mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-06 21:12:55 +00:00
test_lazy_startup: fix statement_timeout setting (#6654)
## Problem Test `test_lazy_startup` is flaky[0], sometimes (pretty frequently) it fails with `canceling statement due to statement timeout`. - [0] https://neon-github-public-dev.s3.amazonaws.com/reports/main/7803316870/index.html#suites/355b1a7a5b1e740b23ea53728913b4fa/7263782d30986c50/history ## Summary of changes - Fix setting `statement_timeout` setting by reusing a connection for all queries. - Also fix label (`lazy`, `eager`) assignment - Split `test_lazy_startup` into two, by `slru` laziness and make tests smaller
This commit is contained in:
Alexander Bayandin
committed by
GitHub
GitHub
parent
f4cc7cae14
commit
9f75da7c0a
@@ -26,86 +26,81 @@ from fixtures.neon_fixtures import NeonEnvBuilder
|
||||
# apply during config step, like more users, databases, or extensions. By default
|
||||
# we load extensions 'neon,pg_stat_statements,timescaledb,pg_cron', but in this
|
||||
# test we only load neon.
|
||||
@pytest.mark.timeout(1000)
|
||||
def test_lazy_startup(neon_env_builder: NeonEnvBuilder, zenbenchmark: NeonBenchmarker):
|
||||
@pytest.mark.timeout(1800)
|
||||
@pytest.mark.parametrize("slru", ["lazy", "eager"])
|
||||
def test_lazy_startup(slru: str, neon_env_builder: NeonEnvBuilder, zenbenchmark: NeonBenchmarker):
|
||||
neon_env_builder.num_safekeepers = 3
|
||||
env = neon_env_builder.init_start()
|
||||
|
||||
lazy_tenant, _ = env.neon_cli.create_tenant(
|
||||
lazy_slru_download = "true" if slru == "lazy" else "false"
|
||||
tenant, _ = env.neon_cli.create_tenant(
|
||||
conf={
|
||||
"lazy_slru_download": "true",
|
||||
"lazy_slru_download": lazy_slru_download,
|
||||
}
|
||||
)
|
||||
eager_tenant, _ = env.neon_cli.create_tenant(
|
||||
conf={
|
||||
"lazy_slru_download": "false",
|
||||
}
|
||||
)
|
||||
tenants = [lazy_tenant, eager_tenant]
|
||||
slru = "lazy"
|
||||
for tenant in tenants:
|
||||
endpoint = env.endpoints.create_start("main", tenant_id=tenant)
|
||||
endpoint.safe_psql("CREATE TABLE t (pk integer PRIMARY KEY, x integer)")
|
||||
endpoint.safe_psql("ALTER TABLE t SET (autovacuum_enabled = false)")
|
||||
endpoint.safe_psql("INSERT INTO t VALUES (1, 0)")
|
||||
endpoint.safe_psql(
|
||||
"""
|
||||
CREATE PROCEDURE updating() as
|
||||
$$
|
||||
DECLARE
|
||||
i integer;
|
||||
BEGIN
|
||||
FOR i IN 1..10000000 LOOP
|
||||
UPDATE t SET x = x + 1 WHERE pk=1;
|
||||
COMMIT;
|
||||
END LOOP;
|
||||
END
|
||||
$$ LANGUAGE plpgsql
|
||||
"""
|
||||
)
|
||||
endpoint.safe_psql("SET statement_timeout=0")
|
||||
endpoint.safe_psql("call updating()")
|
||||
|
||||
endpoint = env.endpoints.create_start("main", tenant_id=tenant)
|
||||
with endpoint.cursor() as cur:
|
||||
cur.execute("CREATE TABLE t (pk integer PRIMARY KEY, x integer)")
|
||||
cur.execute("ALTER TABLE t SET (autovacuum_enabled = false)")
|
||||
cur.execute("INSERT INTO t VALUES (1, 0)")
|
||||
cur.execute(
|
||||
"""
|
||||
CREATE PROCEDURE updating() as
|
||||
$$
|
||||
DECLARE
|
||||
i integer;
|
||||
BEGIN
|
||||
FOR i IN 1..1000000 LOOP
|
||||
UPDATE t SET x = x + 1 WHERE pk=1;
|
||||
COMMIT;
|
||||
END LOOP;
|
||||
END
|
||||
$$ LANGUAGE plpgsql
|
||||
"""
|
||||
)
|
||||
cur.execute("SET statement_timeout=0")
|
||||
cur.execute("call updating()")
|
||||
|
||||
endpoint.stop()
|
||||
|
||||
# We do two iterations so we can see if the second startup is faster. It should
|
||||
# be because the compute node should already be configured with roles, databases,
|
||||
# extensions, etc from the first run.
|
||||
for i in range(2):
|
||||
# Start
|
||||
with zenbenchmark.record_duration(f"{slru}_{i}_start"):
|
||||
endpoint.start()
|
||||
|
||||
with zenbenchmark.record_duration(f"{slru}_{i}_select"):
|
||||
sum = endpoint.safe_psql("select sum(x) from t")[0][0]
|
||||
assert sum == 1000000
|
||||
|
||||
# Get metrics
|
||||
metrics = requests.get(f"http://localhost:{endpoint.http_port}/metrics.json").json()
|
||||
durations = {
|
||||
"wait_for_spec_ms": f"{slru}_{i}_wait_for_spec",
|
||||
"sync_safekeepers_ms": f"{slru}_{i}_sync_safekeepers",
|
||||
"sync_sk_check_ms": f"{slru}_{i}_sync_sk_check",
|
||||
"basebackup_ms": f"{slru}_{i}_basebackup",
|
||||
"start_postgres_ms": f"{slru}_{i}_start_postgres",
|
||||
"config_ms": f"{slru}_{i}_config",
|
||||
"total_startup_ms": f"{slru}_{i}_total_startup",
|
||||
}
|
||||
for key, name in durations.items():
|
||||
value = metrics[key]
|
||||
zenbenchmark.record(name, value, "ms", report=MetricReport.LOWER_IS_BETTER)
|
||||
|
||||
basebackup_bytes = metrics["basebackup_bytes"]
|
||||
zenbenchmark.record(
|
||||
f"{slru}_{i}_basebackup_bytes",
|
||||
basebackup_bytes,
|
||||
"bytes",
|
||||
report=MetricReport.LOWER_IS_BETTER,
|
||||
)
|
||||
|
||||
# Stop so we can restart
|
||||
endpoint.stop()
|
||||
|
||||
# We do two iterations so we can see if the second startup is faster. It should
|
||||
# be because the compute node should already be configured with roles, databases,
|
||||
# extensions, etc from the first run.
|
||||
for i in range(2):
|
||||
# Start
|
||||
with zenbenchmark.record_duration(f"{slru}_{i}_start"):
|
||||
endpoint.start()
|
||||
|
||||
with zenbenchmark.record_duration(f"{slru}_{i}_select"):
|
||||
sum = endpoint.safe_psql("select sum(x) from t")[0][0]
|
||||
assert sum == 10000000
|
||||
|
||||
# Get metrics
|
||||
metrics = requests.get(f"http://localhost:{endpoint.http_port}/metrics.json").json()
|
||||
durations = {
|
||||
"wait_for_spec_ms": f"{slru}_{i}_wait_for_spec",
|
||||
"sync_safekeepers_ms": f"{slru}_{i}_sync_safekeepers",
|
||||
"sync_sk_check_ms": f"{slru}_{i}_sync_sk_check",
|
||||
"basebackup_ms": f"{slru}_{i}_basebackup",
|
||||
"start_postgres_ms": f"{slru}_{i}_start_postgres",
|
||||
"config_ms": f"{slru}_{i}_config",
|
||||
"total_startup_ms": f"{slru}_{i}_total_startup",
|
||||
}
|
||||
for key, name in durations.items():
|
||||
value = metrics[key]
|
||||
zenbenchmark.record(name, value, "ms", report=MetricReport.LOWER_IS_BETTER)
|
||||
|
||||
basebackup_bytes = metrics["basebackup_bytes"]
|
||||
zenbenchmark.record(
|
||||
f"{slru}_{i}_basebackup_bytes",
|
||||
basebackup_bytes,
|
||||
"bytes",
|
||||
report=MetricReport.LOWER_IS_BETTER,
|
||||
)
|
||||
|
||||
# Stop so we can restart
|
||||
endpoint.stop()
|
||||
|
||||
# Imitate optimizations that console would do for the second start
|
||||
endpoint.respec(skip_pg_catalog_updates=True)
|
||||
slru = "eager"
|
||||
# Imitate optimizations that console would do for the second start
|
||||
endpoint.respec(skip_pg_catalog_updates=True)
|
||||
|
||||
Reference in New Issue
Block a user