def execute_query_with_caching(
clickhouse_query: Query,
request_settings: RequestSettings,
formatted_query: SqlQuery,
reader: Reader[SqlQuery],
timer: Timer,
stats: MutableMapping[str, Any],
query_settings: MutableMapping[str, Any],
) -> Result:
# XXX: ``uncompressed_cache_max_cols`` is used to control both the result
# cache, as well as the uncompressed cache. These should be independent.
use_cache, uc_max = state.get_configs([("use_cache",
settings.USE_RESULT_CACHE),
("uncompressed_cache_max_cols", 5)])
if (len(
set((
# Skip aliases when counting columns
(c.table_name, c.column_name)
for c in clickhouse_query.get_all_ast_referenced_columns()))) >
uc_max):
use_cache = False
execute = partial(
execute_query_with_rate_limits,
clickhouse_query,
request_settings,
formatted_query,
reader,
timer,
stats,
query_settings,
)
with sentry_sdk.start_span(description="execute", op="db") as span:
if use_cache:
key = get_query_cache_key(formatted_query)
result = cache.get(key)
timer.mark("cache_get")
stats["cache_hit"] = result is not None
if result is not None:
span.set_tag("cache", "hit")
return result
span.set_tag("cache", "miss")
result = execute()
cache.set(key, result)
timer.mark("cache_set")
return result
else:
return execute()
def execute_query(
# TODO: Passing the whole clickhouse query here is needed as long
# as the execute method depends on it. Otherwise we can make this
# file rely either entirely on clickhouse query or entirely on
# the formatter.
clickhouse_query: Query,
request_settings: RequestSettings,
formatted_query: SqlQuery,
reader: Reader[SqlQuery],
timer: Timer,
stats: MutableMapping[str, Any],
query_settings: MutableMapping[str, Any],
) -> Result:
"""
Execute a query and return a result.
"""
# Experiment, if we are going to grab more than X columns worth of data,
# don't use uncompressed_cache in ClickHouse.
uc_max = state.get_config("uncompressed_cache_max_cols", 5)
if (len(
set((
# Skip aliases when counting columns
(c.table_name, c.column_name)
for c in clickhouse_query.get_all_ast_referenced_columns()))) >
uc_max):
query_settings["use_uncompressed_cache"] = 0
# Force query to use the first shard replica, which
# should have synchronously received any cluster writes
# before this query is run.
consistent = request_settings.get_consistent()
stats["consistent"] = consistent
if consistent:
query_settings["load_balancing"] = "in_order"
query_settings["max_threads"] = 1
result = reader.execute(
formatted_query,
query_settings,
with_totals=clickhouse_query.has_totals(),
)
timer.mark("execute")
stats.update({
"result_rows": len(result["data"]),
"result_cols": len(result["meta"])
})
return result
def _get_all_columns(query: Query) -> Columnset:
return {c.column_name for c in query.get_all_ast_referenced_columns()}
def execute(
self,
query: Query,
request_settings: RequestSettings,
runner: SplitQueryRunner,
) -> Optional[QueryResult]:
"""
Split query in 2 steps if a large number of columns is being selected.
- First query only selects event_id, project_id and timestamp.
- Second query selects all fields for only those events.
- Shrink the date range.
"""
limit = query.get_limit()
if (limit is None or limit == 0 or query.get_groupby()
or query.get_aggregations()
or not query.get_selected_columns()):
return None
if limit > settings.COLUMN_SPLIT_MAX_LIMIT:
metrics.increment("column_splitter.query_above_limit")
return None
# Do not split if there is already a = or IN condition on an ID column
id_column_matcher = FunctionCall(
Or([String(ConditionFunctions.EQ),
String(ConditionFunctions.IN)]),
(
Column(None, String(self.__id_column)),
AnyExpression(),
),
)
for expr in query.get_condition_from_ast() or []:
match = id_column_matcher.match(expr)
if match:
return None
# We need to count the number of table/column name pairs
# not the number of distinct Column objects in the query
# so to avoid counting aliased columns multiple times.
total_columns = {(col.table_name, col.column_name)
for col in query.get_all_ast_referenced_columns()}
minimal_query = copy.deepcopy(query)
minimal_query.set_selected_columns(
[self.__id_column, self.__project_column, self.__timestamp_column])
# TODO: provide the table alias name to this splitter if we ever use it
# in joins.
minimal_query.set_ast_selected_columns([
SelectedExpression(self.__id_column,
ColumnExpr(None, None, self.__id_column)),
SelectedExpression(self.__project_column,
ColumnExpr(None, None, self.__project_column)),
SelectedExpression(
self.__timestamp_column,
ColumnExpr(None, None, self.__timestamp_column),
),
])
for exp in minimal_query.get_all_expressions():
if exp.alias in (
self.__id_column,
self.__project_column,
self.__timestamp_column,
) and not (isinstance(exp, ColumnExpr)
and exp.column_name == exp.alias):
logger.warning(
"Potential alias shadowing due to column splitter",
extra={"expression": exp},
exc_info=True,
)
minimal_columns = {
(col.table_name, col.column_name)
for col in minimal_query.get_all_ast_referenced_columns()
}
if len(total_columns) <= len(minimal_columns):
return None
# Ensures the AST minimal query is actually runnable on its own.
if not minimal_query.validate_aliases():
return None
legacy_references = set(minimal_query.get_all_referenced_columns())
ast_column_names = {
c.column_name
for c in minimal_query.get_all_ast_referenced_columns()
}
# Ensures the legacy minimal query (which does not expand alias references)
# does not contain alias references we removed when creating minimal_query.
if legacy_references - ast_column_names:
metrics.increment("columns.skip_invalid_legacy_query")
return None
result = runner(minimal_query, request_settings)
del minimal_query
if not result.result["data"]:
return None
# Making a copy just in case runner returned None (which would drive the execution
# strategy to ignore the result of this splitter and try the next one).
query = copy.deepcopy(query)
event_ids = list(
set([event[self.__id_column] for event in result.result["data"]]))
if len(event_ids) > settings.COLUMN_SPLIT_MAX_RESULTS:
# We may be runing a query that is beyond clickhouse maximum query size,
# so we cowardly abandon.
metrics.increment(
"column_splitter.intermediate_results_beyond_limit")
return None
query.add_conditions([(self.__id_column, "IN", event_ids)])
query.add_condition_to_ast(
in_condition(
None,
ColumnExpr(None, None, self.__id_column),
[LiteralExpr(None, e_id) for e_id in event_ids],
))
query.set_offset(0)
# TODO: This is technically wrong. Event ids are unique per project, not globally.
# So, if the minimal query only returned the same event_id from two projects, we
# would be underestimating the limit here.
query.set_limit(len(event_ids))
project_ids = list(
set([
event[self.__project_column] for event in result.result["data"]
]))
_replace_condition(
query,
self.__project_column,
"IN",
project_ids,
)
_replace_ast_condition(
query,
self.__project_column,
"IN",
literals_tuple(None,
[LiteralExpr(None, p_id) for p_id in project_ids]),
)
timestamps = [
event[self.__timestamp_column] for event in result.result["data"]
]
_replace_condition(
query,
self.__timestamp_column,
">=",
util.parse_datetime(min(timestamps)).isoformat(),
)
_replace_ast_condition(
query,
self.__timestamp_column,
">=",
LiteralExpr(None, util.parse_datetime(min(timestamps))),
)
# We add 1 second since this gets translated to ('timestamp', '<', to_date)
# and events are stored with a granularity of 1 second.
_replace_condition(
query,
self.__timestamp_column,
"<",
(util.parse_datetime(max(timestamps)) +
timedelta(seconds=1)).isoformat(),
)
_replace_ast_condition(
query,
self.__timestamp_column,
"<",
LiteralExpr(
None,
(util.parse_datetime(max(timestamps)) + timedelta(seconds=1)),
),
)
return runner(query, request_settings)
