bvandeusenandClaude Opus 5.5
39b6066f3b
#5256 "Traefik — Request chart: blank on the live dashboard; time axis and honest labels". - "Req/s" was the average of the routers, not the total. Each scrape is now summed over routers, then averaged per bucket (request_history). - The 5xx share is now weighted by each router's traffic. The axis is no longer pinned at 0–100 (suggestedMax 5). - The x axis shows times, in the viewer's local time. The tooltip shows both series at that time. - A verdict line comes first: now / peak req/s and the peak 5xx share. The figures read even if the chart doesn't. - The blank live chart's cause is still unknown. Chart.js and chart-colors.js both load on the dashboard. A missing library or a thrown error is now written into the widget instead of leaving it empty, so the cause will show on the page. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
72 lines
2.8 KiB
Python
72 lines
2.8 KiB
Python
"""Integration: the newest Traefik row per router, read by walking the
|
|
(router_name, scraped_at) index rather than grouping every row (#5254).
|
|
Requires STEWARD_DATABASE_URL."""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import os
|
|
import uuid
|
|
from datetime import datetime, timedelta, timezone
|
|
|
|
import pytest
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
@pytest.fixture
|
|
def app():
|
|
if not os.environ.get("STEWARD_DATABASE_URL"):
|
|
pytest.skip("needs Postgres")
|
|
from steward.app import create_app
|
|
return create_app(testing=False)
|
|
|
|
|
|
def test_each_router_reads_as_its_newest_row(app):
|
|
from plugins.traefik.models import TraefikMetric
|
|
from plugins.traefik.routes import latest_per_router
|
|
|
|
now = datetime.now(timezone.utc).replace(microsecond=0)
|
|
tag = uuid.uuid4().hex[:8]
|
|
a, b = f"a-{tag}@docker", f"b-{tag}@docker"
|
|
|
|
def row(name, ago, rate):
|
|
return TraefikMetric(router_name=name, scraped_at=now - timedelta(minutes=ago), request_rate=rate,
|
|
error_rate_4xx_pct=0.0, error_rate_5xx_pct=0.0, latency_p50_ms=1.0,
|
|
latency_p95_ms=2.0, latency_p99_ms=3.0, response_bytes_rate=0.0)
|
|
|
|
async def go():
|
|
async with app.db_sessionmaker() as s:
|
|
async with s.begin():
|
|
s.add_all([row(a, 3, 1.0), row(a, 1, 2.0), row(a, 2, 3.0), row(b, 5, 4.0)])
|
|
async with s.begin():
|
|
return {m.router_name: m for m in await latest_per_router(s)}
|
|
|
|
got = asyncio.run(go())
|
|
assert got[a].request_rate == 2.0 and got[a].scraped_at == now - timedelta(minutes=1)
|
|
assert got[b].request_rate == 4.0
|
|
|
|
|
|
def test_the_request_chart_sums_routers_and_weights_the_5xx_share(app):
|
|
"""#5256: two routers in one scrape are 4 req/s in total, not an average
|
|
of 2; a 5xx share of 50% on the 3 req/s router is 37.5% of all traffic."""
|
|
from plugins.traefik.models import TraefikMetric
|
|
from plugins.traefik.routes import request_history
|
|
|
|
# Far ahead of every other test's rows, so only these fall in the window.
|
|
at = datetime(2099, 1, 1, 12, 0, tzinfo=timezone.utc) + timedelta(minutes=uuid.uuid4().int % 10_000)
|
|
|
|
def row(name, rate, e5):
|
|
return TraefikMetric(router_name=name, scraped_at=at, request_rate=rate, error_rate_4xx_pct=0.0,
|
|
error_rate_5xx_pct=e5, latency_p50_ms=1.0, latency_p95_ms=2.0,
|
|
latency_p99_ms=3.0, response_bytes_rate=0.0)
|
|
|
|
async def go():
|
|
async with app.db_sessionmaker() as s:
|
|
async with s.begin():
|
|
s.add_all([row("quiet@docker", 1.0, 0.0), row("busy@docker", 3.0, 50.0)])
|
|
async with s.begin():
|
|
return await request_history(s, at, 60)
|
|
|
|
got = asyncio.run(go())
|
|
assert got == [{"at": at, "req_rate": 4.0, "err_pct": 37.5}]
|