = _resp(200, json_data={"app": {"state": "RUNNING"}})
|
|
conn = Connection(name="prod", master="yarn", ssl_verify=False)
|
|
cfg = YarnClientConfig.from_connection(conn)
|
|
with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
|
|
get_application_status("application_1", cfg)
|
|
assert m.call_args.kwargs["verify"] is False
|