fix: rebuild trustworthy local-day evidence (#99)

This commit is contained in:
xavierk
2026-09-28 13:09:00 +05:30
parent 7e392c4ea2
commit 017a562566
15 changed files with 1305 additions and 151 deletions
+520
View File
@@ -0,0 +1,520 @@
"""Historical local-day migration and repair acceptance tests for issue #99."""
import sqlite3
import sys
from datetime import datetime, timezone
from pathlib import Path
import pytest
sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
from fenris.local_day import (
query_local_day_summary,
record_local_activity_interval,
)
from fenris.status import read_status
from fenris.store import init_store
SOURCE_SCHEMA_VERSION = 5
LOCAL_DATE = "2026-09-02"
TIMEZONE = "Asia/Kolkata"
UTC_START = "2026-09-01T18:30:00+00:00"
UTC_END = "2026-09-02T18:30:00+00:00"
def _legacy_store(path: Path) -> sqlite3.Connection:
"""Build a v5 store with one old coarse local-day summary."""
conn = init_store(path)
conn.execute(
"INSERT INTO local_days "
"(local_date, tz_name, tz_offset, utc_start, utc_end, bytes_written, "
" bytes_read, coverage, sample_count, complete, activity_incomplete, "
" activity_precision) "
"VALUES (?, ?, '+05:30', ?, ?, 999999, 888888, 1.0, 24, 1, 0, 'legacy')",
(LOCAL_DATE, TIMEZONE, UTC_START, UTC_END),
)
conn.execute(
"INSERT INTO monitoring_periods (started_at, ended_at) VALUES (?, ?)",
(UTC_START, "2026-09-03T00:00:00+00:00"),
)
conn.execute(
"INSERT INTO controller_segments "
"(opened_at, identity_key, identity_degraded) VALUES (?, ?, 0)",
(UTC_START, "controller-a"),
)
conn.execute(
"INSERT INTO hour_observations "
"(hour, bytes_written_delta, bytes_read_delta, sample_count, coverage) "
"VALUES ('2026-09-02T00:00:00+00:00', 123, 45, 2, 1.0)"
)
conn.execute(
"INSERT INTO day_aggregates "
"(day, bytes_written_delta, bytes_read_delta, coverage) "
"VALUES ('2026-09-02', 678, 90, 1.0)"
)
conn.execute(
"INSERT INTO samples (ts, device, bytes_written, bytes_read, power_on_hours, "
" segment_id, local_tz) VALUES (?, '/dev/nvme0', 1000, 2000, 100, 1, ?)",
("2026-09-01T19:00:00+00:00", TIMEZONE),
)
conn.execute(
"INSERT INTO samples (ts, device, bytes_written, bytes_read, power_on_hours, "
" segment_id, local_tz) VALUES (?, '/dev/nvme0', 11000, 5000, 115, 1, ?)",
("2026-09-02T10:00:00+00:00", TIMEZONE),
)
conn.execute(f"PRAGMA user_version={SOURCE_SCHEMA_VERSION}")
conn.commit()
return conn
def test_upgrade_rebuilds_legacy_day_from_samples_and_keeps_recorded_bounds(
tmp_path, monkeypatch,
):
db = tmp_path / "legacy.db"
conn = _legacy_store(db)
conn.close()
monkeypatch.setenv("TZ", "UTC")
conn = init_store(db)
conn.close()
with read_status(
db, datetime(2026, 9, 4, tzinfo=timezone.utc), query_services=False,
) as (reader, composition):
assert reader is not None
assert composition.store_fault is None
summary = query_local_day_summary(
reader, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary is not None
assert summary["local_date"] == LOCAL_DATE
assert summary["tz_name"] == TIMEZONE
assert summary["tz_offset"] == "+05:30"
assert summary["utc_start"] == UTC_START
assert summary["utc_end"] == UTC_END
assert summary["bytes_written"] == 10_000
assert summary["bytes_read"] == 3_000
assert summary["activity_precision"] == "measured"
assert summary["segments"] == [{
"segment_id": 1,
"bytes_written": 10_000,
"bytes_read": 3_000,
"activity_seconds": 54_000,
"activity_intervals": 1,
}]
assert summary["activity_state"] == "incomplete"
assert reader.execute(
"SELECT bytes_written_delta FROM hour_observations"
).fetchone()[0] == 123
assert reader.execute(
"SELECT bytes_written_delta FROM day_aggregates"
).fetchone()[0] == 678
conn = init_store(db)
conn.close()
with read_status(
db, datetime(2026, 9, 4, tzinfo=timezone.utc), query_services=False,
) as (reader, _composition):
assert reader is not None
summary = query_local_day_summary(
reader, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] == 10_000
assert summary["bytes_read"] == 3_000
def test_repair_rebuilds_legacy_local_day_once_across_restarts(tmp_path):
from fenris.repair import repair_derivation
db = tmp_path / "repair.db"
conn = _legacy_store(db)
first = repair_derivation(conn)
assert first.ok
summary = query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] == 10_000
assert summary["bytes_read"] == 3_000
conn.close()
conn = sqlite3.connect(db)
second = repair_derivation(conn)
assert second.ok
summary = query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] == 10_000
assert summary["bytes_read"] == 3_000
assert conn.execute(
"SELECT bytes_written, bytes_read, activity_intervals "
"FROM local_day_segment_totals"
).fetchall() == [(10_000, 3_000, 1)]
conn.close()
def test_interrupted_repair_keeps_local_day_rebuild_retryable(tmp_path):
from fenris.repair import repair_derivation
db = tmp_path / "repair-interrupted.db"
conn = _legacy_store(db)
conn.execute(
"CREATE TRIGGER interrupt_repair_local_rebuild "
"BEFORE INSERT ON local_day_segment_totals "
"BEGIN SELECT RAISE(ABORT, 'simulated repair interruption'); END"
)
conn.commit()
failed = repair_derivation(conn)
assert not failed.ok
assert query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)["bytes_written"] is None
assert conn.execute(
"SELECT activity_precision, bytes_written FROM local_days"
).fetchone() == ("legacy", 999_999)
conn.execute("DROP TRIGGER interrupt_repair_local_rebuild")
conn.commit()
conn.close()
conn = sqlite3.connect(db)
retried = repair_derivation(conn)
assert retried.ok
summary = query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] == 10_000
assert summary["bytes_read"] == 3_000
conn.close()
def test_stale_repair_marker_does_not_block_crash_retry(tmp_path):
from fenris.repair import repair_derivation
conn = _legacy_store(tmp_path / "stale-repair.db")
conn.execute(
"INSERT OR REPLACE INTO store_metadata (key, value) "
"VALUES ('repair_in_progress', 'true')"
)
conn.commit()
result = repair_derivation(conn)
assert result.ok
assert conn.execute(
"SELECT value FROM store_metadata WHERE key = 'repair_in_progress'"
).fetchone() == ("false",)
assert query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)["bytes_written"] == 10_000
conn.close()
def test_upgrade_uses_whole_utc_hours_but_skips_midnight_straddling_hours(
tmp_path,
):
db = tmp_path / "coarse.db"
conn = _legacy_store(db)
conn.execute("DELETE FROM samples")
conn.execute(
"INSERT INTO hour_observations "
"(hour, bytes_written_delta, bytes_read_delta, sample_count, "
" active_seconds, coverage) "
"VALUES ('2026-09-01T18:00:00+00:00', 99999, 9999, 2, 3600, 1.0)"
)
conn.execute(
"INSERT INTO hour_observations "
"(hour, bytes_written_delta, bytes_read_delta, sample_count, "
" active_seconds, coverage) "
"VALUES ('2026-09-02T18:00:00+00:00', 88888, 8888, 2, 3600, 1.0)"
)
conn.commit()
conn.close()
conn = init_store(db)
summary = query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] == 123
assert summary["bytes_read"] == 45
assert summary["activity_precision"] == "coarse"
assert summary["activity_state"] == "incomplete"
assert summary["utc_start"] == UTC_START
assert summary["utc_end"] == UTC_END
conn.execute(
"INSERT INTO samples "
"(id, ts, device, bytes_written, bytes_read, segment_id, local_tz) "
"VALUES (10, '2026-09-02T12:00:00+00:00', '/dev/nvme0', 1000, 2000, 1, ?), "
" (11, '2026-09-02T12:05:00+00:00', '/dev/nvme0', 2000, 2500, 1, ?)",
(TIMEZONE, TIMEZONE),
)
conn.commit()
assert record_local_activity_interval(
conn,
{
"id": 10, "ts": "2026-09-02T12:00:00+00:00",
"bytes_written": 1_000, "bytes_read": 2_000,
"local_tz": TIMEZONE,
},
{
"id": 11, "ts": "2026-09-02T12:05:00+00:00",
"bytes_written": 2_000, "bytes_read": 2_500,
"local_tz": TIMEZONE,
},
start_sample_id=10, end_sample_id=11, segment_id=1,
) == "known"
summary = query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] == 1_000
assert summary["bytes_read"] == 500
assert summary["activity_precision"] == "measured"
assert summary["segments"] == [{
"segment_id": 1,
"bytes_written": 1_000,
"bytes_read": 500,
"activity_seconds": 300,
"activity_intervals": 1,
}]
conn.close()
def test_upgrade_does_not_double_count_coarse_hours_in_overlapping_days(tmp_path):
db = tmp_path / "overlapping-coarse-days.db"
conn = _legacy_store(db)
conn.execute("DELETE FROM samples")
conn.execute(
"INSERT INTO local_days "
"(local_date, tz_name, tz_offset, utc_start, utc_end, bytes_written, "
" bytes_read, coverage, sample_count, complete, activity_precision) "
"VALUES ('2026-09-02', 'UTC', '+00:00', "
"'2026-09-02T00:00:00+00:00', '2026-09-03T00:00:00+00:00', "
"999999, 888888, 1.0, 24, 1, 'legacy')"
)
conn.commit()
conn.close()
conn = init_store(db)
for tz_name in (TIMEZONE, "UTC"):
summary = query_local_day_summary(
conn, LOCAL_DATE, tz_name,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] is None
assert summary["bytes_read"] is None
assert summary["activity_precision"] == "unavailable"
assert summary["activity_state"] == "unavailable"
assert conn.execute(
"SELECT bytes_written_delta, bytes_read_delta FROM hour_observations "
"WHERE hour = '2026-09-02T00:00:00+00:00'"
).fetchone() == (123, 45)
conn.close()
def test_upgrade_retains_local_midnight_interval_once_as_shared_evidence(tmp_path):
db = tmp_path / "shared.db"
conn = _legacy_store(db)
conn.execute(
"INSERT INTO local_days "
"(local_date, tz_name, tz_offset, utc_start, utc_end, bytes_written, "
" bytes_read, coverage, sample_count, complete, activity_precision) "
"VALUES ('2026-09-01', ?, '+05:30', "
"'2026-08-31T18:30:00+00:00', '2026-09-01T18:30:00+00:00', "
"500, 600, 1.0, 24, 1, 'legacy')",
(TIMEZONE,),
)
conn.execute(
"UPDATE monitoring_periods SET started_at = '2026-08-31T18:00:00+00:00'"
)
conn.execute(
"UPDATE controller_segments SET opened_at = '2026-08-31T18:00:00+00:00'"
)
conn.execute(
"UPDATE samples SET ts = '2026-09-01T18:25:00+00:00', "
"bytes_written = 1000, bytes_read = 2000 WHERE id = 1"
)
conn.execute(
"UPDATE samples SET ts = '2026-09-01T18:35:00+00:00', "
"bytes_written = 1100, bytes_read = 2050 WHERE id = 2"
)
conn.commit()
conn.close()
conn = init_store(db)
shared = conn.execute(
"SELECT COUNT(*), SUM(bytes_written), SUM(bytes_read) "
"FROM local_day_unallocated_evidence"
).fetchone()
assert shared == (1, 100, 50)
for local_date in ("2026-09-01", "2026-09-02"):
summary = query_local_day_summary(
conn, local_date, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] is None
assert summary["shared_bytes_written"] == 100
assert summary["shared_bytes_read"] == 50
assert summary["activity_state"] == "incomplete"
from fenris.repair import repair_derivation
assert repair_derivation(conn).ok
assert conn.execute(
"SELECT COUNT(*), SUM(bytes_written), SUM(bytes_read) "
"FROM local_day_unallocated_evidence"
).fetchone() == (1, 100, 50)
conn.close()
def test_interrupted_upgrade_keeps_legacy_day_retryable(tmp_path):
db = tmp_path / "interrupted.db"
conn = _legacy_store(db)
conn.execute(
"CREATE TRIGGER interrupt_local_rebuild "
"BEFORE INSERT ON local_day_segment_totals "
"BEGIN SELECT RAISE(ABORT, 'simulated interruption'); END"
)
conn.commit()
conn.close()
with pytest.raises(sqlite3.IntegrityError, match="simulated interruption"):
init_store(db)
conn = sqlite3.connect(db)
assert conn.execute("PRAGMA user_version").fetchone() == (SOURCE_SCHEMA_VERSION,)
assert conn.execute(
"SELECT activity_precision, bytes_written FROM local_days"
).fetchone() == ("legacy", 999_999)
conn.execute("DROP TRIGGER interrupt_local_rebuild")
conn.commit()
conn.close()
conn = init_store(db)
summary = query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] == 10_000
assert summary["bytes_read"] == 3_000
conn.close()
def test_prior_migration_step_commits_before_local_day_repair(tmp_path):
db = tmp_path / "migration-steps.db"
conn = _legacy_store(db)
conn.execute("PRAGMA user_version=4")
conn.execute(
"CREATE TRIGGER interrupt_local_rebuild BEFORE UPDATE OF bytes_written "
"ON local_days BEGIN SELECT RAISE(ABORT, 'simulated interruption'); END"
)
conn.commit()
conn.close()
with pytest.raises(sqlite3.IntegrityError, match="simulated interruption"):
init_store(db)
conn = sqlite3.connect(db)
assert conn.execute("PRAGMA user_version").fetchone() == (5,)
assert conn.execute(
"SELECT 1 FROM sqlite_master WHERE type='table' "
"AND name='local_day_segment_totals'"
).fetchone() is not None
assert conn.execute(
"SELECT bytes_written FROM local_days WHERE local_date=?",
(LOCAL_DATE,),
).fetchone() == (999_999,)
conn.close()
def test_upgrade_does_not_allocate_unzoned_interval_to_overlapping_timezones(
tmp_path,
):
db = tmp_path / "overlapping-timezones.db"
conn = _legacy_store(db)
conn.execute(
"INSERT INTO local_days "
"(local_date, tz_name, tz_offset, utc_start, utc_end, bytes_written, "
" bytes_read, coverage, sample_count, complete, activity_precision) "
"VALUES ('2026-09-02', 'UTC', '+00:00', "
"'2026-09-02T00:00:00+00:00', '2026-09-03T00:00:00+00:00', "
"999999, 888888, 1.0, 24, 1, 'legacy')"
)
conn.execute(
"UPDATE samples SET ts = '2026-09-02T01:00:00+00:00', local_tz = NULL "
"WHERE id = 1"
)
conn.execute(
"UPDATE samples SET ts = '2026-09-02T10:00:00+00:00', local_tz = NULL "
"WHERE id = 2"
)
conn.commit()
conn.close()
conn = init_store(db)
for tz_name in (TIMEZONE, "UTC"):
summary = query_local_day_summary(
conn, LOCAL_DATE, tz_name,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] is None
assert summary["bytes_read"] is None
assert summary["activity_precision"] == "unavailable"
assert summary["activity_state"] == "unavailable"
conn.close()
def test_upgrade_rejects_interval_before_recorded_controller_segment(
tmp_path,
):
db = tmp_path / "segment-boundary.db"
conn = _legacy_store(db)
conn.execute(
"UPDATE controller_segments "
"SET opened_at = '2026-09-01T20:00:00+00:00' WHERE id = 1"
)
conn.commit()
conn.close()
conn = init_store(db)
summary = query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] is None
assert summary["bytes_read"] is None
assert summary["activity_precision"] == "unavailable"
conn.close()
def test_sample_at_local_midnight_does_not_hide_coarse_reconstruction(tmp_path):
db = tmp_path / "midnight-sample.db"
conn = _legacy_store(db)
conn.execute(
"UPDATE samples SET ts = '2026-09-01T17:00:00+00:00' WHERE id = 1"
)
conn.execute(
"UPDATE samples SET ts = ?, local_tz = ? WHERE id = 2",
(UTC_END, TIMEZONE),
)
conn.commit()
conn.close()
conn = init_store(db)
summary = query_local_day_summary(
conn, LOCAL_DATE, TIMEZONE,
datetime(2026, 9, 4, tzinfo=timezone.utc),
)
assert summary["bytes_written"] == 123
assert summary["bytes_read"] == 45
assert summary["activity_precision"] == "coarse"
assert summary["activity_state"] == "incomplete"
conn.close()