thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 00:30:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #7653 from vitlibar/skip-unknown-settings-with-warnings

Browse Source 
Skip unknown settings with warnings.
This commit is contained in:
Vitaly Baranov 2019-11-18 13:50:52 +03:00 committed by GitHub
commit 681f03c625
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
25 changed files with 850 additions and 630 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
dbms/programs/server/TCPHandler.cpp
View File

@ -924,7 +924,9 @@ void TCPHandler::receiveQuery()
/// Per query settings.
Settings & settings = query_context->getSettingsRef();
settings.deserialize(*in);
auto settings_format = (client_revision >= DBMS_MIN_REVISION_WITH_SETTINGS_SERIALIZED_AS_STRINGS) ? SettingsBinaryFormat::STRINGS
: SettingsBinaryFormat::OLD;
settings.deserialize(*in, settings_format);
/// Sync timeouts on client and server during current query to avoid dangling queries on server
/// NOTE: We use settings.send_timeout for the receive timeout and vice versa (change arguments ordering in TimeoutSetter),
@ -953,7 +955,9 @@ void TCPHandler::receiveUnexpectedQuery()
skip_client_info.read(*in, client_revision);
Settings & skip_settings = query_context->getSettingsRef();
skip_settings.deserialize(*in);
auto settings_format = (client_revision >= DBMS_MIN_REVISION_WITH_SETTINGS_SERIALIZED_AS_STRINGS) ? SettingsBinaryFormat::STRINGS
: SettingsBinaryFormat::OLD;
skip_settings.deserialize(*in, settings_format);
readVarUInt(skip_uint_64, *in);
readVarUInt(skip_uint_64, *in);

6
dbms/src/Client/Connection.cpp
View File

@ -409,7 +409,11 @@ void Connection::sendQuery(
/// Per query settings.
if (settings)
settings->serialize(*out);
{
auto settings_format = (server_revision >= DBMS_MIN_REVISION_WITH_SETTINGS_SERIALIZED_AS_STRINGS) ? SettingsBinaryFormat::STRINGS
: SettingsBinaryFormat::OLD;
settings->serialize(*out, settings_format);
}
else
writeStringBinary("" /* empty string is a marker of the end of settings */, *out);

2
dbms/src/Common/ThreadStatus.h
View File

@ -4,7 +4,7 @@
#include <Common/ProfileEvents.h>
#include <Common/MemoryTracker.h>
#include <Core/SettingsCommon.h>
#include <Core/SettingsCollection.h>
#include <IO/Progress.h>

10
dbms/src/Core/Defines.h
View File

@ -59,9 +59,11 @@
#define DBMS_MIN_REVISION_WITH_COLUMN_DEFAULTS_METADATA 54410
#define DBMS_MIN_REVISION_WITH_LOW_CARDINALITY_TYPE 54405
#define DBMS_MIN_REVISION_WITH_CLIENT_WRITE_INFO 54420
/// Mininum revision supporting SettingsBinaryFormat::STRINGS.
#define DBMS_MIN_REVISION_WITH_SETTINGS_SERIALIZED_AS_STRINGS 54429
/// Version of ClickHouse TCP protocol. Set to git tag with latest protocol change.
#define DBMS_TCP_PROTOCOL_VERSION 54226
@ -148,9 +150,9 @@
#define OPTIMIZE(x)
#endif
/// This number is only used for distributed version compatible.
/// It could be any magic number.
#define DBMS_DISTRIBUTED_SENDS_MAGIC_NUMBER 0xCAFECABE
/// Marks that extra information is sent to a shard. It could be any magic numbers.
#define DBMS_DISTRIBUTED_SIGNATURE_EXTRA_INFO 0xCAFEDACEull
#define DBMS_DISTRIBUTED_SIGNATURE_SETTINGS_OLD_FORMAT 0xCAFECABEull
#if !__has_include(<sanitizer/asan_interface.h>)
# define ASAN_UNPOISON_MEMORY_REGION(a, b)

515
dbms/src/Core/Settings.h
View File

@ -1,6 +1,6 @@
#pragma once
#include "SettingsCommon.h"
#include <Core/SettingsCollection.h>
#include <Core/Defines.h>
@ -35,219 +35,222 @@ struct Settings : public SettingsCollection<Settings>
/// http://en.cppreference.com/w/cpp/language/aggregate_initialization
Settings() {}
/** List of settings: type, name, default value.
/** List of settings: type, name, default value, description, flags
*
* This looks rather unconvenient. It is done that way to avoid repeating settings in different places.
* Note: as an alternative, we could implement settings to be completely dynamic in form of map: String -> Field,
* but we are not going to do it, because settings is used everywhere as static struct fields.
*
* `flags` can be either 0 or IGNORABLE.
* A setting is "IGNORABLE" if it doesn't affects the results of the queries and can be ignored without exception.
*/
#define LIST_OF_SETTINGS(M) \
M(SettingUInt64, min_compress_block_size, 65536, "The actual size of the block to compress, if the uncompressed data less than max_compress_block_size is no less than this value and no less than the volume of data for one mark.") \
M(SettingUInt64, max_compress_block_size, 1048576, "The maximum size of blocks of uncompressed data before compressing for writing to a table.") \
M(SettingUInt64, max_block_size, DEFAULT_BLOCK_SIZE, "Maximum block size for reading") \
M(SettingUInt64, max_insert_block_size, DEFAULT_INSERT_BLOCK_SIZE, "The maximum block size for insertion, if we control the creation of blocks for insertion.") \
M(SettingUInt64, min_insert_block_size_rows, DEFAULT_INSERT_BLOCK_SIZE, "Squash blocks passed to INSERT query to specified size in rows, if blocks are not big enough.") \
M(SettingUInt64, min_insert_block_size_bytes, (DEFAULT_INSERT_BLOCK_SIZE * 256), "Squash blocks passed to INSERT query to specified size in bytes, if blocks are not big enough.") \
M(SettingMaxThreads, max_threads, 0, "The maximum number of threads to execute the request. By default, it is determined automatically.") \
M(SettingMaxThreads, max_alter_threads, 0, "The maximum number of threads to execute the ALTER requests. By default, it is determined automatically.") \
M(SettingUInt64, max_read_buffer_size, DBMS_DEFAULT_BUFFER_SIZE, "The maximum size of the buffer to read from the filesystem.") \
M(SettingUInt64, max_distributed_connections, 1024, "The maximum number of connections for distributed processing of one query (should be greater than max_threads).") \
M(SettingUInt64, max_query_size, 262144, "Which part of the query can be read into RAM for parsing (the remaining data for INSERT, if any, is read later)") \
M(SettingUInt64, interactive_delay, 100000, "The interval in microseconds to check if the request is cancelled, and to send progress info.") \
M(SettingSeconds, connect_timeout, DBMS_DEFAULT_CONNECT_TIMEOUT_SEC, "Connection timeout if there are no replicas.") \
M(SettingMilliseconds, connect_timeout_with_failover_ms, DBMS_DEFAULT_CONNECT_TIMEOUT_WITH_FAILOVER_MS, "Connection timeout for selecting first healthy replica.") \
M(SettingSeconds, receive_timeout, DBMS_DEFAULT_RECEIVE_TIMEOUT_SEC, "") \
M(SettingSeconds, send_timeout, DBMS_DEFAULT_SEND_TIMEOUT_SEC, "") \
M(SettingSeconds, tcp_keep_alive_timeout, 0, "The time in seconds the connection needs to remain idle before TCP starts sending keepalive probes") \
M(SettingMilliseconds, queue_max_wait_ms, 0, "The wait time in the request queue, if the number of concurrent requests exceeds the maximum.") \
M(SettingMilliseconds, connection_pool_max_wait_ms, 0, "The wait time when connection pool is full.") \
M(SettingMilliseconds, replace_running_query_max_wait_ms, 5000, "The wait time for running query with the same query_id to finish when setting 'replace_running_query' is active.") \
M(SettingMilliseconds, kafka_max_wait_ms, 5000, "The wait time for reading from Kafka before retry.") \
M(SettingUInt64, poll_interval, DBMS_DEFAULT_POLL_INTERVAL, "Block at the query wait loop on the server for the specified number of seconds.") \
M(SettingUInt64, idle_connection_timeout, 3600, "Close idle TCP connections after specified number of seconds.") \
M(SettingUInt64, distributed_connections_pool_size, DBMS_DEFAULT_DISTRIBUTED_CONNECTIONS_POOL_SIZE, "Maximum number of connections with one remote server in the pool.") \
M(SettingUInt64, connections_with_failover_max_tries, DBMS_CONNECTION_POOL_WITH_FAILOVER_DEFAULT_MAX_TRIES, "The maximum number of attempts to connect to replicas.") \
M(SettingUInt64, s3_min_upload_part_size, 512*1024*1024, "The mininum size of part to upload during multipart upload to S3.") \
M(SettingBool, extremes, false, "Calculate minimums and maximums of the result columns. They can be output in JSON-formats.") \
M(SettingBool, use_uncompressed_cache, true, "Whether to use the cache of uncompressed blocks.") \
M(SettingBool, replace_running_query, false, "Whether the running request should be canceled with the same id as the new one.") \
M(SettingUInt64, background_pool_size, 16, "Number of threads performing background work for tables (for example, merging in merge tree). Only has meaning at server startup.") \
M(SettingUInt64, background_schedule_pool_size, 16, "Number of threads performing background tasks for replicated tables. Only has meaning at server startup.") \
M(SettingUInt64, min_compress_block_size, 65536, "The actual size of the block to compress, if the uncompressed data less than max_compress_block_size is no less than this value and no less than the volume of data for one mark.", 0) \
M(SettingUInt64, max_compress_block_size, 1048576, "The maximum size of blocks of uncompressed data before compressing for writing to a table.", 0) \
M(SettingUInt64, max_block_size, DEFAULT_BLOCK_SIZE, "Maximum block size for reading", 0) \
M(SettingUInt64, max_insert_block_size, DEFAULT_INSERT_BLOCK_SIZE, "The maximum block size for insertion, if we control the creation of blocks for insertion.", 0) \
M(SettingUInt64, min_insert_block_size_rows, DEFAULT_INSERT_BLOCK_SIZE, "Squash blocks passed to INSERT query to specified size in rows, if blocks are not big enough.", 0) \
M(SettingUInt64, min_insert_block_size_bytes, (DEFAULT_INSERT_BLOCK_SIZE * 256), "Squash blocks passed to INSERT query to specified size in bytes, if blocks are not big enough.", 0) \
M(SettingMaxThreads, max_threads, 0, "The maximum number of threads to execute the request. By default, it is determined automatically.", 0) \
M(SettingMaxThreads, max_alter_threads, 0, "The maximum number of threads to execute the ALTER requests. By default, it is determined automatically.", 0) \
M(SettingUInt64, max_read_buffer_size, DBMS_DEFAULT_BUFFER_SIZE, "The maximum size of the buffer to read from the filesystem.", 0) \
M(SettingUInt64, max_distributed_connections, 1024, "The maximum number of connections for distributed processing of one query (should be greater than max_threads).", 0) \
M(SettingUInt64, max_query_size, 262144, "Which part of the query can be read into RAM for parsing (the remaining data for INSERT, if any, is read later)", 0) \
M(SettingUInt64, interactive_delay, 100000, "The interval in microseconds to check if the request is cancelled, and to send progress info.", 0) \
M(SettingSeconds, connect_timeout, DBMS_DEFAULT_CONNECT_TIMEOUT_SEC, "Connection timeout if there are no replicas.", 0) \
M(SettingMilliseconds, connect_timeout_with_failover_ms, DBMS_DEFAULT_CONNECT_TIMEOUT_WITH_FAILOVER_MS, "Connection timeout for selecting first healthy replica.", 0) \
M(SettingSeconds, receive_timeout, DBMS_DEFAULT_RECEIVE_TIMEOUT_SEC, "", 0) \
M(SettingSeconds, send_timeout, DBMS_DEFAULT_SEND_TIMEOUT_SEC, "", 0) \
M(SettingSeconds, tcp_keep_alive_timeout, 0, "The time in seconds the connection needs to remain idle before TCP starts sending keepalive probes", 0) \
M(SettingMilliseconds, queue_max_wait_ms, 0, "The wait time in the request queue, if the number of concurrent requests exceeds the maximum.", 0) \
M(SettingMilliseconds, connection_pool_max_wait_ms, 0, "The wait time when connection pool is full.", 0) \
M(SettingMilliseconds, replace_running_query_max_wait_ms, 5000, "The wait time for running query with the same query_id to finish when setting 'replace_running_query' is active.", 0) \
M(SettingMilliseconds, kafka_max_wait_ms, 5000, "The wait time for reading from Kafka before retry.", 0) \
M(SettingUInt64, poll_interval, DBMS_DEFAULT_POLL_INTERVAL, "Block at the query wait loop on the server for the specified number of seconds.", 0) \
M(SettingUInt64, idle_connection_timeout, 3600, "Close idle TCP connections after specified number of seconds.", 0) \
M(SettingUInt64, distributed_connections_pool_size, DBMS_DEFAULT_DISTRIBUTED_CONNECTIONS_POOL_SIZE, "Maximum number of connections with one remote server in the pool.", 0) \
M(SettingUInt64, connections_with_failover_max_tries, DBMS_CONNECTION_POOL_WITH_FAILOVER_DEFAULT_MAX_TRIES, "The maximum number of attempts to connect to replicas.", 0) \
M(SettingUInt64, s3_min_upload_part_size, 512*1024*1024, "The mininum size of part to upload during multipart upload to S3.", 0) \
M(SettingBool, extremes, false, "Calculate minimums and maximums of the result columns. They can be output in JSON-formats.", 0) \
M(SettingBool, use_uncompressed_cache, true, "Whether to use the cache of uncompressed blocks.", 0) \
M(SettingBool, replace_running_query, false, "Whether the running request should be canceled with the same id as the new one.", 0) \
M(SettingUInt64, background_pool_size, 16, "Number of threads performing background work for tables (for example, merging in merge tree). Only has meaning at server startup.", 0) \
M(SettingUInt64, background_schedule_pool_size, 16, "Number of threads performing background tasks for replicated tables. Only has meaning at server startup.", 0) \
\
M(SettingMilliseconds, distributed_directory_monitor_sleep_time_ms, 100, "Sleep time for StorageDistributed DirectoryMonitors, in case of any errors delay grows exponentially.") \
M(SettingMilliseconds, distributed_directory_monitor_max_sleep_time_ms, 30000, "Maximum sleep time for StorageDistributed DirectoryMonitors, it limits exponential growth too.") \
M(SettingMilliseconds, distributed_directory_monitor_sleep_time_ms, 100, "Sleep time for StorageDistributed DirectoryMonitors, in case of any errors delay grows exponentially.", 0) \
M(SettingMilliseconds, distributed_directory_monitor_max_sleep_time_ms, 30000, "Maximum sleep time for StorageDistributed DirectoryMonitors, it limits exponential growth too.", 0) \
\
M(SettingBool, distributed_directory_monitor_batch_inserts, false, "Should StorageDistributed DirectoryMonitors try to batch individual inserts into bigger ones.") \
M(SettingBool, distributed_directory_monitor_batch_inserts, false, "Should StorageDistributed DirectoryMonitors try to batch individual inserts into bigger ones.", 0) \
\
M(SettingBool, optimize_move_to_prewhere, true, "Allows disabling WHERE to PREWHERE optimization in SELECT queries from MergeTree.") \
M(SettingBool, optimize_move_to_prewhere, true, "Allows disabling WHERE to PREWHERE optimization in SELECT queries from MergeTree.", 0) \
\
M(SettingUInt64, replication_alter_partitions_sync, 1, "Wait for actions to manipulate the partitions. 0 - do not wait, 1 - wait for execution only of itself, 2 - wait for everyone.") \
M(SettingUInt64, replication_alter_columns_timeout, 60, "Wait for actions to change the table structure within the specified number of seconds. 0 - wait unlimited time.") \
M(SettingUInt64, replication_alter_partitions_sync, 1, "Wait for actions to manipulate the partitions. 0 - do not wait, 1 - wait for execution only of itself, 2 - wait for everyone.", 0) \
M(SettingUInt64, replication_alter_columns_timeout, 60, "Wait for actions to change the table structure within the specified number of seconds. 0 - wait unlimited time.", 0) \
\
M(SettingLoadBalancing, load_balancing, LoadBalancing::RANDOM, "Which replicas (among healthy replicas) to preferably send a query to (on the first attempt) for distributed processing.") \
M(SettingLoadBalancing, load_balancing, LoadBalancing::RANDOM, "Which replicas (among healthy replicas) to preferably send a query to (on the first attempt) for distributed processing.", 0) \
\
M(SettingTotalsMode, totals_mode, TotalsMode::AFTER_HAVING_EXCLUSIVE, "How to calculate TOTALS when HAVING is present, as well as when max_rows_to_group_by and group_by_overflow_mode = ‘any’ are present.") \
M(SettingFloat, totals_auto_threshold, 0.5, "The threshold for totals_mode = 'auto'.") \
M(SettingTotalsMode, totals_mode, TotalsMode::AFTER_HAVING_EXCLUSIVE, "How to calculate TOTALS when HAVING is present, as well as when max_rows_to_group_by and group_by_overflow_mode = ‘any’ are present.", 0) \
M(SettingFloat, totals_auto_threshold, 0.5, "The threshold for totals_mode = 'auto'.", 0) \
\
M(SettingBool, allow_suspicious_low_cardinality_types, false, "In CREATE TABLE statement allows specifying LowCardinality modifier for types of small fixed size (8 or less). Enabling this may increase merge times and memory consumption.") \
M(SettingBool, compile_expressions, false, "Compile some scalar functions and operators to native code.") \
M(SettingUInt64, min_count_to_compile, 3, "The number of structurally identical queries before they are compiled.") \
M(SettingUInt64, min_count_to_compile_expression, 3, "The number of identical expressions before they are JIT-compiled") \
M(SettingUInt64, group_by_two_level_threshold, 100000, "From what number of keys, a two-level aggregation starts. 0 - the threshold is not set.") \
M(SettingUInt64, group_by_two_level_threshold_bytes, 100000000, "From what size of the aggregation state in bytes, a two-level aggregation begins to be used. 0 - the threshold is not set. Two-level aggregation is used when at least one of the thresholds is triggered.") \
M(SettingBool, distributed_aggregation_memory_efficient, false, "Is the memory-saving mode of distributed aggregation enabled.") \
M(SettingUInt64, aggregation_memory_efficient_merge_threads, 0, "Number of threads to use for merge intermediate aggregation results in memory efficient mode. When bigger, then more memory is consumed. 0 means - same as 'max_threads'.") \
M(SettingBool, allow_suspicious_low_cardinality_types, false, "In CREATE TABLE statement allows specifying LowCardinality modifier for types of small fixed size (8 or less). Enabling this may increase merge times and memory consumption.", 0) \
M(SettingBool, compile_expressions, false, "Compile some scalar functions and operators to native code.", 0) \
M(SettingUInt64, min_count_to_compile, 3, "The number of structurally identical queries before they are compiled.", 0) \
M(SettingUInt64, min_count_to_compile_expression, 3, "The number of identical expressions before they are JIT-compiled", 0) \
M(SettingUInt64, group_by_two_level_threshold, 100000, "From what number of keys, a two-level aggregation starts. 0 - the threshold is not set.", 0) \
M(SettingUInt64, group_by_two_level_threshold_bytes, 100000000, "From what size of the aggregation state in bytes, a two-level aggregation begins to be used. 0 - the threshold is not set. Two-level aggregation is used when at least one of the thresholds is triggered.", 0) \
M(SettingBool, distributed_aggregation_memory_efficient, false, "Is the memory-saving mode of distributed aggregation enabled.", 0) \
M(SettingUInt64, aggregation_memory_efficient_merge_threads, 0, "Number of threads to use for merge intermediate aggregation results in memory efficient mode. When bigger, then more memory is consumed. 0 means - same as 'max_threads'.", 0) \
\
M(SettingUInt64, max_parallel_replicas, 1, "The maximum number of replicas of each shard used when the query is executed. For consistency (to get different parts of the same partition), this option only works for the specified sampling key. The lag of the replicas is not controlled.") \
M(SettingUInt64, parallel_replicas_count, 0, "") \
M(SettingUInt64, parallel_replica_offset, 0, "") \
M(SettingUInt64, max_parallel_replicas, 1, "The maximum number of replicas of each shard used when the query is executed. For consistency (to get different parts of the same partition), this option only works for the specified sampling key. The lag of the replicas is not controlled.", 0) \
M(SettingUInt64, parallel_replicas_count, 0, "", 0) \
M(SettingUInt64, parallel_replica_offset, 0, "", 0) \
\
M(SettingBool, skip_unavailable_shards, false, "If 1, ClickHouse silently skips unavailable shards and nodes unresolvable through DNS. Shard is marked as unavailable when none of the replicas can be reached.") \
M(SettingBool, skip_unavailable_shards, false, "If 1, ClickHouse silently skips unavailable shards and nodes unresolvable through DNS. Shard is marked as unavailable when none of the replicas can be reached.", 0) \
\
M(SettingBool, distributed_group_by_no_merge, false, "Do not merge aggregation states from different servers for distributed query processing - in case it is for certain that there are different keys on different shards.") \
M(SettingBool, optimize_skip_unused_shards, false, "Assumes that data is distributed by sharding_key. Optimization to skip unused shards if SELECT query filters by sharding_key.") \
M(SettingBool, distributed_group_by_no_merge, false, "Do not merge aggregation states from different servers for distributed query processing - in case it is for certain that there are different keys on different shards.", 0) \
M(SettingBool, optimize_skip_unused_shards, false, "Assumes that data is distributed by sharding_key. Optimization to skip unused shards if SELECT query filters by sharding_key.", 0) \
\
M(SettingUInt64, merge_tree_min_rows_for_concurrent_read, (20 * 8192), "If at least as many lines are read from one file, the reading can be parallelized.") \
M(SettingUInt64, merge_tree_min_bytes_for_concurrent_read, (24 * 10 * 1024 * 1024), "If at least as many bytes are read from one file, the reading can be parallelized.") \
M(SettingUInt64, merge_tree_min_rows_for_seek, 0, "You can skip reading more than that number of rows at the price of one seek per file.") \
M(SettingUInt64, merge_tree_min_bytes_for_seek, 0, "You can skip reading more than that number of bytes at the price of one seek per file.") \
M(SettingUInt64, merge_tree_coarse_index_granularity, 8, "If the index segment can contain the required keys, divide it into as many parts and recursively check them.") \
M(SettingUInt64, merge_tree_max_rows_to_use_cache, (128 * 8192), "The maximum number of rows per request, to use the cache of uncompressed data. If the request is large, the cache is not used. (For large queries not to flush out the cache.)") \
M(SettingUInt64, merge_tree_max_bytes_to_use_cache, (192 * 10 * 1024 * 1024), "The maximum number of rows per request, to use the cache of uncompressed data. If the request is large, the cache is not used. (For large queries not to flush out the cache.)") \
M(SettingUInt64, merge_tree_min_rows_for_concurrent_read, (20 * 8192), "If at least as many lines are read from one file, the reading can be parallelized.", 0) \
M(SettingUInt64, merge_tree_min_bytes_for_concurrent_read, (24 * 10 * 1024 * 1024), "If at least as many bytes are read from one file, the reading can be parallelized.", 0) \
M(SettingUInt64, merge_tree_min_rows_for_seek, 0, "You can skip reading more than that number of rows at the price of one seek per file.", 0) \
M(SettingUInt64, merge_tree_min_bytes_for_seek, 0, "You can skip reading more than that number of bytes at the price of one seek per file.", 0) \
M(SettingUInt64, merge_tree_coarse_index_granularity, 8, "If the index segment can contain the required keys, divide it into as many parts and recursively check them.", 0) \
M(SettingUInt64, merge_tree_max_rows_to_use_cache, (128 * 8192), "The maximum number of rows per request, to use the cache of uncompressed data. If the request is large, the cache is not used. (For large queries not to flush out the cache.)", 0) \
M(SettingUInt64, merge_tree_max_bytes_to_use_cache, (192 * 10 * 1024 * 1024), "The maximum number of rows per request, to use the cache of uncompressed data. If the request is large, the cache is not used. (For large queries not to flush out the cache.)", 0) \
\
M(SettingBool, merge_tree_uniform_read_distribution, true, "Distribute read from MergeTree over threads evenly, ensuring stable average execution time of each thread within one read operation.") \
M(SettingBool, merge_tree_uniform_read_distribution, true, "Distribute read from MergeTree over threads evenly, ensuring stable average execution time of each thread within one read operation.", 0) \
\
M(SettingUInt64, mysql_max_rows_to_insert, 65536, "The maximum number of rows in MySQL batch insertion of the MySQL storage engine") \
M(SettingUInt64, mysql_max_rows_to_insert, 65536, "The maximum number of rows in MySQL batch insertion of the MySQL storage engine", 0) \
\
M(SettingUInt64, optimize_min_equality_disjunction_chain_length, 3, "The minimum length of the expression `expr = x1 OR ... expr = xN` for optimization ") \
M(SettingUInt64, optimize_min_equality_disjunction_chain_length, 3, "The minimum length of the expression `expr = x1 OR ... expr = xN` for optimization ", 0) \
\
M(SettingUInt64, min_bytes_to_use_direct_io, 0, "The minimum number of bytes for reading the data with O_DIRECT option during SELECT queries execution. 0 - disabled.") \
M(SettingUInt64, min_bytes_to_use_direct_io, 0, "The minimum number of bytes for reading the data with O_DIRECT option during SELECT queries execution. 0 - disabled.", 0) \
\
M(SettingBool, force_index_by_date, 0, "Throw an exception if there is a partition key in a table, and it is not used.") \
M(SettingBool, force_primary_key, 0, "Throw an exception if there is primary key in a table, and it is not used.") \
M(SettingBool, force_index_by_date, 0, "Throw an exception if there is a partition key in a table, and it is not used.", 0) \
M(SettingBool, force_primary_key, 0, "Throw an exception if there is primary key in a table, and it is not used.", 0) \
\
M(SettingUInt64, mark_cache_min_lifetime, 10000, "If the maximum size of mark_cache is exceeded, delete only records older than mark_cache_min_lifetime seconds.") \
M(SettingUInt64, mark_cache_min_lifetime, 10000, "If the maximum size of mark_cache is exceeded, delete only records older than mark_cache_min_lifetime seconds.", 0) \
\
M(SettingFloat, max_streams_to_max_threads_ratio, 1, "Allows you to use more sources than the number of threads - to more evenly distribute work across threads. It is assumed that this is a temporary solution, since it will be possible in the future to make the number of sources equal to the number of threads, but for each source to dynamically select available work for itself.") \
M(SettingFloat, max_streams_multiplier_for_merge_tables, 5, "Ask more streams when reading from Merge table. Streams will be spread across tables that Merge table will use. This allows more even distribution of work across threads and especially helpful when merged tables differ in size.") \
M(SettingFloat, max_streams_to_max_threads_ratio, 1, "Allows you to use more sources than the number of threads - to more evenly distribute work across threads. It is assumed that this is a temporary solution, since it will be possible in the future to make the number of sources equal to the number of threads, but for each source to dynamically select available work for itself.", 0) \
M(SettingFloat, max_streams_multiplier_for_merge_tables, 5, "Ask more streams when reading from Merge table. Streams will be spread across tables that Merge table will use. This allows more even distribution of work across threads and especially helpful when merged tables differ in size.", 0) \
\
M(SettingString, network_compression_method, "LZ4", "Allows you to select the method of data compression when writing.") \
M(SettingString, network_compression_method, "LZ4", "Allows you to select the method of data compression when writing.", 0) \
\
M(SettingInt64, network_zstd_compression_level, 1, "Allows you to select the level of ZSTD compression.") \
M(SettingInt64, network_zstd_compression_level, 1, "Allows you to select the level of ZSTD compression.", 0) \
\
M(SettingUInt64, priority, 0, "Priority of the query. 1 - the highest, higher value - lower priority; 0 - do not use priorities.") \
M(SettingInt64, os_thread_priority, 0, "If non zero - set corresponding 'nice' value for query processing threads. Can be used to adjust query priority for OS scheduler.") \
M(SettingUInt64, priority, 0, "Priority of the query. 1 - the highest, higher value - lower priority; 0 - do not use priorities.", 0) \
M(SettingInt64, os_thread_priority, 0, "If non zero - set corresponding 'nice' value for query processing threads. Can be used to adjust query priority for OS scheduler.", 0) \
\
M(SettingBool, log_queries, 0, "Log requests and write the log to the system table.") \
M(SettingBool, log_queries, 0, "Log requests and write the log to the system table.", 0) \
\
M(SettingUInt64, log_queries_cut_to_length, 100000, "If query length is greater than specified threshold (in bytes), then cut query when writing to query log. Also limit length of printed query in ordinary text log.") \
M(SettingUInt64, log_queries_cut_to_length, 100000, "If query length is greater than specified threshold (in bytes), then cut query when writing to query log. Also limit length of printed query in ordinary text log.", 0) \
\
M(SettingDistributedProductMode, distributed_product_mode, DistributedProductMode::DENY, "How are distributed subqueries performed inside IN or JOIN sections?") \
M(SettingDistributedProductMode, distributed_product_mode, DistributedProductMode::DENY, "How are distributed subqueries performed inside IN or JOIN sections?", 0) \
\
M(SettingUInt64, max_concurrent_queries_for_user, 0, "The maximum number of concurrent requests per user.") \
M(SettingUInt64, max_concurrent_queries_for_user, 0, "The maximum number of concurrent requests per user.", 0) \
\
M(SettingBool, insert_deduplicate, true, "For INSERT queries in the replicated table, specifies that deduplication of insertings blocks should be preformed") \
M(SettingBool, insert_deduplicate, true, "For INSERT queries in the replicated table, specifies that deduplication of insertings blocks should be preformed", 0) \
\
M(SettingUInt64, insert_quorum, 0, "For INSERT queries in the replicated table, wait writing for the specified number of replicas and linearize the addition of the data. 0 - disabled.") \
M(SettingMilliseconds, insert_quorum_timeout, 600000, "") \
M(SettingUInt64, select_sequential_consistency, 0, "For SELECT queries from the replicated table, throw an exception if the replica does not have a chunk written with the quorum; do not read the parts that have not yet been written with the quorum.") \
M(SettingUInt64, table_function_remote_max_addresses, 1000, "The maximum number of different shards and the maximum number of replicas of one shard in the `remote` function.") \
M(SettingMilliseconds, read_backoff_min_latency_ms, 1000, "Setting to reduce the number of threads in case of slow reads. Pay attention only to reads that took at least that much time.") \
M(SettingUInt64, read_backoff_max_throughput, 1048576, "Settings to reduce the number of threads in case of slow reads. Count events when the read bandwidth is less than that many bytes per second.") \
M(SettingMilliseconds, read_backoff_min_interval_between_events_ms, 1000, "Settings to reduce the number of threads in case of slow reads. Do not pay attention to the event, if the previous one has passed less than a certain amount of time.") \
M(SettingUInt64, read_backoff_min_events, 2, "Settings to reduce the number of threads in case of slow reads. The number of events after which the number of threads will be reduced.") \
M(SettingUInt64, insert_quorum, 0, "For INSERT queries in the replicated table, wait writing for the specified number of replicas and linearize the addition of the data. 0 - disabled.", 0) \
M(SettingMilliseconds, insert_quorum_timeout, 600000, "", 0) \
M(SettingUInt64, select_sequential_consistency, 0, "For SELECT queries from the replicated table, throw an exception if the replica does not have a chunk written with the quorum; do not read the parts that have not yet been written with the quorum.", 0) \
M(SettingUInt64, table_function_remote_max_addresses, 1000, "The maximum number of different shards and the maximum number of replicas of one shard in the `remote` function.", 0) \
M(SettingMilliseconds, read_backoff_min_latency_ms, 1000, "Setting to reduce the number of threads in case of slow reads. Pay attention only to reads that took at least that much time.", 0) \
M(SettingUInt64, read_backoff_max_throughput, 1048576, "Settings to reduce the number of threads in case of slow reads. Count events when the read bandwidth is less than that many bytes per second.", 0) \
M(SettingMilliseconds, read_backoff_min_interval_between_events_ms, 1000, "Settings to reduce the number of threads in case of slow reads. Do not pay attention to the event, if the previous one has passed less than a certain amount of time.", 0) \
M(SettingUInt64, read_backoff_min_events, 2, "Settings to reduce the number of threads in case of slow reads. The number of events after which the number of threads will be reduced.", 0) \
\
M(SettingFloat, memory_tracker_fault_probability, 0., "For testing of `exception safety` - throw an exception every time you allocate memory with the specified probability.") \
M(SettingFloat, memory_tracker_fault_probability, 0., "For testing of `exception safety` - throw an exception every time you allocate memory with the specified probability.", 0) \
\
M(SettingBool, enable_http_compression, 0, "Compress the result if the client over HTTP said that it understands data compressed by gzip or deflate.") \
M(SettingInt64, http_zlib_compression_level, 3, "Compression level - used if the client on HTTP said that it understands data compressed by gzip or deflate.") \
M(SettingBool, enable_http_compression, 0, "Compress the result if the client over HTTP said that it understands data compressed by gzip or deflate.", 0) \
M(SettingInt64, http_zlib_compression_level, 3, "Compression level - used if the client on HTTP said that it understands data compressed by gzip or deflate.", 0) \
\
M(SettingBool, http_native_compression_disable_checksumming_on_decompress, 0, "If you uncompress the POST data from the client compressed by the native format, do not check the checksum.") \
M(SettingBool, http_native_compression_disable_checksumming_on_decompress, 0, "If you uncompress the POST data from the client compressed by the native format, do not check the checksum.", 0) \
\
M(SettingString, count_distinct_implementation, "uniqExact", "What aggregate function to use for implementation of count(DISTINCT ...)") \
M(SettingString, count_distinct_implementation, "uniqExact", "What aggregate function to use for implementation of count(DISTINCT ...)", 0) \
\
M(SettingBool, output_format_write_statistics, true, "Write statistics about read rows, bytes, time elapsed in suitable output formats.") \
M(SettingBool, output_format_write_statistics, true, "Write statistics about read rows, bytes, time elapsed in suitable output formats.", 0) \
\
M(SettingBool, add_http_cors_header, false, "Write add http CORS header.") \
M(SettingBool, add_http_cors_header, false, "Write add http CORS header.", 0) \
\
M(SettingUInt64, max_http_get_redirects, 0, "Max number of http GET redirects hops allowed. Make sure additional security measures are in place to prevent a malicious server to redirect your requests to unexpected services.") \
M(SettingUInt64, max_http_get_redirects, 0, "Max number of http GET redirects hops allowed. Make sure additional security measures are in place to prevent a malicious server to redirect your requests to unexpected services.", 0) \
\
M(SettingBool, input_format_skip_unknown_fields, false, "Skip columns with unknown names from input data (it works for JSONEachRow, CSVWithNames, TSVWithNames and TSKV formats).") \
M(SettingBool, input_format_with_names_use_header, false, "For TSVWithNames and CSVWithNames input formats this controls whether format parser is to assume that column data appear in the input exactly as they are specified in the header.") \
M(SettingBool, input_format_import_nested_json, false, "Map nested JSON data to nested tables (it works for JSONEachRow format).") \
M(SettingBool, input_format_defaults_for_omitted_fields, true, "For input data calculate default expressions for omitted fields (it works for JSONEachRow, CSV and TSV formats).") \
M(SettingBool, input_format_tsv_empty_as_default, false, "Treat empty fields in TSV input as default values.") \
M(SettingBool, input_format_null_as_default, false, "For text input formats initialize null fields with default values if data type of this field is not nullable") \
M(SettingBool, input_format_skip_unknown_fields, false, "Skip columns with unknown names from input data (it works for JSONEachRow, CSVWithNames, TSVWithNames and TSKV formats).", 0) \
M(SettingBool, input_format_with_names_use_header, false, "For TSVWithNames and CSVWithNames input formats this controls whether format parser is to assume that column data appear in the input exactly as they are specified in the header.", 0) \
M(SettingBool, input_format_import_nested_json, false, "Map nested JSON data to nested tables (it works for JSONEachRow format).", 0) \
M(SettingBool, input_format_defaults_for_omitted_fields, true, "For input data calculate default expressions for omitted fields (it works for JSONEachRow, CSV and TSV formats).", 0) \
M(SettingBool, input_format_tsv_empty_as_default, false, "Treat empty fields in TSV input as default values.", 0) \
M(SettingBool, input_format_null_as_default, false, "For text input formats initialize null fields with default values if data type of this field is not nullable", 0) \
\
M(SettingBool, input_format_values_interpret_expressions, true, "For Values format: if field could not be parsed by streaming parser, run SQL parser and try to interpret it as SQL expression.") \
M(SettingBool, input_format_values_deduce_templates_of_expressions, false, "For Values format: if field could not be parsed by streaming parser, run SQL parser, deduce template of the SQL expression, try to parse all rows using template and then interpret expression for all rows.") \
M(SettingBool, input_format_values_accurate_types_of_literals, true, "For Values format: when parsing and interpreting expressions using template, check actual type of literal to avoid possible overflow and precision issues.") \
M(SettingBool, input_format_values_interpret_expressions, true, "For Values format: if field could not be parsed by streaming parser, run SQL parser and try to interpret it as SQL expression.", 0) \
M(SettingBool, input_format_values_deduce_templates_of_expressions, false, "For Values format: if field could not be parsed by streaming parser, run SQL parser, deduce template of the SQL expression, try to parse all rows using template and then interpret expression for all rows.", 0) \
M(SettingBool, input_format_values_accurate_types_of_literals, true, "For Values format: when parsing and interpreting expressions using template, check actual type of literal to avoid possible overflow and precision issues.", 0) \
\
M(SettingBool, output_format_json_quote_64bit_integers, true, "Controls quoting of 64-bit integers in JSON output format.") \
M(SettingBool, output_format_json_quote_64bit_integers, true, "Controls quoting of 64-bit integers in JSON output format.", 0) \
\
M(SettingBool, output_format_json_quote_denormals, false, "Enables '+nan', '-nan', '+inf', '-inf' outputs in JSON output format.") \
M(SettingBool, output_format_json_quote_denormals, false, "Enables '+nan', '-nan', '+inf', '-inf' outputs in JSON output format.", 0) \
\
M(SettingBool, output_format_json_escape_forward_slashes, true, "Controls escaping forward slashes for string outputs in JSON output format. This is intended for compatibility with JavaScript. Don't confuse with backslashes that are always escaped.") \
M(SettingBool, output_format_json_escape_forward_slashes, true, "Controls escaping forward slashes for string outputs in JSON output format. This is intended for compatibility with JavaScript. Don't confuse with backslashes that are always escaped.", 0) \
\
M(SettingUInt64, output_format_pretty_max_rows, 10000, "Rows limit for Pretty formats.") \
M(SettingUInt64, output_format_pretty_max_column_pad_width, 250, "Maximum width to pad all values in a column in Pretty formats.") \
M(SettingBool, output_format_pretty_color, true, "Use ANSI escape sequences to paint colors in Pretty formats") \
M(SettingUInt64, output_format_parquet_row_group_size, 1000000, "Row group size in rows.") \
M(SettingUInt64, output_format_pretty_max_rows, 10000, "Rows limit for Pretty formats.", 0) \
M(SettingUInt64, output_format_pretty_max_column_pad_width, 250, "Maximum width to pad all values in a column in Pretty formats.", 0) \
M(SettingBool, output_format_pretty_color, true, "Use ANSI escape sequences to paint colors in Pretty formats", 0) \
M(SettingUInt64, output_format_parquet_row_group_size, 1000000, "Row group size in rows.", 0) \
\
M(SettingBool, use_client_time_zone, false, "Use client timezone for interpreting DateTime string values, instead of adopting server timezone.") \
M(SettingBool, use_client_time_zone, false, "Use client timezone for interpreting DateTime string values, instead of adopting server timezone.", 0) \
\
M(SettingBool, send_progress_in_http_headers, false, "Send progress notifications using X-ClickHouse-Progress headers. Some clients do not support high amount of HTTP headers (Python requests in particular), so it is disabled by default.") \
M(SettingBool, send_progress_in_http_headers, false, "Send progress notifications using X-ClickHouse-Progress headers. Some clients do not support high amount of HTTP headers (Python requests in particular), so it is disabled by default.", 0) \
\
M(SettingUInt64, http_headers_progress_interval_ms, 100, "Do not send HTTP headers X-ClickHouse-Progress more frequently than at each specified interval.") \
M(SettingUInt64, http_headers_progress_interval_ms, 100, "Do not send HTTP headers X-ClickHouse-Progress more frequently than at each specified interval.", 0) \
\
M(SettingBool, fsync_metadata, 1, "Do fsync after changing metadata for tables and databases (.sql files). Could be disabled in case of poor latency on server with high load of DDL queries and high load of disk subsystem.") \
M(SettingBool, fsync_metadata, 1, "Do fsync after changing metadata for tables and databases (.sql files). Could be disabled in case of poor latency on server with high load of DDL queries and high load of disk subsystem.", 0) \
\
M(SettingUInt64, input_format_allow_errors_num, 0, "Maximum absolute amount of errors while reading text formats (like CSV, TSV). In case of error, if at least absolute or relative amount of errors is lower than corresponding value, will skip until next line and continue.") \
M(SettingFloat, input_format_allow_errors_ratio, 0, "Maximum relative amount of errors while reading text formats (like CSV, TSV). In case of error, if at least absolute or relative amount of errors is lower than corresponding value, will skip until next line and continue.") \
M(SettingUInt64, input_format_allow_errors_num, 0, "Maximum absolute amount of errors while reading text formats (like CSV, TSV). In case of error, if at least absolute or relative amount of errors is lower than corresponding value, will skip until next line and continue.", 0) \
M(SettingFloat, input_format_allow_errors_ratio, 0, "Maximum relative amount of errors while reading text formats (like CSV, TSV). In case of error, if at least absolute or relative amount of errors is lower than corresponding value, will skip until next line and continue.", 0) \
\
M(SettingBool, join_use_nulls, 0, "Use NULLs for non-joined rows of outer JOINs for types that can be inside Nullable. If false, use default value of corresponding columns data type.") \
M(SettingBool, join_use_nulls, 0, "Use NULLs for non-joined rows of outer JOINs for types that can be inside Nullable. If false, use default value of corresponding columns data type.", 0) \
\
M(SettingJoinStrictness, join_default_strictness, JoinStrictness::ALL, "Set default strictness in JOIN query. Possible values: empty string, 'ANY', 'ALL'. If empty, query without strictness will throw exception.") \
M(SettingBool, any_join_distinct_right_table_keys, false, "Enable old ANY JOIN logic with many-to-one left-to-right table keys mapping for all ANY JOINs. It leads to confusing not equal results for 't1 ANY LEFT JOIN t2' and 't2 ANY RIGHT JOIN t1'. ANY RIGHT JOIN needs one-to-many keys maping to be consistent with LEFT one.") \
M(SettingJoinStrictness, join_default_strictness, JoinStrictness::ALL, "Set default strictness in JOIN query. Possible values: empty string, 'ANY', 'ALL'. If empty, query without strictness will throw exception.", 0) \
M(SettingBool, any_join_distinct_right_table_keys, false, "Enable old ANY JOIN logic with many-to-one left-to-right table keys mapping for all ANY JOINs. It leads to confusing not equal results for 't1 ANY LEFT JOIN t2' and 't2 ANY RIGHT JOIN t1'. ANY RIGHT JOIN needs one-to-many keys maping to be consistent with LEFT one.", 0) \
\
M(SettingUInt64, preferred_block_size_bytes, 1000000, "") \
M(SettingUInt64, preferred_block_size_bytes, 1000000, "", 0) \
\
M(SettingUInt64, max_replica_delay_for_distributed_queries, 300, "If set, distributed queries of Replicated tables will choose servers with replication delay in seconds less than the specified value (not inclusive). Zero means do not take delay into account.") \
M(SettingBool, fallback_to_stale_replicas_for_distributed_queries, 1, "Suppose max_replica_delay_for_distributed_queries is set and all replicas for the queried table are stale. If this setting is enabled, the query will be performed anyway, otherwise the error will be reported.") \
M(SettingUInt64, preferred_max_column_in_block_size_bytes, 0, "Limit on max column size in block while reading. Helps to decrease cache misses count. Should be close to L2 cache size.") \
M(SettingUInt64, max_replica_delay_for_distributed_queries, 300, "If set, distributed queries of Replicated tables will choose servers with replication delay in seconds less than the specified value (not inclusive). Zero means do not take delay into account.", 0) \
M(SettingBool, fallback_to_stale_replicas_for_distributed_queries, 1, "Suppose max_replica_delay_for_distributed_queries is set and all replicas for the queried table are stale. If this setting is enabled, the query will be performed anyway, otherwise the error will be reported.", 0) \
M(SettingUInt64, preferred_max_column_in_block_size_bytes, 0, "Limit on max column size in block while reading. Helps to decrease cache misses count. Should be close to L2 cache size.", 0) \
\
M(SettingBool, insert_distributed_sync, false, "If setting is enabled, insert query into distributed waits until data will be sent to all nodes in cluster.") \
M(SettingUInt64, insert_distributed_timeout, 0, "Timeout for insert query into distributed. Setting is used only with insert_distributed_sync enabled. Zero value means no timeout.") \
M(SettingInt64, distributed_ddl_task_timeout, 180, "Timeout for DDL query responses from all hosts in cluster. If a ddl request has not been performed on all hosts, a response will contain a timeout error and a request will be executed in an async mode. Negative value means infinite.") \
M(SettingMilliseconds, stream_flush_interval_ms, 7500, "Timeout for flushing data from streaming storages.") \
M(SettingMilliseconds, stream_poll_timeout_ms, 500, "Timeout for polling data from/to streaming storages.") \
M(SettingBool, insert_distributed_sync, false, "If setting is enabled, insert query into distributed waits until data will be sent to all nodes in cluster.", 0) \
M(SettingUInt64, insert_distributed_timeout, 0, "Timeout for insert query into distributed. Setting is used only with insert_distributed_sync enabled. Zero value means no timeout.", 0) \
M(SettingInt64, distributed_ddl_task_timeout, 180, "Timeout for DDL query responses from all hosts in cluster. If a ddl request has not been performed on all hosts, a response will contain a timeout error and a request will be executed in an async mode. Negative value means infinite.", 0) \
M(SettingMilliseconds, stream_flush_interval_ms, 7500, "Timeout for flushing data from streaming storages.", 0) \
M(SettingMilliseconds, stream_poll_timeout_ms, 500, "Timeout for polling data from/to streaming storages.", 0) \
\
M(SettingString, format_schema, "", "Schema identifier (used by schema-based formats)") \
M(SettingString, format_template_resultset, "", "Path to file which contains format string for result set (for Template format)") \
M(SettingString, format_template_row, "", "Path to file which contains format string for rows (for Template format)") \
M(SettingString, format_template_rows_between_delimiter, "\n", "Delimiter between rows (for Template format)") \
M(SettingString, format_schema, "", "Schema identifier (used by schema-based formats)", 0) \
M(SettingString, format_template_resultset, "", "Path to file which contains format string for result set (for Template format)", 0) \
M(SettingString, format_template_row, "", "Path to file which contains format string for rows (for Template format)", 0) \
M(SettingString, format_template_rows_between_delimiter, "\n", "Delimiter between rows (for Template format)", 0) \
\
M(SettingString, format_custom_escaping_rule, "Escaped", "Field escaping rule (for CustomSeparated format)") \
M(SettingString, format_custom_field_delimiter, "\t", "Delimiter between fields (for CustomSeparated format)") \
M(SettingString, format_custom_row_before_delimiter, "", "Delimiter before field of the first column (for CustomSeparated format)") \
M(SettingString, format_custom_row_after_delimiter, "\n", "Delimiter after field of the last column (for CustomSeparated format)") \
M(SettingString, format_custom_row_between_delimiter, "", "Delimiter between rows (for CustomSeparated format)") \
M(SettingString, format_custom_result_before_delimiter, "", "Prefix before result set (for CustomSeparated format)") \
M(SettingString, format_custom_result_after_delimiter, "", "Suffix after result set (for CustomSeparated format)") \
M(SettingString, format_custom_escaping_rule, "Escaped", "Field escaping rule (for CustomSeparated format)", 0) \
M(SettingString, format_custom_field_delimiter, "\t", "Delimiter between fields (for CustomSeparated format)", 0) \
M(SettingString, format_custom_row_before_delimiter, "", "Delimiter before field of the first column (for CustomSeparated format)", 0) \
M(SettingString, format_custom_row_after_delimiter, "\n", "Delimiter after field of the last column (for CustomSeparated format)", 0) \
M(SettingString, format_custom_row_between_delimiter, "", "Delimiter between rows (for CustomSeparated format)", 0) \
M(SettingString, format_custom_result_before_delimiter, "", "Prefix before result set (for CustomSeparated format)", 0) \
M(SettingString, format_custom_result_after_delimiter, "", "Suffix after result set (for CustomSeparated format)", 0) \
\
M(SettingBool, insert_allow_materialized_columns, 0, "If setting is enabled, Allow materialized columns in INSERT.") \
M(SettingSeconds, http_connection_timeout, DEFAULT_HTTP_READ_BUFFER_CONNECTION_TIMEOUT, "HTTP connection timeout.") \
M(SettingSeconds, http_send_timeout, DEFAULT_HTTP_READ_BUFFER_TIMEOUT, "HTTP send timeout") \
M(SettingSeconds, http_receive_timeout, DEFAULT_HTTP_READ_BUFFER_TIMEOUT, "HTTP receive timeout") \
M(SettingBool, optimize_throw_if_noop, false, "If setting is enabled and OPTIMIZE query didn't actually assign a merge then an explanatory exception is thrown") \
M(SettingBool, use_index_for_in_with_subqueries, true, "Try using an index if there is a subquery or a table expression on the right side of the IN operator.") \
M(SettingBool, joined_subquery_requires_alias, false, "Force joined subqueries to have aliases for correct name qualification.") \
M(SettingBool, empty_result_for_aggregation_by_empty_set, false, "Return empty result when aggregating without keys on empty set.") \
M(SettingBool, allow_distributed_ddl, true, "If it is set to true, then a user is allowed to executed distributed DDL queries.") \
M(SettingUInt64, odbc_max_field_size, 1024, "Max size of filed can be read from ODBC dictionary. Long strings are truncated.") \
M(SettingUInt64, query_profiler_real_time_period_ns, 1000000000, "Highly experimental. Period for real clock timer of query profiler (in nanoseconds). Set 0 value to turn off real clock query profiler. Recommended value is at least 10000000 (100 times a second) for single queries or 1000000000 (once a second) for cluster-wide profiling.") \
M(SettingUInt64, query_profiler_cpu_time_period_ns, 1000000000, "Highly experimental. Period for CPU clock timer of query profiler (in nanoseconds). Set 0 value to turn off CPU clock query profiler. Recommended value is at least 10000000 (100 times a second) for single queries or 1000000000 (once a second) for cluster-wide profiling.") \
M(SettingBool, insert_allow_materialized_columns, 0, "If setting is enabled, Allow materialized columns in INSERT.", 0) \
M(SettingSeconds, http_connection_timeout, DEFAULT_HTTP_READ_BUFFER_CONNECTION_TIMEOUT, "HTTP connection timeout.", 0) \
M(SettingSeconds, http_send_timeout, DEFAULT_HTTP_READ_BUFFER_TIMEOUT, "HTTP send timeout", 0) \
M(SettingSeconds, http_receive_timeout, DEFAULT_HTTP_READ_BUFFER_TIMEOUT, "HTTP receive timeout", 0) \
M(SettingBool, optimize_throw_if_noop, false, "If setting is enabled and OPTIMIZE query didn't actually assign a merge then an explanatory exception is thrown", 0) \
M(SettingBool, use_index_for_in_with_subqueries, true, "Try using an index if there is a subquery or a table expression on the right side of the IN operator.", 0) \
M(SettingBool, joined_subquery_requires_alias, false, "Force joined subqueries to have aliases for correct name qualification.", 0) \
M(SettingBool, empty_result_for_aggregation_by_empty_set, false, "Return empty result when aggregating without keys on empty set.", 0) \
M(SettingBool, allow_distributed_ddl, true, "If it is set to true, then a user is allowed to executed distributed DDL queries.", 0) \
M(SettingUInt64, odbc_max_field_size, 1024, "Max size of filed can be read from ODBC dictionary. Long strings are truncated.", 0) \
M(SettingUInt64, query_profiler_real_time_period_ns, 1000000000, "Highly experimental. Period for real clock timer of query profiler (in nanoseconds). Set 0 value to turn off real clock query profiler. Recommended value is at least 10000000 (100 times a second) for single queries or 1000000000 (once a second) for cluster-wide profiling.", 0) \
M(SettingUInt64, query_profiler_cpu_time_period_ns, 1000000000, "Highly experimental. Period for CPU clock timer of query profiler (in nanoseconds). Set 0 value to turn off CPU clock query profiler. Recommended value is at least 10000000 (100 times a second) for single queries or 1000000000 (once a second) for cluster-wide profiling.", 0) \
\
\
/** Limits during query execution are part of the settings. \
@ -257,135 +260,135 @@ struct Settings : public SettingsCollection<Settings>
* Almost all limits apply to each stream individually. \
*/ \
\
M(SettingUInt64, max_rows_to_read, 0, "Limit on read rows from the most 'deep' sources. That is, only in the deepest subquery. When reading from a remote server, it is only checked on a remote server.") \
M(SettingUInt64, max_bytes_to_read, 0, "Limit on read bytes (after decompression) from the most 'deep' sources. That is, only in the deepest subquery. When reading from a remote server, it is only checked on a remote server.") \
M(SettingOverflowMode, read_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingUInt64, max_rows_to_read, 0, "Limit on read rows from the most 'deep' sources. That is, only in the deepest subquery. When reading from a remote server, it is only checked on a remote server.", 0) \
M(SettingUInt64, max_bytes_to_read, 0, "Limit on read bytes (after decompression) from the most 'deep' sources. That is, only in the deepest subquery. When reading from a remote server, it is only checked on a remote server.", 0) \
M(SettingOverflowMode, read_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
\
M(SettingUInt64, max_rows_to_group_by, 0, "") \
M(SettingOverflowModeGroupBy, group_by_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingUInt64, max_bytes_before_external_group_by, 0, "") \
M(SettingUInt64, max_rows_to_group_by, 0, "", 0) \
M(SettingOverflowModeGroupBy, group_by_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
M(SettingUInt64, max_bytes_before_external_group_by, 0, "", 0) \
\
M(SettingUInt64, max_rows_to_sort, 0, "") \
M(SettingUInt64, max_bytes_to_sort, 0, "") \
M(SettingOverflowMode, sort_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingUInt64, max_bytes_before_external_sort, 0, "") \
M(SettingUInt64, max_bytes_before_remerge_sort, 1000000000, "In case of ORDER BY with LIMIT, when memory usage is higher than specified threshold, perform additional steps of merging blocks before final merge to keep just top LIMIT rows.") \
M(SettingUInt64, max_rows_to_sort, 0, "", 0) \
M(SettingUInt64, max_bytes_to_sort, 0, "", 0) \
M(SettingOverflowMode, sort_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
M(SettingUInt64, max_bytes_before_external_sort, 0, "", 0) \
M(SettingUInt64, max_bytes_before_remerge_sort, 1000000000, "In case of ORDER BY with LIMIT, when memory usage is higher than specified threshold, perform additional steps of merging blocks before final merge to keep just top LIMIT rows.", 0) \
\
M(SettingUInt64, max_result_rows, 0, "Limit on result size in rows. Also checked for intermediate data sent from remote servers.") \
M(SettingUInt64, max_result_bytes, 0, "Limit on result size in bytes (uncompressed). Also checked for intermediate data sent from remote servers.") \
M(SettingOverflowMode, result_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingUInt64, max_result_rows, 0, "Limit on result size in rows. Also checked for intermediate data sent from remote servers.", 0) \
M(SettingUInt64, max_result_bytes, 0, "Limit on result size in bytes (uncompressed). Also checked for intermediate data sent from remote servers.", 0) \
M(SettingOverflowMode, result_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
\
/* TODO: Check also when merging and finalizing aggregate functions. */ \
M(SettingSeconds, max_execution_time, 0, "") \
M(SettingOverflowMode, timeout_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingSeconds, max_execution_time, 0, "", 0) \
M(SettingOverflowMode, timeout_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
\
M(SettingUInt64, min_execution_speed, 0, "Minimum number of execution rows per second.") \
M(SettingUInt64, max_execution_speed, 0, "Maximum number of execution rows per second.") \
M(SettingUInt64, min_execution_speed_bytes, 0, "Minimum number of execution bytes per second.") \
M(SettingUInt64, max_execution_speed_bytes, 0, "Maximum number of execution bytes per second.") \
M(SettingSeconds, timeout_before_checking_execution_speed, 0, "Check that the speed is not too low after the specified time has elapsed.") \
M(SettingUInt64, min_execution_speed, 0, "Minimum number of execution rows per second.", 0) \
M(SettingUInt64, max_execution_speed, 0, "Maximum number of execution rows per second.", 0) \
M(SettingUInt64, min_execution_speed_bytes, 0, "Minimum number of execution bytes per second.", 0) \
M(SettingUInt64, max_execution_speed_bytes, 0, "Maximum number of execution bytes per second.", 0) \
M(SettingSeconds, timeout_before_checking_execution_speed, 0, "Check that the speed is not too low after the specified time has elapsed.", 0) \
\
M(SettingUInt64, max_columns_to_read, 0, "") \
M(SettingUInt64, max_temporary_columns, 0, "") \
M(SettingUInt64, max_temporary_non_const_columns, 0, "") \
M(SettingUInt64, max_columns_to_read, 0, "", 0) \
M(SettingUInt64, max_temporary_columns, 0, "", 0) \
M(SettingUInt64, max_temporary_non_const_columns, 0, "", 0) \
\
M(SettingUInt64, max_subquery_depth, 100, "") \
M(SettingUInt64, max_pipeline_depth, 1000, "") \
M(SettingUInt64, max_ast_depth, 1000, "Maximum depth of query syntax tree. Checked after parsing.") \
M(SettingUInt64, max_ast_elements, 50000, "Maximum size of query syntax tree in number of nodes. Checked after parsing.") \
M(SettingUInt64, max_expanded_ast_elements, 500000, "Maximum size of query syntax tree in number of nodes after expansion of aliases and the asterisk.") \
M(SettingUInt64, max_subquery_depth, 100, "", 0) \
M(SettingUInt64, max_pipeline_depth, 1000, "", 0) \
M(SettingUInt64, max_ast_depth, 1000, "Maximum depth of query syntax tree. Checked after parsing.", 0) \
M(SettingUInt64, max_ast_elements, 50000, "Maximum size of query syntax tree in number of nodes. Checked after parsing.", 0) \
M(SettingUInt64, max_expanded_ast_elements, 500000, "Maximum size of query syntax tree in number of nodes after expansion of aliases and the asterisk.", 0) \
\
M(SettingUInt64, readonly, 0, "0 - everything is allowed. 1 - only read requests. 2 - only read requests, as well as changing settings, except for the 'readonly' setting.") \
M(SettingUInt64, readonly, 0, "0 - everything is allowed. 1 - only read requests. 2 - only read requests, as well as changing settings, except for the 'readonly' setting.", 0) \
\
M(SettingUInt64, max_rows_in_set, 0, "Maximum size of the set (in number of elements) resulting from the execution of the IN section.") \
M(SettingUInt64, max_bytes_in_set, 0, "Maximum size of the set (in bytes in memory) resulting from the execution of the IN section.") \
M(SettingOverflowMode, set_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingUInt64, max_rows_in_set, 0, "Maximum size of the set (in number of elements) resulting from the execution of the IN section.", 0) \
M(SettingUInt64, max_bytes_in_set, 0, "Maximum size of the set (in bytes in memory) resulting from the execution of the IN section.", 0) \
M(SettingOverflowMode, set_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
\
M(SettingUInt64, max_rows_in_join, 0, "Maximum size of the hash table for JOIN (in number of rows).") \
M(SettingUInt64, max_bytes_in_join, 0, "Maximum size of the hash table for JOIN (in number of bytes in memory).") \
M(SettingOverflowMode, join_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingBool, join_any_take_last_row, false, "When disabled (default) ANY JOIN will take the first found row for a key. When enabled, it will take the last row seen if there are multiple rows for the same key.") \
M(SettingBool, partial_merge_join, false, "Use partial merge join instead of hash join for LEFT and INNER JOINs.") \
M(SettingBool, partial_merge_join_optimizations, false, "Enable optimizations in partial merge join") \
M(SettingUInt64, default_max_bytes_in_join, 100000000, "Maximum size of right-side table if limit's required but max_bytes_in_join is not set.") \
M(SettingUInt64, partial_merge_join_rows_in_right_blocks, 10000, "Split right-hand joining data in blocks of specified size. It's a portion of data indexed by min-max values and possibly unloaded on disk.") \
M(SettingUInt64, partial_merge_join_rows_in_left_blocks, 10000, "Group left-hand joining data in bigger blocks. Setting it to a bigger value increase JOIN performance and memory usage.") \
M(SettingUInt64, max_rows_in_join, 0, "Maximum size of the hash table for JOIN (in number of rows).", 0) \
M(SettingUInt64, max_bytes_in_join, 0, "Maximum size of the hash table for JOIN (in number of bytes in memory).", 0) \
M(SettingOverflowMode, join_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
M(SettingBool, join_any_take_last_row, false, "When disabled (default) ANY JOIN will take the first found row for a key. When enabled, it will take the last row seen if there are multiple rows for the same key.", 0) \
M(SettingBool, partial_merge_join, false, "Use partial merge join instead of hash join for LEFT and INNER JOINs.", 0) \
M(SettingBool, partial_merge_join_optimizations, false, "Enable optimizations in partial merge join", 0) \
M(SettingUInt64, default_max_bytes_in_join, 100000000, "Maximum size of right-side table if limit's required but max_bytes_in_join is not set.", 0) \
M(SettingUInt64, partial_merge_join_rows_in_right_blocks, 10000, "Split right-hand joining data in blocks of specified size. It's a portion of data indexed by min-max values and possibly unloaded on disk.", 0) \
M(SettingUInt64, partial_merge_join_rows_in_left_blocks, 10000, "Group left-hand joining data in bigger blocks. Setting it to a bigger value increase JOIN performance and memory usage.", 0) \
\
M(SettingUInt64, max_rows_to_transfer, 0, "Maximum size (in rows) of the transmitted external table obtained when the GLOBAL IN/JOIN section is executed.") \
M(SettingUInt64, max_bytes_to_transfer, 0, "Maximum size (in uncompressed bytes) of the transmitted external table obtained when the GLOBAL IN/JOIN section is executed.") \
M(SettingOverflowMode, transfer_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingUInt64, max_rows_to_transfer, 0, "Maximum size (in rows) of the transmitted external table obtained when the GLOBAL IN/JOIN section is executed.", 0) \
M(SettingUInt64, max_bytes_to_transfer, 0, "Maximum size (in uncompressed bytes) of the transmitted external table obtained when the GLOBAL IN/JOIN section is executed.", 0) \
M(SettingOverflowMode, transfer_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
\
M(SettingUInt64, max_rows_in_distinct, 0, "Maximum number of elements during execution of DISTINCT.") \
M(SettingUInt64, max_bytes_in_distinct, 0, "Maximum total size of state (in uncompressed bytes) in memory for the execution of DISTINCT.") \
M(SettingOverflowMode, distinct_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.") \
M(SettingUInt64, max_rows_in_distinct, 0, "Maximum number of elements during execution of DISTINCT.", 0) \
M(SettingUInt64, max_bytes_in_distinct, 0, "Maximum total size of state (in uncompressed bytes) in memory for the execution of DISTINCT.", 0) \
M(SettingOverflowMode, distinct_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
\
M(SettingUInt64, max_memory_usage, 0, "Maximum memory usage for processing of single query. Zero means unlimited.") \
M(SettingUInt64, max_memory_usage_for_user, 0, "Maximum memory usage for processing all concurrently running queries for the user. Zero means unlimited.") \
M(SettingUInt64, max_memory_usage_for_all_queries, 0, "Maximum memory usage for processing all concurrently running queries on the server. Zero means unlimited.") \
M(SettingUInt64, max_memory_usage, 0, "Maximum memory usage for processing of single query. Zero means unlimited.", 0) \
M(SettingUInt64, max_memory_usage_for_user, 0, "Maximum memory usage for processing all concurrently running queries for the user. Zero means unlimited.", 0) \
M(SettingUInt64, max_memory_usage_for_all_queries, 0, "Maximum memory usage for processing all concurrently running queries on the server. Zero means unlimited.", 0) \
\
M(SettingUInt64, max_network_bandwidth, 0, "The maximum speed of data exchange over the network in bytes per second for a query. Zero means unlimited.") \
M(SettingUInt64, max_network_bytes, 0, "The maximum number of bytes (compressed) to receive or transmit over the network for execution of the query.") \
M(SettingUInt64, max_network_bandwidth_for_user, 0, "The maximum speed of data exchange over the network in bytes per second for all concurrently running user queries. Zero means unlimited.")\
M(SettingUInt64, max_network_bandwidth_for_all_users, 0, "The maximum speed of data exchange over the network in bytes per second for all concurrently running queries. Zero means unlimited.") \
M(SettingChar, format_csv_delimiter, ',', "The character to be considered as a delimiter in CSV data. If setting with a string, a string has to have a length of 1.") \
M(SettingBool, format_csv_allow_single_quotes, 1, "If it is set to true, allow strings in single quotes.") \
M(SettingBool, format_csv_allow_double_quotes, 1, "If it is set to true, allow strings in double quotes.") \
M(SettingBool, input_format_csv_unquoted_null_literal_as_null, false, "Consider unquoted NULL literal as \\N") \
M(SettingUInt64, max_network_bandwidth, 0, "The maximum speed of data exchange over the network in bytes per second for a query. Zero means unlimited.", 0) \
M(SettingUInt64, max_network_bytes, 0, "The maximum number of bytes (compressed) to receive or transmit over the network for execution of the query.", 0) \
M(SettingUInt64, max_network_bandwidth_for_user, 0, "The maximum speed of data exchange over the network in bytes per second for all concurrently running user queries. Zero means unlimited.", 0)\
M(SettingUInt64, max_network_bandwidth_for_all_users, 0, "The maximum speed of data exchange over the network in bytes per second for all concurrently running queries. Zero means unlimited.", 0) \
M(SettingChar, format_csv_delimiter, ',', "The character to be considered as a delimiter in CSV data. If setting with a string, a string has to have a length of 1.", 0) \
M(SettingBool, format_csv_allow_single_quotes, 1, "If it is set to true, allow strings in single quotes.", 0) \
M(SettingBool, format_csv_allow_double_quotes, 1, "If it is set to true, allow strings in double quotes.", 0) \
M(SettingBool, input_format_csv_unquoted_null_literal_as_null, false, "Consider unquoted NULL literal as \\N", 0) \
\
M(SettingDateTimeInputFormat, date_time_input_format, FormatSettings::DateTimeInputFormat::Basic, "Method to read DateTime from text input formats. Possible values: 'basic' and 'best_effort'.") \
M(SettingBool, log_profile_events, true, "Log query performance statistics into the query_log and query_thread_log.") \
M(SettingBool, log_query_settings, true, "Log query settings into the query_log.") \
M(SettingBool, log_query_threads, true, "Log query threads into system.query_thread_log table. This setting have effect only when 'log_queries' is true.") \
M(SettingLogsLevel, send_logs_level, LogsLevel::none, "Send server text logs with specified minimum level to client. Valid values: 'trace', 'debug', 'information', 'warning', 'error', 'none'") \
M(SettingBool, enable_optimize_predicate_expression, 1, "If it is set to true, optimize predicates to subqueries.") \
M(SettingBool, enable_optimize_predicate_expression_to_final_subquery, 1, "Allow push predicate to final subquery.") \
M(SettingDateTimeInputFormat, date_time_input_format, FormatSettings::DateTimeInputFormat::Basic, "Method to read DateTime from text input formats. Possible values: 'basic' and 'best_effort'.", 0) \
M(SettingBool, log_profile_events, true, "Log query performance statistics into the query_log and query_thread_log.", 0) \
M(SettingBool, log_query_settings, true, "Log query settings into the query_log.", 0) \
M(SettingBool, log_query_threads, true, "Log query threads into system.query_thread_log table. This setting have effect only when 'log_queries' is true.", 0) \
M(SettingLogsLevel, send_logs_level, LogsLevel::none, "Send server text logs with specified minimum level to client. Valid values: 'trace', 'debug', 'information', 'warning', 'error', 'none'", 0) \
M(SettingBool, enable_optimize_predicate_expression, 1, "If it is set to true, optimize predicates to subqueries.", 0) \
M(SettingBool, enable_optimize_predicate_expression_to_final_subquery, 1, "Allow push predicate to final subquery.", 0) \
\
M(SettingUInt64, low_cardinality_max_dictionary_size, 8192, "Maximum size (in rows) of shared global dictionary for LowCardinality type.") \
M(SettingBool, low_cardinality_use_single_dictionary_for_part, false, "LowCardinality type serialization setting. If is true, than will use additional keys when global dictionary overflows. Otherwise, will create several shared dictionaries.") \
M(SettingBool, decimal_check_overflow, true, "Check overflow of decimal arithmetic/comparison operations") \
M(SettingUInt64, low_cardinality_max_dictionary_size, 8192, "Maximum size (in rows) of shared global dictionary for LowCardinality type.", 0) \
M(SettingBool, low_cardinality_use_single_dictionary_for_part, false, "LowCardinality type serialization setting. If is true, than will use additional keys when global dictionary overflows. Otherwise, will create several shared dictionaries.", 0) \
M(SettingBool, decimal_check_overflow, true, "Check overflow of decimal arithmetic/comparison operations", 0) \
\
M(SettingBool, prefer_localhost_replica, 1, "1 - always send query to local replica, if it exists. 0 - choose replica to send query between local and remote ones according to load_balancing") \
M(SettingUInt64, max_fetch_partition_retries_count, 5, "Amount of retries while fetching partition from another host.") \
M(SettingUInt64, http_max_multipart_form_data_size, 1024 * 1024 * 1024, "Limit on size of multipart/form-data content. This setting cannot be parsed from URL parameters and should be set in user profile. Note that content is parsed and external tables are created in memory before start of query execution. And this is the only limit that has effect on that stage (limits on max memory usage and max execution time have no effect while reading HTTP form data).") \
M(SettingBool, calculate_text_stack_trace, 1, "Calculate text stack trace in case of exceptions during query execution. This is the default. It requires symbol lookups that may slow down fuzzing tests when huge amount of wrong queries are executed. In normal cases you should not disable this option.") \
M(SettingBool, allow_ddl, true, "If it is set to true, then a user is allowed to executed DDL queries.") \
M(SettingBool, parallel_view_processing, false, "Enables pushing to attached views concurrently instead of sequentially.") \
M(SettingBool, enable_debug_queries, false, "Enables debug queries such as AST.") \
M(SettingBool, enable_unaligned_array_join, false, "Allow ARRAY JOIN with multiple arrays that have different sizes. When this settings is enabled, arrays will be resized to the longest one.") \
M(SettingBool, optimize_read_in_order, true, "Enable ORDER BY optimization for reading data in corresponding order in MergeTree tables.") \
M(SettingBool, low_cardinality_allow_in_native_format, true, "Use LowCardinality type in Native format. Otherwise, convert LowCardinality columns to ordinary for select query, and convert ordinary columns to required LowCardinality for insert query.") \
M(SettingBool, allow_experimental_multiple_joins_emulation, true, "Emulate multiple joins using subselects") \
M(SettingBool, allow_experimental_cross_to_join_conversion, true, "Convert CROSS JOIN to INNER JOIN if possible") \
M(SettingBool, cancel_http_readonly_queries_on_client_close, false, "Cancel HTTP readonly queries when a client closes the connection without waiting for response.") \
M(SettingBool, external_table_functions_use_nulls, true, "If it is set to true, external table functions will implicitly use Nullable type if needed. Otherwise NULLs will be substituted with default values. Currently supported only by 'mysql' and 'odbc' table functions.") \
M(SettingBool, allow_experimental_data_skipping_indices, false, "If it is set to true, data skipping indices can be used in CREATE TABLE/ALTER TABLE queries.") \
M(SettingBool, prefer_localhost_replica, 1, "1 - always send query to local replica, if it exists. 0 - choose replica to send query between local and remote ones according to load_balancing", 0) \
M(SettingUInt64, max_fetch_partition_retries_count, 5, "Amount of retries while fetching partition from another host.", 0) \
M(SettingUInt64, http_max_multipart_form_data_size, 1024 * 1024 * 1024, "Limit on size of multipart/form-data content. This setting cannot be parsed from URL parameters and should be set in user profile. Note that content is parsed and external tables are created in memory before start of query execution. And this is the only limit that has effect on that stage (limits on max memory usage and max execution time have no effect while reading HTTP form data).", 0) \
M(SettingBool, calculate_text_stack_trace, 1, "Calculate text stack trace in case of exceptions during query execution. This is the default. It requires symbol lookups that may slow down fuzzing tests when huge amount of wrong queries are executed. In normal cases you should not disable this option.", 0) \
M(SettingBool, allow_ddl, true, "If it is set to true, then a user is allowed to executed DDL queries.", 0) \
M(SettingBool, parallel_view_processing, false, "Enables pushing to attached views concurrently instead of sequentially.", 0) \
M(SettingBool, enable_debug_queries, false, "Enables debug queries such as AST.", 0) \
M(SettingBool, enable_unaligned_array_join, false, "Allow ARRAY JOIN with multiple arrays that have different sizes. When this settings is enabled, arrays will be resized to the longest one.", 0) \
M(SettingBool, optimize_read_in_order, true, "Enable ORDER BY optimization for reading data in corresponding order in MergeTree tables.", 0) \
M(SettingBool, low_cardinality_allow_in_native_format, true, "Use LowCardinality type in Native format. Otherwise, convert LowCardinality columns to ordinary for select query, and convert ordinary columns to required LowCardinality for insert query.", 0) \
M(SettingBool, allow_experimental_multiple_joins_emulation, true, "Emulate multiple joins using subselects", 0) \
M(SettingBool, allow_experimental_cross_to_join_conversion, true, "Convert CROSS JOIN to INNER JOIN if possible", 0) \
M(SettingBool, cancel_http_readonly_queries_on_client_close, false, "Cancel HTTP readonly queries when a client closes the connection without waiting for response.", 0) \
M(SettingBool, external_table_functions_use_nulls, true, "If it is set to true, external table functions will implicitly use Nullable type if needed. Otherwise NULLs will be substituted with default values. Currently supported only by 'mysql' and 'odbc' table functions.", 0) \
M(SettingBool, allow_experimental_data_skipping_indices, false, "If it is set to true, data skipping indices can be used in CREATE TABLE/ALTER TABLE queries.", 0) \
\
M(SettingBool, experimental_use_processors, false, "Use processors pipeline.") \
M(SettingBool, experimental_use_processors, false, "Use processors pipeline.", 0) \
\
M(SettingBool, allow_hyperscan, true, "Allow functions that use Hyperscan library. Disable to avoid potentially long compilation times and excessive resource usage.") \
M(SettingBool, allow_simdjson, true, "Allow using simdjson library in 'JSON*' functions if AVX2 instructions are available. If disabled rapidjson will be used.") \
M(SettingBool, allow_introspection_functions, false, "Allow functions for introspection of ELF and DWARF for query profiling. These functions are slow and may impose security considerations.") \
M(SettingBool, allow_hyperscan, true, "Allow functions that use Hyperscan library. Disable to avoid potentially long compilation times and excessive resource usage.", 0) \
M(SettingBool, allow_simdjson, true, "Allow using simdjson library in 'JSON*' functions if AVX2 instructions are available. If disabled rapidjson will be used.", 0) \
M(SettingBool, allow_introspection_functions, false, "Allow functions for introspection of ELF and DWARF for query profiling. These functions are slow and may impose security considerations.", 0) \
\
M(SettingUInt64, max_partitions_per_insert_block, 100, "Limit maximum number of partitions in single INSERTed block. Zero means unlimited. Throw exception if the block contains too many partitions. This setting is a safety threshold, because using large number of partitions is a common misconception.") \
M(SettingBool, check_query_single_value_result, true, "Return check query result as single 1/0 value") \
M(SettingBool, allow_drop_detached, false, "Allow ALTER TABLE ... DROP DETACHED PART[ITION] ... queries") \
M(SettingUInt64, max_partitions_per_insert_block, 100, "Limit maximum number of partitions in single INSERTed block. Zero means unlimited. Throw exception if the block contains too many partitions. This setting is a safety threshold, because using large number of partitions is a common misconception.", 0) \
M(SettingBool, check_query_single_value_result, true, "Return check query result as single 1/0 value", 0) \
M(SettingBool, allow_drop_detached, false, "Allow ALTER TABLE ... DROP DETACHED PART[ITION] ... queries", 0) \
\
M(SettingSeconds, distributed_replica_error_half_life, DBMS_CONNECTION_POOL_WITH_FAILOVER_DEFAULT_DECREASE_ERROR_PERIOD, "Time period reduces replica error counter by 2 times.") \
M(SettingUInt64, distributed_replica_error_cap, DBMS_CONNECTION_POOL_WITH_FAILOVER_MAX_ERROR_COUNT, "Max number of errors per replica, prevents piling up increadible amount of errors if replica was offline for some time and allows it to be reconsidered in a shorter amount of time.") \
M(SettingSeconds, distributed_replica_error_half_life, DBMS_CONNECTION_POOL_WITH_FAILOVER_DEFAULT_DECREASE_ERROR_PERIOD, "Time period reduces replica error counter by 2 times.", 0) \
M(SettingUInt64, distributed_replica_error_cap, DBMS_CONNECTION_POOL_WITH_FAILOVER_MAX_ERROR_COUNT, "Max number of errors per replica, prevents piling up increadible amount of errors if replica was offline for some time and allows it to be reconsidered in a shorter amount of time.", 0) \
\
M(SettingBool, allow_experimental_live_view, false, "Enable LIVE VIEW. Not mature enough.") \
M(SettingSeconds, live_view_heartbeat_interval, DEFAULT_LIVE_VIEW_HEARTBEAT_INTERVAL_SEC, "The heartbeat interval in seconds to indicate live query is alive.") \
M(SettingSeconds, temporary_live_view_timeout, DEFAULT_TEMPORARY_LIVE_VIEW_TIMEOUT_SEC, "Timeout after which temporary live view is deleted.") \
M(SettingUInt64, max_live_view_insert_blocks_before_refresh, 64, "Limit maximum number of inserted blocks after which mergeable blocks are dropped and query is re-executed.") \
M(SettingUInt64, min_free_disk_space_for_temporary_data, 0, "The minimum disk space to keep while writing temporary data used in external sorting and aggregation.") \
M(SettingBool, allow_experimental_live_view, false, "Enable LIVE VIEW. Not mature enough.", 0) \
M(SettingSeconds, live_view_heartbeat_interval, DEFAULT_LIVE_VIEW_HEARTBEAT_INTERVAL_SEC, "The heartbeat interval in seconds to indicate live query is alive.", 0) \
M(SettingSeconds, temporary_live_view_timeout, DEFAULT_TEMPORARY_LIVE_VIEW_TIMEOUT_SEC, "Timeout after which temporary live view is deleted.", 0) \
M(SettingUInt64, max_live_view_insert_blocks_before_refresh, 64, "Limit maximum number of inserted blocks after which mergeable blocks are dropped and query is re-executed.", 0) \
M(SettingUInt64, min_free_disk_space_for_temporary_data, 0, "The minimum disk space to keep while writing temporary data used in external sorting and aggregation.", 0) \
\
M(SettingBool, enable_scalar_subquery_optimization, true, "If it is set to true, prevent scalar subqueries from (de)serializing large scalar values and possibly avoid running the same subquery more than once.") \
M(SettingBool, optimize_trivial_count_query, true, "Process trivial 'SELECT count() FROM table' query from metadata.") \
M(SettingBool, enable_scalar_subquery_optimization, true, "If it is set to true, prevent scalar subqueries from (de)serializing large scalar values and possibly avoid running the same subquery more than once.", 0) \
M(SettingBool, optimize_trivial_count_query, true, "Process trivial 'SELECT count() FROM table' query from metadata.", 0) \
\
/** Obsolete settings that do nothing but left for compatibility reasons. Remove each one after half a year of obsolescence. */ \
\
M(SettingBool, allow_experimental_low_cardinality_type, true, "Obsolete setting, does nothing. Will be removed after 2019-08-13") \
M(SettingBool, compile, false, "Whether query compilation is enabled. Will be removed after 2020-03-13") \
M(SettingBool, allow_experimental_low_cardinality_type, true, "Obsolete setting, does nothing. Will be removed after 2019-08-13", 0) \
M(SettingBool, compile, false, "Whether query compilation is enabled. Will be removed after 2020-03-13", 0) \
DECLARE_SETTINGS_COLLECTION(LIST_OF_SETTINGS)

121
dbms/src/Core/SettingsCommon.cpp → dbms/src/Core/SettingsCollection.cpp
View File

@ -1,17 +1,17 @@
#include "SettingsCommon.h"
#include <Core/SettingsCollection.h>
#include <Core/SettingsCollectionImpl.h>
#include <Core/Field.h>
#include <Common/getNumberOfPhysicalCPUCores.h>
#include <Common/FieldVisitors.h>
#include <common/logger_useful.h>
#include <IO/ReadHelpers.h>
#include <IO/ReadBufferFromString.h>
#include <IO/WriteHelpers.h>
namespace DB
{
namespace ErrorCodes
{
extern const int TYPE_MISMATCH;
@ -90,8 +90,14 @@ void SettingNumber<bool>::set(const String & x)
}
template <typename Type>
void SettingNumber<Type>::serialize(WriteBuffer & buf) const
void SettingNumber<Type>::serialize(WriteBuffer & buf, SettingsBinaryFormat format) const
{
if (format >= SettingsBinaryFormat::STRINGS)
{
writeStringBinary(toString(), buf);
return;
}
if constexpr (is_integral_v<Type> && is_unsigned_v<Type>)
writeVarUInt(static_cast<UInt64>(value), buf);
else if constexpr (is_integral_v<Type> && is_signed_v<Type>)
@ -99,13 +105,21 @@ void SettingNumber<Type>::serialize(WriteBuffer & buf) const
else
{
static_assert(std::is_floating_point_v<Type>);
writeBinary(toString(), buf);
writeStringBinary(toString(), buf);
}
}
template <typename Type>
void SettingNumber<Type>::deserialize(ReadBuffer & buf)
void SettingNumber<Type>::deserialize(ReadBuffer & buf, SettingsBinaryFormat format)
{
if (format >= SettingsBinaryFormat::STRINGS)
{
String x;
readStringBinary(x, buf);
set(x);
return;
}
if constexpr (is_integral_v<Type> && is_unsigned_v<Type>)
{
UInt64 x;
@ -122,7 +136,7 @@ void SettingNumber<Type>::deserialize(ReadBuffer & buf)
{
static_assert(std::is_floating_point_v<Type>);
String x;
readBinary(x, buf);
readStringBinary(x, buf);
set(x);
}
}
@ -167,13 +181,27 @@ void SettingMaxThreads::set(const String & x)
set(parse<UInt64>(x));
}
void SettingMaxThreads::serialize(WriteBuffer & buf) const
void SettingMaxThreads::serialize(WriteBuffer & buf, SettingsBinaryFormat format) const
{
if (format >= SettingsBinaryFormat::STRINGS)
{
writeStringBinary(is_auto ? "auto" : DB::toString(value), buf);
return;
}
writeVarUInt(is_auto ? 0 : value, buf);
}
void SettingMaxThreads::deserialize(ReadBuffer & buf)
void SettingMaxThreads::deserialize(ReadBuffer & buf, SettingsBinaryFormat format)
{
if (format >= SettingsBinaryFormat::STRINGS)
{
String x;
readStringBinary(x, buf);
set(x);
return;
}
UInt64 x = 0;
readVarUInt(x, buf);
set(x);
@ -233,14 +261,28 @@ void SettingTimespan<io_unit>::set(const String & x)
}
template <SettingTimespanIO io_unit>
void SettingTimespan<io_unit>::serialize(WriteBuffer & buf) const
void SettingTimespan<io_unit>::serialize(WriteBuffer & buf, SettingsBinaryFormat format) const
{
if (format >= SettingsBinaryFormat::STRINGS)
{
writeStringBinary(toString(), buf);
return;
}
writeVarUInt(value.totalMicroseconds() / microseconds_per_io_unit, buf);
}
template <SettingTimespanIO io_unit>
void SettingTimespan<io_unit>::deserialize(ReadBuffer & buf)
void SettingTimespan<io_unit>::deserialize(ReadBuffer & buf, SettingsBinaryFormat format)
{
if (format >= SettingsBinaryFormat::STRINGS)
{
String x;
readStringBinary(x, buf);
set(x);
return;
}
UInt64 x = 0;
readVarUInt(x, buf);
set(x);
@ -271,15 +313,15 @@ void SettingString::set(const Field & x)
set(safeGet<const String &>(x));
}
void SettingString::serialize(WriteBuffer & buf) const
void SettingString::serialize(WriteBuffer & buf, SettingsBinaryFormat) const
{
writeBinary(value, buf);
writeStringBinary(value, buf);
}
void SettingString::deserialize(ReadBuffer & buf)
void SettingString::deserialize(ReadBuffer & buf, SettingsBinaryFormat)
{
String s;
readBinary(s, buf);
readStringBinary(s, buf);
set(s);
}
@ -314,30 +356,30 @@ void SettingChar::set(const Field & x)
set(s);
}
void SettingChar::serialize(WriteBuffer & buf) const
void SettingChar::serialize(WriteBuffer & buf, SettingsBinaryFormat) const
{
writeBinary(toString(), buf);
writeStringBinary(toString(), buf);
}
void SettingChar::deserialize(ReadBuffer & buf)
void SettingChar::deserialize(ReadBuffer & buf, SettingsBinaryFormat)
{
String s;
readBinary(s, buf);
readStringBinary(s, buf);
set(s);
}
template <typename EnumType, typename Tag>
void SettingEnum<EnumType, Tag>::serialize(WriteBuffer & buf) const
void SettingEnum<EnumType, Tag>::serialize(WriteBuffer & buf, SettingsBinaryFormat) const
{
writeBinary(toString(), buf);
writeStringBinary(toString(), buf);
}
template <typename EnumType, typename Tag>
void SettingEnum<EnumType, Tag>::deserialize(ReadBuffer & buf)
void SettingEnum<EnumType, Tag>::deserialize(ReadBuffer & buf, SettingsBinaryFormat)
{
String s;
readBinary(s, buf);
readStringBinary(s, buf);
set(s);
}
@ -462,14 +504,43 @@ IMPLEMENT_SETTING_ENUM(LogsLevel, LOGS_LEVEL_LIST_OF_NAMES, ErrorCodes::BAD_ARGU
namespace details
{
void SettingsCollectionUtils::serializeName(const StringRef & name, WriteBuffer & buf)
{
writeStringBinary(name, buf);
}
String SettingsCollectionUtils::deserializeName(ReadBuffer & buf)
{
String name;
readBinary(name, buf);
readStringBinary(name, buf);
return name;
}
void SettingsCollectionUtils::serializeName(const StringRef & name, WriteBuffer & buf) { writeBinary(name, buf); }
void SettingsCollectionUtils::serializeFlag(bool flag, WriteBuffer & buf)
{
buf.write(flag);
}
bool SettingsCollectionUtils::deserializeFlag(ReadBuffer & buf)
{
char c;
buf.readStrict(c);
return c;
}
void SettingsCollectionUtils::skipValue(ReadBuffer & buf)
{
/// Ignore a string written by the function writeStringBinary().
UInt64 size;
readVarUInt(size, buf);
buf.ignore(size);
}
void SettingsCollectionUtils::warningNameNotFound(const StringRef & name)
{
static auto * log = &Logger::get("Settings");
LOG_WARNING(log, "Unknown setting " << name << ", skipping");
}
void SettingsCollectionUtils::throwNameNotFound(const StringRef & name)
{

236
dbms/src/Core/SettingsCommon.h → dbms/src/Core/SettingsCollection.h
View File

@ -6,7 +6,6 @@
#include <common/StringRef.h>
#include <Core/Types.h>
#include <unordered_map>
#include <boost/noncopyable.hpp>
namespace DB
@ -17,6 +16,8 @@ struct SettingChange;
using SettingsChanges = std::vector<SettingChange>;
class ReadBuffer;
class WriteBuffer;
enum class SettingsBinaryFormat;
/** One setting for any type.
* Stores a value within itself, as well as a flag - whether the value was changed.
@ -51,10 +52,10 @@ struct SettingNumber
void set(const String & x);
/// Serialize to binary stream suitable for transfer over network.
void serialize(WriteBuffer & buf) const;
void serialize(WriteBuffer & buf, SettingsBinaryFormat format) const;
/// Read from binary stream.
void deserialize(ReadBuffer & buf);
void deserialize(ReadBuffer & buf, SettingsBinaryFormat format);
};
using SettingUInt64 = SettingNumber<UInt64>;
@ -85,8 +86,8 @@ struct SettingMaxThreads
void set(const Field & x);
void set(const String & x);
void serialize(WriteBuffer & buf) const;
void deserialize(ReadBuffer & buf);
void serialize(WriteBuffer & buf, SettingsBinaryFormat format) const;
void deserialize(ReadBuffer & buf, SettingsBinaryFormat format);
void setAuto();
UInt64 getAutoValue() const;
@ -118,8 +119,8 @@ struct SettingTimespan
void set(const Field & x);
void set(const String & x);
void serialize(WriteBuffer & buf) const;
void deserialize(ReadBuffer & buf);
void serialize(WriteBuffer & buf, SettingsBinaryFormat format) const;
void deserialize(ReadBuffer & buf, SettingsBinaryFormat format);
static constexpr UInt64 microseconds_per_io_unit = (io_unit == SettingTimespanIO::MILLISECOND) ? 1000 : 1000000;
};
@ -144,8 +145,8 @@ struct SettingString
void set(const String & x);
void set(const Field & x);
void serialize(WriteBuffer & buf) const;
void deserialize(ReadBuffer & buf);
void serialize(WriteBuffer & buf, SettingsBinaryFormat format) const;
void deserialize(ReadBuffer & buf, SettingsBinaryFormat format);
};
@ -167,8 +168,8 @@ public:
void set(const String & x);
void set(const Field & x);
void serialize(WriteBuffer & buf) const;
void deserialize(ReadBuffer & buf);
void serialize(WriteBuffer & buf, SettingsBinaryFormat format) const;
void deserialize(ReadBuffer & buf, SettingsBinaryFormat format);
};
@ -191,8 +192,8 @@ struct SettingEnum
void set(const Field & x);
void set(const String & x);
void serialize(WriteBuffer & buf) const;
void deserialize(ReadBuffer & buf);
void serialize(WriteBuffer & buf, SettingsBinaryFormat format) const;
void deserialize(ReadBuffer & buf, SettingsBinaryFormat format);
};
@ -269,15 +270,12 @@ enum class LogsLevel
using SettingLogsLevel = SettingEnum<LogsLevel>;
namespace details
enum class SettingsBinaryFormat
{
struct SettingsCollectionUtils
{
static void serializeName(const StringRef & name, WriteBuffer & buf);
static String deserializeName(ReadBuffer & buf);
[[noreturn]] static void throwNameNotFound(const StringRef & name);
};
}
OLD, /// Part of the settings are serialized as strings, and other part as varints. This is the old behaviour.
STRINGS, /// All settings are serialized as strings. Before each value the flag `is_ignorable` is serialized.
DEFAULT = STRINGS,
};
/** Template class to define collections of settings.
@ -287,9 +285,9 @@ namespace details
* struct MySettings : public SettingsCollection<MySettings>
* {
* # define APPLY_FOR_MYSETTINGS(M) \
* M(SettingUInt64, a, 100, "Description of a") \
* M(SettingFloat, f, 3.11, "Description of f") \
* M(SettingString, s, "default", "Description of s")
* M(SettingUInt64, a, 100, "Description of a", 0) \
* M(SettingFloat, f, 3.11, "Description of f", IGNORABLE) // IGNORABLE - means the setting can be ignored by older versions) \
* M(SettingString, s, "default", "Description of s", 0)
*
* DECLARE_SETTINGS_COLLECTION(MySettings, APPLY_FOR_MYSETTINGS)
* };
@ -304,21 +302,22 @@ private:
Derived & castToDerived() { return *static_cast<Derived *>(this); }
const Derived & castToDerived() const { return *static_cast<const Derived *>(this); }
using IsChangedFunction = bool (*)(const Derived &);
using GetStringFunction = String (*)(const Derived &);
using GetFieldFunction = Field (*)(const Derived &);
using SetStringFunction = void (*)(Derived &, const String &);
using SetFieldFunction = void (*)(Derived &, const Field &);
using SerializeFunction = void (*)(const Derived &, WriteBuffer & buf);
using DeserializeFunction = void (*)(Derived &, ReadBuffer & buf);
using ValueToStringFunction = String (*)(const Field &);
using ValueToCorrespondingTypeFunction = Field (*)(const Field &);
struct MemberInfo
{
IsChangedFunction is_changed;
using IsChangedFunction = bool (*)(const Derived &);
using GetStringFunction = String (*)(const Derived &);
using GetFieldFunction = Field (*)(const Derived &);
using SetStringFunction = void (*)(Derived &, const String &);
using SetFieldFunction = void (*)(Derived &, const Field &);
using SerializeFunction = void (*)(const Derived &, WriteBuffer & buf, SettingsBinaryFormat);
using DeserializeFunction = void (*)(Derived &, ReadBuffer & buf, SettingsBinaryFormat);
using ValueToStringFunction = String (*)(const Field &);
using ValueToCorrespondingTypeFunction = Field (*)(const Field &);
StringRef name;
StringRef description;
bool is_ignorable;
IsChangedFunction is_changed;
GetStringFunction get_string;
GetFieldFunction get_field;
SetStringFunction set_string;
@ -329,52 +328,22 @@ private:
ValueToCorrespondingTypeFunction value_to_corresponding_type;
};
class MemberInfos : private boost::noncopyable
class MemberInfos
{
public:
static const MemberInfos & instance();
size_t size() const { return infos.size(); }
const MemberInfo & operator[](size_t index) const { return infos[index]; }
const MemberInfo * begin() const { return infos.data(); }
const MemberInfo * end() const { return infos.data() + infos.size(); }
size_t findIndex(const StringRef & name) const
{
auto it = by_name_map.find(name);
if (it == by_name_map.end())
return static_cast<size_t>(-1); // npos
return it->second;
}
size_t findIndexStrict(const StringRef & name) const
{
auto it = by_name_map.find(name);
if (it == by_name_map.end())
details::SettingsCollectionUtils::throwNameNotFound(name);
return it->second;
}
const MemberInfo * find(const StringRef & name) const
{
auto it = by_name_map.find(name);
if (it == by_name_map.end())
return end();
else
return &infos[it->second];
}
const MemberInfo * findStrict(const StringRef & name) const { return &infos[findIndexStrict(name)]; }
private:
MemberInfos();
void add(MemberInfo && member)
{
size_t index = infos.size();
infos.emplace_back(member);
by_name_map.emplace(infos.back().name, index);
}
size_t size() const { return infos.size(); }
const MemberInfo * data() const { return infos.data(); }
const MemberInfo & operator[](size_t index) const { return infos[index]; }
const MemberInfo * find(const StringRef & name) const;
const MemberInfo & findStrict(const StringRef & name) const;
size_t findIndex(const StringRef & name) const;
size_t findIndexStrict(const StringRef & name) const;
private:
void add(MemberInfo && member);
std::vector<MemberInfo> infos;
std::unordered_map<StringRef, size_t> by_name_map;
@ -396,6 +365,7 @@ public:
bool isChanged() const { return member->is_changed(*collection); }
Field getValue() const;
String getValueAsString() const { return member->get_string(*collection); }
protected:
friend class SettingsCollection<Derived>::const_iterator;
const_reference() : collection(nullptr), member(nullptr) {}
@ -410,7 +380,7 @@ public:
public:
reference(Derived & collection_, const MemberInfo & member_) : const_reference(collection_, member_) {}
reference(const const_reference & src) : const_reference(src) {}
void setValue(const Field & value);
void setValue(const Field & value) { this->member->set_field(*const_cast<Derived *>(this->collection), value); }
void setValue(const String & value) { this->member->set_string(*const_cast<Derived *>(this->collection), value); }
};
@ -453,7 +423,7 @@ public:
/// Returns description of a setting.
static StringRef getDescription(size_t index) { return members()[index].description; }
static StringRef getDescription(const String & name) { return members().findStrict(name)->description; }
static StringRef getDescription(const String & name) { return members().findStrict(name).description; }
/// Searches a setting by its name; returns `npos` if not found.
static size_t findIndex(const StringRef & name) { return members().findIndex(name); }
@ -463,36 +433,36 @@ public:
static size_t findIndexStrict(const StringRef & name) { return members().findIndexStrict(name); }
/// Casts a value to a string according to a specified setting without actual changing this settings.
static String valueToString(size_t index, const Field & value);
static String valueToString(const StringRef & name, const Field & value);
static String valueToString(size_t index, const Field & value) { return members()[index].value_to_string(value); }
static String valueToString(const StringRef & name, const Field & value) { return members().findStrict(name).value_to_string(value); }
/// Casts a value to a type according to a specified setting without actual changing this settings.
/// E.g. for SettingInt64 it casts Field to Field::Types::Int64.
static Field valueToCorrespondingType(size_t index, const Field & value);
static Field valueToCorrespondingType(const StringRef & name, const Field & value);
iterator begin() { return iterator(castToDerived(), members().begin()); }
const_iterator begin() const { return const_iterator(castToDerived(), members().begin()); }
iterator end() { return iterator(castToDerived(), members().end()); }
const_iterator end() const { return const_iterator(castToDerived(), members().end()); }
iterator begin() { return iterator(castToDerived(), members().data()); }
const_iterator begin() const { return const_iterator(castToDerived(), members().data()); }
iterator end() { const auto & the_members = members(); return iterator(castToDerived(), the_members.data() + the_members.size()); }
const_iterator end() const { const auto & the_members = members(); return const_iterator(castToDerived(), the_members.data() + the_members.size()); }
/// Returns a proxy object for accessing to a setting. Throws an exception if there is not setting with such name.
reference operator[](size_t index) { return reference(castToDerived(), members()[index]); }
reference operator[](const StringRef & name) { return reference(castToDerived(), *(members().findStrict(name))); }
reference operator[](const StringRef & name) { return reference(castToDerived(), members().findStrict(name)); }
const_reference operator[](size_t index) const { return const_reference(castToDerived(), members()[index]); }
const_reference operator[](const StringRef & name) const { return const_reference(castToDerived(), *(members().findStrict(name))); }
const_reference operator[](const StringRef & name) const { return const_reference(castToDerived(), members().findStrict(name)); }
/// Searches a setting by its name; returns end() if not found.
iterator find(const StringRef & name) { return iterator(castToDerived(), members().find(name)); }
const_iterator find(const StringRef & name) const { return const_iterator(castToDerived(), members().find(name)); }
iterator find(const StringRef & name);
const_iterator find(const StringRef & name) const;
/// Searches a setting by its name; throws an exception if not found.
iterator findStrict(const StringRef & name) { return iterator(castToDerived(), members().findStrict(name)); }
const_iterator findStrict(const StringRef & name) const { return const_iterator(castToDerived(), members().findStrict(name)); }
iterator findStrict(const StringRef & name);
const_iterator findStrict(const StringRef & name) const;
/// Sets setting's value.
void set(size_t index, const Field & value);
void set(const StringRef & name, const Field & value);
void set(size_t index, const Field & value) { (*this)[index].setValue(value); }
void set(const StringRef & name, const Field & value) { (*this)[name].setValue(value); }
/// Sets setting's value. Read value in text form from string (for example, from configuration file or from URL parameter).
void set(size_t index, const String & value) { (*this)[index].setValue(value); }
@ -514,11 +484,7 @@ public:
/// Compares two collections of settings.
bool operator ==(const Derived & rhs) const;
bool operator !=(const Derived & rhs) const
{
return !(*this == rhs);
}
bool operator!=(const Derived & rhs) const { return !(*this == rhs); }
/// Gathers all changed values (e.g. for applying them later to another collection of settings).
SettingsChanges changes() const;
@ -536,82 +502,16 @@ public:
/// Writes the settings to buffer (e.g. to be sent to remote server).
/// Only changed settings are written. They are written as list of contiguous name-value pairs,
/// finished with empty name.
void serialize(WriteBuffer & buf) const
{
for (const auto & member : members())
{
if (member.is_changed(castToDerived()))
{
details::SettingsCollectionUtils::serializeName(member.name, buf);
member.serialize(castToDerived(), buf);
}
}
details::SettingsCollectionUtils::serializeName(StringRef{} /* empty string is a marker of the end of settings */, buf);
}
void serialize(WriteBuffer & buf, SettingsBinaryFormat format = SettingsBinaryFormat::DEFAULT) const;
/// Reads the settings from buffer.
void deserialize(ReadBuffer & buf)
{
const auto & the_members = members();
while (true)
{
String name = details::SettingsCollectionUtils::deserializeName(buf);
if (name.empty() /* empty string is a marker of the end of settings */)
break;
the_members.findStrict(name)->deserialize(castToDerived(), buf);
}
}
void deserialize(ReadBuffer & buf, SettingsBinaryFormat format = SettingsBinaryFormat::DEFAULT);
};
#define DECLARE_SETTINGS_COLLECTION(LIST_OF_SETTINGS_MACRO) \
LIST_OF_SETTINGS_MACRO(DECLARE_SETTINGS_COLLECTION_DECLARE_VARIABLES_HELPER_)
#define IMPLEMENT_SETTINGS_COLLECTION(DERIVED_CLASS_NAME, LIST_OF_SETTINGS_MACRO) \
template<> \
SettingsCollection<DERIVED_CLASS_NAME>::MemberInfos::MemberInfos() \
{ \
using Derived = DERIVED_CLASS_NAME; \
struct Functions \
{ \
LIST_OF_SETTINGS_MACRO(IMPLEMENT_SETTINGS_COLLECTION_DEFINE_FUNCTIONS_HELPER_) \
}; \
LIST_OF_SETTINGS_MACRO(IMPLEMENT_SETTINGS_COLLECTION_ADD_MEMBER_INFO_HELPER_) \
} \
template <> \
const SettingsCollection<DERIVED_CLASS_NAME>::MemberInfos & SettingsCollection<DERIVED_CLASS_NAME>::MemberInfos::instance() \
{ \
static const SettingsCollection<DERIVED_CLASS_NAME>::MemberInfos single_instance; \
return single_instance; \
} \
/** \
* Instantiation should happen when all method definitions from SettingsCollectionImpl.h \
* are accessible, so we instantiate explicitly. \
*/ \
template class SettingsCollection<DERIVED_CLASS_NAME>;
#define DECLARE_SETTINGS_COLLECTION_DECLARE_VARIABLES_HELPER_(TYPE, NAME, DEFAULT, DESCRIPTION) \
#define DECLARE_SETTINGS_COLLECTION_DECLARE_VARIABLES_HELPER_(TYPE, NAME, DEFAULT, DESCRIPTION, FLAGS) \
TYPE NAME {DEFAULT};
#define IMPLEMENT_SETTINGS_COLLECTION_DEFINE_FUNCTIONS_HELPER_(TYPE, NAME, DEFAULT, DESCRIPTION) \
static String NAME##_getString(const Derived & collection) { return collection.NAME.toString(); } \
static Field NAME##_getField(const Derived & collection) { return collection.NAME.toField(); } \
static void NAME##_setString(Derived & collection, const String & value) { collection.NAME.set(value); } \
static void NAME##_setField(Derived & collection, const Field & value) { collection.NAME.set(value); } \
static void NAME##_serialize(const Derived & collection, WriteBuffer & buf) { collection.NAME.serialize(buf); } \
static void NAME##_deserialize(Derived & collection, ReadBuffer & buf) { collection.NAME.deserialize(buf); } \
static String NAME##_valueToString(const Field & value) { TYPE temp{DEFAULT}; temp.set(value); return temp.toString(); } \
static Field NAME##_valueToCorrespondingType(const Field & value) { TYPE temp{DEFAULT}; temp.set(value); return temp.toField(); } \
#define IMPLEMENT_SETTINGS_COLLECTION_ADD_MEMBER_INFO_HELPER_(TYPE, NAME, DEFAULT, DESCRIPTION) \
add({[](const Derived & d) { return d.NAME.changed; }, \
StringRef(#NAME, strlen(#NAME)), StringRef(DESCRIPTION, strlen(DESCRIPTION)), \
&Functions::NAME##_getString, &Functions::NAME##_getField, \
&Functions::NAME##_setString, &Functions::NAME##_setField, \
&Functions::NAME##_serialize, &Functions::NAME##_deserialize, \
&Functions::NAME##_valueToString, &Functions::NAME##_valueToCorrespondingType});
}

245
dbms/src/Core/SettingsCollectionImpl.h
View File

@ -2,15 +2,84 @@
/**
* This file implements some functions that are dependent on Field type.
* Unlinke SettingsCommon.h, we only have to include it once for each
* instantiation of SettingsCollection<>. This allows to work on Field without
* always recompiling the entire project.
* Unlike SettingsCollection.h, we only have to include it once for each
* instantiation of SettingsCollection<>.
*/
#include <Common/SettingsChanges.h>
namespace DB
{
namespace details
{
struct SettingsCollectionUtils
{
static void serializeName(const StringRef & name, WriteBuffer & buf);
static String deserializeName(ReadBuffer & buf);
static void serializeFlag(bool flag, WriteBuffer & buf);
static bool deserializeFlag(ReadBuffer & buf);
static void skipValue(ReadBuffer & buf);
static void warningNameNotFound(const StringRef & name);
[[noreturn]] static void throwNameNotFound(const StringRef & name);
};
}
template <class Derived>
size_t SettingsCollection<Derived>::MemberInfos::findIndex(const StringRef & name) const
{
auto it = by_name_map.find(name);
if (it == by_name_map.end())
return static_cast<size_t>(-1); // npos
return it->second;
}
template <class Derived>
size_t SettingsCollection<Derived>::MemberInfos::findIndexStrict(const StringRef & name) const
{
auto it = by_name_map.find(name);
if (it == by_name_map.end())
details::SettingsCollectionUtils::throwNameNotFound(name);
return it->second;
}
template <class Derived>
const typename SettingsCollection<Derived>::MemberInfo * SettingsCollection<Derived>::MemberInfos::find(const StringRef & name) const
{
auto it = by_name_map.find(name);
if (it == by_name_map.end())
return nullptr;
else
return &infos[it->second];
}
template <class Derived>
const typename SettingsCollection<Derived>::MemberInfo & SettingsCollection<Derived>::MemberInfos::findStrict(const StringRef & name) const
{
return infos[findIndexStrict(name)];
}
template <class Derived>
void SettingsCollection<Derived>::MemberInfos::add(MemberInfo && member)
{
size_t index = infos.size();
infos.emplace_back(member);
by_name_map.emplace(infos.back().name, index);
}
template <class Derived>
const typename SettingsCollection<Derived>::MemberInfos &
SettingsCollection<Derived>::members()
{
static const MemberInfos the_instance;
return the_instance;
}
template <class Derived>
Field SettingsCollection<Derived>::const_reference::getValue() const
@ -18,23 +87,6 @@ Field SettingsCollection<Derived>::const_reference::getValue() const
return member->get_field(*collection);
}
template <class Derived>
void SettingsCollection<Derived>::reference::setValue(const Field & value)
{
this->member->set_field(*const_cast<Derived *>(this->collection), value);
}
template <class Derived>
String SettingsCollection<Derived>::valueToString(size_t index, const Field & value)
{
return members()[index].value_to_string(value);
}
template <class Derived>
String SettingsCollection<Derived>::valueToString(const StringRef & name, const Field & value)
{
return members().findStrict(name)->value_to_string(value);
}
template <class Derived>
Field SettingsCollection<Derived>::valueToCorrespondingType(size_t index, const Field & value)
@ -42,36 +94,62 @@ Field SettingsCollection<Derived>::valueToCorrespondingType(size_t index, const
return members()[index].value_to_corresponding_type(value);
}
template <class Derived>
Field SettingsCollection<Derived>::valueToCorrespondingType(const StringRef & name, const Field & value)
{
return members().findStrict(name)->value_to_corresponding_type(value);
return members().findStrict(name).value_to_corresponding_type(value);
}
template <class Derived>
void SettingsCollection<Derived>::set(size_t index, const Field & value)
{
(*this)[index].setValue(value);
}
template <class Derived>
void SettingsCollection<Derived>::set(const StringRef & name, const Field & value)
typename SettingsCollection<Derived>::iterator SettingsCollection<Derived>::find(const StringRef & name)
{
(*this)[name].setValue(value);
const auto * member = members().find(name);
if (member)
return iterator(castToDerived(), member);
return end();
}
template <class Derived>
typename SettingsCollection<Derived>::const_iterator SettingsCollection<Derived>::find(const StringRef & name) const
{
const auto * member = members().find(name);
if (member)
return const_iterator(castToDerived(), member);
return end();
}
template <class Derived>
typename SettingsCollection<Derived>::iterator SettingsCollection<Derived>::findStrict(const StringRef & name)
{
return iterator(castToDerived(), &members().findStrict(name));
}
template <class Derived>
typename SettingsCollection<Derived>::const_iterator SettingsCollection<Derived>::findStrict(const StringRef & name) const
{
return const_iterator(castToDerived(), &members().findStrict(name));
}
template <class Derived>
Field SettingsCollection<Derived>::get(size_t index) const
{
return (*this)[index].getValue();
}
template <class Derived>
Field SettingsCollection<Derived>::get(const StringRef & name) const
{
return (*this)[name].getValue();
}
template <class Derived>
bool SettingsCollection<Derived>::tryGet(const StringRef & name, Field & value) const
{
@ -82,6 +160,7 @@ bool SettingsCollection<Derived>::tryGet(const StringRef & name, Field & value)
return true;
}
template <class Derived>
bool SettingsCollection<Derived>::tryGet(const StringRef & name, String & value) const
{
@ -92,11 +171,14 @@ bool SettingsCollection<Derived>::tryGet(const StringRef & name, String & value)
return true;
}
template <class Derived>
bool SettingsCollection<Derived>::operator ==(const Derived & rhs) const
{
for (const auto & member : members())
const auto & the_members = members();
for (size_t i = 0; i != the_members.size(); ++i)
{
const auto & member = the_members[i];
bool left_changed = member.is_changed(castToDerived());
bool right_changed = member.is_changed(rhs);
if (left_changed || right_changed)
@ -110,27 +192,29 @@ bool SettingsCollection<Derived>::operator ==(const Derived & rhs) const
return true;
}
/// Gathers all changed values (e.g. for applying them later to another collection of settings).
template <class Derived>
SettingsChanges SettingsCollection<Derived>::changes() const
{
SettingsChanges found_changes;
for (const auto & member : members())
const auto & the_members = members();
for (size_t i = 0; i != the_members.size(); ++i)
{
const auto & member = the_members[i];
if (member.is_changed(castToDerived()))
found_changes.push_back({member.name.toString(), member.get_field(castToDerived())});
}
return found_changes;
}
/// Applies change to concrete setting.
template <class Derived>
void SettingsCollection<Derived>::applyChange(const SettingChange & change)
{
set(change.name, change.value);
}
/// Applies changes to the settings.
template <class Derived>
void SettingsCollection<Derived>::applyChanges(const SettingsChanges & changes)
{
@ -138,25 +222,110 @@ void SettingsCollection<Derived>::applyChanges(const SettingsChanges & changes)
applyChange(change);
}
template <class Derived>
void SettingsCollection<Derived>::copyChangesFrom(const Derived & src)
{
for (const auto & member : members())
const auto & the_members = members();
for (size_t i = 0; i != the_members.size(); ++i)
{
const auto & member = the_members[i];
if (member.is_changed(src))
member.set_field(castToDerived(), member.get_field(src));
}
}
template <class Derived>
void SettingsCollection<Derived>::copyChangesTo(Derived & dest) const
{
dest.copyChangesFrom(castToDerived());
}
template <class Derived>
const typename SettingsCollection<Derived>::MemberInfos &
SettingsCollection<Derived>::members()
void SettingsCollection<Derived>::serialize(WriteBuffer & buf, SettingsBinaryFormat format) const
{
return MemberInfos::instance();
const auto & the_members = members();
for (size_t i = 0; i != the_members.size(); ++i)
{
const auto & member = the_members[i];
if (member.is_changed(castToDerived()))
{
details::SettingsCollectionUtils::serializeName(member.name, buf);
if (format >= SettingsBinaryFormat::STRINGS)
details::SettingsCollectionUtils::serializeFlag(member.is_ignorable, buf);
member.serialize(castToDerived(), buf, format);
}
}
details::SettingsCollectionUtils::serializeName(StringRef{} /* empty string is a marker of the end of settings */, buf);
}
} /* namespace DB */
template <class Derived>
void SettingsCollection<Derived>::deserialize(ReadBuffer & buf, SettingsBinaryFormat format)
{
const auto & the_members = members();
while (true)
{
String name = details::SettingsCollectionUtils::deserializeName(buf);
if (name.empty() /* empty string is a marker of the end of settings */)
break;
auto * member = the_members.find(name);
bool is_ignorable = (format >= SettingsBinaryFormat::STRINGS) ? details::SettingsCollectionUtils::deserializeFlag(buf) : false;
if (member)
{
member->deserialize(castToDerived(), buf, format);
}
else if (is_ignorable)
{
details::SettingsCollectionUtils::warningNameNotFound(name);
details::SettingsCollectionUtils::skipValue(buf);
}
else
details::SettingsCollectionUtils::throwNameNotFound(name);
}
}
//-V:IMPLEMENT_SETTINGS_COLLECTION:501
#define IMPLEMENT_SETTINGS_COLLECTION(DERIVED_CLASS_NAME, LIST_OF_SETTINGS_MACRO) \
template<> \
SettingsCollection<DERIVED_CLASS_NAME>::MemberInfos::MemberInfos() \
{ \
using Derived = DERIVED_CLASS_NAME; \
struct Functions \
{ \
LIST_OF_SETTINGS_MACRO(IMPLEMENT_SETTINGS_COLLECTION_DEFINE_FUNCTIONS_HELPER_) \
}; \
constexpr int IGNORABLE = 1; \
UNUSED(IGNORABLE); \
LIST_OF_SETTINGS_MACRO(IMPLEMENT_SETTINGS_COLLECTION_ADD_MEMBER_INFO_HELPER_) \
} \
/** \
* Instantiation should happen when all method definitions from SettingsCollectionImpl.h \
* are accessible, so we instantiate explicitly. \
*/ \
template class SettingsCollection<DERIVED_CLASS_NAME>;
#define IMPLEMENT_SETTINGS_COLLECTION_DEFINE_FUNCTIONS_HELPER_(TYPE, NAME, DEFAULT, DESCRIPTION, FLAGS) \
static String NAME##_getString(const Derived & collection) { return collection.NAME.toString(); } \
static Field NAME##_getField(const Derived & collection) { return collection.NAME.toField(); } \
static void NAME##_setString(Derived & collection, const String & value) { collection.NAME.set(value); } \
static void NAME##_setField(Derived & collection, const Field & value) { collection.NAME.set(value); } \
static void NAME##_serialize(const Derived & collection, WriteBuffer & buf, SettingsBinaryFormat format) { collection.NAME.serialize(buf, format); } \
static void NAME##_deserialize(Derived & collection, ReadBuffer & buf, SettingsBinaryFormat format) { collection.NAME.deserialize(buf, format); } \
static String NAME##_valueToString(const Field & value) { TYPE temp{DEFAULT}; temp.set(value); return temp.toString(); } \
static Field NAME##_valueToCorrespondingType(const Field & value) { TYPE temp{DEFAULT}; temp.set(value); return temp.toField(); } \
#define IMPLEMENT_SETTINGS_COLLECTION_ADD_MEMBER_INFO_HELPER_(TYPE, NAME, DEFAULT, DESCRIPTION, FLAGS) \
add({StringRef(#NAME, strlen(#NAME)), StringRef(DESCRIPTION, strlen(DESCRIPTION)), \
FLAGS & IGNORABLE, \
[](const Derived & d) { return d.NAME.changed; }, \
&Functions::NAME##_getString, &Functions::NAME##_getField, \
&Functions::NAME##_setString, &Functions::NAME##_setField, \
&Functions::NAME##_serialize, &Functions::NAME##_deserialize, \
&Functions::NAME##_valueToString, &Functions::NAME##_valueToCorrespondingType});
}

1
dbms/src/DataStreams/IBlockInputStream.h
View File

@ -1,7 +1,6 @@
#pragma once
#include <Core/Block.h>
#include <Core/SettingsCommon.h>
#include <DataStreams/BlockStreamProfileInfo.h>
#include <DataStreams/IBlockStream_fwd.h>
#include <DataStreams/SizeLimits.h>

2
dbms/src/DataStreams/TotalsHavingBlockInputStream.h
View File

@ -10,7 +10,7 @@ class Arena;
using ArenaPtr = std::shared_ptr<Arena>;
class ExpressionActions;
enum class TotalsMode;
/** Takes blocks after grouping, with non-finalized aggregate functions.
* Calculates total values according to totals_mode.

1
dbms/src/Dictionaries/readInvalidateQuery.cpp
View File

@ -1,6 +1,7 @@
#include "readInvalidateQuery.h"
#include <DataStreams/IBlockInputStream.h>
#include <IO/WriteBufferFromString.h>
#include <Formats/FormatSettings.h>
namespace DB

1
dbms/src/Interpreters/AnalyzedJoin.h
View File

@ -2,7 +2,6 @@
#include <Core/Names.h>
#include <Core/NamesAndTypes.h>
#include <Core/SettingsCommon.h>
#include <Parsers/ASTTablesInSelectQuery.h>
#include <Interpreters/IJoin.h>
#include <Interpreters/asof.h>

1
dbms/src/Interpreters/InJoinSubqueriesPreprocessor.h
View File

@ -1,6 +1,5 @@
#pragma once
#include <Core/SettingsCommon.h>
#include <Core/Types.h>
#include <Parsers/IAST_fwd.h>
#include <Storages/IStorage_fwd.h>

1
dbms/src/Interpreters/Join.h
View File

@ -10,7 +10,6 @@
#include <Interpreters/IJoin.h>
#include <Interpreters/AggregationCommon.h>
#include <Interpreters/RowRefs.h>
#include <Core/SettingsCommon.h>
#include <Common/Arena.h>
#include <Common/ColumnsHashing.h>

3
dbms/src/Processors/Transforms/TotalsHavingTransform.h
View File

@ -1,7 +1,6 @@
#include <Processors/ISimpleTransform.h>
#include <Common/Arena.h>
#include <Core/SettingsCommon.h>
namespace DB
{
@ -12,6 +11,8 @@ using ArenaPtr = std::shared_ptr<Arena>;
class ExpressionActions;
using ExpressionActionsPtr = std::shared_ptr<ExpressionActions>;
enum class TotalsMode;
/** Takes blocks after grouping, with non-finalized aggregate functions.
* Calculates total values according to totals_mode.
* If necessary, evaluates the expression from HAVING and filters rows. Returns the finalized and filtered blocks.

41
dbms/src/Storages/Distributed/DirectoryMonitor.cpp
View File

@ -10,6 +10,7 @@
#include <Interpreters/Context.h>
#include <Storages/Distributed/DirectoryMonitor.h>
#include <IO/ReadBufferFromFile.h>
#include <IO/ReadBufferFromString.h>
#include <IO/WriteBufferFromFile.h>
#include <Compression/CompressedReadBuffer.h>
#include <IO/ConnectionTimeouts.h>
@ -269,17 +270,41 @@ void StorageDistributedDirectoryMonitor::processFile(const std::string & file_pa
void StorageDistributedDirectoryMonitor::readQueryAndSettings(
ReadBuffer & in, Settings & insert_settings, std::string & insert_query) const
{
UInt64 magic_number_or_query_size;
UInt64 query_size;
readVarUInt(query_size, in);
readVarUInt(magic_number_or_query_size, in);
if (magic_number_or_query_size == UInt64(DBMS_DISTRIBUTED_SENDS_MAGIC_NUMBER))
if (query_size == DBMS_DISTRIBUTED_SIGNATURE_EXTRA_INFO)
{
insert_settings.deserialize(in);
readVarUInt(magic_number_or_query_size, in);
/// Read extra information.
String extra_info_as_string;
readStringBinary(extra_info_as_string, in);
readVarUInt(query_size, in);
ReadBufferFromString extra_info(extra_info_as_string);
UInt64 initiator_revision;
readVarUInt(initiator_revision, extra_info);
if (ClickHouseRevision::get() < initiator_revision)
{
LOG_WARNING(
log,
"ClickHouse shard version is older than ClickHouse initiator version. "
<< "It may lack support for new features.");
}
insert_settings.deserialize(extra_info);
/// Add handling new data here, for example:
/// if (initiator_revision >= DBMS_MIN_REVISION_WITH_MY_NEW_DATA)
/// readVarUInt(my_new_data, extra_info);
}
insert_query.resize(magic_number_or_query_size);
in.readStrict(insert_query.data(), magic_number_or_query_size);
else if (query_size == DBMS_DISTRIBUTED_SIGNATURE_SETTINGS_OLD_FORMAT)
{
insert_settings.deserialize(in, SettingsBinaryFormat::OLD);
readVarUInt(query_size, in);
}
insert_query.resize(query_size);
in.readStrict(insert_query.data(), query_size);
}
struct StorageDistributedDirectoryMonitor::BatchHeader

15
dbms/src/Storages/Distributed/DistributedBlockOutputStream.cpp
View File

@ -588,8 +588,19 @@ void DistributedBlockOutputStream::writeToShard(const Block & block, const std::
CompressedWriteBuffer compress{out};
NativeBlockOutputStream stream{compress, ClickHouseRevision::get(), block.cloneEmpty()};
writeVarUInt(UInt64(DBMS_DISTRIBUTED_SENDS_MAGIC_NUMBER), out);
context.getSettingsRef().serialize(out);
/// We wrap the extra information into a string for compatibility with older versions:
/// a shard will able to read this information partly and ignore other parts
/// based on its version.
WriteBufferFromOwnString extra_info;
writeVarUInt(ClickHouseRevision::get(), extra_info);
context.getSettingsRef().serialize(extra_info);
/// Add new fields here, for example:
/// writeVarUInt(my_new_data, extra_info);
writeVarUInt(DBMS_DISTRIBUTED_SIGNATURE_EXTRA_INFO, out);
writeStringBinary(extra_info.str(), out);
writeStringBinary(query_string, out);
stream.writePrefix();

22
dbms/src/Storages/Kafka/KafkaSettings.h
View File

@ -1,6 +1,6 @@
#pragma once
#include <Core/SettingsCommon.h>
#include <Core/SettingsCollection.h>
namespace DB
@ -16,16 +16,16 @@ struct KafkaSettings : public SettingsCollection<KafkaSettings>
#define LIST_OF_KAFKA_SETTINGS(M) \
M(SettingString, kafka_broker_list, "", "A comma-separated list of brokers for Kafka engine.") \
M(SettingString, kafka_topic_list, "", "A list of Kafka topics.") \
M(SettingString, kafka_group_name, "", "A group of Kafka consumers.") \
M(SettingString, kafka_format, "", "The message format for Kafka engine.") \
M(SettingChar, kafka_row_delimiter, '\0', "The character to be considered as a delimiter in Kafka message.") \
M(SettingString, kafka_schema, "", "Schema identifier (used by schema-based formats) for Kafka engine") \
M(SettingUInt64, kafka_num_consumers, 1, "The number of consumers per table for Kafka engine.") \
M(SettingUInt64, kafka_max_block_size, 0, "The maximum block size per table for Kafka engine.") \
M(SettingUInt64, kafka_skip_broken_messages, 0, "Skip at least this number of broken messages from Kafka topic per block") \
M(SettingUInt64, kafka_commit_every_batch, 0, "Commit every consumed and handled batch instead of a single commit after writing a whole block")
M(SettingString, kafka_broker_list, "", "A comma-separated list of brokers for Kafka engine.", 0) \
M(SettingString, kafka_topic_list, "", "A list of Kafka topics.", 0) \
M(SettingString, kafka_group_name, "", "A group of Kafka consumers.", 0) \
M(SettingString, kafka_format, "", "The message format for Kafka engine.", 0) \
M(SettingChar, kafka_row_delimiter, '\0', "The character to be considered as a delimiter in Kafka message.", 0) \
M(SettingString, kafka_schema, "", "Schema identifier (used by schema-based formats) for Kafka engine", 0) \
M(SettingUInt64, kafka_num_consumers, 1, "The number of consumers per table for Kafka engine.", 0) \
M(SettingUInt64, kafka_max_block_size, 0, "The maximum block size per table for Kafka engine.", 0) \
M(SettingUInt64, kafka_skip_broken_messages, 0, "Skip at least this number of broken messages from Kafka topic per block", 0) \
M(SettingUInt64, kafka_commit_every_batch, 0, "Commit every consumed and handled batch instead of a single commit after writing a whole block", 0)
DECLARE_SETTINGS_COLLECTION(LIST_OF_KAFKA_SETTINGS)

110
dbms/src/Storages/MergeTree/MergeTreeSettings.h
View File

@ -1,7 +1,7 @@
#pragma once
#include <Core/Defines.h>
#include <Core/SettingsCommon.h>
#include <Core/SettingsCollection.h>
#include <Common/SettingsChanges.h>
@ -26,70 +26,70 @@ struct MergeTreeSettings : public SettingsCollection<MergeTreeSettings>
{
#define LIST_OF_MERGE_TREE_SETTINGS(M) \
M(SettingUInt64, index_granularity, 8192, "How many rows correspond to one primary key value.") \
M(SettingUInt64, index_granularity, 8192, "How many rows correspond to one primary key value.", 0) \
\
/** Merge settings. */ \
M(SettingUInt64, merge_max_block_size, DEFAULT_MERGE_BLOCK_SIZE, "How many rows in blocks should be formed for merge operations.") \
M(SettingUInt64, max_bytes_to_merge_at_max_space_in_pool, 150ULL * 1024 * 1024 * 1024, "Maximum in total size of parts to merge, when there are maximum free threads in background pool (or entries in replication queue).") \
M(SettingUInt64, max_bytes_to_merge_at_min_space_in_pool, 1024 * 1024, "Maximum in total size of parts to merge, when there are minimum free threads in background pool (or entries in replication queue).") \
M(SettingUInt64, max_replicated_merges_in_queue, 16, "How many tasks of merging and mutating parts are allowed simultaneously in ReplicatedMergeTree queue.") \
M(SettingUInt64, max_replicated_mutations_in_queue, 8, "How many tasks of mutating parts are allowed simultaneously in ReplicatedMergeTree queue.") \
M(SettingUInt64, number_of_free_entries_in_pool_to_lower_max_size_of_merge, 8, "When there is less than specified number of free entries in pool (or replicated queue), start to lower maximum size of merge to process (or to put in queue). This is to allow small merges to process - not filling the pool with long running merges.") \
M(SettingUInt64, number_of_free_entries_in_pool_to_execute_mutation, 10, "When there is less than specified number of free entries in pool, do not execute part mutations. This is to leave free threads for regular merges and avoid \"Too many parts\"") \
M(SettingSeconds, old_parts_lifetime, 8 * 60, "How many seconds to keep obsolete parts.") \
M(SettingSeconds, temporary_directories_lifetime, 86400, "How many seconds to keep tmp_-directories.") \
M(SettingUInt64, merge_max_block_size, DEFAULT_MERGE_BLOCK_SIZE, "How many rows in blocks should be formed for merge operations.", 0) \
M(SettingUInt64, max_bytes_to_merge_at_max_space_in_pool, 150ULL * 1024 * 1024 * 1024, "Maximum in total size of parts to merge, when there are maximum free threads in background pool (or entries in replication queue).", 0) \
M(SettingUInt64, max_bytes_to_merge_at_min_space_in_pool, 1024 * 1024, "Maximum in total size of parts to merge, when there are minimum free threads in background pool (or entries in replication queue).", 0) \
M(SettingUInt64, max_replicated_merges_in_queue, 16, "How many tasks of merging and mutating parts are allowed simultaneously in ReplicatedMergeTree queue.", 0) \
M(SettingUInt64, max_replicated_mutations_in_queue, 8, "How many tasks of mutating parts are allowed simultaneously in ReplicatedMergeTree queue.", 0) \
M(SettingUInt64, number_of_free_entries_in_pool_to_lower_max_size_of_merge, 8, "When there is less than specified number of free entries in pool (or replicated queue), start to lower maximum size of merge to process (or to put in queue). This is to allow small merges to process - not filling the pool with long running merges.", 0) \
M(SettingUInt64, number_of_free_entries_in_pool_to_execute_mutation, 10, "When there is less than specified number of free entries in pool, do not execute part mutations. This is to leave free threads for regular merges and avoid \"Too many parts\"", 0) \
M(SettingSeconds, old_parts_lifetime, 8 * 60, "How many seconds to keep obsolete parts.", 0) \
M(SettingSeconds, temporary_directories_lifetime, 86400, "How many seconds to keep tmp_-directories.", 0) \
\
/** Inserts settings. */ \
M(SettingUInt64, parts_to_delay_insert, 150, "If table contains at least that many active parts in single partition, artificially slow down insert into table.") \
M(SettingUInt64, parts_to_throw_insert, 300, "If more than this number active parts in single partition, throw 'Too many parts ...' exception.") \
M(SettingUInt64, max_delay_to_insert, 1, "Max delay of inserting data into MergeTree table in seconds, if there are a lot of unmerged parts in single partition.") \
M(SettingUInt64, max_parts_in_total, 100000, "If more than this number active parts in all partitions in total, throw 'Too many parts ...' exception.") \
M(SettingUInt64, parts_to_delay_insert, 150, "If table contains at least that many active parts in single partition, artificially slow down insert into table.", 0) \
M(SettingUInt64, parts_to_throw_insert, 300, "If more than this number active parts in single partition, throw 'Too many parts ...' exception.", 0) \
M(SettingUInt64, max_delay_to_insert, 1, "Max delay of inserting data into MergeTree table in seconds, if there are a lot of unmerged parts in single partition.", 0) \
M(SettingUInt64, max_parts_in_total, 100000, "If more than this number active parts in all partitions in total, throw 'Too many parts ...' exception.", 0) \
\
/** Replication settings. */ \
M(SettingUInt64, replicated_deduplication_window, 100, "How many last blocks of hashes should be kept in ZooKeeper (old blocks will be deleted).") \
M(SettingUInt64, replicated_deduplication_window_seconds, 7 * 24 * 60 * 60 /* one week */, "Similar to \"replicated_deduplication_window\", but determines old blocks by their lifetime. Hash of an inserted block will be deleted (and the block will not be deduplicated after) if it outside of one \"window\". You can set very big replicated_deduplication_window to avoid duplicating INSERTs during that period of time.") \
M(SettingUInt64, max_replicated_logs_to_keep, 10000, "How many records may be in log, if there is inactive replica.") \
M(SettingUInt64, min_replicated_logs_to_keep, 100, "Keep about this number of last records in ZooKeeper log, even if they are obsolete. It doesn't affect work of tables: used only to diagnose ZooKeeper log before cleaning.") \
M(SettingSeconds, prefer_fetch_merged_part_time_threshold, 3600, "If time passed after replication log entry creation exceeds this threshold and sum size of parts is greater than \"prefer_fetch_merged_part_size_threshold\", prefer fetching merged part from replica instead of doing merge locally. To speed up very long merges.") \
M(SettingUInt64, prefer_fetch_merged_part_size_threshold, 10ULL * 1024 * 1024 * 1024, "If sum size of parts exceeds this threshold and time passed after replication log entry creation is greater than \"prefer_fetch_merged_part_time_threshold\", prefer fetching merged part from replica instead of doing merge locally. To speed up very long merges.") \
M(SettingUInt64, max_suspicious_broken_parts, 10, "Max broken parts, if more - deny automatic deletion.") \
M(SettingUInt64, max_files_to_modify_in_alter_columns, 75, "Not apply ALTER if number of files for modification(deletion, addition) more than this.") \
M(SettingUInt64, max_files_to_remove_in_alter_columns, 50, "Not apply ALTER, if number of files for deletion more than this.") \
M(SettingFloat, replicated_max_ratio_of_wrong_parts, 0.5, "If ratio of wrong parts to total number of parts is less than this - allow to start.") \
M(SettingUInt64, replicated_max_parallel_fetches, 0, "Limit parallel fetches.") \
M(SettingUInt64, replicated_max_parallel_fetches_for_table, 0, "Limit parallel fetches for one table.") \
M(SettingUInt64, replicated_max_parallel_fetches_for_host, DEFAULT_COUNT_OF_HTTP_CONNECTIONS_PER_ENDPOINT, "Limit parallel fetches from endpoint (actually pool size).") \
M(SettingUInt64, replicated_max_parallel_sends, 0, "Limit parallel sends.") \
M(SettingUInt64, replicated_max_parallel_sends_for_table, 0, "Limit parallel sends for one table.") \
M(SettingBool, replicated_can_become_leader, true, "If true, Replicated tables replicas on this node will try to acquire leadership.") \
M(SettingSeconds, zookeeper_session_expiration_check_period, 60, "ZooKeeper session expiration check period, in seconds.") \
M(SettingUInt64, replicated_deduplication_window, 100, "How many last blocks of hashes should be kept in ZooKeeper (old blocks will be deleted).", 0) \
M(SettingUInt64, replicated_deduplication_window_seconds, 7 * 24 * 60 * 60 /* one week */, "Similar to \"replicated_deduplication_window\", but determines old blocks by their lifetime. Hash of an inserted block will be deleted (and the block will not be deduplicated after) if it outside of one \"window\". You can set very big replicated_deduplication_window to avoid duplicating INSERTs during that period of time.", 0) \
M(SettingUInt64, max_replicated_logs_to_keep, 10000, "How many records may be in log, if there is inactive replica.", 0) \
M(SettingUInt64, min_replicated_logs_to_keep, 100, "Keep about this number of last records in ZooKeeper log, even if they are obsolete. It doesn't affect work of tables: used only to diagnose ZooKeeper log before cleaning.", 0) \
M(SettingSeconds, prefer_fetch_merged_part_time_threshold, 3600, "If time passed after replication log entry creation exceeds this threshold and sum size of parts is greater than \"prefer_fetch_merged_part_size_threshold\", prefer fetching merged part from replica instead of doing merge locally. To speed up very long merges.", 0) \
M(SettingUInt64, prefer_fetch_merged_part_size_threshold, 10ULL * 1024 * 1024 * 1024, "If sum size of parts exceeds this threshold and time passed after replication log entry creation is greater than \"prefer_fetch_merged_part_time_threshold\", prefer fetching merged part from replica instead of doing merge locally. To speed up very long merges.", 0) \
M(SettingUInt64, max_suspicious_broken_parts, 10, "Max broken parts, if more - deny automatic deletion.", 0) \
M(SettingUInt64, max_files_to_modify_in_alter_columns, 75, "Not apply ALTER if number of files for modification(deletion, addition) more than this.", 0) \
M(SettingUInt64, max_files_to_remove_in_alter_columns, 50, "Not apply ALTER, if number of files for deletion more than this.", 0) \
M(SettingFloat, replicated_max_ratio_of_wrong_parts, 0.5, "If ratio of wrong parts to total number of parts is less than this - allow to start.", 0) \
M(SettingUInt64, replicated_max_parallel_fetches, 0, "Limit parallel fetches.", 0) \
M(SettingUInt64, replicated_max_parallel_fetches_for_table, 0, "Limit parallel fetches for one table.", 0) \
M(SettingUInt64, replicated_max_parallel_fetches_for_host, DEFAULT_COUNT_OF_HTTP_CONNECTIONS_PER_ENDPOINT, "Limit parallel fetches from endpoint (actually pool size).", 0) \
M(SettingUInt64, replicated_max_parallel_sends, 0, "Limit parallel sends.", 0) \
M(SettingUInt64, replicated_max_parallel_sends_for_table, 0, "Limit parallel sends for one table.", 0) \
M(SettingBool, replicated_can_become_leader, true, "If true, Replicated tables replicas on this node will try to acquire leadership.", 0) \
M(SettingSeconds, zookeeper_session_expiration_check_period, 60, "ZooKeeper session expiration check period, in seconds.", 0) \
\
/** Check delay of replicas settings. */ \
M(SettingUInt64, check_delay_period, 60, "Period to check replication delay and compare with other replicas.") \
M(SettingUInt64, cleanup_delay_period, 30, "Period to clean old queue logs, blocks hashes and parts.") \
M(SettingUInt64, cleanup_delay_period_random_add, 10, "Add uniformly distributed value from 0 to x seconds to cleanup_delay_period to avoid thundering herd effect and subsequent DoS of ZooKeeper in case of very large number of tables.") \
M(SettingUInt64, min_relative_delay_to_yield_leadership, 120, "Minimal delay from other replicas to yield leadership. Here and further 0 means unlimited.") \
M(SettingUInt64, min_relative_delay_to_close, 300, "Minimal delay from other replicas to close, stop serving requests and not return Ok during status check.") \
M(SettingUInt64, min_absolute_delay_to_close, 0, "Minimal absolute delay to close, stop serving requests and not return Ok during status check.") \
M(SettingUInt64, enable_vertical_merge_algorithm, 1, "Enable usage of Vertical merge algorithm.") \
M(SettingUInt64, vertical_merge_algorithm_min_rows_to_activate, 16 * DEFAULT_MERGE_BLOCK_SIZE, "Minimal (approximate) sum of rows in merging parts to activate Vertical merge algorithm.") \
M(SettingUInt64, vertical_merge_algorithm_min_columns_to_activate, 11, "Minimal amount of non-PK columns to activate Vertical merge algorithm.") \
M(SettingUInt64, check_delay_period, 60, "Period to check replication delay and compare with other replicas.", 0) \
M(SettingUInt64, cleanup_delay_period, 30, "Period to clean old queue logs, blocks hashes and parts.", 0) \
M(SettingUInt64, cleanup_delay_period_random_add, 10, "Add uniformly distributed value from 0 to x seconds to cleanup_delay_period to avoid thundering herd effect and subsequent DoS of ZooKeeper in case of very large number of tables.", 0) \
M(SettingUInt64, min_relative_delay_to_yield_leadership, 120, "Minimal delay from other replicas to yield leadership. Here and further 0 means unlimited.", 0) \
M(SettingUInt64, min_relative_delay_to_close, 300, "Minimal delay from other replicas to close, stop serving requests and not return Ok during status check.", 0) \
M(SettingUInt64, min_absolute_delay_to_close, 0, "Minimal absolute delay to close, stop serving requests and not return Ok during status check.", 0) \
M(SettingUInt64, enable_vertical_merge_algorithm, 1, "Enable usage of Vertical merge algorithm.", 0) \
M(SettingUInt64, vertical_merge_algorithm_min_rows_to_activate, 16 * DEFAULT_MERGE_BLOCK_SIZE, "Minimal (approximate) sum of rows in merging parts to activate Vertical merge algorithm.", 0) \
M(SettingUInt64, vertical_merge_algorithm_min_columns_to_activate, 11, "Minimal amount of non-PK columns to activate Vertical merge algorithm.", 0) \
\
/** Compatibility settings */ \
M(SettingBool, compatibility_allow_sampling_expression_not_in_primary_key, false, "Allow to create a table with sampling expression not in primary key. This is needed only to temporarily allow to run the server with wrong tables for backward compatibility.") \
M(SettingBool, use_minimalistic_checksums_in_zookeeper, true, "Use small format (dozens bytes) for part checksums in ZooKeeper instead of ordinary ones (dozens KB). Before enabling check that all replicas support new format.") \
M(SettingBool, use_minimalistic_part_header_in_zookeeper, false, "Store part header (checksums and columns) in a compact format and a single part znode instead of separate znodes (<part>/columns and <part>/checksums). This can dramatically reduce snapshot size in ZooKeeper. Before enabling check that all replicas support new format.") \
M(SettingUInt64, finished_mutations_to_keep, 100, "How many records about mutations that are done to keep. If zero, then keep all of them.") \
M(SettingUInt64, min_merge_bytes_to_use_direct_io, 10ULL * 1024 * 1024 * 1024, "Minimal amount of bytes to enable O_DIRECT in merge (0 - disabled).") \
M(SettingUInt64, index_granularity_bytes, 10 * 1024 * 1024, "Approximate amount of bytes in single granule (0 - disabled).") \
M(SettingInt64, merge_with_ttl_timeout, 3600 * 24, "Minimal time in seconds, when merge with TTL can be repeated.") \
M(SettingBool, ttl_only_drop_parts, false, "Only drop altogether the expired parts and not partially prune them.") \
M(SettingBool, write_final_mark, 1, "Write final mark after end of column (0 - disabled, do nothing if index_granularity_bytes=0)") \
M(SettingBool, enable_mixed_granularity_parts, 0, "Enable parts with adaptive and non adaptive granularity") \
M(SettingMaxThreads, max_part_loading_threads, 0, "The number of theads to load data parts at startup.") \
M(SettingMaxThreads, max_part_removal_threads, 0, "The number of theads for concurrent removal of inactive data parts. One is usually enough, but in 'Google Compute Environment SSD Persistent Disks' file removal (unlink) operation is extraordinarily slow and you probably have to increase this number (recommended is up to 16).") \
M(SettingUInt64, concurrent_part_removal_threshold, 100, "Activate concurrent part removal (see 'max_part_removal_threads') only if the number of inactive data parts is at least this.") \
M(SettingString, storage_policy, "default", "Name of storage disk policy")
M(SettingBool, compatibility_allow_sampling_expression_not_in_primary_key, false, "Allow to create a table with sampling expression not in primary key. This is needed only to temporarily allow to run the server with wrong tables for backward compatibility.", 0) \
M(SettingBool, use_minimalistic_checksums_in_zookeeper, true, "Use small format (dozens bytes) for part checksums in ZooKeeper instead of ordinary ones (dozens KB). Before enabling check that all replicas support new format.", 0) \
M(SettingBool, use_minimalistic_part_header_in_zookeeper, false, "Store part header (checksums and columns) in a compact format and a single part znode instead of separate znodes (<part>/columns and <part>/checksums). This can dramatically reduce snapshot size in ZooKeeper. Before enabling check that all replicas support new format.", 0) \
M(SettingUInt64, finished_mutations_to_keep, 100, "How many records about mutations that are done to keep. If zero, then keep all of them.", 0) \
M(SettingUInt64, min_merge_bytes_to_use_direct_io, 10ULL * 1024 * 1024 * 1024, "Minimal amount of bytes to enable O_DIRECT in merge (0 - disabled).", 0) \
M(SettingUInt64, index_granularity_bytes, 10 * 1024 * 1024, "Approximate amount of bytes in single granule (0 - disabled).", 0) \
M(SettingInt64, merge_with_ttl_timeout, 3600 * 24, "Minimal time in seconds, when merge with TTL can be repeated.", 0) \
M(SettingBool, ttl_only_drop_parts, false, "Only drop altogether the expired parts and not partially prune them.", 0) \
M(SettingBool, write_final_mark, 1, "Write final mark after end of column (0 - disabled, do nothing if index_granularity_bytes=0)", 0) \
M(SettingBool, enable_mixed_granularity_parts, 0, "Enable parts with adaptive and non adaptive granularity", 0) \
M(SettingMaxThreads, max_part_loading_threads, 0, "The number of theads to load data parts at startup.", 0) \
M(SettingMaxThreads, max_part_removal_threads, 0, "The number of theads for concurrent removal of inactive data parts. One is usually enough, but in 'Google Compute Environment SSD Persistent Disks' file removal (unlink) operation is extraordinarily slow and you probably have to increase this number (recommended is up to 16).", 0) \
M(SettingUInt64, concurrent_part_removal_threshold, 100, "Activate concurrent part removal (see 'max_part_removal_threads') only if the number of inactive data parts is at least this.", 0) \
M(SettingString, storage_policy, "default", "Name of storage disk policy", 0)
DECLARE_SETTINGS_COLLECTION(LIST_OF_MERGE_TREE_SETTINGS)

1
dbms/src/Storages/StorageMerge.cpp
View File

@ -25,7 +25,6 @@
#include <Common/typeid_cast.h>
#include <Common/checkStackSize.h>
#include <Databases/IDatabase.h>
#include <Core/SettingsCommon.h>
#include <ext/range.h>
#include <algorithm>
#include <Parsers/ASTFunction.h>

0
dbms/tests/integration/test_old_versions_client/__init__.py → dbms/tests/integration/test_old_versions/__init__.py
View File

13
dbms/tests/integration/test_old_versions/configs/config.d/test_cluster.xml Normal file
View File

@ -0,0 +1,13 @@
<yandex>
<remote_servers>
<test_cluster>
<shard>
<weight>1</weight>
<replica>
<host>node_new</host>
<port>9000</port>
</replica>
</shard>
</test_cluster>
</remote_servers>
</yandex>

73
dbms/tests/integration/test_old_versions/test.py Normal file
View File

@ -0,0 +1,73 @@
import time
import os
import pytest
from helpers.cluster import ClickHouseCluster
from multiprocessing.dummy import Pool
from helpers.client import QueryRuntimeException, QueryTimeoutExceedException
from helpers.test_tools import assert_eq_with_retry
cluster = ClickHouseCluster(__file__)
node18_14 = cluster.add_instance('node18_14', image='yandex/clickhouse-server:18.14.19', with_installed_binary=True, config_dir="configs")
node19_1 = cluster.add_instance('node19_1', image='yandex/clickhouse-server:19.1.16', with_installed_binary=True, config_dir="configs")
node19_4 = cluster.add_instance('node19_4', image='yandex/clickhouse-server:19.4.5.35', with_installed_binary=True, config_dir="configs")
node19_8 = cluster.add_instance('node19_8', image='yandex/clickhouse-server:19.8.3.8', with_installed_binary=True, config_dir="configs")
node19_11 = cluster.add_instance('node19_11', image='yandex/clickhouse-server:19.11.13.74', with_installed_binary=True, config_dir="configs")
node19_13 = cluster.add_instance('node19_13', image='yandex/clickhouse-server:19.13.7.57', with_installed_binary=True, config_dir="configs")
node19_16 = cluster.add_instance('node19_16', image='yandex/clickhouse-server:19.16.2.2', with_installed_binary=True, config_dir="configs")
old_nodes = [node18_14, node19_1, node19_4, node19_8, node19_11, node19_13, node19_16]
new_node = cluster.add_instance('node_new')
def query_from_one_node_to_another(client_node, server_node, query):
client_node.exec_in_container(["bash", "-c", "/usr/bin/clickhouse client --host {} --query {!r}".format(server_node.name, query)])
@pytest.fixture(scope="module")
def setup_nodes():
try:
cluster.start()
for n in old_nodes + [new_node]:
n.query('''CREATE TABLE test_table (id UInt32, value UInt64) ENGINE = MergeTree() ORDER BY tuple()''')
for n in old_nodes:
n.query('''CREATE TABLE dist_table AS test_table ENGINE = Distributed('test_cluster', 'default', 'test_table')''')
yield cluster
finally:
cluster.shutdown()
def test_client_is_older_than_server(setup_nodes):
server = new_node
for i, client in enumerate(old_nodes):
query_from_one_node_to_another(client, server, "INSERT INTO test_table VALUES (1, {})".format(i))
for client in old_nodes:
query_from_one_node_to_another(client, server, "SELECT COUNT() FROM test_table")
assert server.query("SELECT COUNT() FROM test_table WHERE id=1") == str(len(old_nodes)) + "\n"
def test_server_is_older_than_client(setup_nodes):
client = new_node
for i, server in enumerate(old_nodes):
query_from_one_node_to_another(client, server, "INSERT INTO test_table VALUES (2, {})".format(i))
for server in old_nodes:
query_from_one_node_to_another(client, server, "SELECT COUNT() FROM test_table")
for server in old_nodes:
assert server.query("SELECT COUNT() FROM test_table WHERE id=2") == "1\n"
def test_distributed_query_initiator_is_older_than_shard(setup_nodes):
distributed_query_initiator_old_nodes = [node18_14, node19_13, node19_16]
shard = new_node
for i, initiator in enumerate(distributed_query_initiator_old_nodes):
initiator.query("INSERT INTO dist_table VALUES (3, {})".format(i))
assert_eq_with_retry(shard, "SELECT COUNT() FROM test_table WHERE id=3", str(len(distributed_query_initiator_old_nodes)))
assert_eq_with_retry(initiator, "SELECT COUNT() FROM dist_table WHERE id=3", str(len(distributed_query_initiator_old_nodes)))

51
dbms/tests/integration/test_old_versions_client/test.py
View File

@ -1,51 +0,0 @@
import time
import pytest
from helpers.cluster import ClickHouseCluster
from multiprocessing.dummy import Pool
from helpers.client import QueryRuntimeException, QueryTimeoutExceedException
from helpers.test_tools import assert_eq_with_retry
cluster = ClickHouseCluster(__file__)
node18_14 = cluster.add_instance('node18_14', image='yandex/clickhouse-server:18.14.19', with_installed_binary=True)
node19_1 = cluster.add_instance('node19_1', image='yandex/clickhouse-server:19.1.16', with_installed_binary=True)
node19_4 = cluster.add_instance('node19_4', image='yandex/clickhouse-server:19.4.5.35', with_installed_binary=True)
node19_6 = cluster.add_instance('node19_6', image='yandex/clickhouse-server:19.6.3.18', with_installed_binary=True)
node19_8 = cluster.add_instance('node19_8', image='yandex/clickhouse-server:19.8.3.8', with_installed_binary=True)
node_new = cluster.add_instance('node_new')
@pytest.fixture(scope="module")
def setup_nodes():
try:
cluster.start()
for n in (node18_14, node19_1, node19_4, node19_6, node19_8, node_new):
n.query('''CREATE TABLE test_table (id UInt32, value UInt64) ENGINE = MergeTree() ORDER BY tuple()''')
yield cluster
finally:
cluster.shutdown()
def query_from_one_node_to_another(client_node, server_node, query):
client_node.exec_in_container(["bash", "-c", "/usr/bin/clickhouse client --host {} --query '{}'".format(server_node.name, query)])
def test_client_from_different_versions(setup_nodes):
old_nodes = (node18_14, node19_1, node19_4, node19_6, node19_8)
# from new to old
for n in old_nodes:
query_from_one_node_to_another(node_new, n, "INSERT INTO test_table VALUES (1, 1)")
for n in old_nodes:
query_from_one_node_to_another(node_new, n, "SELECT COUNT() FROM test_table")
for n in old_nodes:
assert n.query("SELECT COUNT() FROM test_table") == "1\n"
# from old to new
for i, n in enumerate(old_nodes):
query_from_one_node_to_another(n, node_new, "INSERT INTO test_table VALUES ({i}, {i})".format(i=i))
for n in old_nodes:
query_from_one_node_to_another(n, node_new, "SELECT COUNT() FROM test_table")
assert node_new.query("SELECT COUNT() FROM test_table") == str(len(old_nodes)) + "\n"

1
libs/libcommon/include/common/logger_useful.h
View File

@ -6,7 +6,6 @@
#include <Poco/Logger.h>
#include <Poco/Message.h>
#include <Poco/Version.h>
#include <Core/SettingsCommon.h>
#include <Common/CurrentThread.h>
#ifndef QUERY_PREVIEW_LENGTH