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

@@ -2,9 +2,14 @@ import os
from contextlib import closing
from fixtures.benchmark_fixture import MetricReport
from fixtures.zenith_fixtures import ZenithEnv
from fixtures.compare_fixtures import PgCompare, VanillaCompare, ZenithCompare
from fixtures.log_helper import log
pytest_plugins = ("fixtures.zenith_fixtures", "fixtures.benchmark_fixture")
pytest_plugins = (
"fixtures.zenith_fixtures",
"fixtures.benchmark_fixture",
"fixtures.compare_fixtures",
)
#
@@ -12,24 +17,11 @@ pytest_plugins = ("fixtures.zenith_fixtures", "fixtures.benchmark_fixture")
# As of this writing, we're duplicate those giant WAL records for each page,
# which makes the delta layer about 32x larger than it needs to be.
#
def test_gist_buffering_build(zenith_simple_env: ZenithEnv, zenbenchmark):
env = zenith_simple_env
# Create a branch for us
env.zenith_cli(["branch", "test_gist_buffering_build", "empty"])
def test_gist_buffering_build(zenith_with_baseline: PgCompare):
env = zenith_with_baseline
pg = env.postgres.create_start('test_gist_buffering_build')
log.info("postgres is running on 'test_gist_buffering_build' 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()
# 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]
# Create test table.
cur.execute("create table gist_point_tbl(id int4, p point)")
@@ -38,27 +30,12 @@ def test_gist_buffering_build(zenith_simple_env: ZenithEnv, zenbenchmark):
)
# Build the index.
with zenbenchmark.record_pageserver_writes(env.pageserver, 'pageserver_writes'):
with zenbenchmark.record_duration('build'):
with env.record_pageserver_writes('pageserver_writes'):
with env.record_duration('build'):
cur.execute(
"create index gist_pointidx2 on gist_point_tbl using gist(p) with (buffering = on)"
)
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} 1000000")
# 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()