mirror of
https://github.com/neondatabase/neon.git
synced 2025-12-26 23:59:58 +00:00
e9e77ee744
Extracted from https://github.com/neondatabase/neon/pull/6953 Part of https://github.com/neondatabase/neon/issues/5899 Core Change ----------- In #6953, we need the ability to scan the log _after_ a specific line and ignore anything before that line. This PR changes `log_contains` to returns a tuple of `(matching line, cursor)`. Hand that cursor to a subsequent `log_contains` call to search the log for the next occurrence of the pattern. Other Changes ------------- - Inspect all the callsites of `log_contains` to handle the new tuple return type. - Above inspection unveiled many callers aren't using `assert log_contains(...) is not None` but some weaker version of the code that breaks if `log_contains` ever returns a not-None but falsy value. Fix that. - Above changes unveiled that `test_remote_storage_upload_queue_retries` was using `wait_until` incorrectly; after fixing the usage, I had to raise the `wait_until` timeout. So, maybe this will fix its flakiness.
52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
import uuid
|
|
|
|
import pytest
|
|
from fixtures.log_helper import log
|
|
from fixtures.neon_fixtures import NeonEnvBuilder
|
|
from fixtures.pg_version import run_only_on_default_postgres
|
|
from fixtures.utils import wait_until
|
|
|
|
|
|
@pytest.mark.parametrize("level", ["trace", "debug", "info", "warn", "error"])
|
|
@run_only_on_default_postgres("it does not use any postgres functionality")
|
|
def test_logging_event_count(neon_env_builder: NeonEnvBuilder, level: str):
|
|
# self-test: make sure the event is logged (i.e., our testing endpoint works)
|
|
log_expected = {
|
|
"trace": False,
|
|
"debug": False,
|
|
"info": True,
|
|
"warn": True,
|
|
"error": True,
|
|
}[level]
|
|
|
|
env = neon_env_builder.init_start()
|
|
ps_http = env.pageserver.http_client()
|
|
msg_id = uuid.uuid4().hex
|
|
|
|
# NB: the _total suffix is added by our prometheus client
|
|
before = ps_http.get_metric_value("libmetrics_tracing_event_count_total", {"level": level})
|
|
|
|
# post the event
|
|
ps_http.post_tracing_event(level, msg_id)
|
|
if log_expected:
|
|
env.pageserver.allowed_errors.append(f".*{msg_id}.*")
|
|
|
|
def assert_logged():
|
|
if not log_expected:
|
|
return
|
|
env.pageserver.assert_log_contains(f".*{msg_id}.*")
|
|
|
|
wait_until(10, 0.5, assert_logged)
|
|
|
|
# make sure it's counted
|
|
def assert_metric_value():
|
|
if not log_expected:
|
|
return
|
|
# NB: the _total suffix is added by our prometheus client
|
|
val = ps_http.get_metric_value("libmetrics_tracing_event_count_total", {"level": level})
|
|
val = val or 0.0
|
|
log.info("libmetrics_tracing_event_count: %s", val)
|
|
assert val > (before or 0.0)
|
|
|
|
wait_until(10, 1, assert_metric_value)
|