mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-12-16 11:22:12 +00:00
c25d6cd624
* 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>
90 lines
3.0 KiB
SQL
90 lines
3.0 KiB
SQL
-- Tags: shard
|
|
|
|
-- make the order static
|
|
SET max_threads = 1;
|
|
|
|
-- data should be inserted into Distributed table synchronously
|
|
SET distributed_foreground_insert = 1;
|
|
|
|
DROP TABLE IF EXISTS mem1;
|
|
DROP TABLE IF EXISTS mem2;
|
|
DROP TABLE IF EXISTS mem3;
|
|
DROP TABLE IF EXISTS dist_1;
|
|
DROP TABLE IF EXISTS dist_2;
|
|
DROP TABLE IF EXISTS dist_3;
|
|
|
|
CREATE TABLE mem1 (key Int) Engine=Memory();
|
|
INSERT INTO mem1 VALUES (10);
|
|
CREATE TABLE dist_1 AS mem1 Engine=Distributed(test_shard_localhost, currentDatabase(), mem1);
|
|
INSERT INTO dist_1 VALUES (20);
|
|
|
|
CREATE TABLE mem2 (key Int) Engine=Memory();
|
|
INSERT INTO mem2 VALUES (100);
|
|
CREATE TABLE dist_2 AS mem2 Engine=Distributed(test_cluster_two_shards_localhost, currentDatabase(), mem2);
|
|
|
|
CREATE TABLE mem3 (key Int, _shard_num String) Engine=Memory();
|
|
INSERT INTO mem3 VALUES (100, 'foo');
|
|
CREATE TABLE dist_3 AS mem3 Engine=Distributed(test_shard_localhost, currentDatabase(), mem3);
|
|
|
|
-- { echoOn }
|
|
|
|
-- remote(system.one)
|
|
SELECT 'remote(system.one)';
|
|
SELECT * FROM remote('127.0.0.1', system.one);
|
|
SELECT * FROM remote('127.0.0.{1,2}', system.one);
|
|
SELECT _shard_num, * FROM remote('127.0.0.1', system.one);
|
|
SELECT _shard_num, * FROM remote('127.0.0.{1,2}', system.one) order by _shard_num;
|
|
SELECT _shard_num, * FROM remote('127.0.0.{1,2}', system.one) WHERE _shard_num = 1;
|
|
|
|
-- dist_1 using test_shard_localhost
|
|
SELECT 'dist_1';
|
|
SELECT _shard_num FROM dist_1 order by _shard_num;
|
|
|
|
SELECT _shard_num FROM dist_1 order by _shard_num;
|
|
SELECT _shard_num, key FROM dist_1 order by _shard_num;
|
|
SELECT key FROM dist_1;
|
|
|
|
SELECT _shard_num FROM dist_1 order by _shard_num;
|
|
SELECT _shard_num, key FROM dist_1 order by _shard_num, key;
|
|
SELECT key FROM dist_1;
|
|
|
|
-- dist_2 using test_cluster_two_shards_localhost
|
|
SELECT 'dist_2';
|
|
SELECT _shard_num FROM dist_2 order by _shard_num;
|
|
|
|
SELECT _shard_num FROM dist_2 order by _shard_num;
|
|
SELECT _shard_num, key FROM dist_2 order by _shard_num, key;
|
|
SELECT key FROM dist_2;
|
|
|
|
-- multiple _shard_num
|
|
SELECT 'remote(Distributed)';
|
|
SELECT _shard_num, key FROM remote('127.0.0.1', currentDatabase(), dist_2) order by _shard_num, key;
|
|
|
|
-- JOIN system.clusters
|
|
SELECT 'JOIN system.clusters';
|
|
|
|
SELECT a._shard_num, a.key, b.host_name, b.host_address IN ('::1', '127.0.0.1'), b.port
|
|
FROM (SELECT *, _shard_num FROM dist_1) a
|
|
JOIN system.clusters b
|
|
ON a._shard_num = b.shard_num
|
|
WHERE b.cluster = 'test_cluster_two_shards_localhost';
|
|
|
|
SELECT _shard_num, key, b.host_name, b.host_address IN ('::1', '127.0.0.1'), b.port
|
|
FROM dist_1 a
|
|
JOIN system.clusters b
|
|
ON _shard_num = b.shard_num
|
|
WHERE b.cluster = 'test_cluster_two_shards_localhost'; -- { serverError 403 }
|
|
|
|
SELECT 'Rewrite with alias';
|
|
SELECT a._shard_num, key FROM dist_1 a;
|
|
-- the same with JOIN, just in case
|
|
SELECT a._shard_num, a.key, b.host_name, b.host_address IN ('::1', '127.0.0.1'), b.port
|
|
FROM dist_1 a
|
|
JOIN system.clusters b
|
|
ON a._shard_num = b.shard_num
|
|
WHERE b.cluster = 'test_cluster_two_shards_localhost'; -- { serverError 47, 403 }
|
|
|
|
SELECT 'dist_3';
|
|
SELECT * FROM dist_3;
|
|
SELECT _shard_num, * FROM dist_3 order by _shard_num;
|