Split clickbench query set into one file per query

benchmarks/bench.sh

@@ -586,23 +586,23 @@ run_clickbench_1() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_1.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (1 file) benchmark..."
-    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet"  --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet"  --queries-path "${SCRIPT_DIR}/queries/clickbench/queries" -o "${RESULTS_FILE}"
 }
 
  # Runs the clickbench benchmark with the partitioned parquet files
 run_clickbench_partitioned() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_partitioned.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (partitioned, 100 files) benchmark..."
-    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits_partitioned" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits_partitioned" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries" -o "${RESULTS_FILE}"
 }
 
 # Runs the clickbench "extended" benchmark with a single large parquet file
 run_clickbench_extended() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_extended.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (1 file) extended benchmark..."
-    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet" --queries-path "${SCRIPT_DIR}/queries/clickbench/extended.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet" --queries-path "${SCRIPT_DIR}/queries/clickbench/extended" -o "${RESULTS_FILE}"
 }
 
 # Downloads the csv.gz files IMDB datasets from Peter Boncz's homepage(one of the JOB paper authors)

benchmarks/queries/clickbench/README.md

@@ -6,17 +6,17 @@ ClickBench is focused on aggregation and filtering performance (though it has no
 
 ## Files:
 
-- `queries.sql` - Actual ClickBench queries, downloaded from the [ClickBench repository]
-- `extended.sql` - "Extended" DataFusion specific queries.
+- `queries/*.sql` - Actual ClickBench queries, downloaded from the [ClickBench repository](https://raw.githubusercontent.com/ClickHouse/ClickBench/main/datafusion/queries.sql) and split by the `update_queries.sh` script.
+- `extended/*.sql` - "Extended" DataFusion specific queries.
 
 [clickbench repository]: https://github.com/ClickHouse/ClickBench/blob/main/datafusion/queries.sql
 
 ## "Extended" Queries
 
 The "extended" queries are not part of the official ClickBench benchmark.
 Instead they are used to test other DataFusion features that are not covered by
-the standard benchmark. Each description below is for the corresponding line in
-`extended.sql` (line 1 is `Q0`, line 2 is `Q1`, etc.)
+the standard benchmark. Each description below is for the corresponding file in
+`extended`
 
 ### Q0: Data Exploration
 

benchmarks/queries/clickbench/extended/q0.sql

@@ -0,0 +1 @@
+SELECT COUNT(DISTINCT "SearchPhrase"), COUNT(DISTINCT "MobilePhone"), COUNT(DISTINCT "MobilePhoneModel") FROM hits;

benchmarks/queries/clickbench/extended/q1.sql

@@ -0,0 +1 @@
+SELECT COUNT(DISTINCT "HitColor"), COUNT(DISTINCT "BrowserCountry"), COUNT(DISTINCT "BrowserLanguage")  FROM hits;

benchmarks/queries/clickbench/extended/q2.sql

@@ -0,0 +1 @@
+SELECT "BrowserCountry",  COUNT(DISTINCT "SocialNetwork"), COUNT(DISTINCT "HitColor"), COUNT(DISTINCT "BrowserLanguage"), COUNT(DISTINCT "SocialAction") FROM hits GROUP BY 1 ORDER BY 2 DESC LIMIT 10;

benchmarks/queries/clickbench/extended/q3.sql

@@ -0,0 +1 @@
+SELECT "SocialSourceNetworkID", "RegionID", COUNT(*), AVG("Age"), AVG("ParamPrice"), STDDEV("ParamPrice") as s, VAR("ParamPrice")  FROM hits GROUP BY "SocialSourceNetworkID", "RegionID" HAVING s IS NOT NULL ORDER BY s DESC LIMIT 10;

benchmarks/queries/clickbench/extended/q4.sql

@@ -0,0 +1 @@
+SELECT "ClientIP", "WatchID",  COUNT(*) c, MIN("ResponseStartTiming") tmin, MEDIAN("ResponseStartTiming") tmed, MAX("ResponseStartTiming") tmax FROM hits WHERE "JavaEnable" = 0  GROUP BY  "ClientIP", "WatchID" HAVING c > 1 ORDER BY tmed DESC LIMIT 10;

benchmarks/queries/clickbench/extended/q5.sql

@@ -0,0 +1 @@
+SELECT "ClientIP", "WatchID",  COUNT(*) c, MIN("ResponseStartTiming") tmin, APPROX_PERCENTILE_CONT(0.95) WITHIN GROUP (ORDER BY "ResponseStartTiming") tp95, MAX("ResponseStartTiming") tmax FROM 'hits' WHERE "JavaEnable" = 0 GROUP BY  "ClientIP", "WatchID" HAVING c > 1 ORDER BY tp95 DESC LIMIT 10;

benchmarks/queries/clickbench/extended/q6.sql

@@ -0,0 +1 @@
+SELECT COUNT(*) AS ShareCount FROM hits WHERE "IsMobile" = 1 AND "MobilePhoneModel" LIKE 'iPhone%' AND "SocialAction" = 'share' AND "SocialSourceNetworkID" IN (5, 12) AND "ClientTimeZone" BETWEEN -5 AND 5 AND regexp_match("Referer", '\/campaign\/(spring|summer)_promo') IS NOT NULL AND CASE WHEN split_part(split_part("URL", 'resolution=', 2), '&', 1) ~ '^\d+$' THEN split_part(split_part("URL", 'resolution=', 2), '&', 1)::INT ELSE 0 END > 1920 AND levenshtein(CAST("UTMSource" AS STRING), CAST("UTMCampaign" AS STRING)) < 3;

benchmarks/queries/clickbench/extended/q7.sql

@@ -0,0 +1 @@
+SELECT "WatchID", MIN("ResolutionWidth") as wmin, MAX("ResolutionWidth") as wmax, SUM("IsRefresh") as srefresh FROM hits GROUP BY "WatchID" ORDER BY "WatchID" DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q0.sql

@@ -0,0 +1 @@
+SELECT COUNT(*) FROM hits;

benchmarks/queries/clickbench/queries/q1.sql

@@ -0,0 +1 @@
+SELECT COUNT(*) FROM hits WHERE "AdvEngineID" <> 0;

benchmarks/queries/clickbench/queries/q10.sql

@@ -0,0 +1 @@
+SELECT "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhoneModel" ORDER BY u DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q11.sql

@@ -0,0 +1 @@
+SELECT "MobilePhone", "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhone", "MobilePhoneModel" ORDER BY u DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q12.sql

@@ -0,0 +1 @@
+SELECT "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q13.sql

@@ -0,0 +1 @@
+SELECT "SearchPhrase", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY u DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q14.sql

@@ -0,0 +1 @@
+SELECT "SearchEngineID", "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "SearchPhrase" ORDER BY c DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q15.sql

@@ -0,0 +1 @@
+SELECT "UserID", COUNT(*) FROM hits GROUP BY "UserID" ORDER BY COUNT(*) DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q16.sql

@@ -0,0 +1 @@
+SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q17.sql

@@ -0,0 +1 @@
+SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" LIMIT 10;

benchmarks/queries/clickbench/queries/q18.sql

@@ -0,0 +1 @@
+SELECT "UserID", extract(minute FROM to_timestamp_seconds("EventTime")) AS m, "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", m, "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q19.sql

@@ -0,0 +1 @@
+SELECT "UserID" FROM hits WHERE "UserID" = 435090932899640449;

benchmarks/queries/clickbench/queries/q2.sql

@@ -0,0 +1 @@
+SELECT SUM("AdvEngineID"), COUNT(*), AVG("ResolutionWidth") FROM hits;

benchmarks/queries/clickbench/queries/q20.sql

@@ -0,0 +1 @@
+SELECT COUNT(*) FROM hits WHERE "URL" LIKE '%google%';

benchmarks/queries/clickbench/queries/q21.sql

@@ -0,0 +1 @@
+SELECT "SearchPhrase", MIN("URL"), COUNT(*) AS c FROM hits WHERE "URL" LIKE '%google%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q22.sql

@@ -0,0 +1 @@
+SELECT "SearchPhrase", MIN("URL"), MIN("Title"), COUNT(*) AS c, COUNT(DISTINCT "UserID") FROM hits WHERE "Title" LIKE '%Google%' AND "URL" NOT LIKE '%.google.%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;

benchmarks/queries/clickbench/queries/q23.sql

@@ -0,0 +1 @@
+SELECT * FROM hits WHERE "URL" LIKE '%google%' ORDER BY "EventTime" LIMIT 10;

benchmarks/queries/clickbench/queries/q24.sql

@@ -0,0 +1 @@
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime" LIMIT 10;

benchmarks/queries/clickbench/queries/q25.sql

@@ -0,0 +1 @@
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;

benchmarks/queries/clickbench/queries/q26.sql

@@ -0,0 +1 @@
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime", "SearchPhrase" LIMIT 10;

benchmarks/queries/clickbench/queries/q27.sql

@@ -0,0 +1 @@
+SELECT "CounterID", AVG(length("URL")) AS l, COUNT(*) AS c FROM hits WHERE "URL" <> '' GROUP BY "CounterID" HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;

benchmarks/queries/clickbench/queries/q28.sql

@@ -0,0 +1 @@
+SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length("Referer")) AS l, COUNT(*) AS c, MIN("Referer") FROM hits WHERE "Referer" <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;