Add clickbench performance tests on PostgreSQL syntax over YDB (#10861)

iddqdex · web-flow · commit 4338c7145886 · 2024-10-25T11:34:29.000+03:00
diff --git a/ydb/library/workload/benchmark_base/workload.h b/ydb/library/workload/benchmark_base/workload.h
@@ -17,6 +17,10 @@ class TWorkloadBaseParams: public TWorkloadParams {
         Column  /* "column" */,
         ExternalS3      /* "external-s3"     */
     };
+    enum class EQuerySyntax {
+        YQL /* "yql" */,
+        PG /* "pg"*/
+    };
     void ConfigureOpts(NLastGetopt::TOpts& opts, const ECommandType commandType, int workloadType) override;
     TString GetFullTableName(const char* table) const;
     YDB_ACCESSOR_DEF(TString, Path);
diff --git a/ydb/library/workload/benchmark_base/ya.make b/ydb/library/workload/benchmark_base/ya.make
@@ -13,7 +13,7 @@ PEERDIR(
     ydb/public/api/protos
 )
 
-GENERATE_ENUM_SERIALIZATION(workload.h)
+GENERATE_ENUM_SERIALIZATION_WITH_HEADER(workload.h)
 
 END()
 
diff --git a/ydb/library/workload/clickbench/click_bench_queries_pg.sql b/ydb/library/workload/clickbench/click_bench_queries_pg.sql
@@ -0,0 +1,86 @@
+-- q00
+SELECT COUNT(*) FROM {table};
+-- q01
+SELECT COUNT(*) FROM {table} WHERE AdvEngineID <> 0;
+-- q02
+SELECT SUM(AdvEngineID), COUNT(*), AVG(ResolutionWidth) FROM {table};
+-- q03
+SELECT AVG(UserID) FROM {table};
+-- q04
+SELECT COUNT(DISTINCT UserID) FROM {table};
+-- q05
+SELECT COUNT(DISTINCT SearchPhrase) FROM {table};
+-- q06
+SELECT MIN(EventDate), MAX(EventDate) FROM {table};
+-- q07
+SELECT AdvEngineID, COUNT(*) FROM {table} WHERE AdvEngineID <> 0 GROUP BY AdvEngineID ORDER BY COUNT(*) DESC;
+-- q08
+SELECT RegionID, COUNT(DISTINCT UserID) AS u FROM {table} GROUP BY RegionID ORDER BY u DESC LIMIT 10;
+-- q09
+SELECT RegionID, SUM(AdvEngineID), COUNT(*) AS c, AVG(ResolutionWidth), COUNT(DISTINCT UserID) FROM {table} GROUP BY RegionID ORDER BY c DESC LIMIT 10;
+-- q10
+SELECT MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM {table} WHERE MobilePhoneModel <> '' GROUP BY MobilePhoneModel ORDER BY u DESC LIMIT 10;
+-- q11
+SELECT MobilePhone, MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM {table} WHERE MobilePhoneModel <> '' GROUP BY MobilePhone, MobilePhoneModel ORDER BY u DESC LIMIT 10;
+-- q12
+SELECT SearchPhrase, COUNT(*) AS c FROM {table} WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
+-- q13
+SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM {table} WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
+-- q14
+SELECT SearchEngineID, SearchPhrase, COUNT(*) AS c FROM {table} WHERE SearchPhrase <> '' GROUP BY SearchEngineID, SearchPhrase ORDER BY c DESC LIMIT 10;
+-- q15
+SELECT UserID, COUNT(*) FROM {table} GROUP BY UserID ORDER BY COUNT(*) DESC LIMIT 10;
+-- q16
+SELECT UserID, SearchPhrase, COUNT(*) FROM {table} GROUP BY UserID, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
+-- q17
+SELECT UserID, SearchPhrase, COUNT(*) FROM {table} GROUP BY UserID, SearchPhrase LIMIT 10;
+-- q18
+SELECT UserID, extract(minute FROM EventTime) AS m, SearchPhrase, COUNT(*) FROM {table} GROUP BY UserID, m, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
+-- q19
+SELECT UserID FROM {table} WHERE UserID = 435090932899640449;
+-- q20
+SELECT COUNT(*) FROM {table} WHERE URL LIKE '%google%';
+-- q21
+SELECT SearchPhrase, MIN(URL), COUNT(*) AS c FROM {table} WHERE URL LIKE '%google%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
+-- q22
+SELECT SearchPhrase, MIN(URL), MIN(Title), COUNT(*) AS c, COUNT(DISTINCT UserID) FROM {table} WHERE Title LIKE '%Google%' AND URL NOT LIKE '%.google.%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
+-- q23
+SELECT * FROM {table} WHERE URL LIKE '%google%' ORDER BY EventTime LIMIT 10;
+-- q24
+SELECT SearchPhrase FROM {table} WHERE SearchPhrase <> '' ORDER BY EventTime LIMIT 10;
+-- q25
+SELECT SearchPhrase FROM {table} WHERE SearchPhrase <> '' ORDER BY SearchPhrase LIMIT 10;
+-- q26
+SELECT SearchPhrase FROM {table} WHERE SearchPhrase <> '' ORDER BY EventTime, SearchPhrase LIMIT 10;
+-- q27
+SELECT CounterID, AVG(length(URL)) AS l, COUNT(*) AS c FROM {table} WHERE URL <> '' GROUP BY CounterID HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
+-- q28
+SELECT REGEXP_REPLACE(Referer, '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length(Referer)) AS l, COUNT(*) AS c, MIN(Referer) FROM {table} WHERE Referer <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
+-- q29
+SELECT SUM(ResolutionWidth), SUM(ResolutionWidth + 1), SUM(ResolutionWidth + 2), SUM(ResolutionWidth + 3), SUM(ResolutionWidth + 4), SUM(ResolutionWidth + 5), SUM(ResolutionWidth + 6), SUM(ResolutionWidth + 7), SUM(ResolutionWidth + 8), SUM(ResolutionWidth + 9), SUM(ResolutionWidth + 10), SUM(ResolutionWidth + 11), SUM(ResolutionWidth + 12), SUM(ResolutionWidth + 13), SUM(ResolutionWidth + 14), SUM(ResolutionWidth + 15), SUM(ResolutionWidth + 16), SUM(ResolutionWidth + 17), SUM(ResolutionWidth + 18), SUM(ResolutionWidth + 19), SUM(ResolutionWidth + 20), SUM(ResolutionWidth + 21), SUM(ResolutionWidth + 22), SUM(ResolutionWidth + 23), SUM(ResolutionWidth + 24), SUM(ResolutionWidth + 25), SUM(ResolutionWidth + 26), SUM(ResolutionWidth + 27), SUM(ResolutionWidth + 28), SUM(ResolutionWidth + 29), SUM(ResolutionWidth + 30), SUM(ResolutionWidth + 31), SUM(ResolutionWidth + 32), SUM(ResolutionWidth + 33), SUM(ResolutionWidth + 34), SUM(ResolutionWidth + 35), SUM(ResolutionWidth + 36), SUM(ResolutionWidth + 37), SUM(ResolutionWidth + 38), SUM(ResolutionWidth + 39), SUM(ResolutionWidth + 40), SUM(ResolutionWidth + 41), SUM(ResolutionWidth + 42), SUM(ResolutionWidth + 43), SUM(ResolutionWidth + 44), SUM(ResolutionWidth + 45), SUM(ResolutionWidth + 46), SUM(ResolutionWidth + 47), SUM(ResolutionWidth + 48), SUM(ResolutionWidth + 49), SUM(ResolutionWidth + 50), SUM(ResolutionWidth + 51), SUM(ResolutionWidth + 52), SUM(ResolutionWidth + 53), SUM(ResolutionWidth + 54), SUM(ResolutionWidth + 55), SUM(ResolutionWidth + 56), SUM(ResolutionWidth + 57), SUM(ResolutionWidth + 58), SUM(ResolutionWidth + 59), SUM(ResolutionWidth + 60), SUM(ResolutionWidth + 61), SUM(ResolutionWidth + 62), SUM(ResolutionWidth + 63), SUM(ResolutionWidth + 64), SUM(ResolutionWidth + 65), SUM(ResolutionWidth + 66), SUM(ResolutionWidth + 67), SUM(ResolutionWidth + 68), SUM(ResolutionWidth + 69), SUM(ResolutionWidth + 70), SUM(ResolutionWidth + 71), SUM(ResolutionWidth + 72), SUM(ResolutionWidth + 73), SUM(ResolutionWidth + 74), SUM(ResolutionWidth + 75), SUM(ResolutionWidth + 76), SUM(ResolutionWidth + 77), SUM(ResolutionWidth + 78), SUM(ResolutionWidth + 79), SUM(ResolutionWidth + 80), SUM(ResolutionWidth + 81), SUM(ResolutionWidth + 82), SUM(ResolutionWidth + 83), SUM(ResolutionWidth + 84), SUM(ResolutionWidth + 85), SUM(ResolutionWidth + 86), SUM(ResolutionWidth + 87), SUM(ResolutionWidth + 88), SUM(ResolutionWidth + 89) FROM {table};
+-- q30
+SELECT SearchEngineID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM {table} WHERE SearchPhrase <> '' GROUP BY SearchEngineID, ClientIP ORDER BY c DESC LIMIT 10;
+-- q31
+SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM {table} WHERE SearchPhrase <> '' GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
+-- q32
+SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM {table} GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
+-- q33
+SELECT URL, COUNT(*) AS c FROM {table} GROUP BY URL ORDER BY c DESC LIMIT 10;
+-- q34
+SELECT 1, URL, COUNT(*) AS c FROM {table} GROUP BY 1, URL ORDER BY c DESC LIMIT 10;
+-- q35
+SELECT ClientIP, ClientIP - 1, ClientIP - 2, ClientIP - 3, COUNT(*) AS c FROM {table} GROUP BY ClientIP, ClientIP - 1, ClientIP - 2, ClientIP - 3 ORDER BY c DESC LIMIT 10;
+-- q36
+SELECT URL, COUNT(*) AS PageViews FROM {table} WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND DontCountHits = 0 AND IsRefresh = 0 AND URL <> '' GROUP BY URL ORDER BY PageViews DESC LIMIT 10;
+-- q37
+SELECT Title, COUNT(*) AS PageViews FROM {table} WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND DontCountHits = 0 AND IsRefresh = 0 AND Title <> '' GROUP BY Title ORDER BY PageViews DESC LIMIT 10;
+-- q38
+SELECT URL, COUNT(*) AS PageViews FROM {table} WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND IsLink <> 0 AND IsDownload = 0 GROUP BY URL ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
+-- q39
+SELECT TraficSourceID, SearchEngineID, AdvEngineID, CASE WHEN (SearchEngineID = 0 AND AdvEngineID = 0) THEN Referer ELSE '' END AS Src, URL AS Dst, COUNT(*) AS PageViews FROM {table} WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 GROUP BY TraficSourceID, SearchEngineID, AdvEngineID, Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
+-- q40
+SELECT URLHash, EventDate, COUNT(*) AS PageViews FROM {table} WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND TraficSourceID IN (-1, 6) AND RefererHash = 3594120000172545465 GROUP BY URLHash, EventDate ORDER BY PageViews DESC LIMIT 10 OFFSET 100;
+-- q41
+SELECT WindowClientWidth, WindowClientHeight, COUNT(*) AS PageViews FROM {table} WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND DontCountHits = 0 AND URLHash = 2868770270353813622 GROUP BY WindowClientWidth, WindowClientHeight ORDER BY PageViews DESC LIMIT 10 OFFSET 10000;
+-- q42
+SELECT DATE_TRUNC('minute', EventTime) AS M, COUNT(*) AS PageViews FROM {table} WHERE CounterID = 62 AND EventDate >= '2013-07-14' AND EventDate <= '2013-07-15' AND IsRefresh = 0 AND DontCountHits = 0 GROUP BY DATE_TRUNC('minute', EventTime) ORDER BY DATE_TRUNC('minute', EventTime) LIMIT 10 OFFSET 1000;
diff --git a/ydb/library/workload/clickbench/clickbench.cpp b/ydb/library/workload/clickbench/clickbench.cpp
@@ -1,5 +1,6 @@
 #include "clickbench.h"
 #include "data_generator.h"
+#include <ydb/library/workload/benchmark_base/workload.h_serialized.h>
 
 #include <library/cpp/resource/resource.h>
 #include <library/cpp/string_utils/csv/csv.h>
@@ -82,7 +83,12 @@ TQueryInfoList TClickbenchWorkloadGenerator::GetWorkload(int type) {
             queries.emplace_back(fInput.ReadAll());
         }
     } else {
-        const auto resourceName = Params.IsCheckCanonical() ? "queries-deterministic.sql" : "click_bench_queries.sql";
+        TString resourceName = "click_bench_queries.sql";
+        if (Params.GetSyntax() == TWorkloadBaseParams::EQuerySyntax::PG) {
+            resourceName = "click_bench_queries_pg.sql";
+        } else if (Params.IsCheckCanonical()) {
+            resourceName = "queries-deterministic.sql";
+        }
         queries = StringSplitter(NResource::Find(resourceName)).Split(';').ToList<TString>();
     }
     auto strVariables = StringSplitter(Params.GetExternalVariablesString()).Split(';').SkipEmpty().ToList<TString>();
@@ -92,14 +98,26 @@ TQueryInfoList TClickbenchWorkloadGenerator::GetWorkload(int type) {
         Y_ABORT_UNLESS(v.DeserializeFromString(i));
         vars.emplace_back(v);
     }
-    vars.emplace_back("table", "`" + Params.GetPath() + "`");
+    TString quote;
+    switch (Params.GetSyntax()) {
+    case TWorkloadBaseParams::EQuerySyntax::YQL:
+        quote = "`";
+        break;
+    case TWorkloadBaseParams::EQuerySyntax::PG:
+        quote = "\"";
+        break;
+    };
+    vars.emplace_back("table", quote + Params.GetPath() + quote);
     ui32 resultsUsage = 0;
     for (ui32 i = 0; i < queries.size(); ++i) {
         auto& query = queries[i];
+        if (Params.GetSyntax() == TWorkloadBaseParams::EQuerySyntax::PG) {
+            query = "--!syntax_pg\n" + query;
+        }
         for (auto&& v : vars) {
             SubstGlobal(query, "{" + v.GetId() + "}", v.GetValue());
         }
-        SubstGlobal(query, "$data", "`" + Params.GetPath() + "`");
+        SubstGlobal(query, "$data", quote + Params.GetPath() + quote);
         result.emplace_back();
         result.back().Query = query;
         if (const auto* res = MapFindPtr(qResults, i)) {
@@ -164,6 +182,8 @@ void TClickbenchWorkloadParams::ConfigureOpts(NLastGetopt::TOpts& opts, const EC
             .StoreResult(&ExternalQueries);
         opts.AddLongOption('c', "check-canonical", "Use deterministic queries and check results with canonical ones.")
             .NoArgument().StoreTrue(&CheckCanonicalFlag);
+        opts.AddLongOption( "syntax", "Query syntax [" + GetEnumAllNames<EQuerySyntax>() + "].")
+            .StoreResult(&Syntax).DefaultValue(Syntax);
         break;
     default:
         break;
diff --git a/ydb/library/workload/clickbench/clickbench.h b/ydb/library/workload/clickbench/clickbench.h
@@ -19,6 +19,7 @@ class TClickbenchWorkloadParams final: public TWorkloadBaseParams {
     YDB_READONLY_DEF(TFsPath, ExternalQueriesDir);
     YDB_READONLY_DEF(TFsPath, DataFiles);
     YDB_READONLY_FLAG(CheckCanonical, false);
+    YDB_READONLY(EQuerySyntax, Syntax, EQuerySyntax::YQL);
 };
 
 class TClickbenchWorkloadGenerator final: public TWorkloadGeneratorBase {
diff --git a/ydb/library/workload/clickbench/ya.make b/ydb/library/workload/clickbench/ya.make
@@ -8,6 +8,7 @@ SRCS(
 
 RESOURCE(
     click_bench_queries.sql click_bench_queries.sql
+    click_bench_queries_pg.sql click_bench_queries_pg.sql
     ${ARCADIA_ROOT}/ydb/tests/functional/clickbench/data/queries-deterministic.sql queries-deterministic.sql
     click_bench_schema.sql click_bench_schema.sql
     click_bench_canonical/q0.result click_bench_canonical/q0.result
diff --git a/ydb/tests/olap/lib/ydb_cli.py b/ydb/tests/olap/lib/ydb_cli.py
@@ -60,7 +60,8 @@ def __init__(self,
                      query_num: int,
                      iterations: int,
                      timeout: float,
-                     check_canonical: bool):
+                     check_canonical: bool,
+                     query_syntax: str):
             def _get_output_path(ext: str) -> str:
                 return yatest.common.test_output_path(f'q{query_num}.{ext}')
 
@@ -71,6 +72,7 @@ def _get_output_path(ext: str) -> str:
             self.iterations = iterations
             self.timeout = timeout
             self.check_canonical = check_canonical
+            self.query_syntax = query_syntax
             self._nodes_info: dict[str, dict[str, int]] = {}
             self._plan_path = _get_output_path('plan')
             self._query_output_path = _get_output_path('out')
@@ -194,6 +196,8 @@ def _get_cmd(self) -> list[str]:
                 cmd += ['--query-settings', query_preffix]
             if self.check_canonical:
                 cmd.append('--check-canonical')
+            if self.query_syntax:
+                cmd += ['--syntax', self.query_syntax]
             return cmd
 
         def _exec_cli(self) -> None:
@@ -222,5 +226,5 @@ def process(self) -> YdbCliHelper.WorkloadRunResult:
 
     @staticmethod
     def workload_run(workload_type: WorkloadType, path: str, query_num: int, iterations: int = 5,
-                     timeout: float = 100., check_canonical: bool = False) -> YdbCliHelper.WorkloadRunResult:
-        return YdbCliHelper.WorkloadProcessor(workload_type, path, query_num, iterations, timeout, check_canonical).process()
+                     timeout: float = 100., check_canonical: bool = False, query_syntax: str = '') -> YdbCliHelper.WorkloadRunResult:
+        return YdbCliHelper.WorkloadProcessor(workload_type, path, query_num, iterations, timeout, check_canonical, query_syntax).process()
diff --git a/ydb/tests/olap/load/conftest.py b/ydb/tests/olap/load/conftest.py
@@ -23,6 +23,7 @@ def __init__(self, iterations: Optional[int] = None, timeout: Optional[float] =
     timeout: float = 1800.
     refference: str = ''
     check_canonical: bool = False
+    query_syntax: str = ''
     query_settings: dict[int, LoadSuiteBase.QuerySettings] = {}
 
     @property
@@ -195,7 +196,8 @@ def run_workload_test(self, path: str, query_num: int) -> None:
             iterations=self._get_iterations(query_num),
             workload_type=self.workload_type,
             timeout=self._get_timeout(query_num),
-            check_canonical=self.check_canonical
+            check_canonical=self.check_canonical,
+            query_syntax=self.query_syntax
         )
         allure_test_description(self.suite, self._test_name(query_num), refference_set=self.refference, start_time=start_time, end_time=time())
         self.process_query_result(result, query_num, self._get_iterations(query_num), True)
diff --git a/ydb/tests/olap/load/test_clickbench.py b/ydb/tests/olap/load/test_clickbench.py
@@ -41,3 +41,7 @@ def do_setup_class(self):
     @pytest.mark.parametrize('query_num', [i for i in range(0, 43)])
     def test_clickbench(self, query_num):
         self.run_workload_test(self.path, query_num)
+
+
+class TestClickbenchPg(TestClickbench):
+    query_syntax = 'pg'

Original file line number	Diff line number	Diff line change
`@@ -13,7 +13,7 @@ PEERDIR(`
`13`	`13`	`ydb/public/api/protos`
`14`	`14`	`)`
`15`	`15`
`16`		`-GENERATE_ENUM_SERIALIZATION(workload.h)`
	`16`	`+GENERATE_ENUM_SERIALIZATION_WITH_HEADER(workload.h)`
`17`	`17`
`18`	`18`	`END()`
`19`	`19`