mirror of
https://github.com/GreptimeTeam/greptimedb.git
synced 2026-10-23 04:12:32 +00:00
jeremyhi
7df99f946e
* test: add repeatable metric snapshot S3 benchmark Signed-off-by: jeremyhi <fengjiachun@gmail.com> * test: use only existing CI S3 permissions in the metric snapshot benchmark The CI S3 user is not allowed GetBucketLocation or ListBucketMultipartUploads, so the bucket probe and the prefix cleanup failed with AccessDenied. Use only list, put, get and delete under the run prefix, as the object store WAL benchmark does, and probe S3 before allocating the EC2 runner. Signed-off-by: jeremyhi <fengjiachun@gmail.com> * test: scope metric snapshot inventory to the current round The full round's S3 inventory listed the whole run prefix, so it also counted the smoke snapshot. List only the round's snapshot prefix while cleanup still covers the run, and assert that the teardown's S3 cleanup step runs always() with the validated run prefix. Signed-off-by: jeremyhi <fengjiachun@gmail.com> * docs: record the AWS validation run of the metric snapshot benchmark Signed-off-by: jeremyhi <fengjiachun@gmail.com> --------- Signed-off-by: jeremyhi <fengjiachun@gmail.com>
102 lines
4.5 KiB
Python
102 lines
4.5 KiB
Python
# Copyright 2023 Greptime Team
|
|
#
|
|
# 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 copy
|
|
import importlib.util
|
|
from pathlib import Path
|
|
import unittest
|
|
|
|
spec = importlib.util.spec_from_file_location(
|
|
"fixture", Path(__file__).resolve().parents[1] / "metric-snapshot-fixture.py"
|
|
)
|
|
fixture = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(fixture)
|
|
|
|
|
|
class ValidatorTests(unittest.TestCase):
|
|
def records(self):
|
|
return {
|
|
"schema": {"column_schemas": [
|
|
{"name": "ts", "data_type": "TimestampMillisecond"},
|
|
*[{"name": f"tag_{i:03d}", "data_type": "String"} for i in range(10)],
|
|
{"name": "val", "data_type": "Float64"},
|
|
]},
|
|
"rows": [fixture.row(0, j, 50) for j in range(32)],
|
|
}
|
|
|
|
def test_full_tag_coverage_and_heterogeneous_schemas(self):
|
|
for per_group in (50, 10000):
|
|
variants = {tuple(fixture.tags(i, per_group)) for i in range(per_group)}
|
|
self.assertEqual(set().union(*map(set, variants)), set(range(298)))
|
|
self.assertGreater(len(variants), 1)
|
|
self.assertTrue(all(len(tags) == 10 for tags in variants))
|
|
|
|
def test_accepts_engine_column_order_with_matching_values(self):
|
|
records = self.records()
|
|
order = [*range(1, 11), 0, 11] # The engine returns tags, timestamp, value.
|
|
records["schema"]["column_schemas"] = [
|
|
records["schema"]["column_schemas"][index] for index in order
|
|
]
|
|
records["rows"] = [[values[index] for index in order] for values in records["rows"]]
|
|
fixture.check_records(0, 50, records)
|
|
records["rows"][1][10] = 2
|
|
with self.assertRaisesRegex(RuntimeError, "typed values"):
|
|
fixture.check_records(0, 50, records)
|
|
|
|
def test_rejects_column_type_and_membership_changes(self):
|
|
fixture.check_records(0, 50, self.records())
|
|
for mutation in ("type", "extra", "missing"):
|
|
records = self.records()
|
|
columns = records["schema"]["column_schemas"]
|
|
if mutation == "type":
|
|
columns[0]["data_type"] = "TimestampMicrosecond"
|
|
elif mutation == "extra":
|
|
columns.append({"name": "unexpected", "data_type": "String"})
|
|
else:
|
|
del columns[1]
|
|
with self.subTest(mutation=mutation), self.assertRaisesRegex(RuntimeError, "schema"):
|
|
fixture.check_records(0, 50, records)
|
|
|
|
def test_rejects_null_and_numeric_type_changes(self):
|
|
for value in ("", 0, False):
|
|
records = self.records()
|
|
records["rows"][0][-1] = value # Expected SQL NULL.
|
|
with self.subTest(value=value), self.assertRaisesRegex(RuntimeError, "typed values"):
|
|
fixture.check_records(0, 50, records)
|
|
records = self.records()
|
|
records["rows"][4][-1] = 1 # Numeric equality to 1.0 must not hide a type change.
|
|
with self.assertRaisesRegex(RuntimeError, "typed values"):
|
|
fixture.check_records(0, 50, records)
|
|
|
|
def test_source_comparison_requires_same_ddl_and_remapped_ids(self):
|
|
source = {"fixture": {"tables_per_group": 50}, "schema_sha256": "schema",
|
|
"data_sha256": "data", "ddl_sha256": "ddl",
|
|
"table_ids": {"m000000": 1024, "phy_00": 1025}}
|
|
target = copy.deepcopy(source)
|
|
target["table_ids"] = {"m000000": 1041, "phy_00": 1042}
|
|
fixture.compare_source(target, source)
|
|
self.assertEqual(target["remapped_table_ids"], 2)
|
|
for field in ("schema_sha256", "data_sha256", "ddl_sha256"):
|
|
changed = copy.deepcopy(target)
|
|
changed[field] = "changed"
|
|
with self.subTest(field=field), self.assertRaisesRegex(RuntimeError, field):
|
|
fixture.compare_source(changed, source)
|
|
target["table_ids"]["phy_00"] = 1025
|
|
with self.assertRaisesRegex(RuntimeError, "not all remapped"):
|
|
fixture.compare_source(target, source)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|