From 944d4c9a2ba45ce4a313370bbeae1591b1d5e354 Mon Sep 17 00:00:00 2001 From: Jennifer Davis Date: Wed, 18 Nov 2026 22:16:11 +0000 Subject: [PATCH 1/2] feat(spanner): Add table and index AddSplitPoints pre-splitting sample Pre-splitting tables and indexes ahead of bulk loads prevents initial hotspots using DatabaseAdminClient.add_split_points. Add a standalone spanner_database_add_split_points sample. --- .../database_add_split_points.py | 119 +++++++++++++++ .../tests/database_add_split_points_test.py | 136 ++++++++++++++++++ 2 files changed, 255 insertions(+) create mode 100644 spanner/database_admin/src/spanner_database_admin/database_add_split_points.py create mode 100644 spanner/database_admin/tests/database_add_split_points_test.py diff --git a/spanner/database_admin/src/spanner_database_admin/database_add_split_points.py b/spanner/database_admin/src/spanner_database_admin/database_add_split_points.py new file mode 100644 index 0000000000..ba13b87f86 --- /dev/null +++ b/spanner/database_admin/src/spanner_database_admin/database_add_split_points.py @@ -0,0 +1,119 @@ +# Copyright 2026 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +# [START spanner_database_add_split_points] +import sys + +from google.api_core import exceptions +from google.cloud import spanner_admin_database_v1 + + +def add_split_points(project_id: str, instance_id: str, database_id: str) -> None: + """Pre-splits a Spanner table and secondary index via AddSplitPoints. + + Args: + project_id: The Google Cloud project ID. + instance_id: The Spanner instance ID. + database_id: The Spanner database ID containing Singers. + """ + client = spanner_admin_database_v1.DatabaseAdminClient() + database_path = client.database_path(project_id, instance_id, database_id) + index_name = "SingersByFirstLastName" + ddl_request = spanner_admin_database_v1.UpdateDatabaseDdlRequest( + database=database_path, + statements=[ + f"CREATE INDEX IF NOT EXISTS {index_name} " + "ON Singers(FirstName, LastName)" + ], + ) + + table_key = spanner_admin_database_v1.SplitPoints.Key(key_parts=["42"]) + idx_only_key = spanner_admin_database_v1.SplitPoints.Key(key_parts=["John", "Doe"]) + idx_prefix_key = spanner_admin_database_v1.SplitPoints.Key( + key_parts=["Jane", "Doe"] + ) + idx_table_key = spanner_admin_database_v1.SplitPoints.Key(key_parts=["38"]) + + split_points = [ + spanner_admin_database_v1.SplitPoints(table="Singers", keys=[table_key]), + spanner_admin_database_v1.SplitPoints(index=index_name, keys=[idx_only_key]), + spanner_admin_database_v1.SplitPoints( + index=index_name, keys=[idx_prefix_key, idx_table_key] + ), + ] + split_request = spanner_admin_database_v1.AddSplitPointsRequest( + database=database_path, + split_points=split_points, + ) + + try: + ddl_op = client.update_database_ddl(request=ddl_request) + print(f"Waiting for index '{index_name}' before adding split points...") + ddl_op.result(timeout=300) + client.add_split_points(request=split_request) + except exceptions.ResourceExhausted as err: + print( + f"error: split-point quota exceeded on database '{database_id}' " + f"in instance '{instance_id}': {err.message}", + file=sys.stderr, + ) + except TimeoutError as err: + print( + f"error: timed out waiting for the operation on database '{database_id}' " + f"to complete; the operation may still be running: {err}", + file=sys.stderr, + ) + except exceptions.GoogleAPICallError as err: + print( + f"error: failed to add split points on database '{database_id}' " + f"in instance '{instance_id}': {err.message}", + file=sys.stderr, + ) + else: + print(f"Resource ID: {database_id}") + print(f"Split Points Added: {len(split_points)}") + + +# [END spanner_database_add_split_points] + + +if __name__ == "__main__": + import argparse + import os + + parser = argparse.ArgumentParser( + description="Add table and index split points to a Spanner database." + ) + parser.add_argument( + "--project-id", + default=os.environ.get("GOOGLE_CLOUD_PROJECT", "example-project-id"), + help="Google Cloud project ID (default: $GOOGLE_CLOUD_PROJECT)", + ) + parser.add_argument( + "--instance-id", + default=os.environ.get("SPANNER_INSTANCE_ID", "example-instance"), + help="Spanner instance ID (default: $SPANNER_INSTANCE_ID)", + ) + parser.add_argument( + "--database-id", + default=os.environ.get("SPANNER_DATABASE_ID", "example-db"), + help="Spanner database ID (default: $SPANNER_DATABASE_ID)", + ) + args = parser.parse_args() + + add_split_points( + project_id=args.project_id, + instance_id=args.instance_id, + database_id=args.database_id, + ) diff --git a/spanner/database_admin/tests/database_add_split_points_test.py b/spanner/database_admin/tests/database_add_split_points_test.py new file mode 100644 index 0000000000..4167b50950 --- /dev/null +++ b/spanner/database_admin/tests/database_add_split_points_test.py @@ -0,0 +1,136 @@ +# Copyright 2026 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import runpy +from unittest import mock +import uuid + +from google.api_core import exceptions +from google.cloud import spanner_admin_database_v1 +import pytest +from spanner_database_admin import create_database +from spanner_database_admin import database_add_split_points + +from . import conftest + +PROJECT_ID = "example-project-id" +INSTANCE_ID = "example-instance" +DATABASE_ID = "example-db" +ADMIN_CLIENT = "google.cloud.spanner_admin_database_v1.DatabaseAdminClient" + + +@mock.patch(ADMIN_CLIENT) +def test_add_split_points_success( + mock_client_class: mock.MagicMock, capsys: pytest.CaptureFixture[str] +) -> None: + mock_client_class.return_value.database_path.return_value = ( + f"projects/{PROJECT_ID}/instances/{INSTANCE_ID}/databases/{DATABASE_ID}" + ) + + database_add_split_points.add_split_points(PROJECT_ID, INSTANCE_ID, DATABASE_ID) + + mock_client_class.return_value.add_split_points.assert_called_once() + out, err = capsys.readouterr() + assert f"Resource ID: {DATABASE_ID}" in out + assert "Split Points Added: 3" in out + assert PROJECT_ID not in out + assert err == "" + + +@pytest.mark.parametrize( + "error, expected_prefix", + [ + (TimeoutError("deadline"), "error: timed out waiting for the operation"), + ( + exceptions.ResourceExhausted("quota"), + "error: split-point quota exceeded", + ), + ( + exceptions.InvalidArgument("bad key"), + "error: failed to add split points", + ), + ], +) +@mock.patch(ADMIN_CLIENT) +def test_add_split_points_errors( + mock_client_class: mock.MagicMock, + capsys: pytest.CaptureFixture[str], + error: Exception, + expected_prefix: str, +) -> None: + mock_client_class.return_value.database_path.return_value = ( + f"projects/{PROJECT_ID}/instances/{INSTANCE_ID}/databases/{DATABASE_ID}" + ) + mock_client_class.return_value.add_split_points.side_effect = error + + database_add_split_points.add_split_points(PROJECT_ID, INSTANCE_ID, DATABASE_ID) + + _out, err = capsys.readouterr() + assert err.startswith(expected_prefix) + assert PROJECT_ID not in err + + +@mock.patch(ADMIN_CLIENT) +def test_add_split_points_cli_entrypoint( + mock_client_class: mock.MagicMock, + monkeypatch: pytest.MonkeyPatch, + capsys: pytest.CaptureFixture[str], +) -> None: + mock_client_class.return_value.database_path.return_value = ( + f"projects/{PROJECT_ID}/instances/{INSTANCE_ID}/databases/{DATABASE_ID}" + ) + monkeypatch.setattr( + "sys.argv", + [ + "database_add_split_points.py", + "--project-id", + PROJECT_ID, + "--instance-id", + INSTANCE_ID, + "--database-id", + DATABASE_ID, + ], + ) + + runpy.run_module( + "spanner_database_admin.database_add_split_points", run_name="__main__" + ) + + assert "Split Points Added: 3" in capsys.readouterr().out + + +@conftest.live_only +def test_add_split_points_live(capsys: pytest.CaptureFixture[str]) -> None: + admin = spanner_admin_database_v1.DatabaseAdminClient() + temp_db_id = f"example-spl-{uuid.uuid4().hex[:6]}" + db_path = admin.database_path( + conftest.LIVE_PROJECT_ID, conftest.LIVE_INSTANCE_ID, temp_db_id + ) + try: + create_database.create_database( + conftest.LIVE_PROJECT_ID, conftest.LIVE_INSTANCE_ID, temp_db_id + ) + capsys.readouterr() + database_add_split_points.add_split_points( + conftest.LIVE_PROJECT_ID, conftest.LIVE_INSTANCE_ID, temp_db_id + ) + out, err = capsys.readouterr() + assert err == "" + assert conftest.LIVE_PROJECT_ID not in out + assert "Split Points Added: 3" in out + finally: + try: + admin.drop_database(database=db_path) + except exceptions.NotFound: + pass From 3586e801909bcd5ff2990920e2f03857dc87ffb9 Mon Sep 17 00:00:00 2001 From: Jennifer Davis Date: Thu, 19 Nov 2026 04:44:37 +0000 Subject: [PATCH 2/2] style(spanner): use triple-quoted SQL strings in database_add_split_points Problem: multi-line SQL and DDL statements were written as adjacent string fragments. That style is easy to get wrong (a missing trailing space joins two SQL tokens) and is harder to read than the statement itself, and the samples in this set mixed it with triple-quoted SQL. Solution: write each multi-line statement as a single triple-quoted string, matching the layout already used by the other samples. Only whitespace between SQL tokens changes; the statements are otherwise identical. Files updated: - spanner/database_admin/src/spanner_database_admin/database_add_split_points.py --- .../spanner_database_admin/database_add_split_points.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/spanner/database_admin/src/spanner_database_admin/database_add_split_points.py b/spanner/database_admin/src/spanner_database_admin/database_add_split_points.py index ba13b87f86..6280d0f31a 100644 --- a/spanner/database_admin/src/spanner_database_admin/database_add_split_points.py +++ b/spanner/database_admin/src/spanner_database_admin/database_add_split_points.py @@ -32,10 +32,10 @@ def add_split_points(project_id: str, instance_id: str, database_id: str) -> Non index_name = "SingersByFirstLastName" ddl_request = spanner_admin_database_v1.UpdateDatabaseDdlRequest( database=database_path, - statements=[ - f"CREATE INDEX IF NOT EXISTS {index_name} " - "ON Singers(FirstName, LastName)" - ], + statements=[f""" + CREATE INDEX IF NOT EXISTS {index_name} + ON Singers(FirstName, LastName) + """], ) table_key = spanner_admin_database_v1.SplitPoints.Key(key_parts=["42"])