core/homeassistant/components/recorder/util.py

273 lines
8.1 KiB
Python
Raw Normal View History

"""SQLAlchemy util functions."""
2021-03-11 17:52:07 +00:00
from __future__ import annotations
from collections.abc import Generator
from contextlib import contextmanager
from datetime import timedelta
import logging
import os
import time
from sqlalchemy.exc import OperationalError, SQLAlchemyError
2021-03-11 17:52:07 +00:00
from sqlalchemy.orm.session import Session
from homeassistant.core import HomeAssistant
import homeassistant.util.dt as dt_util
from .const import DATA_INSTANCE, SQLITE_URL_PREFIX
from .models import (
ALL_TABLES,
TABLE_RECORDER_RUNS,
TABLE_SCHEMA_CHANGES,
RecorderRuns,
process_timestamp,
)
_LOGGER = logging.getLogger(__name__)
RETRIES = 3
QUERY_RETRY_WAIT = 0.1
SQLITE3_POSTFIXES = ["", "-wal", "-shm"]
# This is the maximum time after the recorder ends the session
# before we no longer consider startup to be a "restart" and we
# should do a check on the sqlite3 database.
MAX_RESTART_TIME = timedelta(minutes=10)
@contextmanager
2021-03-11 17:52:07 +00:00
def session_scope(
*, hass: HomeAssistant | None = None, session: Session | None = None
2021-03-11 17:52:07 +00:00
) -> Generator[Session, None, None]:
"""Provide a transactional scope around a series of operations."""
if session is None and hass is not None:
session = hass.data[DATA_INSTANCE].get_session()
if session is None:
2019-07-31 19:25:30 +00:00
raise RuntimeError("Session required")
2019-03-09 20:04:13 +00:00
need_rollback = False
try:
yield session
2021-04-22 06:29:36 +00:00
if session.get_transaction():
2019-03-09 20:04:13 +00:00
need_rollback = True
session.commit()
except Exception as err:
_LOGGER.error("Error executing query: %s", err)
2019-03-09 20:04:13 +00:00
if need_rollback:
session.rollback()
raise
finally:
session.close()
def commit(session, work):
"""Commit & retry work: Either a model or in a function."""
for _ in range(0, RETRIES):
try:
if callable(work):
work(session)
else:
session.add(work)
session.commit()
return True
except OperationalError as err:
_LOGGER.error("Error executing query: %s", err)
session.rollback()
time.sleep(QUERY_RETRY_WAIT)
return False
def execute(qry, to_native=False, validate_entity_ids=True):
"""Query the database and convert the objects to HA native form.
This method also retries a few times in the case of stale connections.
"""
for tryno in range(0, RETRIES):
try:
History query and schema optimizations for huge performance boost (#8748) * Add DEBUG-level log for db row to native object conversion This is now the bottleneck (by a large margin) for big history queries, so I'm leaving this log feature in to help diagnose users with a slow history page * Rewrite of the "first synthetic datapoint" query for multiple entities The old method was written in a manner that prevented an index from being used in the inner-most GROUP BY statement, causing massive performance issues especially when querying for a large time period. The new query does have one material change that will cause it to return different results than before: instead of using max(state_id) to get the latest entry, we now get the max(last_updated). This is more appropriate (primary key should not be assumed to be in order of event firing) and allows an index to be used on the inner-most query. I added another JOIN layer to account for cases where there are two entries on the exact same `last_created` for a given entity. In this case we do use `state_id` as a tiebreaker. For performance reasons the domain filters were also moved to the outermost query, as it's way more efficient to do it there than on the innermost query as before (due to indexing with GROUP BY problems) The result is a query that only needs to do a filesort on the final result set, which will only be as many rows as there are entities. * Remove the ORDER BY entity_id when fetching states, and add logging Having this ORDER BY in the query prevents it from using an index due to the range filter, so it has been removed. We already do a `groupby` in the `states_to_json` method which accomplishes exactly what the ORDER BY in the query was trying to do anyway, so this change causes no functional difference. Also added DEBUG-level logging to allow diagnosing a user's slow history page. * Add DEBUG-level logging for the synthetic-first-datapoint query For diagnosing a user's slow history page * Missed a couple instances of `created` that should be `last_updated` * Remove `entity_id` sorting from state_changes; match significant_update This is the same change as 09b3498f410106881fc5e095c49a8d527fa89644 , but applied to the `state_changes_during_period` method which I missed before. This should give the same performance boost to the history sensor component! * Bugfix in History query used for History Sensor The date filter was using a different column for the upper and lower bounds. It would work, but it would be slow! * Update Recorder purge script to use more appropriate columns Two reasons: 1. the `created` column's meaning is fairly arbitrary and does not represent when an event or state change actually ocurred. It seems more correct to purge based on the event date than the time the database row was written. 2. The new columns are indexed, which will speed up this purge script by orders of magnitude * Updating db model to match new query optimizations A few things here: 1. New schema version with a new index and several removed indexes 2. A new method in the migration script to drop old indexes 3. Added an INFO-level log message when a new index will be added, as this can take quite some time on a Raspberry Pi
2017-08-05 06:16:53 +00:00
timer_start = time.perf_counter()
Improve history api performance (#35822) * Improve history api performance A new option "minimal_response" reduces the amount of data sent between the first and last history states to only the "last_changed" and "state" fields. Calling to_native is now avoided where possible and only done at the end for rows that will be returned in the response. When sending the `minimal_response` option, the history api now returns a json response similar to the following for an entity Testing: History API Response time for 1 day Average of 10 runs with minimal_response Before: 19.89s. (content length : 3427428) After: 8.44s (content length: 592199) ``` [{ "attributes": {--TRUNCATED--}, "context": {--TRUNCATED--}, "entity_id": "binary_sensor.powerwall_status", "last_changed": "2020-05-18T23:20:03.213000+00:00", "last_updated": "2020-05-18T23:20:03.213000+00:00", "state": "on" }, ... { "last_changed": "2020-05-19T00:41:08Z", "state": "unavailable" }, ... { "attributes": {--TRUNCATED--}, "context": {--TRUNCATED--}, "entity_id": "binary_sensor.powerwall_status", "last_changed": "2020-05-19T00:42:08.069698+00:00", "last_updated": "2020-05-19T00:42:08.069698+00:00", "state": "on" }] ``` * Remove impossible state check * Remove another impossible state check * Update homeassistant/components/history/__init__.py Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io> * Reorder to save some indent per review * Make query response make sense with to_native=False * Update test for 00:00 to Z change * Update homeassistant/components/recorder/models.py Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io> Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io>
2020-05-27 02:53:56 +00:00
if to_native:
result = [
row
for row in (
row.to_native(validate_entity_id=validate_entity_ids)
for row in qry
)
if row is not None
Improve history api performance (#35822) * Improve history api performance A new option "minimal_response" reduces the amount of data sent between the first and last history states to only the "last_changed" and "state" fields. Calling to_native is now avoided where possible and only done at the end for rows that will be returned in the response. When sending the `minimal_response` option, the history api now returns a json response similar to the following for an entity Testing: History API Response time for 1 day Average of 10 runs with minimal_response Before: 19.89s. (content length : 3427428) After: 8.44s (content length: 592199) ``` [{ "attributes": {--TRUNCATED--}, "context": {--TRUNCATED--}, "entity_id": "binary_sensor.powerwall_status", "last_changed": "2020-05-18T23:20:03.213000+00:00", "last_updated": "2020-05-18T23:20:03.213000+00:00", "state": "on" }, ... { "last_changed": "2020-05-19T00:41:08Z", "state": "unavailable" }, ... { "attributes": {--TRUNCATED--}, "context": {--TRUNCATED--}, "entity_id": "binary_sensor.powerwall_status", "last_changed": "2020-05-19T00:42:08.069698+00:00", "last_updated": "2020-05-19T00:42:08.069698+00:00", "state": "on" }] ``` * Remove impossible state check * Remove another impossible state check * Update homeassistant/components/history/__init__.py Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io> * Reorder to save some indent per review * Make query response make sense with to_native=False * Update test for 00:00 to Z change * Update homeassistant/components/recorder/models.py Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io> Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io>
2020-05-27 02:53:56 +00:00
]
else:
result = list(qry)
History query and schema optimizations for huge performance boost (#8748) * Add DEBUG-level log for db row to native object conversion This is now the bottleneck (by a large margin) for big history queries, so I'm leaving this log feature in to help diagnose users with a slow history page * Rewrite of the "first synthetic datapoint" query for multiple entities The old method was written in a manner that prevented an index from being used in the inner-most GROUP BY statement, causing massive performance issues especially when querying for a large time period. The new query does have one material change that will cause it to return different results than before: instead of using max(state_id) to get the latest entry, we now get the max(last_updated). This is more appropriate (primary key should not be assumed to be in order of event firing) and allows an index to be used on the inner-most query. I added another JOIN layer to account for cases where there are two entries on the exact same `last_created` for a given entity. In this case we do use `state_id` as a tiebreaker. For performance reasons the domain filters were also moved to the outermost query, as it's way more efficient to do it there than on the innermost query as before (due to indexing with GROUP BY problems) The result is a query that only needs to do a filesort on the final result set, which will only be as many rows as there are entities. * Remove the ORDER BY entity_id when fetching states, and add logging Having this ORDER BY in the query prevents it from using an index due to the range filter, so it has been removed. We already do a `groupby` in the `states_to_json` method which accomplishes exactly what the ORDER BY in the query was trying to do anyway, so this change causes no functional difference. Also added DEBUG-level logging to allow diagnosing a user's slow history page. * Add DEBUG-level logging for the synthetic-first-datapoint query For diagnosing a user's slow history page * Missed a couple instances of `created` that should be `last_updated` * Remove `entity_id` sorting from state_changes; match significant_update This is the same change as 09b3498f410106881fc5e095c49a8d527fa89644 , but applied to the `state_changes_during_period` method which I missed before. This should give the same performance boost to the history sensor component! * Bugfix in History query used for History Sensor The date filter was using a different column for the upper and lower bounds. It would work, but it would be slow! * Update Recorder purge script to use more appropriate columns Two reasons: 1. the `created` column's meaning is fairly arbitrary and does not represent when an event or state change actually ocurred. It seems more correct to purge based on the event date than the time the database row was written. 2. The new columns are indexed, which will speed up this purge script by orders of magnitude * Updating db model to match new query optimizations A few things here: 1. New schema version with a new index and several removed indexes 2. A new method in the migration script to drop old indexes 3. Added an INFO-level log message when a new index will be added, as this can take quite some time on a Raspberry Pi
2017-08-05 06:16:53 +00:00
if _LOGGER.isEnabledFor(logging.DEBUG):
elapsed = time.perf_counter() - timer_start
Improve history api performance (#35822) * Improve history api performance A new option "minimal_response" reduces the amount of data sent between the first and last history states to only the "last_changed" and "state" fields. Calling to_native is now avoided where possible and only done at the end for rows that will be returned in the response. When sending the `minimal_response` option, the history api now returns a json response similar to the following for an entity Testing: History API Response time for 1 day Average of 10 runs with minimal_response Before: 19.89s. (content length : 3427428) After: 8.44s (content length: 592199) ``` [{ "attributes": {--TRUNCATED--}, "context": {--TRUNCATED--}, "entity_id": "binary_sensor.powerwall_status", "last_changed": "2020-05-18T23:20:03.213000+00:00", "last_updated": "2020-05-18T23:20:03.213000+00:00", "state": "on" }, ... { "last_changed": "2020-05-19T00:41:08Z", "state": "unavailable" }, ... { "attributes": {--TRUNCATED--}, "context": {--TRUNCATED--}, "entity_id": "binary_sensor.powerwall_status", "last_changed": "2020-05-19T00:42:08.069698+00:00", "last_updated": "2020-05-19T00:42:08.069698+00:00", "state": "on" }] ``` * Remove impossible state check * Remove another impossible state check * Update homeassistant/components/history/__init__.py Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io> * Reorder to save some indent per review * Make query response make sense with to_native=False * Update test for 00:00 to Z change * Update homeassistant/components/recorder/models.py Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io> Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io>
2020-05-27 02:53:56 +00:00
if to_native:
_LOGGER.debug(
"converting %d rows to native objects took %fs",
len(result),
elapsed,
)
else:
_LOGGER.debug(
2020-08-27 11:56:20 +00:00
"querying %d rows took %fs",
len(result),
elapsed,
Improve history api performance (#35822) * Improve history api performance A new option "minimal_response" reduces the amount of data sent between the first and last history states to only the "last_changed" and "state" fields. Calling to_native is now avoided where possible and only done at the end for rows that will be returned in the response. When sending the `minimal_response` option, the history api now returns a json response similar to the following for an entity Testing: History API Response time for 1 day Average of 10 runs with minimal_response Before: 19.89s. (content length : 3427428) After: 8.44s (content length: 592199) ``` [{ "attributes": {--TRUNCATED--}, "context": {--TRUNCATED--}, "entity_id": "binary_sensor.powerwall_status", "last_changed": "2020-05-18T23:20:03.213000+00:00", "last_updated": "2020-05-18T23:20:03.213000+00:00", "state": "on" }, ... { "last_changed": "2020-05-19T00:41:08Z", "state": "unavailable" }, ... { "attributes": {--TRUNCATED--}, "context": {--TRUNCATED--}, "entity_id": "binary_sensor.powerwall_status", "last_changed": "2020-05-19T00:42:08.069698+00:00", "last_updated": "2020-05-19T00:42:08.069698+00:00", "state": "on" }] ``` * Remove impossible state check * Remove another impossible state check * Update homeassistant/components/history/__init__.py Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io> * Reorder to save some indent per review * Make query response make sense with to_native=False * Update test for 00:00 to Z change * Update homeassistant/components/recorder/models.py Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io> Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io>
2020-05-27 02:53:56 +00:00
)
History query and schema optimizations for huge performance boost (#8748) * Add DEBUG-level log for db row to native object conversion This is now the bottleneck (by a large margin) for big history queries, so I'm leaving this log feature in to help diagnose users with a slow history page * Rewrite of the "first synthetic datapoint" query for multiple entities The old method was written in a manner that prevented an index from being used in the inner-most GROUP BY statement, causing massive performance issues especially when querying for a large time period. The new query does have one material change that will cause it to return different results than before: instead of using max(state_id) to get the latest entry, we now get the max(last_updated). This is more appropriate (primary key should not be assumed to be in order of event firing) and allows an index to be used on the inner-most query. I added another JOIN layer to account for cases where there are two entries on the exact same `last_created` for a given entity. In this case we do use `state_id` as a tiebreaker. For performance reasons the domain filters were also moved to the outermost query, as it's way more efficient to do it there than on the innermost query as before (due to indexing with GROUP BY problems) The result is a query that only needs to do a filesort on the final result set, which will only be as many rows as there are entities. * Remove the ORDER BY entity_id when fetching states, and add logging Having this ORDER BY in the query prevents it from using an index due to the range filter, so it has been removed. We already do a `groupby` in the `states_to_json` method which accomplishes exactly what the ORDER BY in the query was trying to do anyway, so this change causes no functional difference. Also added DEBUG-level logging to allow diagnosing a user's slow history page. * Add DEBUG-level logging for the synthetic-first-datapoint query For diagnosing a user's slow history page * Missed a couple instances of `created` that should be `last_updated` * Remove `entity_id` sorting from state_changes; match significant_update This is the same change as 09b3498f410106881fc5e095c49a8d527fa89644 , but applied to the `state_changes_during_period` method which I missed before. This should give the same performance boost to the history sensor component! * Bugfix in History query used for History Sensor The date filter was using a different column for the upper and lower bounds. It would work, but it would be slow! * Update Recorder purge script to use more appropriate columns Two reasons: 1. the `created` column's meaning is fairly arbitrary and does not represent when an event or state change actually ocurred. It seems more correct to purge based on the event date than the time the database row was written. 2. The new columns are indexed, which will speed up this purge script by orders of magnitude * Updating db model to match new query optimizations A few things here: 1. New schema version with a new index and several removed indexes 2. A new method in the migration script to drop old indexes 3. Added an INFO-level log message when a new index will be added, as this can take quite some time on a Raspberry Pi
2017-08-05 06:16:53 +00:00
return result
except SQLAlchemyError as err:
_LOGGER.error("Error executing query: %s", err)
if tryno == RETRIES - 1:
raise
time.sleep(QUERY_RETRY_WAIT)
def validate_or_move_away_sqlite_database(dburl: str) -> bool:
"""Ensure that the database is valid or move it away."""
dbpath = dburl_to_path(dburl)
if not os.path.exists(dbpath):
# Database does not exist yet, this is OK
return True
if not validate_sqlite_database(dbpath):
move_away_broken_database(dbpath)
return False
return True
def dburl_to_path(dburl):
"""Convert the db url into a filesystem path."""
return dburl[len(SQLITE_URL_PREFIX) :]
def last_run_was_recently_clean(cursor):
"""Verify the last recorder run was recently clean."""
cursor.execute("SELECT end FROM recorder_runs ORDER BY start DESC LIMIT 1;")
end_time = cursor.fetchone()
if not end_time or not end_time[0]:
return False
last_run_end_time = process_timestamp(dt_util.parse_datetime(end_time[0]))
now = dt_util.utcnow()
_LOGGER.debug("The last run ended at: %s (now: %s)", last_run_end_time, now)
if last_run_end_time + MAX_RESTART_TIME < now:
return False
return True
def basic_sanity_check(cursor):
"""Check tables to make sure select does not fail."""
for table in ALL_TABLES:
if table in (TABLE_RECORDER_RUNS, TABLE_SCHEMA_CHANGES):
cursor.execute(f"SELECT * FROM {table};") # nosec # not injection
else:
cursor.execute(f"SELECT * FROM {table} LIMIT 1;") # nosec # not injection
return True
def validate_sqlite_database(dbpath: str) -> bool:
"""Run a quick check on an sqlite database to see if it is corrupt."""
import sqlite3 # pylint: disable=import-outside-toplevel
try:
conn = sqlite3.connect(dbpath)
run_checks_on_open_db(dbpath, conn.cursor())
conn.close()
except sqlite3.DatabaseError:
_LOGGER.exception("The database at %s is corrupt or malformed", dbpath)
return False
return True
def run_checks_on_open_db(dbpath, cursor):
"""Run checks that will generate a sqlite3 exception if there is corruption."""
sanity_check_passed = basic_sanity_check(cursor)
last_run_was_clean = last_run_was_recently_clean(cursor)
if sanity_check_passed and last_run_was_clean:
_LOGGER.debug(
"The system was restarted cleanly and passed the basic sanity check"
)
return
if not sanity_check_passed:
_LOGGER.warning(
"The database sanity check failed to validate the sqlite3 database at %s",
dbpath,
)
if not last_run_was_clean:
_LOGGER.warning(
"The system could not validate that the sqlite3 database at %s was shutdown cleanly",
dbpath,
)
def move_away_broken_database(dbfile: str) -> None:
"""Move away a broken sqlite3 database."""
isotime = dt_util.utcnow().isoformat()
corrupt_postfix = f".corrupt.{isotime}"
_LOGGER.error(
"The system will rename the corrupt database file %s to %s in order to allow startup to proceed",
dbfile,
f"{dbfile}{corrupt_postfix}",
)
for postfix in SQLITE3_POSTFIXES:
path = f"{dbfile}{postfix}"
if not os.path.exists(path):
continue
os.rename(path, f"{path}{corrupt_postfix}")
def execute_on_connection(dbapi_connection, statement):
"""Execute a single statement with a dbapi connection."""
cursor = dbapi_connection.cursor()
cursor.execute(statement)
cursor.close()
def setup_connection_for_dialect(dialect_name, dbapi_connection):
"""Execute statements needed for dialect connection."""
# Returns False if the the connection needs to be setup
# on the next connection, returns True if the connection
# never needs to be setup again.
if dialect_name == "sqlite":
old_isolation = dbapi_connection.isolation_level
dbapi_connection.isolation_level = None
execute_on_connection(dbapi_connection, "PRAGMA journal_mode=WAL")
dbapi_connection.isolation_level = old_isolation
# WAL mode only needs to be setup once
# instead of every time we open the sqlite connection
# as its persistent and isn't free to call every time.
return True
if dialect_name == "mysql":
execute_on_connection(dbapi_connection, "SET session wait_timeout=28800")
return False
def end_incomplete_runs(session, start_time):
"""End any incomplete recorder runs."""
for run in session.query(RecorderRuns).filter_by(end=None):
run.closed_incorrect = True
run.end = start_time
_LOGGER.warning(
"Ended unfinished session (id=%s from %s)", run.run_id, run.start
)
session.add(run)