Files
Fenris/tests/test_local_day.py

925 lines
35 KiB
Python

"""Local-day activity derivation tests (issue #90, ADR 0010).
Verifies that local-day summaries are correctly derived from UTC hour
observations, that the schema migration creates the local_days table,
that timezone boundaries are preserved across system-timezone changes,
and that midnight-spanning intervals are retained as shared evidence
without double counting.
Seams:
- write side: collector.run_collection() → local_day derivation
- read side: local_day.query_current_local_day(), query_local_day_summary()
- persistence: store.init_store() → local_days table, migration 2→3
"""
import sqlite3
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Any, Dict
import pytest
import sys
sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
from fenris.store import init_store, SCHEMA_VERSION
from fenris.local_day import (
derive_local_day_summary,
persist_local_day,
record_local_activity_interval,
query_local_day_summary,
query_current_local_day,
LocalDaySummary,
)
from fenris.monitoring_periods import ensure_period_open, close_period
# ---------------------------------------------------------------------------
# Fixtures
# ---------------------------------------------------------------------------
def _make_smartctl(duw: int, dur: int) -> Dict[str, Any]:
return {
"json_format_version": [1, 0],
"smartctl": {"version": [7, 3], "svn_revision": "5155",
"build_info": "(local build)"},
"nvme_smart_health_information_log": {
"critical_warning": 0, "temperature": 35,
"available_spare": 100, "available_spare_threshold": 10,
"percentage_used": 5, "data_units_written": duw,
"data_units_read": dur, "power_on_hours": 8765,
"power_cycles": 1234, "unsafe_shutdowns": 5,
"media_errors": 0, "num_err_log_entries": 0,
},
"user_capacity": {"bytes": 1024000000000, "units": "bytes"},
"model_name": "Samsung SSD 970 EVO Plus 1TB",
"serial_number": "S4EWNX0N123456",
"firmware_version": "2B2QEXM7",
}
@pytest.fixture
def sysfs_tree(tmp_path: Path) -> Path:
ctrl_dir = tmp_path / "sys" / "class" / "nvme" / "nvme0"
ctrl_dir.mkdir(parents=True)
(ctrl_dir / "subsysnqn").write_text(
"nqn.2014-08.org.nvmexpress:uuid:12345678-1234-1234-1234-123456789abc\n"
)
(ctrl_dir / "model").write_text("Samsung SSD 970 EVO Plus 1TB\n")
(ctrl_dir / "serial").write_text("S4EWNX0N123456\n")
(ctrl_dir / "firmware_rev").write_text("2B2QEXM7\n")
transport_dir = ctrl_dir / "transport"
transport_dir.mkdir()
(transport_dir / "address").write_text("0000:03:00.0")
(transport_dir / "trstring").write_text("pcie")
return tmp_path
class _Clock:
def __init__(self, initial: datetime):
self.now = initial
def utcnow(self):
return self.now
def _insert_hour(conn, hour_iso, bw=0, br=0, sample_count=1,
active=3600, idle=0, powered_off=0, unknown=0):
"""Insert a UTC hour observation."""
known = active + idle + powered_off
coverage = known / 3600.0
conn.execute(
"INSERT INTO hour_observations "
"(hour, active_seconds, idle_seconds, powered_off_seconds, unknown_seconds, "
" bytes_written_delta, bytes_read_delta, sample_count, coverage) "
"VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)",
(hour_iso, active, idle, powered_off, unknown, bw, br, sample_count, coverage),
)
conn.commit()
# ---------------------------------------------------------------------------
# Schema migration: local_days table is created
# ---------------------------------------------------------------------------
class TestSchemaMigration:
"""Store version 3 includes the local_days table."""
def test_fresh_store_has_local_days(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
tables = {row[0] for row in conn.execute(
"SELECT name FROM sqlite_master WHERE type='table'"
).fetchall()}
assert "local_days" in tables
conn.close()
def test_migration_from_v2_creates_local_days(self, tmp_path):
db = tmp_path / "obs.db"
conn = sqlite3.connect(str(db))
conn.execute("PRAGMA user_version=2")
conn.commit()
conn.close()
conn = init_store(db)
tables = {row[0] for row in conn.execute(
"SELECT name FROM sqlite_master WHERE type='table'"
).fetchall()}
assert "local_days" in tables
assert conn.execute("PRAGMA user_version").fetchone()[0] == SCHEMA_VERSION
conn.close()
def test_migration_is_idempotent(self, tmp_path):
db = tmp_path / "obs.db"
conn = init_store(db)
conn.close()
# Reopening should not fail
conn = init_store(db)
count = conn.execute("SELECT COUNT(*) FROM local_days").fetchone()[0]
assert count == 0
conn.close()
def test_v4_totals_keep_values_but_are_not_treated_as_local_precision(
self, tmp_path,
):
db = tmp_path / "v4.db"
conn = sqlite3.connect(db)
conn.execute(
"CREATE TABLE samples (id INTEGER PRIMARY KEY, ts TEXT, device TEXT)"
)
conn.execute(
"CREATE TABLE pending_publications "
"(id INTEGER PRIMARY KEY, sample_ts TEXT, payload TEXT)"
)
conn.execute(
"CREATE TABLE local_days ("
"id INTEGER PRIMARY KEY, local_date TEXT NOT NULL, tz_name TEXT NOT NULL, "
"tz_offset TEXT NOT NULL, utc_start TEXT NOT NULL, utc_end TEXT NOT NULL, "
"bytes_written INTEGER DEFAULT 0, bytes_read INTEGER DEFAULT 0, "
"coverage REAL DEFAULT 0, sample_count INTEGER DEFAULT 0, "
"complete BOOLEAN DEFAULT 0, UNIQUE(local_date, tz_name))"
)
conn.execute(
"INSERT INTO local_days VALUES "
"(1, '2026-09-01', 'UTC', '+00:00', "
"'2026-09-01T00:00:00+00:00', '2026-09-02T00:00:00+00:00', "
"5120000, 2048000, 0.5, 10, 0)"
)
conn.execute("PRAGMA user_version=4")
conn.commit()
conn.close()
conn = init_store(db)
stored = conn.execute(
"SELECT bytes_written, activity_precision FROM local_days"
).fetchone()
assert stored == (5_120_000, "unavailable")
visible = query_local_day_summary(conn, "2026-09-01", "UTC")
assert visible["bytes_written"] is None
assert visible["activity_state"] == "unavailable"
assert "local_tz" in {
row[1] for row in conn.execute("PRAGMA table_info(samples)")
}
conn.close()
# ---------------------------------------------------------------------------
# Local-day coverage derivation from UTC hours
# ---------------------------------------------------------------------------
class TestDeriveLocalDay:
"""Derive coverage from UTC hours without allocating local-day bytes."""
def test_utc_plus_zero(self, tmp_path):
"""UTC timezone: local day boundaries = UTC day boundaries."""
conn = init_store(tmp_path / "obs.db")
ensure_period_open(conn, datetime(2026, 9, 1, 0, 0, 0, tzinfo=timezone.utc))
_insert_hour(conn, "2026-09-01T10:00:00+00:00", bw=100, br=50)
_insert_hour(conn, "2026-09-01T11:00:00+00:00", bw=200, br=80)
clock = datetime(2026, 9, 1, 12, 0, 0, tzinfo=timezone.utc)
summary = derive_local_day_summary(conn, "UTC", clock)
assert summary is not None
assert summary.local_date == "2026-09-01"
assert summary.tz_name == "UTC"
assert summary.tz_offset == "+00:00"
assert summary.bytes_written == 0
assert summary.bytes_read == 0
assert summary.activity_precision == "unavailable"
assert summary.complete is False # not all 24 hours covered
conn.close()
def test_utc_plus_five_thirty(self, tmp_path):
"""Asia/Kolkata half-hour offset: UTC boundaries are offset."""
conn = init_store(tmp_path / "obs.db")
# Local day 2026-09-01 in +05:30 is UTC [2026-08-31T18:30, 2026-09-01T18:30)
# Insert UTC hours that belong to this local day
_insert_hour(conn, "2026-08-31T19:00:00+00:00", bw=100, br=50)
_insert_hour(conn, "2026-09-01T10:00:00+00:00", bw=200, br=80)
clock = datetime(2026, 9, 1, 12, 0, 0, tzinfo=timezone.utc) # 17:30 local
summary = derive_local_day_summary(conn, "Asia/Kolkata", clock)
assert summary is not None
assert summary.local_date == "2026-09-01"
assert summary.tz_name == "Asia/Kolkata"
assert summary.tz_offset == "+05:30"
assert summary.bytes_written == 0
assert summary.bytes_read == 0
assert summary.activity_precision == "unavailable"
conn.close()
def test_hourly_bytes_cannot_be_allocated_to_local_midnight(self, tmp_path):
"""UTC-hour totals do not establish exact local-day byte totals."""
conn = init_store(tmp_path / "obs.db")
# For UTC+5:30, local day 2026-09-01 starts at 2026-08-31T18:30 UTC
# UTC hour 2026-08-31T18:00 covers 18:00-19:00, straddling the midnight
_insert_hour(conn, "2026-08-31T18:00:00+00:00", bw=100, br=50)
_insert_hour(conn, "2026-08-31T19:00:00+00:00", bw=200, br=80)
clock = datetime(2026, 9, 1, 12, 0, 0, tzinfo=timezone.utc)
summary = derive_local_day_summary(conn, "Asia/Kolkata", clock)
assert summary is not None
assert summary.bytes_written == 0
assert summary.bytes_read == 0
assert summary.activity_precision == "unavailable"
conn.close()
def test_no_hours_returns_none(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
clock = datetime(2026, 9, 1, 12, 0, 0, tzinfo=timezone.utc)
summary = derive_local_day_summary(conn, "UTC", clock)
assert summary is None
conn.close()
# ---------------------------------------------------------------------------
# Persistence and querying
# ---------------------------------------------------------------------------
class TestLocalDayPersistence:
"""Local-day summaries persist and can be queried."""
def test_persist_and_query(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
summary = LocalDaySummary(
local_date="2026-09-01", tz_name="UTC", tz_offset="+00:00",
utc_start="2026-09-01T00:00:00+00:00",
utc_end="2026-09-02T00:00:00+00:00",
bytes_written=300, bytes_read=130,
coverage=0.5, sample_count=4, complete=False,
)
created = persist_local_day(conn, summary)
assert created is True
# Upsert again — should update, not create
created2 = persist_local_day(conn, summary)
assert created2 is False
result = query_local_day_summary(conn, "2026-09-01")
assert result is not None
assert result["bytes_written"] == 300
assert result["tz_name"] == "UTC"
conn.close()
def test_query_nonexistent_returns_none(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
assert query_local_day_summary(conn, "2026-01-01") is None
conn.close()
def test_query_current_local_day(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
summary = LocalDaySummary(
local_date="2026-09-01", tz_name="UTC", tz_offset="+00:00",
utc_start="2026-09-01T00:00:00+00:00",
utc_end="2026-09-02T00:00:00+00:00",
bytes_written=500, bytes_read=200,
coverage=0.8, sample_count=10, complete=True,
)
persist_local_day(conn, summary)
clock = datetime(2026, 9, 1, 15, 0, 0, tzinfo=timezone.utc)
result = query_current_local_day(conn, clock, "UTC")
assert result is not None
assert result["bytes_written"] == 500
conn.close()
# ---------------------------------------------------------------------------
# Timezone change handling
# ---------------------------------------------------------------------------
class TestTimezoneChange:
"""Historical summaries retain their recorded timezone."""
def test_old_tz_preserved_after_change(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
# Old summary in UTC
old = LocalDaySummary(
local_date="2026-09-01", tz_name="UTC", tz_offset="+00:00",
utc_start="2026-09-01T00:00:00+00:00",
utc_end="2026-09-02T00:00:00+00:00",
bytes_written=100, bytes_read=50,
coverage=0.5, sample_count=5, complete=False,
)
persist_local_day(conn, old)
# System timezone changes to Asia/Kolkata
# Old summary retains UTC
result = query_local_day_summary(conn, "2026-09-01")
assert result is not None
assert result["tz_name"] == "UTC"
assert result["tz_offset"] == "+00:00"
conn.close()
def test_different_tz_same_date_stored_separately(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
# Two summaries for same date in different timezones
for tz, offset in [("UTC", "+00:00"), ("Asia/Kolkata", "+05:30")]:
summary = LocalDaySummary(
local_date="2026-09-01", tz_name=tz, tz_offset=offset,
utc_start="2026-09-01T00:00:00+00:00",
utc_end="2026-09-02T00:00:00+00:00",
bytes_written=100, bytes_read=50,
coverage=0.5, sample_count=5, complete=False,
)
persist_local_day(conn, summary)
# Both exist independently — query by specific timezone
utc_row = conn.execute(
"SELECT tz_name, bytes_written FROM local_days "
"WHERE local_date = '2026-09-01' AND tz_name = 'UTC'"
).fetchone()
assert utc_row is not None
assert utc_row[0] == "UTC"
assert utc_row[1] == 100
in_row = conn.execute(
"SELECT tz_name, bytes_written FROM local_days "
"WHERE local_date = '2026-09-01' AND tz_name = 'Asia/Kolkata'"
).fetchone()
assert in_row is not None
assert in_row[0] == "Asia/Kolkata"
conn.close()
# ---------------------------------------------------------------------------
# Coverage and completeness
# ---------------------------------------------------------------------------
class TestLocalDayCompleteness:
"""Complete days vs partial current day."""
def test_incomplete_when_missing_hours(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
_insert_hour(conn, "2026-09-01T12:00:00+00:00", bw=100, br=50)
clock = datetime(2026, 9, 1, 13, 0, 0, tzinfo=timezone.utc)
summary = derive_local_day_summary(conn, "UTC", clock)
assert summary is not None
assert summary.complete is False
assert summary.coverage < 1.0
conn.close()
def test_coverage_ratio(self, tmp_path):
conn = init_store(tmp_path / "obs.db")
# 2 hours of known data out of 24 total UTC hours in a UTC day
_insert_hour(conn, "2026-09-01T10:00:00+00:00", bw=100, active=3600)
_insert_hour(conn, "2026-09-01T11:00:00+00:00", bw=200, active=3600)
clock = datetime(2026, 9, 1, 12, 0, 0, tzinfo=timezone.utc)
summary = derive_local_day_summary(conn, "UTC", clock)
assert summary is not None
# 7200 known seconds / 86400 total = ~0.083
assert summary.coverage == pytest.approx(7200 / 86400, rel=0.01)
conn.close()
# ---------------------------------------------------------------------------
# Collector integration
# ---------------------------------------------------------------------------
class TestCollectorIntegration:
"""Collector derives local-day summaries during collection."""
def test_collection_creates_local_day(self, tmp_path, sysfs_tree):
from fenris.collector import run_collection
t1 = datetime(2026, 9, 1, 12, 0, 0, tzinfo=timezone.utc)
t2 = datetime(2026, 9, 1, 12, 5, 0, tzinfo=timezone.utc)
store = str(tmp_path / "obs.db")
cfg = {"device": "/dev/nvme0", "store_path": store}
sysfs_nvme = sysfs_tree / "sys" / "class" / "nvme" / "nvme0"
run_collection(_make_smartctl(10000000, 8000000), sysfs_nvme, cfg, _Clock(t1))
run_collection(_make_smartctl(10000050, 8000030), sysfs_nvme, cfg, _Clock(t2))
conn = sqlite3.connect(store)
count = conn.execute("SELECT COUNT(*) FROM local_days").fetchone()[0]
assert count >= 1
# Verify the local day has the expected write/read data
row = conn.execute(
"SELECT bytes_written, bytes_read, complete FROM local_days LIMIT 1"
).fetchone()
assert row is not None
assert row[0] == 50 * 512000 # writes
assert row[1] == 30 * 512000 # reads
conn.close()
def test_interval_crossing_utc_hour_stays_wholly_in_local_day(
self, tmp_path, sysfs_tree, monkeypatch,
):
"""A measured interval inside one local date keeps its full delta."""
from fenris.collector import run_collection
monkeypatch.setenv("TZ", "Asia/Kolkata")
store = str(tmp_path / "obs.db")
cfg = {"device": "/dev/nvme0", "store_path": store}
sysfs_nvme = sysfs_tree / "sys" / "class" / "nvme" / "nvme0"
first_at = datetime(2026, 9, 1, 12, 59, tzinfo=timezone.utc)
second_at = datetime(2026, 9, 1, 13, 1, tzinfo=timezone.utc)
first = run_collection(
_make_smartctl(10_000_000, 8_000_000),
sysfs_nvme,
cfg,
_Clock(first_at),
)
second = run_collection(
_make_smartctl(10_000_010, 8_000_004),
sysfs_nvme,
cfg,
_Clock(second_at),
)
assert first["ok"] and second["ok"]
conn = sqlite3.connect(store)
summary = query_local_day_summary(conn, "2026-09-01")
assert summary is not None
assert summary["bytes_written"] == 5_120_000
assert summary["bytes_read"] == 2_048_000
assert summary["segments"] == [{
"segment_id": 1,
"bytes_written": 5_120_000,
"bytes_read": 2_048_000,
"activity_seconds": 120,
"activity_intervals": 1,
}]
segment_totals = conn.execute(
"SELECT segment_id, bytes_written, bytes_read, activity_intervals "
"FROM local_day_segment_totals"
).fetchone()
assert segment_totals == (1, 5_120_000, 2_048_000, 1)
samples = conn.execute(
"SELECT id, ts, bytes_written, bytes_read, local_tz "
"FROM samples ORDER BY id"
).fetchall()
first_sample, second_sample = samples
assert record_local_activity_interval(
conn,
dict(zip(("id", "ts", "bytes_written", "bytes_read", "local_tz"), first_sample)),
dict(zip(("id", "ts", "bytes_written", "bytes_read", "local_tz"), second_sample)),
start_sample_id=first_sample[0],
end_sample_id=second_sample[0],
segment_id=1,
) == "known"
repeated = query_local_day_summary(conn, "2026-09-01", "Asia/Kolkata")
assert repeated["bytes_written"] == 5_120_000
assert repeated["bytes_read"] == 2_048_000
assert conn.execute(
"SELECT SUM(bytes_written), SUM(bytes_read), SUM(activity_intervals) "
"FROM local_day_segment_totals"
).fetchone() == (5_120_000, 2_048_000, 1)
conn.close()
@pytest.mark.parametrize(
(
"first_at", "second_at", "local_date", "expected_hours",
"expected_start", "expected_end", "expected_offset",
),
[
(
datetime(2026, 3, 8, 6, 30, tzinfo=timezone.utc),
datetime(2026, 3, 8, 7, 30, tzinfo=timezone.utc),
"2026-03-08", 23,
"2026-03-08T05:00:00+00:00",
"2026-03-09T04:00:00+00:00", "-05:00",
),
(
datetime(2026, 11, 1, 5, 30, tzinfo=timezone.utc),
datetime(2026, 11, 1, 6, 30, tzinfo=timezone.utc),
"2026-11-01", 25,
"2026-11-01T04:00:00+00:00",
"2026-11-02T05:00:00+00:00", "-04:00",
),
],
ids=("spring-forward", "fall-back-repeated-hour"),
)
def test_collector_retains_exact_interval_on_dst_local_day(
self,
tmp_path,
sysfs_tree,
monkeypatch,
first_at,
second_at,
local_date,
expected_hours,
expected_start,
expected_end,
expected_offset,
):
"""Collection preserves exact activity on short and long local days."""
from fenris.collector import run_collection
zone = "America/New_York"
monkeypatch.setenv("TZ", zone)
store = str(tmp_path / "obs.db")
cfg = {"device": "/dev/nvme0", "store_path": store}
sysfs_nvme = sysfs_tree / "sys" / "class" / "nvme" / "nvme0"
assert run_collection(
_make_smartctl(10_000_000, 8_000_000),
sysfs_nvme,
cfg,
_Clock(first_at),
)["ok"]
assert run_collection(
_make_smartctl(10_000_001, 8_000_002),
sysfs_nvme,
cfg,
_Clock(second_at),
)["ok"]
conn = sqlite3.connect(store)
summary = query_local_day_summary(
conn, local_date, zone, second_at + timedelta(minutes=1)
)
assert summary is not None
assert summary["bytes_written"] == 512_000
assert summary["bytes_read"] == 1_024_000
assert summary["activity_seconds"] == 3_600
assert summary["utc_start"] == expected_start
assert summary["utc_end"] == expected_end
assert summary["tz_offset"] == expected_offset
assert (
datetime.fromisoformat(summary["utc_end"])
- datetime.fromisoformat(summary["utc_start"])
).total_seconds() == expected_hours * 3_600
conn.close()
@pytest.mark.asyncio
async def test_local_midnight_interval_is_shared_once(
self, tmp_path, sysfs_tree, monkeypatch,
):
"""A real counter interval crossing local midnight stays unallocated."""
from fenris.collector import run_collection
monkeypatch.setenv("TZ", "Asia/Kolkata")
store = str(tmp_path / "obs.db")
cfg = {"device": "/dev/nvme0", "store_path": store}
sysfs_nvme = sysfs_tree / "sys" / "class" / "nvme" / "nvme0"
first_at = datetime(2026, 9, 1, 18, 25, tzinfo=timezone.utc)
second_at = datetime(2026, 9, 1, 18, 35, tzinfo=timezone.utc)
first = run_collection(
_make_smartctl(10_000_000, 8_000_000),
sysfs_nvme,
cfg,
_Clock(first_at),
)
second = run_collection(
_make_smartctl(10_000_100, 8_000_060),
sysfs_nvme,
cfg,
_Clock(second_at),
)
assert first["ok"] and second["ok"]
conn = sqlite3.connect(store)
evidence = conn.execute(
"SELECT COUNT(*), SUM(bytes_written), SUM(bytes_read) "
"FROM local_day_unallocated_evidence"
).fetchone()
assert evidence == (1, 51_200_000, 30_720_000)
assert conn.execute(
"SELECT SUM(bytes_written), SUM(bytes_read) FROM local_days"
).fetchone() == (0, 0)
for local_date in ("2026-09-01", "2026-09-02"):
summary = query_local_day_summary(
conn, local_date, "Asia/Kolkata", second_at
)
assert summary is not None
assert summary["bytes_written"] is None
assert summary["shared_bytes_written"] == 51_200_000
assert summary["shared_bytes_read"] == 30_720_000
assert summary["activity_state"] in ("incomplete", "so_far")
conn.close()
from fenris.status import read_status
from fenris.tui import FenrisTuiApp
app = FenrisTuiApp(store_path=Path(store), refresh_interval_s=999)
async with app.run_test(size=(100, 32)):
app._browse_date = "2026-09-02"
with read_status(
Path(store), second_at, query_services=False
) as (reader, _):
assert reader is not None
app._render_local_day(reader)
visible = str(app.query_one("#local-day").render())
assert "2026-09-02" in visible
assert "Asia/Kolkata +05:30" in visible
assert "W unavailable" in visible
assert "shared at midnight W 0.051 GB" in visible
def test_synthetic_shared_bytes_conserve_one_hundred_bytes(self, tmp_path):
"""Shared evidence conserves byte values before display rounding."""
conn = init_store(tmp_path / "obs.db")
first_at = datetime(2026, 9, 1, 18, 25, tzinfo=timezone.utc)
second_at = datetime(2026, 9, 3, 18, 35, tzinfo=timezone.utc)
ensure_period_open(conn, first_at)
conn.execute(
"INSERT INTO samples (ts, device, bytes_written, bytes_read, local_tz) "
"VALUES (?, ?, ?, ?, ?)",
(first_at.isoformat(), "/dev/nvme0", 1_000, 2_000, "Asia/Kolkata"),
)
first_id = conn.execute("SELECT last_insert_rowid()").fetchone()[0]
conn.execute(
"INSERT INTO samples (ts, device, bytes_written, bytes_read, local_tz) "
"VALUES (?, ?, ?, ?, ?)",
(second_at.isoformat(), "/dev/nvme0", 1_100, 2_050, "Asia/Kolkata"),
)
second_id = conn.execute("SELECT last_insert_rowid()").fetchone()[0]
result = record_local_activity_interval(
conn,
{
"id": first_id,
"ts": first_at.isoformat(),
"bytes_written": 1_000,
"bytes_read": 2_000,
"local_tz": "Asia/Kolkata",
},
{
"id": second_id,
"ts": second_at.isoformat(),
"bytes_written": 1_100,
"bytes_read": 2_050,
"local_tz": "Asia/Kolkata",
},
start_sample_id=first_id,
end_sample_id=second_id,
segment_id=1,
)
assert result == "local_midnight"
stored = conn.execute(
"SELECT COUNT(*), SUM(bytes_written), SUM(bytes_read) "
"FROM local_day_unallocated_evidence"
).fetchone()
assert stored == (1, 100, 50)
record_local_activity_interval(
conn,
{
"id": first_id,
"ts": first_at.isoformat(),
"bytes_written": 1_000,
"bytes_read": 2_000,
"local_tz": "Asia/Kolkata",
},
{
"id": second_id,
"ts": second_at.isoformat(),
"bytes_written": 1_100,
"bytes_read": 2_050,
"local_tz": "Asia/Kolkata",
},
start_sample_id=first_id,
end_sample_id=second_id,
segment_id=1,
)
assert conn.execute(
"SELECT COUNT(*), SUM(bytes_written), SUM(bytes_read) "
"FROM local_day_unallocated_evidence"
).fetchone() == (1, 100, 50)
assert conn.execute(
"SELECT SUM(bytes_written), SUM(bytes_read) FROM local_days"
).fetchone() == (0, 0)
middle_day = query_local_day_summary(
conn, "2026-09-03", "Asia/Kolkata", second_at + timedelta(days=1)
)
assert middle_day["shared_bytes_written"] == 100
assert middle_day["shared_bytes_read"] == 50
assert middle_day["shared_evidence_count"] == 1
conn.close()
def test_timezone_change_keeps_interval_unallocated(
self, tmp_path, sysfs_tree, monkeypatch,
):
from fenris.collector import run_collection
store = str(tmp_path / "obs.db")
cfg = {"device": "/dev/nvme0", "store_path": store}
sysfs_nvme = sysfs_tree / "sys" / "class" / "nvme" / "nvme0"
first_at = datetime(2026, 9, 1, 22, 0, tzinfo=timezone.utc)
second_at = datetime(2026, 9, 1, 22, 5, tzinfo=timezone.utc)
monkeypatch.setenv("TZ", "UTC")
assert run_collection(
_make_smartctl(10_000_000, 8_000_000),
sysfs_nvme,
cfg,
_Clock(first_at),
)["ok"]
monkeypatch.setenv("TZ", "Asia/Kolkata")
assert run_collection(
_make_smartctl(10_000_010, 8_000_004),
sysfs_nvme,
cfg,
_Clock(second_at),
)["ok"]
conn = sqlite3.connect(store)
event = conn.execute(
"SELECT COUNT(*), SUM(bytes_written), MIN(reason) "
"FROM local_day_unallocated_evidence"
).fetchone()
assert event == (1, 5_120_000, "timezone_change")
old_zone = query_local_day_summary(conn, "2026-09-01", "UTC")
new_zone = query_local_day_summary(conn, "2026-09-02", "Asia/Kolkata")
assert old_zone["bytes_written"] is None
assert new_zone["bytes_written"] is None
assert old_zone["unallocated_bytes_written"] == 5_120_000
assert new_zone["unallocated_bytes_written"] == 5_120_000
conn.close()
def test_pause_boundary_keeps_interval_unallocated(
self, tmp_path, sysfs_tree, monkeypatch,
):
from fenris.collector import run_collection
monkeypatch.setenv("TZ", "UTC")
store = str(tmp_path / "obs.db")
cfg = {"device": "/dev/nvme0", "store_path": store}
sysfs_nvme = sysfs_tree / "sys" / "class" / "nvme" / "nvme0"
first_at = datetime(2026, 9, 1, 12, 0, tzinfo=timezone.utc)
second_at = datetime(2026, 9, 1, 12, 10, tzinfo=timezone.utc)
assert run_collection(
_make_smartctl(10_000_000, 8_000_000),
sysfs_nvme,
cfg,
_Clock(first_at),
)["ok"]
conn = sqlite3.connect(store)
close_period(conn, first_at + timedelta(minutes=5), "user_disabled")
conn.close()
assert run_collection(
_make_smartctl(10_000_010, 8_000_004),
sysfs_nvme,
cfg,
_Clock(second_at),
)["ok"]
conn = sqlite3.connect(store)
reason = conn.execute(
"SELECT reason FROM local_day_unallocated_evidence"
).fetchone()
summary = query_local_day_summary(conn, "2026-09-01", "UTC")
assert reason == ("monitoring_period",)
assert summary["bytes_written"] is None
assert summary["unallocated_bytes_written"] == 5_120_000
assert summary["shared_bytes_written"] == 0
conn.close()
def test_controller_segment_boundary_marks_local_activity_incomplete(
self, tmp_path, sysfs_tree, monkeypatch,
):
from fenris.collector import run_collection
monkeypatch.setenv("TZ", "UTC")
store = str(tmp_path / "obs.db")
cfg = {"device": "/dev/nvme0", "store_path": store}
sysfs_nvme = sysfs_tree / "sys" / "class" / "nvme" / "nvme0"
first_at = datetime(2026, 9, 1, 12, 0, tzinfo=timezone.utc)
second_at = datetime(2026, 9, 1, 12, 5, tzinfo=timezone.utc)
assert run_collection(
_make_smartctl(10_000_000, 8_000_000),
sysfs_nvme,
cfg,
_Clock(first_at),
)["ok"]
assert run_collection(
_make_smartctl(10, 8_000_004),
sysfs_nvme,
cfg,
_Clock(second_at),
)["ok"]
conn = sqlite3.connect(store)
summary = query_local_day_summary(
conn, "2026-09-01", "UTC", second_at
)
assert summary is not None
assert summary["bytes_written"] is None
assert summary["activity_state"] == "incomplete"
assert conn.execute(
"SELECT COUNT(*) FROM local_day_unallocated_evidence"
).fetchone()[0] == 0
conn.close()
# ---------------------------------------------------------------------------
# DST handling (23/25-hour days)
# ---------------------------------------------------------------------------
class TestDSTHandling:
"""Local days with non-24-hour durations from DST transitions."""
def test_short_day_23_hours(self, tmp_path):
"""Spring forward: local day is 23 hours."""
conn = init_store(tmp_path / "obs.db")
# Simulate a 23-hour day in a timezone with DST
# For simplicity, just verify the summary records the correct UTC range
clock = datetime(2026, 3, 8, 12, 0, 0, tzinfo=timezone.utc)
# New York springs forward on 2026-03-08
# Local day 2026-03-08 is 23 hours: UTC [07:00, 06:00+1d)
_insert_hour(conn, "2026-03-08T08:00:00+00:00", bw=100, active=3600)
_insert_hour(conn, "2026-03-08T12:00:00+00:00", bw=200, active=3600)
summary = derive_local_day_summary(conn, "America/New_York", clock)
assert summary is not None
assert summary.local_date == "2026-03-08"
# UTC range should be approximately 23 hours
utc_start = datetime.fromisoformat(summary.utc_start)
utc_end = datetime.fromisoformat(summary.utc_end)
duration = (utc_end - utc_start).total_seconds()
assert duration == 23 * 3600
conn.close()
def test_long_day_25_hours(self):
from fenris.local_day import local_day_boundaries
start, end, offset = local_day_boundaries(
"2026-11-01", "America/New_York"
)
assert (end - start).total_seconds() == 25 * 3600
assert offset == "-04:00"
def test_half_hour_offset_records_exact_local_boundaries(self):
from fenris.local_day import local_day_boundaries
start, end, offset = local_day_boundaries(
"2026-09-01", "Asia/Kolkata"
)
assert start.isoformat() == "2026-08-31T18:30:00+00:00"
assert end.isoformat() == "2026-09-01T18:30:00+00:00"
assert offset == "+05:30"
def test_repeated_local_clock_labels_remain_one_recorded_day(
self, tmp_path, sysfs_tree, monkeypatch,
):
from fenris.collector import run_collection
monkeypatch.setenv("TZ", "America/New_York")
store = str(tmp_path / "obs.db")
cfg = {"device": "/dev/nvme0", "store_path": store}
sysfs_nvme = sysfs_tree / "sys" / "class" / "nvme" / "nvme0"
# Both endpoints display as 01:30 locally, on opposite UTC offsets.
first_at = datetime(2026, 11, 1, 5, 30, tzinfo=timezone.utc)
second_at = datetime(2026, 11, 1, 6, 30, tzinfo=timezone.utc)
assert run_collection(
_make_smartctl(10_000_000, 8_000_000),
sysfs_nvme,
cfg,
_Clock(first_at),
)["ok"]
assert run_collection(
_make_smartctl(10_000_001, 8_000_002),
sysfs_nvme,
cfg,
_Clock(second_at),
)["ok"]
conn = sqlite3.connect(store)
summary = query_local_day_summary(
conn, "2026-11-01", "America/New_York", second_at
)
assert summary is not None
assert summary["bytes_written"] == 512_000
assert summary["bytes_read"] == 1_024_000
assert summary["utc_start"] == "2026-11-01T04:00:00+00:00"
assert summary["utc_end"] == "2026-11-02T05:00:00+00:00"
conn.close()