Add data format backward compatibility tests (#2626)

.github/actions/run-python-test-set/action.yml

@@ -73,6 +73,13 @@ runs:
       shell: bash -euxo pipefail {0}
       run: ./scripts/pysync
 
+    - name: Download compatibility snapshot for Postgres 14
+      uses: ./.github/actions/download
+      with:
+        name: compatibility-snapshot-${{ inputs.build_type }}-pg14
+        path: /tmp/compatibility_snapshot_pg14
+        prefix: latest
+
     - name: Run pytest
       env:
         NEON_BIN: /tmp/neon/bin
@@ -80,6 +87,8 @@ runs:
         BUILD_TYPE: ${{ inputs.build_type }}
         AWS_ACCESS_KEY_ID: ${{ inputs.real_s3_access_key_id }}
         AWS_SECRET_ACCESS_KEY: ${{ inputs.real_s3_secret_access_key }}
+        COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg14
+        ALLOW_BREAKING_CHANGES: contains(github.event.pull_request.labels.*.name, 'breaking changes')
       shell: bash -euxo pipefail {0}
       run: |
         # PLATFORM will be embedded in the perf test report
@@ -154,6 +163,15 @@ runs:
           scripts/generate_and_push_perf_report.sh
         fi
 
+    - name: Upload compatibility snapshot for Postgres 14
+      if: github.ref_name == 'release'
+      uses: ./.github/actions/upload
+      with:
+        name: compatibility-snapshot-${{ inputs.build_type }}-pg14-${{ github.run_id }}
+        # The path includes a test name (test_prepare_snapshot) and directory that the test creates (compatibility_snapshot_pg14), keep the path in sync with the test
+        path: /tmp/test_output/test_prepare_snapshot/compatibility_snapshot_pg14/
+        prefix: latest
+
     - name: Create Allure report
       if: always()
       uses: ./.github/actions/allure-report

.github/workflows/build_and_test.yml

@@ -844,7 +844,7 @@ jobs:
           submodules: true
           fetch-depth: 0
 
-      - name: Configure environment 
+      - name: Configure environment
         run: |
           helm repo add neondatabase https://neondatabase.github.io/helm-charts
           aws --region us-east-2 eks update-kubeconfig --name dev-us-east-2-beta --role-arn arn:aws:iam::369495373322:role/github-runner
@@ -853,3 +853,24 @@ jobs:
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
           helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/dev-us-east-2-beta.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
+
+  promote-compatibility-test-snapshot:
+    runs-on: dev
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+    needs: [ deploy, deploy-proxy ]
+    if: github.ref_name == 'release' && github.event_name != 'workflow_dispatch'
+    steps:
+      - name: Promote compatibility snapshot for the release
+        shell: bash -euxo pipefail {0}
+        env:
+          BUCKET: neon-github-public-dev
+          PREFIX: artifacts/latest
+        run: |
+          for build_type in debug release; do
+            OLD_FILENAME=compatibility-snapshot-${build_type}-pg14-${GITHUB_RUN_ID}.tar.zst
+            NEW_FILENAME=compatibility-snapshot-${build_type}-pg14.tar.zst
+
+            time aws s3 mv --only-show-errors s3://${BUCKET}/${PREFIX}/${OLD_FILENAME} s3://${BUCKET}/${PREFIX}/${NEW_FILENAME}
+          done

poetry.lock

@@ -11,7 +11,7 @@ async-timeout = ">=3.0,<5.0"
 psycopg2-binary = ">=2.8.4"
 
 [package.extras]
-sa = ["sqlalchemy[postgresql_psycopg2binary] (>=1.3,<1.5)"]
+sa = ["sqlalchemy[postgresql-psycopg2binary] (>=1.3,<1.5)"]
 
 [[package]]
 name = "allure-pytest"
@@ -80,7 +80,7 @@ python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 dev = ["cloudpickle", "coverage[toml] (>=5.0.2)", "furo", "hypothesis", "mypy", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "six", "sphinx", "sphinx-notfound-page", "zope.interface"]
 docs = ["furo", "sphinx", "sphinx-notfound-page", "zope.interface"]
 tests = ["cloudpickle", "coverage[toml] (>=5.0.2)", "hypothesis", "mypy", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "six", "zope.interface"]
-tests_no_zope = ["cloudpickle", "coverage[toml] (>=5.0.2)", "hypothesis", "mypy", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "six"]
+tests-no-zope = ["cloudpickle", "coverage[toml] (>=5.0.2)", "hypothesis", "mypy", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "six"]
 
 [[package]]
 name = "aws-sam-translator"
@@ -560,7 +560,7 @@ optional = false
 python-versions = ">=3.6.0"
 
 [package.extras]
-unicode_backport = ["unicodedata2"]
+unicode-backport = ["unicodedata2"]
 
 [[package]]
 name = "click"
@@ -593,7 +593,7 @@ python-versions = ">=3.6"
 cffi = ">=1.12"
 
 [package.extras]
-docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1)", "sphinx-rtd-theme"]
+docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1)", "sphinx_rtd_theme"]
 docstest = ["pyenchant (>=1.6.11)", "sphinxcontrib-spelling (>=4.0.1)", "twine (>=1.12.0)"]
 pep8test = ["black", "flake8", "flake8-import-order", "pep8-naming"]
 sdist = ["setuptools_rust (>=0.11.4)"]
@@ -738,9 +738,9 @@ python-versions = ">=3.6.1,<4.0"
 
 [package.extras]
 colors = ["colorama (>=0.4.3,<0.5.0)"]
-pipfile_deprecated_finder = ["pipreqs", "requirementslib"]
+pipfile-deprecated-finder = ["pipreqs", "requirementslib"]
 plugins = ["setuptools"]
-requirements_deprecated_finder = ["pip-api", "pipreqs"]
+requirements-deprecated-finder = ["pip-api", "pipreqs"]
 
 [[package]]
 name = "itsdangerous"
@@ -815,7 +815,7 @@ python-versions = ">=2.7"
 [package.extras]
 docs = ["jaraco.packaging (>=3.2)", "rst.linker (>=1.9)", "sphinx"]
 testing = ["ecdsa", "enum34", "feedparser", "jsonlib", "numpy", "pandas", "pymongo", "pytest (>=3.5,!=3.7.3)", "pytest-black-multipy", "pytest-checkdocs (>=1.2.3)", "pytest-cov", "pytest-flake8 (<1.1.0)", "pytest-flake8 (>=1.1.1)", "scikit-learn", "sqlalchemy"]
-"testing.libs" = ["simplejson", "ujson", "yajl"]
+testing-libs = ["simplejson", "ujson", "yajl"]
 
 [[package]]
 name = "jsonpointer"
@@ -836,11 +836,12 @@ python-versions = "*"
 [package.dependencies]
 attrs = ">=17.4.0"
 pyrsistent = ">=0.14.0"
+setuptools = "*"
 six = ">=1.11.0"
 
 [package.extras]
 format = ["idna", "jsonpointer (>1.13)", "rfc3987", "strict-rfc3339", "webcolors"]
-format_nongpl = ["idna", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3986-validator (>0.1.0)", "webcolors"]
+format-nongpl = ["idna", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3986-validator (>0.1.0)", "webcolors"]
 
 [[package]]
 name = "junit-xml"
@@ -900,6 +901,7 @@ pytz = "*"
 PyYAML = {version = ">=5.1", optional = true, markers = "extra == \"server\""}
 requests = ">=2.5"
 responses = ">=0.9.0"
+setuptools = {version = "*", optional = true, markers = "extra == \"server\""}
 sshpubkeys = {version = ">=3.1.0", optional = true, markers = "extra == \"server\""}
 werkzeug = ">=0.5,<2.2.0"
 xmltodict = "*"
@@ -1008,6 +1010,7 @@ python-versions = ">=3.7.0,<4.0.0"
 jsonschema = ">=3.2.0,<5.0.0"
 openapi-schema-validator = ">=0.2.0,<0.3.0"
 PyYAML = ">=5.1"
+setuptools = "*"
 
 [package.extras]
 requests = ["requests"]
@@ -1340,7 +1343,7 @@ urllib3 = ">=1.21.1,<1.27"
 
 [package.extras]
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
-use_chardet_on_py3 = ["chardet (>=3.0.2,<6)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 
 [[package]]
 name = "responses"
@@ -1394,6 +1397,19 @@ python-versions = ">= 2.7"
 attrs = "*"
 pbr = "*"
 
+[[package]]
+name = "setuptools"
+version = "65.5.0"
+description = "Easily download, build, install, upgrade, and uninstall Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-hoverxref (<2)", "sphinx-inline-tabs", "sphinx-notfound-page (==0.8.3)", "sphinx-reredirects", "sphinxcontrib-towncrier"]
+testing = ["build[virtualenv]", "filelock (>=3.4.0)", "flake8 (<5)", "flake8-2020", "ini2toml[lite] (>=0.9)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "mock", "pip (>=19.1)", "pip-run (>=8.8)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-xdist", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
+testing-integration = ["build[virtualenv]", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"]
+
 [[package]]
 name = "six"
 version = "1.16.0"
@@ -1460,6 +1476,14 @@ category = "main"
 optional = false
 python-versions = ">=3.7,<4.0"
 
+[[package]]
+name = "types-toml"
+version = "0.10.8"
+description = "Typing stubs for toml"
+category = "dev"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "types-urllib3"
 version = "1.26.17"
@@ -1544,7 +1568,7 @@ testing = ["func-timeout", "jaraco.itertools", "pytest (>=6)", "pytest-black (>=
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.9"
-content-hash = "ead1495454ee6d880bb240447025db93a25ebe263c2709de5f144cc2d85dc975"
+content-hash = "17cdbfe90f1b06dffaf24c3e076384ec08dd4a2dce5a05e50565f7364932eb2d"
 
 [metadata.files]
 aiopg = [
@@ -2182,6 +2206,10 @@ sarif-om = [
     {file = "sarif_om-1.0.4-py3-none-any.whl", hash = "sha256:539ef47a662329b1c8502388ad92457425e95dc0aaaf995fe46f4984c4771911"},
     {file = "sarif_om-1.0.4.tar.gz", hash = "sha256:cd5f416b3083e00d402a92e449a7ff67af46f11241073eea0461802a3b5aef98"},
 ]
+setuptools = [
+    {file = "setuptools-65.5.0-py3-none-any.whl", hash = "sha256:f62ea9da9ed6289bfe868cd6845968a2c854d1427f8548d52cae02a42b4f0356"},
+    {file = "setuptools-65.5.0.tar.gz", hash = "sha256:512e5536220e38146176efb833d4a62aa726b7bbff82cfbc8ba9eaa3996e0b17"},
+]
 six = [
     {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
@@ -2210,6 +2238,10 @@ types-s3transfer = [
     {file = "types-s3transfer-0.6.0.post3.tar.gz", hash = "sha256:92c3704e5d041202bfb5ddb79d083fd1a02de2c5dfec6a91576823e6b5c93993"},
     {file = "types_s3transfer-0.6.0.post3-py3-none-any.whl", hash = "sha256:eedc5117275565b3c83662c0ccc81662a34da5dda8bd502b89d296b6d5cb091d"},
 ]
+types-toml = [
+    {file = "types-toml-0.10.8.tar.gz", hash = "sha256:b7e7ea572308b1030dc86c3ba825c5210814c2825612ec679eb7814f8dd9295a"},
+    {file = "types_toml-0.10.8-py3-none-any.whl", hash = "sha256:8300fd093e5829eb9c1fba69cee38130347d4b74ddf32d0a7df650ae55c2b599"},
+]
 types-urllib3 = [
     {file = "types-urllib3-1.26.17.tar.gz", hash = "sha256:73fd274524c3fc7cd8cd9ceb0cb67ed99b45f9cb2831013e46d50c1451044800"},
     {file = "types_urllib3-1.26.17-py3-none-any.whl", hash = "sha256:0d027fcd27dbb3cb532453b4d977e05bc1e13aefd70519866af211b3003d895d"},

pyproject.toml

@@ -28,12 +28,14 @@ Werkzeug = "2.1.2"
 pytest-order = "^1.0.1"
 allure-pytest = "^2.10.0"
 pytest-asyncio = "^0.19.0"
+toml = "^0.10.2"
 
 [tool.poetry.dev-dependencies]
 flake8 = "^5.0.4"
 mypy = "==0.971"
 black = "^22.6.0"
 isort = "^5.10.1"
+types-toml = "^0.10.8"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]

test_runner/fixtures/neon_fixtures.py

@@ -970,7 +970,7 @@ class NeonPageserverApiException(Exception):
 
 
 class NeonPageserverHttpClient(requests.Session):
-    def __init__(self, port: int, is_testing_enabled_or_skip, auth_token: Optional[str] = None):
+    def __init__(self, port: int, is_testing_enabled_or_skip: Fn, auth_token: Optional[str] = None):
         super().__init__()
         self.port = port
         self.auth_token = auth_token

test_runner/regress/test_compatibility.py

@@ -0,0 +1,267 @@
+import os
+import re
+import shutil
+import subprocess
+from pathlib import Path
+from typing import Any, Dict, Union
+
+import pytest
+import toml
+from fixtures.neon_fixtures import (
+    NeonCli,
+    NeonEnvBuilder,
+    NeonPageserverHttpClient,
+    PgBin,
+    PortDistributor,
+    wait_for_last_record_lsn,
+    wait_for_upload,
+)
+from fixtures.types import Lsn
+from pytest import FixtureRequest
+
+
+def dump_differs(first: Path, second: Path, output: Path) -> bool:
+    """
+    Runs diff(1) command on two SQL dumps and write the output to the given output file.
+    Returns True if the dumps differ, False otherwise.
+    """
+
+    with output.open("w") as stdout:
+        rv = subprocess.run(
+            [
+                "diff",
+                "--unified",  # Make diff output more readable
+                "--ignore-matching-lines=^--",  # Ignore changes in comments
+                "--ignore-blank-lines",
+                str(first),
+                str(second),
+            ],
+            stdout=stdout,
+        )
+
+    return rv.returncode != 0
+
+
+class PortReplacer(object):
+    """
+    Class-helper for replacing ports in config files.
+    """
+
+    def __init__(self, port_distributor: PortDistributor):
+        self.port_distributor = port_distributor
+        self.port_map: Dict[int, int] = {}
+
+    def replace_port(self, value: Union[int, str]) -> Union[int, str]:
+        if isinstance(value, int):
+            if (known_port := self.port_map.get(value)) is not None:
+                return known_port
+
+            self.port_map[value] = self.port_distributor.get_port()
+            return self.port_map[value]
+
+        if isinstance(value, str):
+            # Use regex to find port in a string
+            # urllib.parse.urlparse produces inconvenient results for cases without scheme like "localhost:5432"
+            # See https://bugs.python.org/issue27657
+            ports = re.findall(r":(\d+)(?:/|$)", value)
+            assert len(ports) == 1, f"can't find port in {value}"
+            port_int = int(ports[0])
+
+            if (known_port := self.port_map.get(port_int)) is not None:
+                return value.replace(f":{port_int}", f":{known_port}")
+
+            self.port_map[port_int] = self.port_distributor.get_port()
+            return value.replace(f":{port_int}", f":{self.port_map[port_int]}")
+
+        raise TypeError(f"unsupported type {type(value)} of {value=}")
+
+
+def test_backward_compatibility(
+    pg_bin: PgBin, port_distributor: PortDistributor, test_output_dir: Path, request: FixtureRequest
+):
+    compatibility_snapshot_dir_env = os.environ.get("COMPATIBILITY_SNAPSHOT_DIR")
+    assert (
+        compatibility_snapshot_dir_env is not None
+    ), "COMPATIBILITY_SNAPSHOT_DIR is not set. It should be set to `compatibility_snapshot_pg14` path generateted by test_prepare_snapshot"
+    compatibility_snapshot_dir = Path(compatibility_snapshot_dir_env).resolve()
+
+    # Make compatibility snapshot artifacts pickupable by Allure
+    # by copying the snapshot directory to the curent test output directory.
+    repo_dir = test_output_dir / "compatibility_snapshot" / "repo"
+
+    shutil.copytree(compatibility_snapshot_dir / "repo", repo_dir)
+
+    # Remove old logs to avoid confusion in test artifacts
+    for logfile in repo_dir.glob("**/*.log"):
+        logfile.unlink()
+
+    # Remove tenants data for computes
+    for tenant in (repo_dir / "pgdatadirs" / "tenants").glob("*"):
+        shutil.rmtree(tenant)
+
+    # Remove wal-redo temp directory
+    for tenant in (repo_dir / "tenants").glob("*"):
+        shutil.rmtree(tenant / "wal-redo-datadir.___temp")
+
+    # Update paths and ports in config files
+    pr = PortReplacer(port_distributor)
+
+    pageserver_toml = repo_dir / "pageserver.toml"
+    pageserver_config = toml.load(pageserver_toml)
+    new_local_path = pageserver_config["remote_storage"]["local_path"].replace(
+        "/test_prepare_snapshot/",
+        "/test_backward_compatibility/compatibility_snapshot/",
+    )
+
+    pageserver_config["remote_storage"]["local_path"] = new_local_path
+    pageserver_config["listen_http_addr"] = pr.replace_port(pageserver_config["listen_http_addr"])
+    pageserver_config["listen_pg_addr"] = pr.replace_port(pageserver_config["listen_pg_addr"])
+    pageserver_config["broker_endpoints"] = [
+        pr.replace_port(ep) for ep in pageserver_config["broker_endpoints"]
+    ]
+
+    with pageserver_toml.open("w") as f:
+        toml.dump(pageserver_config, f)
+
+    snapshot_config_toml = repo_dir / "config"
+    snapshot_config = toml.load(snapshot_config_toml)
+    snapshot_config["etcd_broker"]["broker_endpoints"] = [
+        pr.replace_port(ep) for ep in snapshot_config["etcd_broker"]["broker_endpoints"]
+    ]
+    snapshot_config["pageserver"]["listen_http_addr"] = pr.replace_port(
+        snapshot_config["pageserver"]["listen_http_addr"]
+    )
+    snapshot_config["pageserver"]["listen_pg_addr"] = pr.replace_port(
+        snapshot_config["pageserver"]["listen_pg_addr"]
+    )
+    for sk in snapshot_config["safekeepers"]:
+        sk["http_port"] = pr.replace_port(sk["http_port"])
+        sk["pg_port"] = pr.replace_port(sk["pg_port"])
+
+    with (snapshot_config_toml).open("w") as f:
+        toml.dump(snapshot_config, f)
+
+    # Ensure that snapshot doesn't contain references to the original path
+    rv = subprocess.run(
+        [
+            "grep",
+            "--recursive",
+            "--binary-file=without-match",
+            "--files-with-matches",
+            "test_prepare_snapshot/repo",
+            str(repo_dir),
+        ],
+        capture_output=True,
+        text=True,
+    )
+    assert (
+        rv.returncode != 0
+    ), f"there're files referencing `test_prepare_snapshot/repo`, this path should be replaced with {repo_dir}:\n{rv.stdout}"
+
+    # NeonEnv stub to make NeonCli happy
+    config: Any = type("NeonEnvStub", (object,), {})
+    config.rust_log_override = None
+    config.repo_dir = repo_dir
+    config.pg_version = "14"  # Note: `pg_dumpall` (from pg_bin) version is set by DEFAULT_PG_VERSION_DEFAULT and can be overriden by DEFAULT_PG_VERSION env var
+    config.initial_tenant = snapshot_config["default_tenant_id"]
+
+    # Check that we can start the project
+    cli = NeonCli(config)
+    try:
+        cli.raw_cli(["start"])
+        request.addfinalizer(lambda: cli.raw_cli(["stop"]))
+
+        result = cli.pg_start("main")
+        request.addfinalizer(lambda: cli.pg_stop("main"))
+    except Exception:
+        breaking_changes_allowed = (
+            os.environ.get("ALLOW_BREAKING_CHANGES", "false").lower() == "true"
+        )
+        if breaking_changes_allowed:
+            pytest.xfail("Breaking changes are allowed by ALLOW_BREAKING_CHANGES env var")
+        else:
+            raise
+
+    connstr_all = re.findall(r"Starting postgres node at '([^']+)'", result.stdout)
+    assert len(connstr_all) == 1, f"can't parse connstr from {result.stdout}"
+    connstr = connstr_all[0]
+
+    # Check that the project produces the same dump as the previous version.
+    # The assert itself deferred to the end of the test
+    # to allow us to perform checks that change data before failing
+    pg_bin.run(["pg_dumpall", f"--dbname={connstr}", f"--file={test_output_dir / 'dump.sql'}"])
+    initial_dump_differs = dump_differs(
+        compatibility_snapshot_dir / "dump.sql",
+        test_output_dir / "dump.sql",
+        test_output_dir / "dump.filediff",
+    )
+
+    # Check that project can be recovered from WAL
+    # loosely based on https://github.com/neondatabase/cloud/wiki/Recovery-from-WAL
+    tenant_id = snapshot_config["default_tenant_id"]
+    timeline_id = dict(snapshot_config["branch_name_mappings"]["main"])[tenant_id]
+    pageserver_port = snapshot_config["pageserver"]["listen_http_addr"].split(":")[-1]
+    auth_token = snapshot_config["pageserver"]["auth_token"]
+    pageserver_http = NeonPageserverHttpClient(
+        port=pageserver_port,
+        is_testing_enabled_or_skip=lambda: True,  # TODO: check if testing really enabled
+        auth_token=auth_token,
+    )
+
+    shutil.rmtree(repo_dir / "local_fs_remote_storage")
+    pageserver_http.timeline_delete(tenant_id, timeline_id)
+    pageserver_http.timeline_create(tenant_id, timeline_id)
+    pg_bin.run(
+        ["pg_dumpall", f"--dbname={connstr}", f"--file={test_output_dir / 'dump-from-wal.sql'}"]
+    )
+    # The assert itself deferred to the end of the test
+    # to allow us to perform checks that change data before failing
+    dump_from_wal_differs = dump_differs(
+        test_output_dir / "dump.sql",
+        test_output_dir / "dump-from-wal.sql",
+        test_output_dir / "dump-from-wal.filediff",
+    )
+
+    # Check that we can interract with the data
+    pg_bin.run(["pgbench", "--time=10", "--progress=2", connstr])
+
+    assert not dump_from_wal_differs, "dump from WAL differs"
+    assert not initial_dump_differs, "initial dump differs"
+
+
+@pytest.mark.order(after="test_backward_compatibility")
+# 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
+def test_prepare_snapshot(neon_env_builder: NeonEnvBuilder, pg_bin: PgBin, 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`.
+    #
+    # There's no cleanup here, it allows to adjust the data in `test_backward_compatibility` itself without re-collecting it.
+    neon_env_builder.pg_version = "14"
+    neon_env_builder.num_safekeepers = 3
+    neon_env_builder.enable_local_fs_remote_storage()
+
+    env = neon_env_builder.init_start()
+    pg = env.postgres.create_start("main")
+    pg_bin.run(["pgbench", "--initialize", "--scale=10", pg.connstr()])
+    pg_bin.run(["pgbench", "--time=60", "--progress=2", pg.connstr()])
+    pg_bin.run(["pg_dumpall", f"--dbname={pg.connstr()}", f"--file={test_output_dir / 'dump.sql'}"])
+
+    snapshot_config = toml.load(test_output_dir / "repo" / "config")
+    tenant_id = snapshot_config["default_tenant_id"]
+    timeline_id = dict(snapshot_config["branch_name_mappings"]["main"])[tenant_id]
+
+    pageserver_http = env.pageserver.http_client()
+    lsn = Lsn(pg.safe_psql("SELECT pg_current_wal_flush_lsn()")[0][0])
+
+    pageserver_http.timeline_checkpoint(tenant_id, timeline_id)
+    wait_for_last_record_lsn(pageserver_http, tenant_id, timeline_id, lsn)
+    wait_for_upload(pageserver_http, tenant_id, timeline_id, lsn)
+
+    env.postgres.stop_all()
+    for sk in env.safekeepers:
+        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