Add vanilla pg baseline tests (#1275)

This commit is contained in:
bojanserafimov
2022-02-15 13:44:22 -05:00
committed by GitHub
parent 5563ff123f
commit afb3342e46
8 changed files with 306 additions and 338 deletions

View File

@@ -2,8 +2,13 @@ from contextlib import closing
from fixtures.zenith_fixtures import ZenithEnv
from fixtures.log_helper import log
from fixtures.benchmark_fixture import MetricReport, ZenithBenchmarker
from fixtures.compare_fixtures import PgCompare, VanillaCompare, ZenithCompare
pytest_plugins = ("fixtures.zenith_fixtures", "fixtures.benchmark_fixture")
pytest_plugins = (
"fixtures.zenith_fixtures",
"fixtures.benchmark_fixture",
"fixtures.compare_fixtures",
)
#
@@ -16,47 +21,19 @@ pytest_plugins = ("fixtures.zenith_fixtures", "fixtures.benchmark_fixture")
# 3. Disk space used
# 4. Peak memory usage
#
def test_bulk_insert(zenith_simple_env: ZenithEnv, zenbenchmark: ZenithBenchmarker):
env = zenith_simple_env
# Create a branch for us
env.zenith_cli(["branch", "test_bulk_insert", "empty"])
pg = env.postgres.create_start('test_bulk_insert')
log.info("postgres is running on 'test_bulk_insert' branch")
# Open a connection directly to the page server that we'll use to force
# flushing the layers to disk
psconn = env.pageserver.connect()
pscur = psconn.cursor()
def test_bulk_insert(zenith_with_baseline: PgCompare):
env = zenith_with_baseline
# Get the timeline ID of our branch. We need it for the 'do_gc' command
with closing(pg.connect()) as conn:
with closing(env.pg.connect()) as conn:
with conn.cursor() as cur:
cur.execute("SHOW zenith.zenith_timeline")
timeline = cur.fetchone()[0]
cur.execute("create table huge (i int, j int);")
# Run INSERT, recording the time and I/O it takes
with zenbenchmark.record_pageserver_writes(env.pageserver, 'pageserver_writes'):
with zenbenchmark.record_duration('insert'):
with env.record_pageserver_writes('pageserver_writes'):
with env.record_duration('insert'):
cur.execute("insert into huge values (generate_series(1, 5000000), 0);")
env.flush()
# Flush the layers from memory to disk. This is included in the reported
# time and I/O
pscur.execute(f"do_gc {env.initial_tenant} {timeline} 0")
# Record peak memory usage
zenbenchmark.record("peak_mem",
zenbenchmark.get_peak_mem(env.pageserver) / 1024,
'MB',
report=MetricReport.LOWER_IS_BETTER)
# Report disk space used by the repository
timeline_size = zenbenchmark.get_timeline_size(env.repo_dir,
env.initial_tenant,
timeline)
zenbenchmark.record('size',
timeline_size / (1024 * 1024),
'MB',
report=MetricReport.LOWER_IS_BETTER)
env.report_peak_memory_use()
env.report_size()