Files
neon/test_runner/regress/test_parallel_copy.py
Heikki Linnakangas 53f438a8a8 Rename "Postgres nodes" in control_plane to endpoints.
We use the term "endpoint" in for compute Postgres nodes in the web UI
and user-facing documentation now. Adjust the nomenclature in the code.

This changes the name of the "neon_local pg" command to "neon_local
endpoint". Also adjust names of classes, variables etc. in the python
tests accordingly.

This also changes the directory structure so that endpoints are now
stored in:

    .neon/endpoints/<endpoint id>

instead of:

    .neon/pgdatadirs/tenants/<tenant_id>/<endpoint (node) name>

The tenant ID is no longer part of the path. That means that you
cannot have two endpoints with the same name/ID in two different
tenants anymore. That's consistent with how we treat endpoints in the
real control plane and proxy: the endpoint ID must be globally unique.
2023-04-13 14:34:29 +03:00

56 lines
1.8 KiB
Python

import asyncio
from io import BytesIO
from fixtures.log_helper import log
from fixtures.neon_fixtures import Endpoint, NeonEnv
async def repeat_bytes(buf, repetitions: int):
for i in range(repetitions):
yield buf
async def copy_test_data_to_table(endpoint: Endpoint, worker_id: int, table_name: str):
buf = BytesIO()
for i in range(1000):
buf.write(
f"{i}\tLoaded by worker {worker_id}. Long string to consume some space.\n".encode()
)
buf.seek(0)
copy_input = repeat_bytes(buf.read(), 5000)
pg_conn = await endpoint.connect_async()
# PgProtocol.connect_async sets statement_timeout to 2 minutes.
# That's not enough for this test, on a slow system in debug mode.
await pg_conn.execute("SET statement_timeout='300s'")
await pg_conn.copy_to_table(table_name, source=copy_input)
async def parallel_load_same_table(endpoint: Endpoint, n_parallel: int):
workers = []
for worker_id in range(n_parallel):
worker = copy_test_data_to_table(endpoint, worker_id, "copytest")
workers.append(asyncio.create_task(worker))
# await all workers
await asyncio.gather(*workers)
# Load data into one table with COPY TO from 5 parallel connections
def test_parallel_copy(neon_simple_env: NeonEnv, n_parallel=5):
env = neon_simple_env
env.neon_cli.create_branch("test_parallel_copy", "empty")
endpoint = env.endpoints.create_start("test_parallel_copy")
log.info("postgres is running on 'test_parallel_copy' branch")
# Create test table
conn = endpoint.connect()
cur = conn.cursor()
cur.execute("CREATE TABLE copytest (i int, t text)")
# Run COPY TO to load the table with parallel connections.
asyncio.run(parallel_load_same_table(endpoint, n_parallel))