ClickHouse/src/Interpreters/QueryLog.cpp

278 lines
14 KiB
C++
Raw Normal View History

#include <array>
#include <Columns/ColumnArray.h>
#include <Columns/ColumnFixedString.h>
#include <Columns/ColumnString.h>
#include <Columns/ColumnsNumber.h>
#include <DataTypes/DataTypeArray.h>
#include <DataTypes/DataTypeDateTime64.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeNullable.h>
#include <DataTypes/DataTypeDateTime.h>
2019-08-01 11:11:08 +00:00
#include <DataTypes/DataTypeEnum.h>
#include <DataTypes/DataTypeFactory.h>
2020-12-12 05:57:27 +00:00
#include <DataTypes/DataTypeLowCardinality.h>
#include <DataTypes/DataTypeString.h>
#include <DataTypes/DataTypesNumber.h>
#include <Interpreters/ProfileEventsExt.h>
#include <Interpreters/QueryLog.h>
2016-10-27 17:48:12 +00:00
#include <Poco/Net/IPAddress.h>
#include <Common/ClickHouseRevision.h>
#include <Common/IPv6ToBinary.h>
#include <Common/ProfileEvents.h>
namespace DB
{
2016-10-27 17:48:12 +00:00
Block QueryLogElement::createBlock()
{
2020-09-04 16:10:29 +00:00
auto query_status_datatype = std::make_shared<DataTypeEnum8>(
DataTypeEnum8::Values
{
{"QueryStart", static_cast<Int8>(QUERY_START)},
{"QueryFinish", static_cast<Int8>(QUERY_FINISH)},
{"ExceptionBeforeStart", static_cast<Int8>(EXCEPTION_BEFORE_START)},
{"ExceptionWhileProcessing", static_cast<Int8>(EXCEPTION_WHILE_PROCESSING)}
});
2020-09-04 16:10:29 +00:00
return
{
{std::move(query_status_datatype), "type"},
{std::make_shared<DataTypeDate>(), "event_date"},
{std::make_shared<DataTypeDateTime>(), "event_time"},
{std::make_shared<DataTypeDateTime64>(6), "event_time_microseconds"},
2020-09-04 16:10:29 +00:00
{std::make_shared<DataTypeDateTime>(), "query_start_time"},
{std::make_shared<DataTypeDateTime64>(6), "query_start_time_microseconds"},
{std::make_shared<DataTypeUInt64>(), "query_duration_ms"},
2020-09-04 16:10:29 +00:00
{std::make_shared<DataTypeUInt64>(), "read_rows"},
{std::make_shared<DataTypeUInt64>(), "read_bytes"},
{std::make_shared<DataTypeUInt64>(), "written_rows"},
{std::make_shared<DataTypeUInt64>(), "written_bytes"},
{std::make_shared<DataTypeUInt64>(), "result_rows"},
{std::make_shared<DataTypeUInt64>(), "result_bytes"},
{std::make_shared<DataTypeUInt64>(), "memory_usage"},
2020-09-04 16:10:29 +00:00
{std::make_shared<DataTypeString>(), "current_database"},
{std::make_shared<DataTypeString>(), "query"},
{std::make_shared<DataTypeUInt64>(), "normalized_query_hash"},
{std::make_shared<DataTypeLowCardinality>(std::make_shared<DataTypeString>()), "query_kind"},
2020-12-14 03:30:39 +00:00
{std::make_shared<DataTypeArray>(
std::make_shared<DataTypeLowCardinality>(std::make_shared<DataTypeString>())), "databases"},
{std::make_shared<DataTypeArray>(
std::make_shared<DataTypeLowCardinality>(std::make_shared<DataTypeString>())), "tables"},
{std::make_shared<DataTypeArray>(
std::make_shared<DataTypeLowCardinality>(std::make_shared<DataTypeString>())), "columns"},
{std::make_shared<DataTypeArray>(
std::make_shared<DataTypeLowCardinality>(std::make_shared<DataTypeString>())), "projections"},
2020-09-04 16:10:29 +00:00
{std::make_shared<DataTypeInt32>(), "exception_code"},
{std::make_shared<DataTypeString>(), "exception"},
{std::make_shared<DataTypeString>(), "stack_trace"},
2020-09-04 16:10:29 +00:00
{std::make_shared<DataTypeUInt8>(), "is_initial_query"},
{std::make_shared<DataTypeString>(), "user"},
{std::make_shared<DataTypeString>(), "query_id"},
{DataTypeFactory::instance().get("IPv6"), "address"},
{std::make_shared<DataTypeUInt16>(), "port"},
{std::make_shared<DataTypeString>(), "initial_user"},
{std::make_shared<DataTypeString>(), "initial_query_id"},
{DataTypeFactory::instance().get("IPv6"), "initial_address"},
{std::make_shared<DataTypeUInt16>(), "initial_port"},
{std::make_shared<DataTypeUInt8>(), "interface"},
{std::make_shared<DataTypeString>(), "os_user"},
{std::make_shared<DataTypeString>(), "client_hostname"},
{std::make_shared<DataTypeString>(), "client_name"},
{std::make_shared<DataTypeUInt32>(), "client_revision"},
{std::make_shared<DataTypeUInt32>(), "client_version_major"},
{std::make_shared<DataTypeUInt32>(), "client_version_minor"},
{std::make_shared<DataTypeUInt32>(), "client_version_patch"},
{std::make_shared<DataTypeUInt8>(), "http_method"},
{std::make_shared<DataTypeString>(), "http_user_agent"},
2021-01-21 22:55:45 +00:00
{std::make_shared<DataTypeString>(), "http_referer"},
{std::make_shared<DataTypeString>(), "forwarded_for"},
2020-09-04 16:10:29 +00:00
{std::make_shared<DataTypeString>(), "quota_key"},
2020-09-04 16:10:29 +00:00
{std::make_shared<DataTypeUInt32>(), "revision"},
2021-01-25 19:18:23 +00:00
{std::make_shared<DataTypeString>(), "log_comment"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeUInt64>()), "thread_ids"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "ProfileEvents.Names"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeUInt64>()), "ProfileEvents.Values"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "Settings.Names"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "Settings.Values"},
2021-01-21 21:15:11 +00:00
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_aggregate_functions"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_aggregate_function_combinators"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_database_engines"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_data_type_families"},
2021-01-21 21:15:11 +00:00
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_dictionaries"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_formats"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_functions"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_storages"},
{std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>()), "used_table_functions"}
2020-09-04 16:10:29 +00:00
};
}
void QueryLogElement::appendToBlock(MutableColumns & columns) const
{
size_t i = 0;
2019-08-01 11:11:08 +00:00
columns[i++]->insert(type);
Extended range of DateTime64 to years 1925 - 2238 The Year 1925 is a starting point because most of the timezones switched to saner (mostly 15-minutes based) offsets somewhere during 1924 or before. And that significantly simplifies implementation. 2238 is to simplify arithmetics for sanitizing LUT index access; there are less than 0x1ffff days from 1925. * Extended DateLUTImpl internal LUT to 0x1ffff items, some of which represent negative (pre-1970) time values. As a collateral benefit, Date now correctly supports dates up to 2149 (instead of 2106). * Added a new strong typedef ExtendedDayNum, which represents dates pre-1970 and post 2149. * Functions that used to return DayNum now return ExtendedDayNum. * Refactored DateLUTImpl to untie DayNum from the dual role of being a value and an index (due to negative time). Index is now a different type LUTIndex with explicit conversion functions from DatNum, time_t, and ExtendedDayNum. * Updated DateLUTImpl to properly support values close to epoch start (1970-01-01 00:00), including negative ones. * Reduced resolution of DateLUTImpl::Values::time_at_offset_change to multiple of 15-minutes to allow storing 64-bits of time_t in DateLUTImpl::Value while keeping same size. * Minor performance updates to DateLUTImpl when building month LUT by skipping non-start-of-month days. * Fixed extractTimeZoneFromFunctionArguments to work correctly with DateTime64. * New unit-tests and stateless integration tests for both DateTime and DateTime64.
2020-04-17 13:26:44 +00:00
columns[i++]->insert(DateLUT::instance().toDayNum(event_time).toUnderType());
columns[i++]->insert(event_time);
columns[i++]->insert(event_time_microseconds);
columns[i++]->insert(query_start_time);
columns[i++]->insert(query_start_time_microseconds);
columns[i++]->insert(query_duration_ms);
columns[i++]->insert(read_rows);
columns[i++]->insert(read_bytes);
columns[i++]->insert(written_rows);
columns[i++]->insert(written_bytes);
columns[i++]->insert(result_rows);
columns[i++]->insert(result_bytes);
columns[i++]->insert(memory_usage);
columns[i++]->insertData(current_database.data(), current_database.size());
columns[i++]->insertData(query.data(), query.size());
columns[i++]->insert(normalized_query_hash);
columns[i++]->insertData(query_kind.data(), query_kind.size());
{
auto & column_databases = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_tables = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_columns = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_projections = typeid_cast<ColumnArray &>(*columns[i++]);
2021-01-22 09:02:58 +00:00
auto fill_column = [](const std::set<String> & data, ColumnArray & column)
{
size_t size = 0;
for (const auto & name : data)
{
column.getData().insertData(name.data(), name.size());
++size;
}
auto & offsets = column.getOffsets();
offsets.push_back(offsets.back() + size);
};
2021-01-21 21:15:11 +00:00
fill_column(query_databases, column_databases);
fill_column(query_tables, column_tables);
fill_column(query_columns, column_columns);
fill_column(query_projections, column_projections);
}
columns[i++]->insert(exception_code);
2020-01-22 12:29:30 +00:00
columns[i++]->insertData(exception.data(), exception.size());
columns[i++]->insertData(stack_trace.data(), stack_trace.size());
appendClientInfo(client_info, columns, i);
2020-09-17 12:15:05 +00:00
columns[i++]->insert(ClickHouseRevision::getVersionRevision());
2021-01-25 19:18:23 +00:00
columns[i++]->insertData(log_comment.data(), log_comment.size());
{
Array threads_array;
2020-02-02 02:27:15 +00:00
threads_array.reserve(thread_ids.size());
for (const UInt64 thread_id : thread_ids)
threads_array.emplace_back(thread_id);
columns[i++]->insert(threads_array);
}
if (profile_counters)
{
2020-04-22 06:01:33 +00:00
auto * column_names = columns[i++].get();
auto * column_values = columns[i++].get();
ProfileEvents::dumpToArrayColumns(*profile_counters, column_names, column_values, true);
}
else
{
columns[i++]->insertDefault();
columns[i++]->insertDefault();
}
if (query_settings)
{
2020-04-22 06:01:33 +00:00
auto * column_names = columns[i++].get();
auto * column_values = columns[i++].get();
query_settings->dumpToArrayColumns(column_names, column_values, true);
}
else
{
columns[i++]->insertDefault();
columns[i++]->insertDefault();
}
2021-01-21 21:15:11 +00:00
{
2021-01-22 09:02:58 +00:00
auto & column_aggregate_function_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_aggregate_function_combinator_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
2021-01-22 09:02:58 +00:00
auto & column_database_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_data_type_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_dictionary_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_format_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_function_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_storage_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
auto & column_table_function_factory_objects = typeid_cast<ColumnArray &>(*columns[i++]);
2021-01-21 21:15:11 +00:00
auto fill_column = [](const std::unordered_set<String> & data, ColumnArray & column)
{
size_t size = 0;
for (const auto & name : data)
{
column.getData().insertData(name.data(), name.size());
++size;
}
auto & offsets = column.getOffsets();
offsets.push_back(offsets.back() + size);
};
fill_column(used_aggregate_functions, column_aggregate_function_factory_objects);
fill_column(used_aggregate_function_combinators, column_aggregate_function_combinator_factory_objects);
fill_column(used_database_engines, column_database_factory_objects);
fill_column(used_data_type_families, column_data_type_factory_objects);
2021-01-21 21:15:11 +00:00
fill_column(used_dictionaries, column_dictionary_factory_objects);
fill_column(used_formats, column_format_factory_objects);
fill_column(used_functions, column_function_factory_objects);
fill_column(used_storages, column_storage_factory_objects);
fill_column(used_table_functions, column_table_function_factory_objects);
}
}
void QueryLogElement::appendClientInfo(const ClientInfo & client_info, MutableColumns & columns, size_t & i)
{
columns[i++]->insert(client_info.query_kind == ClientInfo::QueryKind::INITIAL_QUERY);
columns[i++]->insert(client_info.current_user);
columns[i++]->insert(client_info.current_query_id);
columns[i++]->insertData(IPv6ToBinary(client_info.current_address.host()).data(), 16);
columns[i++]->insert(client_info.current_address.port());
columns[i++]->insert(client_info.initial_user);
columns[i++]->insert(client_info.initial_query_id);
columns[i++]->insertData(IPv6ToBinary(client_info.initial_address.host()).data(), 16);
columns[i++]->insert(client_info.initial_address.port());
columns[i++]->insert(UInt64(client_info.interface));
columns[i++]->insert(client_info.os_user);
columns[i++]->insert(client_info.client_hostname);
columns[i++]->insert(client_info.client_name);
2020-09-17 12:15:05 +00:00
columns[i++]->insert(client_info.client_tcp_protocol_version);
columns[i++]->insert(client_info.client_version_major);
columns[i++]->insert(client_info.client_version_minor);
columns[i++]->insert(client_info.client_version_patch);
columns[i++]->insert(UInt64(client_info.http_method));
columns[i++]->insert(client_info.http_user_agent);
2021-01-21 22:55:45 +00:00
columns[i++]->insert(client_info.http_referer);
columns[i++]->insert(client_info.forwarded_for);
columns[i++]->insert(client_info.quota_key);
}
}