From 71bca6b60e626399eeb6a14b8d6c01295f10a14b Mon Sep 17 00:00:00 2001 From: Vasily Nemkov Date: Mon, 28 Oct 2024 14:33:17 +0000 Subject: [PATCH 1/2] Set input_format_parquet_filter_push_down default value to 'false' --- src/Core/Settings.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/Core/Settings.h b/src/Core/Settings.h index 6c7a50fba9e2..f0b0e0f0cebc 100644 --- a/src/Core/Settings.h +++ b/src/Core/Settings.h @@ -1001,7 +1001,7 @@ class IColumn; M(Bool, input_format_orc_case_insensitive_column_matching, false, "Ignore case when matching ORC columns with CH columns.", 0) \ M(Bool, input_format_parquet_case_insensitive_column_matching, false, "Ignore case when matching Parquet columns with CH columns.", 0) \ M(Bool, input_format_parquet_preserve_order, false, "Avoid reordering rows when reading from Parquet files. Usually makes it much slower.", 0) \ - M(Bool, input_format_parquet_filter_push_down, true, "When reading Parquet files, skip whole row groups based on the WHERE/PREWHERE expressions and min/max statistics in the Parquet metadata.", 0) \ + M(Bool, input_format_parquet_filter_push_down, false, "When reading Parquet files, skip whole row groups based on the WHERE/PREWHERE expressions and min/max statistics in the Parquet metadata.", 0) \ M(Bool, input_format_allow_seeks, true, "Allow seeks while reading in ORC/Parquet/Arrow input formats", 0) \ M(Bool, input_format_orc_allow_missing_columns, true, "Allow missing columns while reading ORC input formats", 0) \ M(Bool, input_format_orc_use_fast_decoder, true, "Use a faster ORC decoder implementation.", 0) \ From 82b22519001aca8884d51dfa8351b1a008df3b5a Mon Sep 17 00:00:00 2001 From: Vasily Nemkov Date: Mon, 28 Oct 2024 21:41:01 +0000 Subject: [PATCH 2/2] Fixed some tests --- src/Core/SettingsChangesHistory.h | 1 + tests/queries/0_stateless/02841_parquet_filter_pushdown.sql | 1 + 2 files changed, 2 insertions(+) diff --git a/src/Core/SettingsChangesHistory.h b/src/Core/SettingsChangesHistory.h index 4eefec4c74f4..e22c10ad6b47 100644 --- a/src/Core/SettingsChangesHistory.h +++ b/src/Core/SettingsChangesHistory.h @@ -128,6 +128,7 @@ static std::map sett {"input_format_csv_deserialize_separate_columns_into_tuple", true, true, "A new way of how interpret tuples in CSV format was added."}, {"input_format_csv_try_infer_strings_from_quoted_tuples", true, true, "A new way of how interpret tuples in CSV format was added."}, {"temporary_data_in_cache_reserve_space_wait_lock_timeout_milliseconds", (10 * 60 * 1000), (10 * 60 * 1000), "Wait time to lock cache for sapce reservation in temporary data in filesystem cache"}, + {"input_format_parquet_filter_push_down", true, false, "Filter push down breaks selecting from parquet files sometimes"}, }}, {"24.2", {{"allow_suspicious_variant_types", true, false, "Don't allow creating Variant type with suspicious variants by default"}, {"validate_experimental_and_suspicious_types_inside_nested_types", false, true, "Validate usage of experimental and suspicious types inside nested types"}, diff --git a/tests/queries/0_stateless/02841_parquet_filter_pushdown.sql b/tests/queries/0_stateless/02841_parquet_filter_pushdown.sql index 016eb48e879e..6a227e2e9c0a 100644 --- a/tests/queries/0_stateless/02841_parquet_filter_pushdown.sql +++ b/tests/queries/0_stateless/02841_parquet_filter_pushdown.sql @@ -1,5 +1,6 @@ -- Tags: no-fasttest, no-parallel +set input_format_parquet_filter_push_down=true; set output_format_parquet_row_group_size = 100; set input_format_null_as_default = 1;