thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 08:40:50 +00:00
Code Issues Packages Projects Releases Wiki Activity
f3a700b976
ClickHouse/programs/copier/TaskCluster.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

75 lines
2.4 KiB
C++
Raw Normal View History

Up-inline ShardPartition, ShardPartitionPiece and TaskCluster
2022-10-20 11:09:32 +00:00
#include "TaskCluster.h"
namespace DB
{
namespace ErrorCodes
{
extern const int BAD_ARGUMENTS;
}
TaskCluster::TaskCluster(const String & task_zookeeper_path_, const String & default_local_database_)
: task_zookeeper_path(task_zookeeper_path_)
, default_local_database(default_local_database_)
{}
void DB::TaskCluster::loadTasks(const Poco::Util::AbstractConfiguration & config, const String & base_key)
{
String prefix = base_key.empty() ? "" : base_key + ".";
clusters_prefix = prefix + "remote_servers";
if (!config.has(clusters_prefix))
Better formatting for exception messages (#45449) * save format string for NetException * format exceptions * format exceptions 2 * format exceptions 3 * format exceptions 4 * format exceptions 5 * format exceptions 6 * fix * format exceptions 7 * format exceptions 8 * Update MergeTreeIndexGin.cpp * Update AggregateFunctionMap.cpp * Update AggregateFunctionMap.cpp * fix
2023-01-23 21:13:58 +00:00
throw Exception(ErrorCodes::BAD_ARGUMENTS, "You should specify list of clusters in {}", clusters_prefix);
Up-inline ShardPartition, ShardPartitionPiece and TaskCluster
2022-10-20 11:09:32 +00:00
Poco::Util::AbstractConfiguration::Keys tables_keys;
config.keys(prefix + "tables", tables_keys);
for (const auto & table_key : tables_keys)
{
table_tasks.emplace_back(*this, config, prefix + "tables", table_key);
}
}
void DB::TaskCluster::reloadSettings(const Poco::Util::AbstractConfiguration & config, const String & base_key)
{
String prefix = base_key.empty() ? "" : base_key + ".";
max_workers = config.getUInt64(prefix + "max_workers");
settings_common = Settings();
if (config.has(prefix + "settings"))
settings_common.loadSettingsFromConfig(prefix + "settings", config);
Fix clang-tidy
2022-10-26 07:48:37 +00:00
settings_common.prefer_localhost_replica = false;
Up-inline ShardPartition, ShardPartitionPiece and TaskCluster
2022-10-20 11:09:32 +00:00
settings_pull = settings_common;
if (config.has(prefix + "settings_pull"))
settings_pull.loadSettingsFromConfig(prefix + "settings_pull", config);
settings_push = settings_common;
if (config.has(prefix + "settings_push"))
settings_push.loadSettingsFromConfig(prefix + "settings_push", config);
auto set_default_value = [] (auto && setting, auto && default_value)
{
setting = setting.changed ? setting.value : default_value;
};
/// Override important settings
settings_pull.readonly = 1;
settings_pull.prefer_localhost_replica = false;
Rename directory monitor concept into background INSERT (#55978) * Limit log frequence for "Skipping send data over distributed table" message After SYSTEM STOP DISTRIBUTED SENDS it will constantly print this message. Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Rename directory monitor concept into async INSERT Rename the following query settings (with preserving backward compatiblity, by keeping old name as an alias): - distributed_directory_monitor_sleep_time_ms -> distributed_async_insert_sleep_time_ms - distributed_directory_monitor_max_sleep_time_ms -> distributed_async_insert_max_sleep_time_ms - distributed_directory_monitor_batch -> distributed_async_insert_batch_inserts - distributed_directory_monitor_split_batch_on_failure -> distributed_async_insert_split_batch_on_failure Rename the following table settings (with preserving backward compatiblity, by keeping old name as an alias): - monitor_batch_inserts -> async_insert_batch - monitor_split_batch_on_failure -> async_insert_split_batch_on_failure - directory_monitor_sleep_time_ms -> async_insert_sleep_time_ms - directory_monitor_max_sleep_time_ms -> async_insert_max_sleep_time_ms And also update all the references: $ gg -e directory_monitor_ -e monitor_ tests docs | cut -d: -f1 | sort -u | xargs sed -e 's/distributed_directory_monitor_sleep_time_ms/distributed_async_insert_sleep_time_ms/g' -e 's/distributed_directory_monitor_max_sleep_time_ms/distributed_async_insert_max_sleep_time_ms/g' -e 's/distributed_directory_monitor_batch_inserts/distributed_async_insert_batch/g' -e 's/distributed_directory_monitor_split_batch_on_failure/distributed_async_insert_split_batch_on_failure/g' -e 's/monitor_batch_inserts/async_insert_batch/g' -e 's/monitor_split_batch_on_failure/async_insert_split_batch_on_failure/g' -e 's/monitor_sleep_time_ms/async_insert_sleep_time_ms/g' -e 's/monitor_max_sleep_time_ms/async_insert_max_sleep_time_ms/g' -i Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Rename async_insert for Distributed into background_insert This will avoid amigibuity between general async INSERT's and INSERT into Distributed, which are indeed background, so new term express it even better. Mostly done with: $ git di HEAD^ --name-only | xargs sed -i -e 's/distributed_async_insert/distributed_background_insert/g' -e 's/async_insert_batch/background_insert_batch/g' -e 's/async_insert_split_batch_on_failure/background_insert_split_batch_on_failure/g' -e 's/async_insert_sleep_time_ms/background_insert_sleep_time_ms/g' -e 's/async_insert_max_sleep_time_ms/background_insert_max_sleep_time_ms/g' Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Mark 02417_opentelemetry_insert_on_distributed_table as long CI: https://s3.amazonaws.com/clickhouse-test-reports/55978/7a6abb03a0b507e29e999cb7e04f246a119c6f28/stateless_tests_flaky_check__asan_.html Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> --------- Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2023-11-01 14:09:39 +00:00
settings_push.distributed_foreground_insert = true;
Up-inline ShardPartition, ShardPartitionPiece and TaskCluster
2022-10-20 11:09:32 +00:00
settings_push.prefer_localhost_replica = false;
set_default_value(settings_pull.load_balancing, LoadBalancing::NEAREST_HOSTNAME);
set_default_value(settings_pull.max_threads, 1);
set_default_value(settings_pull.max_block_size, 8192UL);
set_default_value(settings_pull.preferred_block_size_bytes, 0);
Rename directory monitor concept into background INSERT (#55978) * Limit log frequence for "Skipping send data over distributed table" message After SYSTEM STOP DISTRIBUTED SENDS it will constantly print this message. Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Rename directory monitor concept into async INSERT Rename the following query settings (with preserving backward compatiblity, by keeping old name as an alias): - distributed_directory_monitor_sleep_time_ms -> distributed_async_insert_sleep_time_ms - distributed_directory_monitor_max_sleep_time_ms -> distributed_async_insert_max_sleep_time_ms - distributed_directory_monitor_batch -> distributed_async_insert_batch_inserts - distributed_directory_monitor_split_batch_on_failure -> distributed_async_insert_split_batch_on_failure Rename the following table settings (with preserving backward compatiblity, by keeping old name as an alias): - monitor_batch_inserts -> async_insert_batch - monitor_split_batch_on_failure -> async_insert_split_batch_on_failure - directory_monitor_sleep_time_ms -> async_insert_sleep_time_ms - directory_monitor_max_sleep_time_ms -> async_insert_max_sleep_time_ms And also update all the references: $ gg -e directory_monitor_ -e monitor_ tests docs | cut -d: -f1 | sort -u | xargs sed -e 's/distributed_directory_monitor_sleep_time_ms/distributed_async_insert_sleep_time_ms/g' -e 's/distributed_directory_monitor_max_sleep_time_ms/distributed_async_insert_max_sleep_time_ms/g' -e 's/distributed_directory_monitor_batch_inserts/distributed_async_insert_batch/g' -e 's/distributed_directory_monitor_split_batch_on_failure/distributed_async_insert_split_batch_on_failure/g' -e 's/monitor_batch_inserts/async_insert_batch/g' -e 's/monitor_split_batch_on_failure/async_insert_split_batch_on_failure/g' -e 's/monitor_sleep_time_ms/async_insert_sleep_time_ms/g' -e 's/monitor_max_sleep_time_ms/async_insert_max_sleep_time_ms/g' -i Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Rename async_insert for Distributed into background_insert This will avoid amigibuity between general async INSERT's and INSERT into Distributed, which are indeed background, so new term express it even better. Mostly done with: $ git di HEAD^ --name-only | xargs sed -i -e 's/distributed_async_insert/distributed_background_insert/g' -e 's/async_insert_batch/background_insert_batch/g' -e 's/async_insert_split_batch_on_failure/background_insert_split_batch_on_failure/g' -e 's/async_insert_sleep_time_ms/background_insert_sleep_time_ms/g' -e 's/async_insert_max_sleep_time_ms/background_insert_max_sleep_time_ms/g' Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Mark 02417_opentelemetry_insert_on_distributed_table as long CI: https://s3.amazonaws.com/clickhouse-test-reports/55978/7a6abb03a0b507e29e999cb7e04f246a119c6f28/stateless_tests_flaky_check__asan_.html Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> --------- Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2023-11-01 14:09:39 +00:00
set_default_value(settings_push.distributed_background_insert_timeout, 0);
Add support for settings alias
2023-01-26 14:06:46 +00:00
set_default_value(settings_push.alter_sync, 2);
Up-inline ShardPartition, ShardPartitionPiece and TaskCluster
2022-10-20 11:09:32 +00:00
}
}
Reference in New Issue Copy Permalink