WIP, made tests for new organization method

This commit is contained in:
Alek Westover
2023-07-10 14:35:59 -04:00
parent 40e8a9bba7
commit 908de0af74
2 changed files with 53 additions and 256 deletions

View File

@@ -800,16 +800,16 @@ class NeonEnvBuilder:
bucket_region=region,
access_key=access_key,
secret_key=secret_key,
prefix_in_bucket=f"{self.remote_storage_prefix}/pageserver",
prefix_in_bucket=self.remote_storage_prefix,
)
if enable_remote_extensions:
self.ext_remote_storage = S3Storage(
bucket_name=bucket_name,
bucket_region=region,
bucket_name="neon-dev-extensions-us-east-2",
bucket_region="us-east-2",
access_key=access_key,
secret_key=secret_key,
prefix_in_bucket=f"{self.remote_storage_prefix}/ext",
prefix_in_bucket="5412197734",
)
def cleanup_local_storage(self):

View File

@@ -1,7 +1,5 @@
import json
import os
from contextlib import closing
from io import BytesIO
import pytest
from fixtures.log_helper import log
@@ -12,132 +10,14 @@ from fixtures.neon_fixtures import (
available_s3_storages,
)
from fixtures.pg_version import PgVersion
from fixtures.types import TenantId
NUM_EXT = 3
def control_file_content(owner, i):
output = f"""# mock {owner} extension{i}
comment = 'This is a mock extension'
default_version = '1.0'
module_pathname = '$libdir/test_ext{i}'
relocatable = true"""
return BytesIO(bytes(output, "utf-8"))
def sql_file_content():
output = """
CREATE FUNCTION test_ext_add(integer, integer) RETURNS integer
AS 'select $1 + $2;'
LANGUAGE SQL
IMMUTABLE
RETURNS NULL ON NULL INPUT;
"""
return BytesIO(bytes(output, "utf-8"))
def fake_library_content():
return BytesIO(bytes("\n111\n", "utf-8"))
# Prepare some mock extension files and upload them to the bucket
# returns a list of files that should be cleaned up after the test
def prepare_mock_ext_storage(
pg_version: PgVersion,
tenant_id: TenantId,
pg_bin: PgBin,
ext_remote_storage,
remote_storage_client,
):
bucket_prefix = ext_remote_storage.prefix_in_bucket
custom_prefix = str(tenant_id)
PUB_EXT_ROOT = f"v{pg_version}/share/extension"
PRIVATE_EXT_ROOT = f"v{pg_version}/{custom_prefix}/share/extension"
LOCAL_EXT_ROOT = f"pg_install/v{pg_version}/share/postgresql/extension"
PUB_LIB_ROOT = f"v{pg_version}/lib"
PRIVATE_LIB_ROOT = f"v{pg_version}/{custom_prefix}/lib"
LOCAL_LIB_ROOT = f"{pg_bin.pg_lib_dir}/postgresql"
log.info(
f"""
PUB_EXT_ROOT: {PUB_EXT_ROOT}
PRIVATE_EXT_ROOT: {PRIVATE_EXT_ROOT}
LOCAL_EXT_ROOT: {LOCAL_EXT_ROOT}
PUB_LIB_ROOT: {PUB_LIB_ROOT}
PRIVATE_LIB_ROOT: {PRIVATE_LIB_ROOT}
LOCAL_LIB_ROOT: {LOCAL_LIB_ROOT}
"""
)
cleanup_files = []
# Upload several test_ext{i}.control files to the bucket
for i in range(NUM_EXT):
public_remote_name = f"{bucket_prefix}/{PUB_EXT_ROOT}/test_ext{i}.control"
custom_remote_name = f"{bucket_prefix}/{PRIVATE_EXT_ROOT}/custom_ext{i}.control"
cleanup_files += [
f"{LOCAL_EXT_ROOT}/test_ext{i}.control",
f"{LOCAL_EXT_ROOT}/custom_ext{i}.control",
]
log.info(f"Uploading control file to {public_remote_name}")
remote_storage_client.upload_fileobj(
control_file_content("public", i), ext_remote_storage.bucket_name, public_remote_name
)
log.info(f"Uploading control file to {custom_remote_name}")
remote_storage_client.upload_fileobj(
control_file_content(str(tenant_id), i),
ext_remote_storage.bucket_name,
custom_remote_name,
)
# Upload SQL file for the extension we're going to create
sql_filename = "test_ext0--1.0.sql"
test_sql_public_remote_path = f"{bucket_prefix}/{PUB_EXT_ROOT}/{sql_filename}"
remote_storage_client.upload_fileobj(
sql_file_content(),
ext_remote_storage.bucket_name,
test_sql_public_remote_path,
)
cleanup_files += [f"{LOCAL_EXT_ROOT}/{sql_filename}"]
# upload some fake library files
for i in range(2):
public_remote_name = f"{bucket_prefix}/{PUB_LIB_ROOT}/test_lib{i}.so"
custom_remote_name = f"{bucket_prefix}/{PRIVATE_LIB_ROOT}/custom_lib{i}.so"
log.info(f"uploading fake library to {public_remote_name}")
remote_storage_client.upload_fileobj(
fake_library_content(),
ext_remote_storage.bucket_name,
public_remote_name,
)
log.info(f"uploading fake library to {custom_remote_name}")
remote_storage_client.upload_fileobj(
fake_library_content(),
ext_remote_storage.bucket_name,
custom_remote_name,
)
cleanup_files += [f"{LOCAL_LIB_ROOT}/test_lib{i}.so", f"{LOCAL_LIB_ROOT}/custom_lib{i}.so"]
return cleanup_files
# Generate mock extension files and upload them to the bucket.
#
# Then check that compute nodes can download them and use them
# to CREATE EXTENSION and LOAD 'library.so'
# Generate mock extension files and upload them to the mock bucket.
#
# NOTE: You must have appropriate AWS credentials to run REAL_S3 test.
# It may also be necessary to set the following environment variables:
# export AWS_ACCESS_KEY_ID='test'
# export AWS_SECRET_ACCESS_KEY='test'
# export AWS_SECURITY_TOKEN='test'
# export AWS_SESSION_TOKEN='test'
# It may also be necessary to set the following environment variables for MOCK_S3 test:
# export AWS_ACCESS_KEY_ID='test' # export AWS_SECRET_ACCESS_KEY='test'
# export AWS_SECURITY_TOKEN='test' # export AWS_SESSION_TOKEN='test'
# export AWS_DEFAULT_REGION='us-east-1'
@@ -146,11 +26,13 @@ def test_remote_extensions(
neon_env_builder: NeonEnvBuilder,
remote_storage_kind: RemoteStorageKind,
pg_version: PgVersion,
pg_bin: PgBin,
):
return None
# TODO: SKIP for now, infra not ready yet
if remote_storage_kind == RemoteStorageKind.REAL_S3:
return None
neon_env_builder.enable_remote_storage(
remote_storage_kind=remote_storage_kind,
remote_storage_kind=RemoteStorageKind.MOCK_S3,
test_name="test_remote_extensions",
enable_remote_extensions=True,
)
@@ -162,136 +44,51 @@ def test_remote_extensions(
assert env.ext_remote_storage is not None
assert env.remote_storage_client is not None
# Prepare some mock extension files and upload them to the bucket
cleanup_files = prepare_mock_ext_storage(
pg_version,
tenant_id,
pg_bin,
env.ext_remote_storage,
env.remote_storage_client,
)
# Start a compute node and check that it can download the extensions
# and use them to CREATE EXTENSION and LOAD 'library.so'
#
# This block is wrapped in a try/finally so that the downloaded files
# are cleaned up even if the test fails
try:
endpoint = env.endpoints.create_start(
"test_remote_extensions",
tenant_id=tenant_id,
remote_ext_config=env.ext_remote_storage.to_string(),
# config_lines=["log_min_messages=debug3"],
)
with closing(endpoint.connect()) as conn:
with conn.cursor() as cur:
# Test query: check that test_ext0 was successfully downloaded
cur.execute("SELECT * FROM pg_available_extensions")
all_extensions = [x[0] for x in cur.fetchall()]
log.info(all_extensions)
for i in range(NUM_EXT):
assert f"test_ext{i}" in all_extensions
assert f"custom_ext{i}" in all_extensions
cur.execute("CREATE EXTENSION test_ext0")
cur.execute("SELECT extname FROM pg_extension")
all_extensions = [x[0] for x in cur.fetchall()]
log.info(all_extensions)
assert "test_ext0" in all_extensions
# Try to load existing library file
try:
cur.execute("LOAD 'test_lib0.so'")
except Exception as e:
# expected to fail with
# could not load library ... test_ext.so: file too short
# because test_lib0.so is not real library file
log.info("LOAD test_lib0.so failed (expectedly): %s", e)
assert "file too short" in str(e)
# Try to load custom library file
try:
cur.execute("LOAD 'custom_lib0.so'")
except Exception as e:
# expected to fail with
# could not load library ... test_ext.so: file too short
# because test_lib0.so is not real library file
log.info("LOAD custom_lib0.so failed (expectedly): %s", e)
assert "file too short" in str(e)
# Try to load existing library file without .so extension
try:
cur.execute("LOAD 'test_lib1'")
except Exception as e:
# expected to fail with
# could not load library ... test_lib1.so: file too short
# because test_lib1.so is not real library file
log.info("LOAD test_lib1 failed (expectedly): %s", e)
assert "file too short" in str(e)
# Try to load non-existent library file
try:
cur.execute("LOAD 'test_lib_fail.so'")
except Exception as e:
# expected to fail because test_lib_fail.so is not found
log.info("LOAD test_lib_fail.so failed (expectedly): %s", e)
assert (
"""could not access file "test_lib_fail.so": No such file or directory"""
in str(e)
)
finally:
# this is important because if the files aren't cleaned up then the test can
# pass even without successfully downloading the files if a previous run (or
# run with different type of remote storage) of the test did download the
# files
for file in cleanup_files:
try:
os.remove(file)
log.info(f"Deleted {file}")
except FileNotFoundError:
log.info(f"{file} does not exist, so cannot be deleted")
"""
This tests against the actual infra for real S3
Note in particular that we don't need to set up a bucket (real or mock)
because we are testing the files already uploaded as part of CI/CD
"""
def test_remote_extensions_in_bucket(neon_env_builder: NeonEnvBuilder):
neon_env_builder.enable_remote_storage(
remote_storage_kind=RemoteStorageKind.REAL_S3,
test_name="test_remote_extensions_in_bucket",
enable_remote_extensions=False, # we don't enable remote extensions here; instead we use the real bucket
)
neon_env_builder.num_safekeepers = 3
env = neon_env_builder.init_start()
tenant_id, _ = env.neon_cli.create_tenant()
env.neon_cli.create_timeline("test_remote_extensions_in_bucket", tenant_id=tenant_id)
# For MOCK_S3 we upload some test files. for REAL_S3 we use the files created in CICD
if remote_storage_kind == RemoteStorageKind.MOCK_S3:
with open("test_runner/regress/data/extension_test/anon.tar.gz", "rb") as f:
env.remote_storage_client.upload_fileobj(
f.read(),
env.ext_remote_storage.bucket_name,
f"{pg_version}/{str(tenant_id)}/anon.tar.gz",
)
with open("test_runner/regress/data/extension_test/embedding.tar.gz", "rb") as f:
env.remote_storage_client.upload_fileobj(
f.read(),
env.ext_remote_storage.bucket_name,
f"{pg_version}/public/embedding.tar.gz",
)
# Start a compute node and check that it can download the extensions
# and use them to CREATE EXTENSION and LOAD 'library.so'
remote_ext_config = {
"bucket": "neon-dev-extensions-us-east-2",
"region": "us-east-2",
"endpoint": None,
"prefix": "5412197734", # build tag
}
# and use them to CREATE EXTENSION and LOAD
endpoint = env.endpoints.create_start(
"test_remote_extensions_in_bucket",
"test_remote_extensions",
tenant_id=tenant_id,
remote_ext_config=json.dumps(remote_ext_config),
# config_lines=["shared_preload_libraries='anon, neon'"],
remote_ext_config=env.ext_remote_storage.to_string(),
# config_lines=["log_min_messages=debug3"],
)
with closing(endpoint.connect()) as conn:
with conn.cursor() as cur:
try:
cur.execute("CREATE EXTENSION anon")
except Exception as e:
# Check that this errors, but for the right reason
# (that it is missing dependencies, not that files failed to download)
log.info(e)
assert 'required extension "pgcrypto" is not installed' in str(e)
# Check that appropriate control files were downloaded
cur.execute("SELECT * FROM pg_available_extensions")
all_extensions = [x[0] for x in cur.fetchall()]
log.info(all_extensions)
assert "anon" in all_extensions
assert "embedding" in all_extensions
# TODO: check that we don't have download custom extensions for other tenant ids
# TODO: not sure how private extension will work with REAL_S3 test. can we rig the tenant id?
log.info("Please MANUALLY cleanup any downloaded files")
# check that we can download public extension
cur.execute("CREATE EXTENSION embedding")
cur.execute("SELECT extname FROM pg_extension")
assert "embedding" in [x[0] for x in cur.fetchall()]
# check that we can download private extension
# TODO: this will fail locally because we don't have the required dependencies
cur.execute("CREATE EXTENSION anon")
cur.execute("SELECT extname FROM pg_extension")
assert "embedding" in [x[0] for x in cur.fetchall()]
# TODO: should we try libraries too?
# TODO: cleanup downloaded files in mock tests.