Skip to content
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

Add Redis instrumentation query sanitization #1572

Merged
merged 16 commits into from
Feb 4, 2023
Merged
Show file tree
Hide file tree
Changes from 5 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
5 changes: 5 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## Unreleased

### Added

- `opentelemetry-instrumentation-redis` Add `sanitize_query` config option to allow query sanitization. Enabled by default.
([#1572](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/1572))
tombruijn marked this conversation as resolved.
Show resolved Hide resolved

## Fixed

- Fix aiopg instrumentation to work with aiopg < 2.0.0
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,8 @@ async def redis_get():
response_hook (Callable) - a function with extra user-defined logic to be performed after performing the request
this function signature is: def response_hook(span: Span, instance: redis.connection.Connection, response) -> None

sanitize_query (Boolean) - default True, enable the Redis query sanitization

for example:

.. code: python
Expand Down Expand Up @@ -139,9 +141,11 @@ def _instrument(
tracer,
request_hook: _RequestHookT = None,
response_hook: _ResponseHookT = None,
sanitize_query: bool = True,
):
def _traced_execute_command(func, instance, args, kwargs):
query = _format_command_args(args)
query = _format_command_args(args, sanitize_query)

if len(args) > 0 and args[0]:
name = args[0]
else:
Expand Down Expand Up @@ -169,7 +173,9 @@ def _traced_execute_pipeline(func, instance, args, kwargs):
)

cmds = [
_format_command_args(c.args if hasattr(c, "args") else c[0])
_format_command_args(
c.args if hasattr(c, "args") else c[0], sanitize_query
)
for c in command_stack
]
resource = "\n".join(cmds)
Expand Down Expand Up @@ -281,6 +287,7 @@ def _instrument(self, **kwargs):
tracer,
request_hook=kwargs.get("request_hook"),
response_hook=kwargs.get("response_hook"),
sanitize_query=kwargs.get("sanitize_query", True),
)

def _uninstrument(self, **kwargs):
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -48,25 +48,29 @@ def _extract_conn_attributes(conn_kwargs):
return attributes


def _format_command_args(args):
"""Format command arguments and trim them as needed"""
value_max_len = 100
value_too_long_mark = "..."
cmd_max_len = 1000
length = 0
out = []
for arg in args:
cmd = str(arg)
def _format_command_args(args, sanitize_query):
"""Format and sanitize command arguments, and trim them as needed"""
if sanitize_query:
# Sanitized query format: "COMMAND ? ?"
out = [str(args[0])] + ["?"] * (len(args) - 1)
tombruijn marked this conversation as resolved.
Show resolved Hide resolved
else:
value_max_len = 100
value_too_long_mark = "..."
cmd_max_len = 1000
length = 0
out = []
for arg in args:
cmd = str(arg)

if len(cmd) > value_max_len:
cmd = cmd[:value_max_len] + value_too_long_mark
if len(cmd) > value_max_len:
cmd = cmd[:value_max_len] + value_too_long_mark

if length + len(cmd) > cmd_max_len:
prefix = cmd[: cmd_max_len - length]
out.append(f"{prefix}{value_too_long_mark}")
break
if length + len(cmd) > cmd_max_len:
prefix = cmd[: cmd_max_len - length]
out.append(f"{prefix}{value_too_long_mark}")
break

out.append(cmd)
length += len(cmd)
out.append(cmd)
length += len(cmd)

return " ".join(out)
Original file line number Diff line number Diff line change
Expand Up @@ -148,6 +148,40 @@ def request_hook(span, conn, args, kwargs):
span = spans[0]
self.assertEqual(span.attributes.get(custom_attribute_name), "GET")

def test_query_sanitizer_enabled(self):
redis_client = redis.Redis()
connection = redis.connection.Connection()
redis_client.connection = connection

with mock.patch.object(redis_client, "connection"):
redis_client.set("key", "value")

spans = self.memory_exporter.get_finished_spans()
self.assertEqual(len(spans), 1)

span = spans[0]
self.assertEqual(span.attributes.get("db.statement"), "SET ? ?")

def test_query_sanitizer_disabled(self):
redis_client = redis.Redis()
connection = redis.connection.Connection()
redis_client.connection = connection

RedisInstrumentor().uninstrument()
RedisInstrumentor().instrument(
tracer_provider=self.tracer_provider,
sanitize_query=False,
)

with mock.patch.object(redis_client, "connection"):
redis_client.set("key", "value")

spans = self.memory_exporter.get_finished_spans()
self.assertEqual(len(spans), 1)

span = spans[0]
self.assertEqual(span.attributes.get("db.statement"), "SET key value")

def test_no_op_tracer_provider(self):
RedisInstrumentor().uninstrument()
tracer_provider = trace.NoOpTracerProvider
Expand Down