ClickHouse/tests/performance
Jiebin Sun 78f3a575f9
Convert hashSets in parallel before merge (#50748)
* Convert hashSets in parallel before merge

Before merge, if one of the lhs and rhs is singleLevelSet and the other is twoLevelSet,
then the SingleLevelSet will call convertToTwoLevel(). The convert process is not in parallel
and it will cost lots of cycle if it cosume all the singleLevelSet.

The idea of the patch is to convert all the singleLevelSets to twoLevelSets in parallel if
the hashsets are not all singleLevel or not all twoLevel.

I have tested the patch on Intel 2 x 112 vCPUs SPR server with clickbench and latest upstream
ClickHouse.
Q5 has got a big 264% performance improvement and 24 queries have got at least 5% performance
gain. The overall geomean of 43 queries has gained 7.4% more than the base code.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>

* add resize() for the data_vec in parallelizeMergePrepare()

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>

* Add the performance test prepare_hash_before_merge.xml

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>

* Fit the CI to rename the data set from hits_v1 to test.hits.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>

* remove the redundant branch in UniqExactSet

Co-authored-by: Nikita Taranov <nickita.taranov@gmail.com>

* Remove the empty methods and add throw exception in parallelizeMergePrepare()

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>

---------

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Co-authored-by: Nikita Taranov <nickita.taranov@gmail.com>
2023-07-27 15:06:34 +02:00
..
agg_functions_min_max_any.xml
aggregate_functions_of_group_by_keys.xml
aggregating_merge_tree_simple_aggregate_function_string.xml
aggregating_merge_tree.xml
aggregation_by_partitions.xml
aggregation_in_order_2.xml
aggregation_in_order.xml
aggregation_overflow.xml
analyze_array_tuples.xml
and_function.xml
any_anyLast.xml
arithmetic_operations_in_aggr_func.xml
arithmetic.xml
array_auc.xml
array_element.xml
array_fill.xml
array_index_low_cardinality_numbers.xml
array_index_low_cardinality_strings.xml
array_join.xml
array_reduce.xml
arrow_format.xml
asof.xml Fix ASOF LEFT JOIN performance degradation (#47544) 2023-03-18 23:53:00 +01:00
async_remote_read.xml
avg_weighted.xml
avg.xml
base64_hits.xml
base64.xml
basename.xml
bigint_arithm.xml
bit_operations_fixed_string_numbers.xml
bit_operations_fixed_string.xml
bitmap_array_element.xml
bloom_filter_insert.xml
bloom_filter_select.xml
bounding_ratio.xml
casts.xml
cidr.xml
classification.xml
codec_none.xml
codecs_float_insert.xml
codecs_float_select.xml
codecs_int_insert.xml
codecs_int_select.xml
collations.xml
column_array_filter.xml
column_array_replicate.xml
ColumnMap.xml
columns_hashing.xml
complex_array_creation.xml
concat_hits.xml
conditional.xml
consistent_hashes.xml
constant_column_comparison.xml
constant_column_search.xml
count.xml
countDigits.xml
countIf.xml
countMatches.xml
cpu_synthetic.xml
cryptographic_hashes.xml
date_parsing.xml
date_time_64.xml
date_time_long.xml
date_time_short.xml
datetime64_conversion.xml
datetime_comparison.xml
decimal_aggregates.xml
decimal_casts.xml
decimal_format.xml
decimal_parse.xml
destroy_aggregate_states.xml
dict_join.xml
direct_dictionary.xml
distinct_combinator.xml
distinct_in_order.xml
distributed_aggregation_memory_efficient.xml
distributed_aggregation.xml
empty_string_deserialization.xml
empty_string_serialization.xml
encodeXMLComponent.xml
encrypt_decrypt_empty_string_slow.xml
encrypt_decrypt_empty_string.xml
encrypt_decrypt.xml
entropy.xml
explain_ast.xml
extract.xml
file_table_function.xml
fixed_string16.xml
flat_dictionary.xml
float_formatting.xml
float_mod.xml
float_parsing.xml
format_date_time.xml
format_readable.xml
formats_columns_sampling.xml
function_calculation_after_sorting_and_limit.xml
functions_coding.xml
functions_geo.xml
functions_with_hash_tables.xml
fuse_sumcount.xml
fuzz_bits.xml
general_purpose_hashes_on_UUID.xml
general_purpose_hashes.xml
generate_table_function.xml
grace_hash_join.xml
great_circle_dist.xml
group_array_moving_sum.xml
group_by_fixed_keys.xml
group_by_sundy_li.xml Make projections production-ready 2023-05-10 03:35:13 +02:00
groupby_onekey_nullable.xml Make projections production-ready 2023-05-10 03:35:13 +02:00
h3.xml
has_all.xml
hash_table_sizes_stats_small.xml
hash_table_sizes_stats.xml
hashed_array_dictionary.xml
hashed_dictionary_load_factor.xml Add ability to configure maximum load factor for the HASHED/SPARSE_HASHED layout 2023-05-19 06:07:21 +02:00
hashed_dictionary_sharded.xml Optimize SPARSE_HASHED layout (by using PackedHashMap) 2023-05-19 06:07:21 +02:00
hashed_dictionary.xml
hierarchical_dictionaries.xml
if_array_num.xml
if_array_string.xml
if_string_const.xml
if_string_hits.xml
if_to_multiif.xml
if_transform_strings_to_enum.xml
information_value.xml
injective_functions_inside_uniq.xml
insert_parallel.xml
insert_select_default_small_block.xml
insert_sequential_and_background_merges.xml
insert_values_with_expressions.xml
inserts_arrays_lowcardinality.xml
int_parsing.xml
intDiv.xml
ip_trie.xml
IPv4.xml
IPv6.xml
jit_aggregate_functions.xml
jit_large_requests.xml
jit_small_requests.xml
jit_sort.xml
join_append_block.xml
join_filter_pushdown.xml add perf test 2023-07-24 20:34:01 +02:00
join_max_streams.xml
join_used_flags.xml enable used flags's reinit only when the hash talbe rehash 2023-05-11 11:06:13 +08:00
joins_in_memory.xml
json_extract_rapidjson.xml
json_extract_simdjson.xml
json_type.xml
least_greatest_hits.xml
leftpad.xml
lightweight_delete.xml
line_as_string_parsing.xml
linear_regression.xml
local_replica.xml
logical_functions_large.xml
logical_functions_medium.xml
logical_functions_small.xml
lot_of_subcolumns.xml
low_cardinality_argument.xml
low_cardinality_from_json.xml
low_cardinality_query.xml
lower_upper_function.xml
lower_upper_utf8.xml
lz4_hits_columns.xml
lz4.xml
map_populate_series.xml
map_update.xml add tests 2023-03-28 17:20:05 +00:00
materialized_view_parallel_insert.xml
materialized_view_parallelize_output_from_storages.xml Adjust min_insert_block_size_rows for materialized_view_parallelize_output_from_storages 2023-06-14 19:11:23 +03:00
math.xml
memory_bound_merging.xml
memory_cache_friendliness.xml
merge_table_streams.xml
merge_tree_huge_pk.xml
merge_tree_insert.xml
merge_tree_many_partitions_2.xml
merge_tree_many_partitions.xml
merge_tree_simple_select.xml
mingroupby-orderbylimit1.xml
mmap_io.xml
modulo.xml
monotonous_order_by.xml
ngram_distance.xml
nlp.xml
norm_distance_float.xml
norm_distance.xml
normalize_utf8.xml
number_formatting_formats.xml
optimize_sorting_for_input_stream.xml
optimize_window_funnel.xml
optimized_select_final_one_part.xml
optimized_select_final.xml
or_null_default.xml
order_by_decimals.xml
order_by_read_in_order.xml
order_by_single_column.xml
order_by_tuple.xml
order_with_limit.xml
parallel_final.xml
parallel_index.xml
parallel_insert.xml
parallel_mv.xml
parse_engine_file.xml
point_in_polygon_const.xml
point_in_polygon.xml
polymorphic_parts_l.xml
polymorphic_parts_m.xml
polymorphic_parts_s.xml Deprecate in-memory parts 2023-05-03 00:31:09 +02:00
position_empty_needle.xml
pre_limit_no_sorting.xml
prefetch_in_aggregation.xml
prepare_hash_before_merge.xml Convert hashSets in parallel before merge (#50748) 2023-07-27 15:06:34 +02:00
prewhere_with_row_level_filter.xml
prewhere.xml
push_down_limit.xml
quantile_merge.xml
quantile.xml
queries_over_aggregation.xml
query_interpretation_join.xml
rand.xml
random_fixed_string.xml
random_printable_ascii.xml
random_string_utf8.xml
random_string.xml
range_hashed_dictionary.xml
range.xml
re2_regex_caching.xml Fix performance test for regexp cache 2023-07-09 02:21:48 +02:00
read_from_comp_parts.xml
read_hits_with_aio.xml
read_in_order_many_parts.xml
reading_from_file.xml Perf test 2023-04-07 20:06:11 +00:00
README.md
redundant_functions_in_order_by.xml
reinterpret_as.xml
removing_group_by_keys.xml
rewrite_array_exists.xml
rewrite_sumIf.xml
right.xml
round_down.xml
round_methods.xml
scalar2.xml
scalar.xml
schema_inference_text_formats.xml
select_format.xml
sequence_match.xml
set_disable_skip_index.xml add perf test 2023-04-04 21:29:52 +00:00
set_hits.xml
set_index.xml
set.xml
short_circuit_functions.xml
simple_join_query.xml
single_fixed_string_groupby.xml
slices_hits.xml
sort_radix_trivial.xml
sort.xml
sparse_column.xml
split_filter.xml
string_join.xml
string_set.xml
string_sort.xml
string_to_int.xml
subqueries.xml
sum_map.xml
sum.xml
sumIf.xml
synthetic_hardware_benchmark.xml
trim_numbers.xml
trim_urls.xml
trim_whitespace.xml
tsv_csv_nullable_parsing.xml
unary_arithmetic_functions.xml
unary_logical_functions.xml
uniq_stored.xml
uniq_without_key.xml
uniq.xml
uniqExactIf.xml Add parallel state merge for some other combinator except If (#50413) 2023-06-08 00:41:32 +02:00
url_hits.xml
vectorize_aggregation_combinators.xml
views_max_insert_threads.xml
visit_param_extract_raw.xml
website.xml
window_functions.xml
writing_valid_utf8.xml

ClickHouse performance tests

This directory contains .xml-files with performance tests for @akuzm tool.

How to write performance test

First of all you should check existing tests don't cover your case. If there are no such tests than you should write your own.

You can use substitions, create, fill and drop queries to prepare test. You can find examples in this folder.

If your test continued more than 10 minutes, please, add tag long to have an opportunity to run all tests and skip long ones.

How to run performance test

TODO @akuzm

How to validate single test

pip3 install clickhouse_driver scipy
../../docker/test/performance-comparison/perf.py --runs 1 insert_parallel.xml