mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-08 22:12:56 +00:00
e1b4d96b5b
## Problem
After commit [840abe3954] (store AUX files
as deltas) we avoid quadratic growth of storage size when storing LR
snapshots but get quadratic slowdown of reconstruct time.
As a result storing 70k snapshots at my local Neon instance took more
than 3 hours and starting node (creation of basecbackup): ~10 minutes.
In prod 70k AUX files cause increase of startup time to 40 minutes:
https://neondb.slack.com/archives/C03F5SM1N02/p1708513010480179
## Summary of changes
Enforce storing full AUX directory (some analog of FPI) each 1024 files.
Time of creation 70k snapshots is reduced to 6 minutes and startup time
- to 1.5 minutes (100 seconds).
## Checklist before requesting a review
- [ ] I have performed a self-review of my code.
- [ ] If it is a core feature, I have added thorough tests.
- [ ] Do we need to implement analytics? if so did you add the relevant
metrics to the dashboard?
- [ ] If this PR requires public announcement, mark it with
/release-notes label and add several sentences in this section.
## Checklist before merging
- [ ] Do not forget to reformat commit message to not include the above
checklist
---------
Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
68 lines
2.4 KiB
Python
68 lines
2.4 KiB
Python
import os
|
|
import time
|
|
|
|
import pytest
|
|
from fixtures.log_helper import log
|
|
from fixtures.neon_fixtures import (
|
|
NeonEnv,
|
|
logical_replication_sync,
|
|
wait_for_last_flush_lsn,
|
|
)
|
|
from fixtures.pg_version import PgVersion
|
|
|
|
|
|
def test_layer_bloating(neon_simple_env: NeonEnv, vanilla_pg):
|
|
env = neon_simple_env
|
|
|
|
if env.pg_version != PgVersion.V16:
|
|
pytest.skip("pg_log_standby_snapshot() function is available only in PG16")
|
|
|
|
timeline = env.neon_cli.create_branch("test_logical_replication", "empty")
|
|
endpoint = env.endpoints.create_start(
|
|
"test_logical_replication", config_lines=["log_statement=all"]
|
|
)
|
|
|
|
pg_conn = endpoint.connect()
|
|
cur = pg_conn.cursor()
|
|
|
|
# create table...
|
|
cur.execute("create table t(pk integer primary key)")
|
|
cur.execute("create publication pub1 for table t")
|
|
# Create slot to hold WAL
|
|
cur.execute("select pg_create_logical_replication_slot('my_slot', 'pgoutput')")
|
|
|
|
# now start subscriber
|
|
vanilla_pg.start()
|
|
vanilla_pg.safe_psql("create table t(pk integer primary key)")
|
|
|
|
connstr = endpoint.connstr().replace("'", "''")
|
|
log.info(f"ep connstr is {endpoint.connstr()}, subscriber connstr {vanilla_pg.connstr()}")
|
|
vanilla_pg.safe_psql(f"create subscription sub1 connection '{connstr}' publication pub1")
|
|
|
|
cur.execute(
|
|
"""create or replace function create_snapshots(n integer) returns void as $$
|
|
declare
|
|
i integer;
|
|
begin
|
|
for i in 1..n loop
|
|
perform pg_log_standby_snapshot();
|
|
end loop;
|
|
end; $$ language plpgsql"""
|
|
)
|
|
cur.execute("set statement_timeout=0")
|
|
cur.execute("select create_snapshots(10000)")
|
|
# Wait logical replication to sync
|
|
logical_replication_sync(vanilla_pg, endpoint)
|
|
wait_for_last_flush_lsn(env, endpoint, env.initial_tenant, timeline)
|
|
time.sleep(10)
|
|
|
|
# Check layer file sizes
|
|
timeline_path = "{}/tenants/{}/timelines/{}/".format(
|
|
env.pageserver.workdir, env.initial_tenant, timeline
|
|
)
|
|
log.info(f"Check {timeline_path}")
|
|
for filename in os.listdir(timeline_path):
|
|
if filename.startswith("00000"):
|
|
log.info(f"layer {filename} size is {os.path.getsize(timeline_path + filename)}")
|
|
assert os.path.getsize(timeline_path + filename) < 512_000_000
|