def process_query(self, query: Query, query_settings: QuerySettings) -> None: mandatory_conditions = query.get_from_clause().mandatory_conditions if len(mandatory_conditions) > 0: query.add_condition_to_ast( combine_and_conditions(mandatory_conditions))
def process_query(self, query: Query, query_settings: QuerySettings) -> None: single_filtered, multiple_filtered = self.get_filtered_arrays( query, self.key_columns) bloom_filter_condition = generate_bloom_filter_condition( self.column_name, single_filtered, multiple_filtered) if bloom_filter_condition: query.add_condition_to_ast(bloom_filter_condition)
def process_query(self, query: Query, request_settings: RequestSettings) -> None: if request_settings.get_turbo(): return project_ids = get_project_ids_in_query_ast(query, self.__project_column) set_final = False condition_to_add = None if project_ids: final, exclude_group_ids = get_projects_query_flags( list(project_ids), self.__replacer_state_name, ) if final: metrics.increment("final", tags={"cause": "final_flag"}) if not final and exclude_group_ids: # If the number of groups to exclude exceeds our limit, the query # should just use final instead of the exclusion set. max_group_ids_exclude = get_config( "max_group_ids_exclude", settings.REPLACER_MAX_GROUP_IDS_TO_EXCLUDE) if len(exclude_group_ids) > max_group_ids_exclude: metrics.increment("final", tags={"cause": "max_groups"}) set_final = True else: condition_to_add = ( ["assumeNotNull", ["group_id"]], "NOT IN", exclude_group_ids, ) query.add_condition_to_ast( not_in_condition( None, FunctionCall(None, "assumeNotNull", (Column(None, None, "group_id"), )), [Literal(None, p) for p in exclude_group_ids], )) else: set_final = final query.set_final(set_final) if condition_to_add: query.add_conditions([condition_to_add])
def process_query(self, query: Query, query_settings: QuerySettings) -> None: if query_settings.get_turbo(): return project_ids = get_object_ids_in_query_ast(query, self.__project_column) if project_ids is None: self._set_query_final(query, False) return flags: ProjectsQueryFlags = ProjectsQueryFlags.load_from_redis( list(project_ids), self.__replacer_state_name ) query_overlaps_replacement = self._query_overlaps_replacements( query, flags.latest_replacement_time ) if not query_overlaps_replacement: self._set_query_final(query, False) return tags = self._initialize_tags(query_settings, flags) set_final = False if flags.needs_final: tags["cause"] = "final_flag" metrics.increment( name=FINAL_METRIC, tags=tags, ) set_final = True elif flags.group_ids_to_exclude: # If the number of groups to exclude exceeds our limit, the query # should just use final instead of the exclusion set. max_group_ids_exclude = get_config( "max_group_ids_exclude", settings.REPLACER_MAX_GROUP_IDS_TO_EXCLUDE, ) assert isinstance(max_group_ids_exclude, int) groups_to_exclude = self._groups_to_exclude( query, flags.group_ids_to_exclude ) if len(groups_to_exclude) > max_group_ids_exclude: tags["cause"] = "max_groups" metrics.increment( name=FINAL_METRIC, tags=tags, ) set_final = True elif groups_to_exclude: query.add_condition_to_ast( not_in_condition( FunctionCall( None, "assumeNotNull", (Column(None, None, self.__groups_column),), ), [Literal(None, p) for p in groups_to_exclude], ) ) self._set_query_final(query, set_final)
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)
def execute( self, query: Query, query_settings: QuerySettings, 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 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() 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. selected_columns = { (col.table_name, col.column_name) for col in query.get_columns_referenced_in_select() } if len(selected_columns) < settings.COLUMN_SPLIT_MIN_COLS: metrics.increment("column_splitter.main_query_min_threshold") return None minimal_query = copy.deepcopy(query) # 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(self.__id_column, None, self.__id_column), ), SelectedExpression( self.__project_column, ColumnExpr(self.__project_column, None, self.__project_column), ), SelectedExpression( self.__timestamp_column, ColumnExpr(self.__timestamp_column, 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, ) # Ensures the AST minimal query is actually runnable on its own. if not minimal_query.validate_aliases(): return None # There is a Clickhouse bug where if functions in the ORDER BY clause are not in the SELECT, # they fail on distributed tables. For that specific case, skip the query splitter. for orderby in minimal_query.get_orderby(): if isinstance(orderby.expression, (FunctionCallExpr, CurriedFunctionCallExpr)): metrics.increment("column_splitter.orderby_has_a_function") return None result = runner(minimal_query, query_settings) del minimal_query if not result.result["data"]: metrics.increment("column_splitter.no_data_from_minimal_query") 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_condition_to_ast( in_condition( ColumnExpr(None, None, self.__id_column), [LiteralExpr(None, e_id) for e_id in event_ids], )) query.set_offset(0) query.set_limit(len(result.result["data"])) project_ids = list( set([ event[self.__project_column] for event in result.result["data"] ])) _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_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_ast_condition( query, self.__timestamp_column, "<", LiteralExpr( None, (util.parse_datetime(max(timestamps)) + timedelta(seconds=1)), ), ) return runner(query, query_settings)