bvandeusenandClaude Opus 5.5
cbbf186f17
plugin_metrics_hourly gains value_p95 beside value_avg and value_max. A two-minute backup spike raises the hour's peak and leaves its p95 low; an hour spent at that level raises both. Learned normals (milestone 513) need that difference to call a recurring spike usual without calling the same level held at another hour usual too. Hours rolled up before this keep a NULL p95 and read as their average. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
63 lines
2.5 KiB
Python
63 lines
2.5 KiB
Python
"""Integration: each rolled-up hour keeps the level it held (#5738).
|
|
|
|
A learned normal has to tell a two-minute backup spike from an hour spent at
|
|
that level. Both have the same peak; only the hour's 95th percentile differs,
|
|
so the rollup must keep it beside the average and the peak.
|
|
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_a_brief_spike_raises_the_peak_and_a_held_level_raises_the_p95(app):
|
|
from sqlalchemy import select
|
|
from steward.core.metrics_retention import rollup_plugin_metrics
|
|
from steward.models.metrics import PluginMetric, PluginMetricHourly
|
|
|
|
now = datetime.now(timezone.utc)
|
|
res = f"p95-{uuid.uuid4().hex[:8]}"
|
|
spike_hour = (now - timedelta(days=10)).replace(minute=0, second=0, microsecond=0)
|
|
held_hour = spike_hour + timedelta(hours=1)
|
|
|
|
def minute(hour, m, metric, value):
|
|
return PluginMetric(source_module="test", resource_name=res, metric_name=metric,
|
|
value=value, recorded_at=hour + timedelta(minutes=m))
|
|
|
|
async def _go():
|
|
async with app.db_sessionmaker() as s:
|
|
async with s.begin():
|
|
# One sample a minute. The spike hour sits at 10 and touches 95
|
|
# for two minutes; the held hour sits at 90 bar a two-minute dip.
|
|
s.add_all([minute(spike_hour, m, "cpu_pct", 95.0 if m in (2, 3) else 10.0)
|
|
for m in range(60)])
|
|
s.add_all([minute(held_hour, m, "cpu_pct", 10.0 if m in (2, 3) else 90.0)
|
|
for m in range(60)])
|
|
async with s.begin():
|
|
await rollup_plugin_metrics(s, raw_days=7, rollup_days=90, now=now)
|
|
rows = (await s.execute(
|
|
select(PluginMetricHourly)
|
|
.where(PluginMetricHourly.resource_name == res)
|
|
.order_by(PluginMetricHourly.bucket))).scalars().all()
|
|
return [(r.bucket, r.value_max, r.value_p95, r.value_avg) for r in rows]
|
|
|
|
(b1, spike_max, spike_p95, _), (b2, held_max, held_p95, _) = asyncio.run(_go())
|
|
assert (b1, b2) == (spike_hour, held_hour)
|
|
assert spike_max == 95.0 and abs(spike_p95 - 10.0) < 0.001
|
|
assert held_max == 90.0 and abs(held_p95 - 90.0) < 0.001
|