Skip to content

[Perfstress][Storage] Added Blobs perf tests #15833

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 16 commits into from
Feb 10, 2021
Merged
Show file tree
Hide file tree
Changes from 10 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------

import os
import uuid

from azure_devtools.perfstress_tests import PerfStressTest

from azure.storage.blob import BlockBlobService

class _LegacyServiceTest(PerfStressTest):
service_client = None
async_service_client = None

def __init__(self, arguments):
super().__init__(arguments)
connection_string = self.get_from_env("AZURE_STORAGE_CONNECTION_STRING")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

another minor nit: could we mention that its fetching the connection string from an env variable in the README?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great catch - forgot all about that!

if not _LegacyServiceTest.service_client or self.args.no_client_share:
_LegacyServiceTest.service_client = BlockBlobService(connection_string=connection_string)
_LegacyServiceTest.service_client.MAX_SINGLE_PUT_SIZE = self.args.max_put_size
_LegacyServiceTest.service_client.MAX_BLOCK_SIZE = self.args.max_block_size
_LegacyServiceTest.service_client.MIN_LARGE_BLOCK_UPLOAD_THRESHOLD = self.args.buffer_threshold
self.async_service_client = None
self.service_client = _LegacyServiceTest.service_client

@staticmethod
def add_arguments(parser):
super(_LegacyServiceTest, _LegacyServiceTest).add_arguments(parser)
parser.add_argument('--max-put-size', nargs='?', type=int, help='Maximum size of data uploading in single HTTP PUT. Defaults to 64*1024*1024', default=64*1024*1024)
parser.add_argument('--max-block-size', nargs='?', type=int, help='Maximum size of data in a block within a blob. Defaults to 4*1024*1024', default=4*1024*1024)
parser.add_argument('--buffer-threshold', nargs='?', type=int, help='Minimum block size to prevent full block buffering. Defaults to 4*1024*1024+1', default=4*1024*1024+1)
parser.add_argument('-c', '--max-concurrency', nargs='?', type=int, help='Maximum number of concurrent threads used for data transfer. Defaults to 1', default=1)
parser.add_argument('-s', '--size', nargs='?', type=int, help='Size of data to transfer. Default is 10240.', default=10240)
parser.add_argument('--no-client-share', action='store_true', help='Create one ServiceClient per test instance. Default is to share a single ServiceClient.', default=False)


class _LegacyContainerTest(_LegacyServiceTest):
container_name = "perfstress-legacy-" + str(uuid.uuid4())

def __init__(self, arguments):
super().__init__(arguments)

async def global_setup(self):
await super().global_setup()
self.service_client.create_container(self.container_name)

async def global_cleanup(self):
self.service_client.delete_container(self.container_name)
await super().global_cleanup()
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------

from azure_devtools.perfstress_tests import get_random_bytes, WriteStream

from ._test_base_legacy import _LegacyContainerTest


class LegacyDownloadTest(_LegacyContainerTest):
def __init__(self, arguments):
super().__init__(arguments)
self.blob_name = "downloadtest"
self.download_stream = WriteStream()

async def global_setup(self):
await super().global_setup()
data = get_random_bytes(self.args.size)
self.service_client.create_blob_from_bytes(
container_name=self.container_name,
blob_name=self.blob_name,
blob=data)

def reset_sync(self):
self.download_stream = WriteStream()

def run_sync(self):
self.service_client.get_blob_to_stream(
container_name=self.container_name,
blob_name=self.blob_name,
stream=self.download_stream,
max_connections=self.args.max_concurrency)

async def run_async(self):
raise NotImplementedError("Async not supported for legacy T1 tests.")
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------

from ._test_base_legacy import _LegacyContainerTest


class LegacyListBlobsTest(_LegacyContainerTest):

async def global_setup(self):
await super().global_setup()
for i in range(self.args.num_blobs):
self.service_client.create_blob_from_bytes(
container_name=self.container_name,
blob_name="listtest" + str(i),
blob=b"")

def run_sync(self):
for _ in self.service_client.list_blobs(container_name=self.container_name):
pass

async def run_async(self):
raise NotImplementedError("Async not supported for legacy T1 tests.")

@staticmethod
def add_arguments(parser):
super(LegacyListBlobsTest, LegacyListBlobsTest).add_arguments(parser)
parser.add_argument('--num-blobs', nargs='?', type=int, help='Number of blobs to list. Defaults to 100', default=100)
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
azure-storage-blob==2.1.0
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------

import uuid

from azure_devtools.perfstress_tests import RandomStream

from ._test_base_legacy import _LegacyContainerTest


class LegacyUploadTest(_LegacyContainerTest):
def __init__(self, arguments):
super().__init__(arguments)
self.blob_name = "blobtest-" + str(uuid.uuid4())
self.upload_stream = RandomStream(self.args.size)

def reset_sync(self):
self.upload_stream = RandomStream(self.args.size)

def run_sync(self):
self.service_client.create_blob_from_stream(
container_name=self.container_name,
blob_name=self.blob_name,
stream=self.upload_stream,
max_connections=self.args.max_concurrency)

async def run_async(self):
raise NotImplementedError("Async not supported for legacy T1 tests.")
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------

import uuid

from azure_devtools.perfstress_tests import get_random_bytes

from ._test_base_legacy import _LegacyContainerTest


class LegacyUploadBlockTest(_LegacyContainerTest):
def __init__(self, arguments):
super().__init__(arguments)
self.blob_name = "blobblocktest-" + str(uuid.uuid4())
self.block_id = str(uuid.uuid4())
self.data = get_random_bytes(self.args.size)

def run_sync(self):
self.service_client.put_block(
container_name=self.container_name,
blob_name=self.blob_name,
block=self.data,
block_id=self.block_id)

async def run_async(self):
raise NotImplementedError("Async not supported for legacy T1 tests.")
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------

import os
import tempfile
import uuid

from azure_devtools.perfstress_tests import get_random_bytes

from ._test_base_legacy import _LegacyContainerTest


class LegacyUploadFromFileTest(_LegacyContainerTest):
temp_file = None

def __init__(self, arguments):
super().__init__(arguments)
self.blob_name = "containertest-" + str(uuid.uuid4())

async def global_setup(self):
await super().global_setup()
data = get_random_bytes(self.args.size)
with tempfile.NamedTemporaryFile(delete=False) as temp_file:
LegacyUploadFromFileTest.temp_file = temp_file.name
temp_file.write(data)

async def global_cleanup(self):
os.remove(LegacyUploadFromFileTest.temp_file)
await super().global_cleanup()

def run_sync(self):
self.service_client.create_blob_from_path(
container_name=self.container_name,
blob_name=self.blob_name,
file_path=LegacyUploadFromFileTest.temp_file,
max_connections=self.args.max_concurrency)

async def run_async(self):
raise NotImplementedError("Async not supported for legacy T1 tests.")
Empty file.
Original file line number Diff line number Diff line change
@@ -0,0 +1,78 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------

import os
import uuid

from azure_devtools.perfstress_tests import PerfStressTest

from azure.core.exceptions import ResourceNotFoundError
from azure.storage.blob import BlobServiceClient as SyncBlobServiceClient
from azure.storage.blob.aio import BlobServiceClient as AsyncBlobServiceClient


class _ServiceTest(PerfStressTest):
service_client = None
async_service_client = None

def __init__(self, arguments):
super().__init__(arguments)
connection_string = self.get_from_env("AZURE_STORAGE_CONNECTION_STRING")
kwargs = {}
kwargs['max_single_put_size'] = self.args.max_put_size
kwargs['max_block_size'] = self.args.max_block_size
kwargs['min_large_block_upload_threshold'] = self.args.buffer_threshold
if not _ServiceTest.service_client or self.args.no_client_share:
_ServiceTest.service_client = SyncBlobServiceClient.from_connection_string(conn_str=connection_string, **kwargs)
_ServiceTest.async_service_client = AsyncBlobServiceClient.from_connection_string(conn_str=connection_string, **kwargs)
self.service_client = _ServiceTest.service_client
self.async_service_client =_ServiceTest.async_service_client

async def close(self):
await self.async_service_client.close()
await super().close()

@staticmethod
def add_arguments(parser):
super(_ServiceTest, _ServiceTest).add_arguments(parser)
parser.add_argument('--max-put-size', nargs='?', type=int, help='Maximum size of data uploading in single HTTP PUT. Defaults to 64*1024*1024', default=64*1024*1024)
parser.add_argument('--max-block-size', nargs='?', type=int, help='Maximum size of data in a block within a blob. Defaults to 4*1024*1024', default=4*1024*1024)
parser.add_argument('--buffer-threshold', nargs='?', type=int, help='Minimum block size to prevent full block buffering. Defaults to 4*1024*1024+1', default=4*1024*1024+1)
parser.add_argument('-c', '--max-concurrency', nargs='?', type=int, help='Maximum number of concurrent threads used for data transfer. Defaults to 1', default=1)
parser.add_argument('-s', '--size', nargs='?', type=int, help='Size of data to transfer. Default is 10240.', default=10240)
parser.add_argument('--no-client-share', action='store_true', help='Create one ServiceClient per test instance. Default is to share a single ServiceClient.', default=False)


class _ContainerTest(_ServiceTest):
container_name = "perfstress-" + str(uuid.uuid4())

def __init__(self, arguments):
super().__init__(arguments)
self.container_client = self.service_client.get_container_client(self.container_name)
self.async_container_client = self.async_service_client.get_container_client(self.container_name)

async def global_setup(self):
await super().global_setup()
await self.async_container_client.create_container()

async def global_cleanup(self):
await self.async_container_client.delete_container()
await super().global_cleanup()

async def close(self):
await self.async_container_client.close()
await super().close()


class _BlobTest(_ContainerTest):
def __init__(self, arguments):
super().__init__(arguments)
blob_name = "blobtest-" + str(uuid.uuid4())
self.blob_client = self.container_client.get_blob_client(blob_name)
self.async_blob_client = self.async_container_client.get_blob_client(blob_name)

async def close(self):
await self.async_blob_client.close()
await super().close()
40 changes: 40 additions & 0 deletions sdk/storage/azure-storage-blob/tests/perfstress_tests/download.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------

from azure_devtools.perfstress_tests import get_random_bytes, WriteStream

from ._test_base import _ContainerTest


class DownloadTest(_ContainerTest):
def __init__(self, arguments):
super().__init__(arguments)
blob_name = "downloadtest"
self.blob_client = self.container_client.get_blob_client(blob_name)
self.async_blob_client = self.async_container_client.get_blob_client(blob_name)
self.download_stream = WriteStream()

async def global_setup(self):
await super().global_setup()
data = get_random_bytes(self.args.size)
await self.async_blob_client.upload_blob(data)

def reset_sync(self):
self.download_stream = WriteStream()

async def reset_async(self):
self.download_stream = WriteStream()

def run_sync(self):
stream = self.blob_client.download_blob(max_concurrency=self.args.max_concurrency)
stream.readinto(self.download_stream)

async def run_async(self):
stream = await self.async_blob_client.download_blob(max_concurrency=self.args.max_concurrency)
await stream.readinto(self.download_stream)

async def close(self):
await self.async_blob_client.close()
await super().close()
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
# --------------------------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# --------------------------------------------------------------------------------------------
import itertools
import asyncio

from ._test_base import _ContainerTest


class ListBlobsTest(_ContainerTest):

async def global_setup(self):
await super().global_setup()
pending = (asyncio.ensure_future(self.async_container_client.upload_blob("listtest" + str(i), data=b"")) for i in range(self.args.num_blobs))
running = list(itertools.islice(pending, 16))
while True:
# Wait for some upload to finish before adding a new one
done, running = await asyncio.wait(running, return_when=asyncio.FIRST_COMPLETED)
try:
for _ in range(0, len(done)):
next_upload = next(pending)
running.add(next_upload)
except StopIteration:
await asyncio.wait(running, return_when=asyncio.ALL_COMPLETED)
break

def run_sync(self):
for _ in self.container_client.list_blobs():
pass

async def run_async(self):
async for _ in self.async_container_client.list_blobs():
pass

@staticmethod
def add_arguments(parser):
super(ListBlobsTest, ListBlobsTest).add_arguments(parser)
parser.add_argument('--num-blobs', nargs='?', type=int, help='Number of blobs to list. Defaults to 100', default=100)
Loading