rust/neon
1
0
Fork 0
mirror of https://github.com/neondatabase/neon.git synced 2026-05-28 10:30:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add vanilla pg baseline tests (#1275)

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

77
test_runner/performance/test_copy.py
View File

@@ -2,10 +2,15 @@ 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
from io import BufferedReader, RawIOBase
from itertools import repeat
pytest_plugins = ("fixtures.zenith_fixtures", "fixtures.benchmark_fixture")
pytest_plugins = (
"fixtures.zenith_fixtures",
"fixtures.benchmark_fixture",
"fixtures.compare_fixtures",
)
class CopyTestData(RawIOBase):
@@ -42,77 +47,41 @@ def copy_test_data(rows: int):
#
# COPY performance tests.
#
def test_copy(zenith_simple_env: ZenithEnv, zenbenchmark: ZenithBenchmarker):
env = zenith_simple_env
# Create a branch for us
env.zenith_cli(["branch", "test_copy", "empty"])
pg = env.postgres.create_start('test_copy')
log.info("postgres is running on 'test_copy' 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_copy(zenith_with_baseline: PgCompare):
env = zenith_with_baseline
# Get the timeline ID of our branch. We need it for the pageserver 'checkpoint' 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 copytest (i int, t text);")
# Load data with COPY, recording the time and I/O it takes.
#
# Since there's no data in the table previously, this extends it.
with zenbenchmark.record_pageserver_writes(env.pageserver,
'copy_extend_pageserver_writes'):
with zenbenchmark.record_duration('copy_extend'):
with env.record_pageserver_writes('copy_extend_pageserver_writes'):
with env.record_duration('copy_extend'):
cur.copy_from(copy_test_data(1000000), 'copytest')
# Flush the layers from memory to disk. This is included in the reported
# time and I/O
pscur.execute(f"checkpoint {env.initial_tenant} {timeline}")
env.flush()
# Delete most rows, and VACUUM to make the space available for reuse.
with zenbenchmark.record_pageserver_writes(env.pageserver, 'delete_pageserver_writes'):
with zenbenchmark.record_duration('delete'):
with env.record_pageserver_writes('delete_pageserver_writes'):
with env.record_duration('delete'):
cur.execute("delete from copytest where i % 100 <> 0;")
# Flush the layers from memory to disk. This is included in the reported
# time and I/O
pscur.execute(f"checkpoint {env.initial_tenant} {timeline}")
env.flush()
with zenbenchmark.record_pageserver_writes(env.pageserver, 'vacuum_pageserver_writes'):
with zenbenchmark.record_duration('vacuum'):
with env.record_pageserver_writes('vacuum_pageserver_writes'):
with env.record_duration('vacuum'):
cur.execute("vacuum copytest")
# Flush the layers from memory to disk. This is included in the reported
# time and I/O
pscur.execute(f"checkpoint {env.initial_tenant} {timeline}")
env.flush()
# Load data into the table again. This time, this will use the space free'd
# by the VACUUM.
#
# This will also clear all the VM bits.
with zenbenchmark.record_pageserver_writes(env.pageserver,
'copy_reuse_pageserver_writes'):
with zenbenchmark.record_duration('copy_reuse'):
with env.record_pageserver_writes('copy_reuse_pageserver_writes'):
with env.record_duration('copy_reuse'):
cur.copy_from(copy_test_data(1000000), 'copytest')
env.flush()
# Flush the layers from memory to disk. This is included in the reported
# time and I/O
pscur.execute(f"checkpoint {env.initial_tenant} {timeline}")
# 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()