Split clickbench query set into one file per query (apache#16476)

* Split clickbench query set into one file per query

* Fix queries-path value in bench.sh

Author: pepijnve

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.sql

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

benchmarks/queries/clickbench/extended/q0.sql

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

benchmarks/queries/clickbench/extended/q1.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/q2.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/q3.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/q4.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/q5.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;