Skip to content

Do not make 'describe table' query when schema is known #1845

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ianton-ru wants to merge 1 commit into
base: antalya-26.3
Choose a base branch
from
Open

Do not make 'describe table' query when schema is known #1845

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions src/Storages/IStorageCluster.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
#include <Storages/SelectQueryInfo.h>
#include <Storages/StorageDistributed.h>
#include <TableFunctions/TableFunctionFactory.h>
#include <TableFunctions/TableFunctionRemote.h>
#include <Poco/URI.h>
#include <Storages/extractTableFunctionFromSelectQuery.h>
#include <Planner/Utils.h>
Expand Down Expand Up @@ -500,6 +501,10 @@ IStorageCluster::RemoteCallVariables IStorageCluster::convertToRemote(

auto remote_function = TableFunctionFactory::instance().get(remote_query, new_context);

std::shared_ptr<TableFunctionRemote> remote_table_function = std::dynamic_pointer_cast<TableFunctionRemote>(remote_function);
Copy link
Copy Markdown
Collaborator

@arthurpassos arthurpassos May 29, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: I would add a comment stating why we can set the structure for remote table functions. And possible scope the remote_table_function to an if statement, something like:

if (auto remote_table_function = cast(remote_function))
{
    ...
}

But this is a minor, no need to do it

if (remote_table_function)
remote_table_function->setActualTableStructure(getInMemoryMetadata().columns);

auto storage = remote_function->execute(query_to_send, new_context, remote_function_name);

return RemoteCallVariables{storage, new_context};
Expand Down
1 change: 1 addition & 0 deletions src/TableFunctions/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ extract_into_parent_list(clickhouse_table_functions_sources dbms_sources
ITableFunction.cpp
TableFunctionView.cpp
TableFunctionFactory.cpp
TableFunctionRemote.cpp
)
extract_into_parent_list(clickhouse_table_functions_headers dbms_headers
ITableFunction.h
Expand Down
3 changes: 3 additions & 0 deletions src/TableFunctions/TableFunctionRemote.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -356,6 +356,9 @@ StoragePtr TableFunctionRemote::executeImpl(const ASTPtr & /*ast_function*/, Con

ColumnsDescription TableFunctionRemote::getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const
{
if (!remote_table_columns.empty())
return remote_table_columns;

assert(cluster);
return getStructureOfRemoteTable(*cluster, remote_table_id, context, remote_table_function_ptr);
}
Expand Down
3 changes: 3 additions & 0 deletions src/TableFunctions/TableFunctionRemote.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,8 @@ class TableFunctionRemote : public ITableFunction

void setRemoteTableFunction(ASTPtr remote_table_function_ptr_) { remote_table_function_ptr = remote_table_function_ptr_; }

void setActualTableStructure(ColumnsDescription remote_table_columns_) { remote_table_columns = remote_table_columns_; }

private:

StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns, bool is_insert_query) const override;
Expand All @@ -44,6 +46,7 @@ class TableFunctionRemote : public ITableFunction
StorageID remote_table_id = StorageID::createEmpty();
ASTPtr remote_table_function_ptr;
ASTPtr sharding_key = nullptr;
ColumnsDescription remote_table_columns;
};

}
24 changes: 12 additions & 12 deletions tests/integration/test_s3_cluster/test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -832,8 +832,8 @@ def test_object_storage_remote_initiator(started_cluster):
"""
).splitlines()

# initial node + describe table + remote initiator + 2 subqueries on replicas
assert queries == ["5"]
# initial node + remote initiator + 2 subqueries on replicas
assert queries == ["4"]

# Cluster with dots in the host names
query_id = uuid.uuid4().hex
Expand All @@ -860,8 +860,8 @@ def test_object_storage_remote_initiator(started_cluster):
"""
).splitlines()

# initial node + describe table + remote initiator + 2 subqueries on replicas
assert queries == ["5"]
# initial node + remote initiator + 2 subqueries on replicas
assert queries == ["4"]

users = node.query(
f"""
Expand Down Expand Up @@ -902,8 +902,8 @@ def test_object_storage_remote_initiator(started_cluster):
"""
).splitlines()

# initial node + describe table + remote initiator + 2 subqueries on replicas
assert queries == ["5"]
# initial node + remote initiator + 2 subqueries on replicas
assert queries == ["4"]

users = node.query(
f"""
Expand Down Expand Up @@ -963,8 +963,8 @@ def test_object_storage_remote_initiator(started_cluster):
"""
).splitlines()

# initial node + describe table + remote initiator + 2 subqueries on replicas
assert queries == ["5"]
# initial node + remote initiator + 2 subqueries on replicas
assert queries == ["4"]

users = node.query(
f"""
Expand Down Expand Up @@ -1427,8 +1427,8 @@ def test_object_storage_remote_initiator_without_cluster_function(started_cluste
"""
).splitlines()

# initial node + describe table + remote initiator
assert queries == ["3"]
# initial node + remote initiator
assert queries == ["2"]

users = node.query(
f"""
Expand Down Expand Up @@ -1472,8 +1472,8 @@ def test_object_storage_remote_initiator_without_cluster_function(started_cluste
"""
).splitlines()

# initial node + describe table + remote initiator + 2 subqueries on replicas
assert queries == ["5"]
# initial node + remote initiator + 2 subqueries on replicas
assert queries == ["4"]

users = node.query(
f"""
Expand Down
4 changes: 3 additions & 1 deletion tests/integration/test_storage_iceberg_with_spark/test_remote_initiator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,7 @@ def flush_logs():
FROM clusterAllReplicas('cluster_simple', system.query_log)
WHERE type='QueryFinish' AND initial_query_id='{query_id}'
""")
# initial node + 3 subqueries on replicas
assert queries == "4\n"

query_id = uuid.uuid4().hex
Expand All @@ -83,7 +84,8 @@ def flush_logs():
FROM clusterAllReplicas('cluster_simple', system.query_log)
WHERE type='QueryFinish' AND initial_query_id='{query_id}'
""")
assert queries == "6\n"
# initial node + remote initiator + 3 subqueries on replicas
assert queries == "5\n"

query_id = uuid.uuid4().hex
res = instance.query(f"""
Expand Down
Loading