Run regressions tests on both Postgres 14 and 15 (#4192)

This PR adds tests runs on Postgres 15 and created unified Allure report
with results for all tests.

- Split `.github/actions/allure-report` into
`.github/actions/allure-report-store` and
`.github/actions/allure-report-generate`
- Add debug or release pytest parameter for all tests (depending on
`BUILD_TYPE` env variable)
- Add Postgres version as a pytest parameter for all tests (depending on
`DEFAULT_PG_VERSION` env variable)
- Fix `test_wal_restore` and `restore_from_wal.sh` to support path with
`[`/`]` in it (fixed by applying spellcheck to the script and fixing all
warnings), `restore_from_wal_archive.sh` is deleted as unused.
- All known failures on Postgres 15 marked with xfail

test_runner/conftest.py

@@ -1,5 +1,6 @@
 pytest_plugins = (
     "fixtures.pg_version",
+    "fixtures.allure",
     "fixtures.neon_fixtures",
     "fixtures.benchmark_fixture",
     "fixtures.pg_stats",

test_runner/fixtures/allure.py

@@ -0,0 +1,25 @@
+import os
+
+import pytest
+
+from fixtures.pg_version import DEFAULT_VERSION, PgVersion
+
+"""
+Set of utilities to make Allure report more informative.
+
+- It adds BUILD_TYPE and DEFAULT_PG_VERSION to the test names (only in test_runner/regress)
+to make tests distinguishable in Allure report.
+"""
+
+
+@pytest.fixture(scope="function", autouse=True)
+def allure_noop():
+    pass
+
+
+def pytest_generate_tests(metafunc):
+    if "test_runner/regress" in metafunc.definition._nodeid:
+        build_type = os.environ.get("BUILD_TYPE", "DEBUG").lower()
+        pg_version = PgVersion(os.environ.get("DEFAULT_PG_VERSION", DEFAULT_VERSION))
+
+        metafunc.parametrize("allure_noop", [f"{build_type}-pg{pg_version}"])

test_runner/fixtures/pg_version.py

@@ -46,6 +46,20 @@ class PgVersion(str, enum.Enum):
 DEFAULT_VERSION: PgVersion = PgVersion.V14
 
 
+def skip_on_postgres(version: PgVersion, reason: str):
+    return pytest.mark.skipif(
+        PgVersion(os.environ.get("DEFAULT_PG_VERSION", DEFAULT_VERSION)) is version,
+        reason=reason,
+    )
+
+
+def xfail_on_postgres(version: PgVersion, reason: str):
+    return pytest.mark.xfail(
+        PgVersion(os.environ.get("DEFAULT_PG_VERSION", DEFAULT_VERSION)) is version,
+        reason=reason,
+    )
+
+
 def pytest_addoption(parser: Parser):
     parser.addoption(
         "--pg-version",

test_runner/regress/test_compatibility.py

@@ -16,7 +16,7 @@ from fixtures.neon_fixtures import (
 )
 from fixtures.pageserver.http import PageserverHttpClient
 from fixtures.pageserver.utils import wait_for_last_record_lsn, wait_for_upload
-from fixtures.pg_version import PgVersion
+from fixtures.pg_version import PgVersion, skip_on_postgres
 from fixtures.types import Lsn
 from pytest import FixtureRequest
 
@@ -41,12 +41,15 @@ check_ondisk_data_compatibility_if_enabled = pytest.mark.skipif(
 )
 
 
-# Note: if renaming this test, don't forget to update a reference to it in a workflow file:
-# "Upload compatibility snapshot" step in .github/actions/run-python-test-set/action.yml
-@check_ondisk_data_compatibility_if_enabled
+@skip_on_postgres(PgVersion.V15, "Compatibility tests doesn't support Postgres 15 yet")
 @pytest.mark.xdist_group("compatibility")
 @pytest.mark.order(before="test_forward_compatibility")
-def test_create_snapshot(neon_env_builder: NeonEnvBuilder, pg_bin: PgBin, test_output_dir: Path):
+def test_create_snapshot(
+    neon_env_builder: NeonEnvBuilder,
+    pg_bin: PgBin,
+    top_output_dir: Path,
+    test_output_dir: Path,
+):
     # The test doesn't really test anything
     # it creates a new snapshot for releases after we tested the current version against the previous snapshot in `test_backward_compatibility`.
     #
@@ -86,10 +89,14 @@ def test_create_snapshot(neon_env_builder: NeonEnvBuilder, pg_bin: PgBin, test_o
         sk.stop()
     env.pageserver.stop()
 
-    shutil.copytree(test_output_dir, test_output_dir / "compatibility_snapshot_pg14")
-    # Directory `test_output_dir / "compatibility_snapshot_pg14"` is uploaded to S3 in a workflow, keep the name in sync with it
+    # Directory `compatibility_snapshot_dir` is uploaded to S3 in a workflow, keep the name in sync with it
+    compatibility_snapshot_dir = top_output_dir / "compatibility_snapshot_pg14"
+    if compatibility_snapshot_dir.exists():
+        shutil.rmtree(compatibility_snapshot_dir)
+    shutil.copytree(test_output_dir, compatibility_snapshot_dir)
 
 
+@skip_on_postgres(PgVersion.V15, "Compatibility tests doesn't support Postgres 15 yet")
 @check_ondisk_data_compatibility_if_enabled
 @pytest.mark.xdist_group("compatibility")
 @pytest.mark.order(after="test_create_snapshot")
@@ -148,11 +155,13 @@ def test_backward_compatibility(
     ), "Breaking changes are allowed by ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE, but the test has passed without any breakage"
 
 
+@skip_on_postgres(PgVersion.V15, "Compatibility tests doesn't support Postgres 15 yet")
 @check_ondisk_data_compatibility_if_enabled
 @pytest.mark.xdist_group("compatibility")
 @pytest.mark.order(after="test_create_snapshot")
 def test_forward_compatibility(
     test_output_dir: Path,
+    top_output_dir: Path,
     port_distributor: PortDistributor,
     pg_version: PgVersion,
     request: FixtureRequest,
@@ -174,9 +183,7 @@ def test_forward_compatibility(
     ), "COMPATIBILITY_POSTGRES_DISTRIB_DIR is not set. It should be set to a pg_install directrory (ideally generated by the previous version of Neon)"
     compatibility_postgres_distrib_dir = Path(compatibility_postgres_distrib_dir_env).resolve()
 
-    compatibility_snapshot_dir = (
-        test_output_dir.parent / "test_create_snapshot" / "compatibility_snapshot_pg14"
-    )
+    compatibility_snapshot_dir = top_output_dir / "compatibility_snapshot_pg14"
 
     breaking_changes_allowed = (
         os.environ.get("ALLOW_FORWARD_COMPATIBILITY_BREAKAGE", "false").lower() == "true"

test_runner/regress/test_hot_standby.py

@@ -1,7 +1,9 @@
 import pytest
 from fixtures.neon_fixtures import NeonEnv
+from fixtures.pg_version import PgVersion, xfail_on_postgres
 
 
+@xfail_on_postgres(PgVersion.V15, reason="https://github.com/neondatabase/neon/pull/4182")
 @pytest.mark.timeout(1800)
 def test_hot_standby(neon_simple_env: NeonEnv):
     env = neon_simple_env

test_runner/regress/test_pg_regress.py

@@ -5,6 +5,7 @@ from pathlib import Path
 
 import pytest
 from fixtures.neon_fixtures import NeonEnv, check_restored_datadir_content
+from fixtures.pg_version import PgVersion, xfail_on_postgres
 
 
 # Run the main PostgreSQL regression tests, in src/test/regress.
@@ -71,6 +72,7 @@ def test_pg_regress(
 #
 # This runs for a long time, especially in debug mode, so use a larger-than-default
 # timeout.
+@xfail_on_postgres(PgVersion.V15, reason="https://github.com/neondatabase/neon/pull/4213")
 @pytest.mark.timeout(1800)
 def test_isolation(
     neon_simple_env: NeonEnv,

test_runner/regress/test_tenant_size.py

@@ -11,6 +11,7 @@ from fixtures.neon_fixtures import (
     wait_for_wal_insert_lsn,
 )
 from fixtures.pageserver.http import PageserverHttpClient
+from fixtures.pg_version import PgVersion, xfail_on_postgres
 from fixtures.types import Lsn, TenantId, TimelineId
 
 
@@ -512,6 +513,7 @@ def test_single_branch_get_tenant_size_grows(
     assert size_after == prev, "size after restarting pageserver should not have changed"
 
 
+@xfail_on_postgres(PgVersion.V15, reason="Test significantly more flaky on Postgres 15")
 def test_get_tenant_size_with_multiple_branches(
     neon_env_builder: NeonEnvBuilder, test_output_dir: Path
 ):

test_runner/regress/test_wal_restore.py

@@ -1,14 +1,20 @@
+import sys
 from pathlib import Path
 
+import pytest
 from fixtures.neon_fixtures import (
     NeonEnvBuilder,
     PgBin,
     PortDistributor,
     VanillaPostgres,
 )
-from fixtures.types import TenantId
+from fixtures.types import TenantId, TimelineId
 
 
+@pytest.mark.skipif(
+    sys.platform != "linux",
+    reason="restore_from_wal.sh supports only Linux",
+)
 def test_wal_restore(
     neon_env_builder: NeonEnvBuilder,
     pg_bin: PgBin,
@@ -22,6 +28,7 @@ def test_wal_restore(
     endpoint = env.endpoints.create_start("test_wal_restore")
     endpoint.safe_psql("create table t as select generate_series(1,300000)")
     tenant_id = TenantId(endpoint.safe_psql("show neon.tenant_id")[0][0])
+    timeline_id = TimelineId(endpoint.safe_psql("show neon.timeline_id")[0][0])
     env.neon_cli.pageserver_stop()
     port = port_distributor.get_port()
     data_dir = test_output_dir / "pgsql.restored"
@@ -30,9 +37,16 @@ def test_wal_restore(
     ) as restored:
         pg_bin.run_capture(
             [
-                str(base_dir / "libs/utils/scripts/restore_from_wal.sh"),
+                str(base_dir / "libs" / "utils" / "scripts" / "restore_from_wal.sh"),
                 str(pg_distrib_dir / f"v{env.pg_version}/bin"),
-                str(test_output_dir / "repo" / "safekeepers" / "sk1" / str(tenant_id) / "*"),
+                str(
+                    test_output_dir
+                    / "repo"
+                    / "safekeepers"
+                    / "sk1"
+                    / str(tenant_id)
+                    / str(timeline_id)
+                ),
                 str(data_dir),
                 str(port),
             ]