Merge pull request ClickHouse#80103 from ClickHouse/parallel-replicas-replace-log-memory

Stateless tests: replace Log* and Memory engines to MergeTree in parallel replicas job

Author: fm4v

tests/clickhouse-test

@@ -204,9 +204,13 @@ class SharedEngineReplacer:
 
     def _need_to_replace_something(self):
         return (
-            (self.replace_replicated or self.replace_non_replicated)
-            and "shared_merge_tree" not in self.file_name
-        ) or self.cloud
+            (
+                (self.replace_replicated or self.replace_non_replicated)
+                and "shared_merge_tree" not in self.file_name
+            )
+            or self.cloud
+            or self.args.replace_log_memory_with_mergetree
+        )
 
     def _has_show_create_table(self):
         with open(self.file_name, "r", encoding="utf-8") as f:
@@ -230,9 +234,12 @@ class SharedEngineReplacer:
         data_engines = r"(Engine\s*=?\s*)(Log|TinyLog|StripeLog|Memory)\(?\)?"
         # Replace them with SMT
         replace_with = f"{replace_engine}() ORDER BY tuple()"
+        if self.reference_file and not self.with_echo:
+            replace_with = f"{replace_engine}\\nORDER BY tuple()\\nSETTINGS index_granularity = 8192"
+
         if (
             re.search(data_engines, line, flags=re.IGNORECASE)
-            and "CREATE DATABASE" not in line
+            and "CREATE DATABASE" not in line.upper()
         ):
             modified_statement = re.sub(
                 data_engines,
@@ -284,6 +291,7 @@ class SharedEngineReplacer:
         self.replace_non_replicated = replace_non_replicated
         self.reference_file = reference_file
         self.cloud = cloud
+        self.with_echo = False
         use_random_path = not reference_file and not self._has_show_create_table()
 
         if not self._need_to_replace_something():
@@ -298,10 +306,18 @@ class SharedEngineReplacer:
         ):
             for line in source:
                 # Replace table engines if echo enabled to match changed reference
-                if self.cloud and line.startswith("-- { echo"):
+                if (
+                    self.cloud or self.args.replace_log_memory_with_mergetree
+                ) and re.match("-- ?\{ ?echo.*", line):
+                    self.with_echo = True
+
+                if self.cloud and self.with_echo:
                     self.replace_replicated = True
                     self.replace_non_replicated = True
 
+                if self.args.replace_log_memory_with_mergetree:
+                    line = self._replace_data_engines(line, replace_engine="MergeTree")
+
                 if (
                     self._is_select_line(line)
                     or (reference_file and not self._is_create_query(line))
@@ -1457,6 +1473,12 @@ class TestCase:
         if "no-async-insert" in tags and args.no_async_insert:
             return FailureReason.NO_ASYNC_INSERT
 
+        # Do not run *Log and Memory engine-specific tests
+        if (
+            "memory-engine" in tags or "log-engine" in tags
+        ) and args.replace_log_memory_with_mergetree:
+            return FailureReason.NOT_SUPPORTED
+
         if args.skip and any(s in self.name for s in args.skip):
             return FailureReason.SKIP
 
@@ -3835,6 +3857,12 @@ def parse_args():
         default=os.environ.get("REPLACE_MT_WITH_SMT", False),
         help="Replace ordinary MergeTree engine with SharedMergeTree",
     )
+    parser.add_argument(
+        "--replace-log-memory-with-mergetree",
+        action="store_true",
+        default=os.environ.get("REPLACE_LOG_MEM_WITH_MT", False),
+        help="Replace *Log and Memory engines with MergeTree",
+    )
 
     parser.add_argument(
         "--client-log",

tests/docker_scripts/stateless_runner.sh

@@ -335,6 +335,7 @@ function run_tests()
         ADDITIONAL_OPTIONS+=('--no-parallel-replicas')
         ADDITIONAL_OPTIONS+=('--no-zookeeper')
         ADDITIONAL_OPTIONS+=('--no-shard')
+        ADDITIONAL_OPTIONS+=('--replace-log-memory-with-mergetree')
     else
         ADDITIONAL_OPTIONS+=('--zookeeper')
         ADDITIONAL_OPTIONS+=('--shard')

tests/parallel_replicas_blacklist.txt

@@ -10,6 +10,9 @@
 03045_unknown_identifier_alias_substitution
 02561_temporary_table_sessions
 02525_different_engines_in_temporary_tables
+00645_date_time_input_format
+02154_default_keyword_insert
+02807_default_date_time_nullable
 
     https://github.com/ClickHouse/ClickHouse/issues/74324
     MULTIPLE_EXPRESSIONS_FOR_ALIAS
@@ -36,6 +39,13 @@
     https://github.com/ClickHouse/ClickHouse/issues/74343
     Cannot find column `tuple(col_a, type)` in source stream, there are only columns: [__table1.id, tuple(replaceAll(__table1.data, 'a'_String, 'e'_String), __table1.type), tuple(replaceAll(__table1.data, 'a'_String, 'e'_String), __table1.type)]. (THERE_IS_NO_COLUMN) (in query: SELECT id, tuple(replaceAll(data, 'a', 'e') AS col_a, type) AS a, tuple(replaceAll(data, 'a', 'e') AS col_b, type) AS b FROM src;)
 03240_insert_select_named_tuple
+00500_point_in_polygon_non_const_poly
+01017_tuplehamming_distance
+01300_svg
+01849_geoToS2
+02504_regexp_dictionary_table_source
+02833_tuple_concat
+02378_analyzer_projection_names
 
     https://github.com/ClickHouse/ClickHouse/issues/74367
     Cannot find column in source stream
@@ -74,6 +84,7 @@
 01594_storage_join_uuid
     Unsupported JOIN keys of type keys256 in StorageJoin: While executing Join. (UNSUPPORTED_JOIN_KEYS) (query: SELECT * FROM t1 ALL INNER JOIN tj USING (key1, key2, key3) ORDER BY key1;)
 02498_storage_join_key_positions.gen
+03447_storage_join_unsupported_keys
 
     https://github.com/ClickHouse/ClickHouse/pull/73609
     Cannot parse string
@@ -130,6 +141,10 @@
 02950_dictionary_ssd_cache_short_circuit
 02504_regexp_dictionary_ua_parser
 03062_analyzer_join_engine_missing_column
+01852_dictionary_query_count_long
+01904_dictionary_default_nullable_type
+02391_hashed_dictionary_shards
+02740_hashed_dictionary_load_factor_smoke
 
     https://github.com/ClickHouse/clickhouse-private/issues/11670
     Actual WithMergeableState
@@ -157,7 +172,8 @@
 01780_column_sparse_full
 01783_merge_engine_join_key_condition
 02789_filesystem_cache_alignment
-
+00475_in_join_db_table
+03325_sqlite_join_wrong_answer
 
     https://github.com/ClickHouse/clickhouse-private/issues/17173
 02023_transform_or_to_in
@@ -183,6 +199,30 @@
     https://github.com/ClickHouse/ClickHouse/issues/74411
 02884_create_view_with_sql_security_option
 
+    https://github.com/ClickHouse/ClickHouse/issues/80426
+    Duplicates with all right join and join engine
+01051_all_join_engine
+02497_storage_join_right_assert
+02495_analyzer_storage_join
+
+    https://github.com/ClickHouse/clickhouse-private/issues/27882
+    duplicates cross_to_inner_join_rewrite=1
+02564_analyzer_cross_to_inner
+
+    https://github.com/ClickHouse/ClickHouse/issues/80439
+    Predicate pushdown CTE incorrect result
+02901_predicate_pushdown_cte_stateful
+
+    https://github.com/ClickHouse/ClickHouse/issues/80440
+    MULTIPLE_EXPRESSIONS_FOR_ALIAS
+03121_analyzer_filed_redefenition_in_subquery
+
+    Correlated subqueries are not supported
+    Cannot clone ReadFromPreparedSource plan step. (NOT_IMPLEMENTED)
+03448_analyzer_correlated_subquery_in_projection
+03412_analyzer_correlated_subquery_bug
+03399_analyzer_correlated_subquery
+
     Transactions
 02421_truncate_isolation_no_merges
 02421_truncate_isolation_with_mutations
@@ -327,6 +367,7 @@
 00175_partition_by_ignore
 01655_plan_optimizations_optimize_read_in_window_order
 01625_constraints_index_append
+01883_with_grouping_sets
     Query memory limit exceeded: would use 19.63 MiB (attempt to allocate chunk of 1308788 bytes), current RSS 21.39 MiB, maximum: 19.07 MiB. (MEMORY_LIMIT_EXCEEDED
 01655_plan_optimizations_optimize_read_in_window_order_long
 01824_move_to_prewhere_many_columns
@@ -384,6 +425,8 @@
 03262_filter_push_down_view
 01283_max_threads_simple_query_optimization
 00183_prewhere_conditions_order
+03302_analyzer_join_filter_push_down_bug
+02815_join_algorithm_setting
 
     # NOT BUGS
     Not a bug

tests/queries/0_stateless/00063_check_query.sql

@@ -1,3 +1,5 @@
+-- Tags: log-engine
+
 SET check_query_single_value_result = 1;
 
 DROP TABLE IF EXISTS check_query_tiny_log;

tests/queries/0_stateless/00080_show_tables_and_system_tables.sql

@@ -1,3 +1,4 @@
+-- Tags: log-engine
 
 DROP DATABASE IF EXISTS {CLICKHOUSE_DATABASE:Identifier};
 

tests/queries/0_stateless/00305_http_and_readonly.sh

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# Tags: log-engine
 
 CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
 # shellcheck source=../shell_config.sh

tests/queries/0_stateless/00340_squashing_insert_select.sql

@@ -1,3 +1,5 @@
+-- Tags: log-engine
+
 DROP TABLE IF EXISTS numbers_squashed;
 CREATE TABLE numbers_squashed AS system.numbers ENGINE = StripeLog;
 

tests/queries/0_stateless/00341_squashing_insert_select2.sql

@@ -1,3 +1,5 @@
+-- Tags: log-engine
+
 DROP TABLE IF EXISTS numbers_squashed;
 CREATE TABLE numbers_squashed (number UInt8) ENGINE = StripeLog;
 

tests/queries/0_stateless/00366_multi_statements.reference

@@ -24,26 +24,26 @@ Syntax error
 5
 6
 1
-2
-3
-4
-5
-6
 1
 2
-3
-1
 2
 3
+3
 4
 5
 6
 1
+1
 2
+2
+3
 3
 4
+4
+5
 5
 6
+6
 1
 1
 1
@@ -53,55 +53,55 @@ Syntax error
 Syntax error
 Syntax error
 1
-2
-3
-4
-5
-6
 1
-2
-3
-4
-5
-6
 1
 2
-3
-1
 2
-3
-4
-5
-6
-1
 2
 3
-4
-5
-6
-1
-2
 3
-4
-5
-6
-1
-2
 3
 4
+4
+5
 5
 6
+6
+1
 1
+1
+2
 2
+2
+3
 3
+3
+4
 4
+4
+5
+5
 5
 6
+6
+6
 1
+1
+1
+2
+2
 2
 3
+3
+3
+4
+4
 4
 5
+5
+5
+6
+6
 6
 7
 8

tests/queries/0_stateless/00366_multi_statements.sh

@@ -22,14 +22,14 @@ $CLICKHOUSE_CLIENT --query="SELECT 1; SELECT 2; SELECT" 2>&1 | grep -o 'Syntax e
 $CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS t_00366; CREATE TABLE t_00366 (x UInt64) ENGINE = TinyLog;"
 
 $CLICKHOUSE_CLIENT --query="INSERT INTO t_00366 VALUES (1),(2),(3);"
-$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366"
+$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366 ORDER BY ALL"
 $CLICKHOUSE_CLIENT --query="INSERT INTO t_00366 VALUES" <<< "(4),(5),(6)"
-$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366"
+$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366 ORDER BY ALL"
 
 $CLICKHOUSE_CLIENT --query="INSERT INTO t_00366 VALUES (1),(2),(3);"
-$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366"
+$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366 ORDER BY ALL"
 $CLICKHOUSE_CLIENT --query="INSERT INTO t_00366 VALUES" <<< "(4),(5),(6)"
-$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366"
+$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366 ORDER BY ALL"
 
 ${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT 1"
 ${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT 1;"
@@ -42,10 +42,10 @@ ${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT 1; SELECT 2;" 2>&1 | grep
 ${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT 1; SELECT 2; SELECT" 2>&1 | grep -o 'Syntax error'
 
 ${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "INSERT INTO t_00366 VALUES (1),(2),(3);"
-$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366"
+$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366 ORDER BY ALL"
 ${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}&query=INSERT" -d "INTO t_00366 VALUES (4),(5),(6);"
-$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366"
+$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366 ORDER BY ALL"
 ${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}&query=INSERT+INTO+t_00366+VALUES" -d "(7),(8),(9)"
-$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366"
+$CLICKHOUSE_CLIENT --query="SELECT * FROM t_00366 ORDER BY ALL"
 
 $CLICKHOUSE_CLIENT --query="DROP TABLE t_00366;"