refactor: replace yarn CLI shell-out with YARN REST API

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.
2026-06-24 17:33:36 +08:00
parent 0d7b1d1ec3
commit b3564737f7
12 changed files with 252 additions and 91 deletions
@@ -1,9 +1,11 @@
 # coding=utf-8
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch

+import httpx
 import pytest

 from spark_executor.core.yarn_client import (
+    YarnConfigError,
    YarnError,
    get_application_logs,
    get_application_status,
@@ -11,53 +13,120 @@ from spark_executor.core.yarn_client import (
 )


-def _fake_proc(returncode: int, stdout: str = "", stderr: str = ""):
-    p = MagicMock()
-    p.returncode = returncode
-    p.stdout = stdout
-    p.stderr = stderr
-    return p
+RM = "http://rm:8088"


-def test_status_parses_state_line():
-    fake = _fake_proc(
-        0,
-        stdout="Application Report :\n  State : RUNNING\n  ...\n",
-    )
-    with patch("spark_executor.core.yarn_client.subprocess.run", return_value=fake):
-        state, raw = get_application_status("application_1")
+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", RM)
    assert state == "RUNNING"
    assert "RUNNING" in raw
+    args = m.call_args.args
+    assert args == ("GET", f"{RM}/ws/v1/cluster/apps/application_1")


-def test_status_raises_on_nonzero_return():
-    fake = _fake_proc(1, stderr="not found")
-    with patch("spark_executor.core.yarn_client.subprocess.run", return_value=fake):
-        with pytest.raises(YarnError):
-            get_application_status("application_x")
+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", RM)


-def test_logs_returns_stdout():
-    fake = _fake_proc(0, stdout="log line 1\nlog line 2\n")
-    with patch("spark_executor.core.yarn_client.subprocess.run", return_value=fake) as m:
-        out = get_application_logs("application_1")
+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", 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", RM)
+
+
+def test_status_requires_rm_url():
+    with patch.dict("os.environ", {}, clear=True):
+        with pytest.raises(YarnConfigError):
+            get_application_status("application_1", None)
+
+
+def test_status_falls_back_to_env_var():
+    fake = _resp(200, json_data={"app": {"state": "FINISHED"}})
+    with patch.dict("os.environ", {"YARN_RESOURCE_MANAGER_URL": "http://env-rm:8088"}, clear=False):
+        with patch("spark_executor.core.yarn_client.httpx.request", return_value=fake) as m:
+            state, _ = get_application_status("application_1", 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", "rm:8088")
+
+
+# --- get_application_logs ---
+
+def test_logs_returns_text():
+    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", RM)
    assert out == "log line 1\nlog line 2\n"
-    args = m.call_args.args[0]
-    assert args[:3] == ["yarn", "logs", "-applicationId"]
-    assert args[3] == "application_1"
+    assert m.call_args.args == ("GET", f"{RM}/ws/v1/cluster/apps/application_1/aggregated-logs")


-def test_kill_invokes_yarn_application_kill():
-    fake = _fake_proc(0)
-    with patch("spark_executor.core.yarn_client.subprocess.run", return_value=fake) as m:
-        kill_application("application_1")
-    args = m.call_args.args[0]
-    assert args[:3] == ["yarn", "application", "-kill"]
-    assert args[3] == "application_1"
+def test_logs_raises_on_404_with_explanation():
+    with patch("spark_executor.core.yarn_client.httpx.request", return_value=_resp(404)):
+        with pytest.raises(YarnError, match="log-aggregation-enable"):
+            get_application_logs("application_1", RM)


-def test_kill_raises_on_nonzero_return():
-    fake = _fake_proc(1, stderr="denied")
-    with patch("spark_executor.core.yarn_client.subprocess.run", return_value=fake):
+def test_logs_raises_on_5xx():
+    with patch(
+        "spark_executor.core.yarn_client.httpx.request",
+        return_value=_resp(500, text="boom"),
+    ):
        with pytest.raises(YarnError):
-            kill_application("application_1")
+            get_application_logs("application_1", RM)
+
+
+# --- 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", 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"}
+
+
+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", 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", RM)