bench: add a ClickBench extended query for a grouped COUNT(DISTINCT) over a string

benchmarks/queries/clickbench/README.md

@@ -261,6 +261,44 @@ WHERE "URL" < 'zzzz';
 ```
 
 
+### Q14: Grouped `COUNT(DISTINCT <string>)` beside a non-distinct `COUNT(*)`
+
+**Question**: "For the top 10 search phrases by hit count, how many distinct
+mobile phone models were used?"
+
+**Important Query Properties**: A single `COUNT(DISTINCT)` over a high
+cardinality string, next to a non-distinct `COUNT(*)`, grouped by a high
+cardinality string.
+
+`COUNT(DISTINCT)` has a specialized `GroupsAccumulator` for the integer types
+and for no other type. Every other type falls back to
+`GroupsAccumulatorAdapter`, which holds one boxed `Accumulator`, and therefore
+one hash table, for each group. The cost of that fallback is per group, so it is
+the group cardinality that decides how much it costs.
+
+Extended Q2 above is the only other query that puts a `COUNT(DISTINCT)` on a
+non-integer column, and it groups by `BrowserCountry`. This query groups by
+`SearchPhrase` instead, which has far more distinct values, so it exercises the
+adapter where its cost actually scales.
+
+The shape is also the one `SingleDistinctToGroupBy` reasons about. That rule
+rewrites a lone distinct aggregate into a two phase group by, which is what
+keeps it off the adapter. Standard Q8, Q10, Q11 and Q13 are already rewritten
+because their distinct aggregate stands alone, and Q9 is not because it carries
+an `AVG`. Q22 is the only standard query that pairs a lone distinct aggregate
+with a non-distinct count, and its distinct argument is an `Int64`, which has a
+specialized accumulator and never reaches the adapter. So no query in either
+suite covers a lone `COUNT(DISTINCT <string>)` next to a non-distinct count.
+
+```sql
+SELECT "SearchPhrase", COUNT(*) AS c, COUNT(DISTINCT "MobilePhoneModel") AS models
+FROM hits
+WHERE "SearchPhrase" <> ''
+GROUP BY "SearchPhrase"
+ORDER BY c DESC
+LIMIT 10;
+```
+
 
 
 ## Data Notes

benchmarks/queries/clickbench/extended/q14.sql

@@ -0,0 +1,9 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
+-- A grouped COUNT(DISTINCT <string>) beside a non-distinct COUNT(*). No query in
+-- the standard suite has this shape: q22 is the only one that pairs a lone
+-- distinct aggregate with a non-distinct count, and its distinct argument is an
+-- Int64, which has a specialized GroupsAccumulator. A string argument has none,
+-- so one boxed Accumulator, and one hash table, is built for every group.
+SELECT "SearchPhrase", COUNT(*) AS c, COUNT(DISTINCT "MobilePhoneModel") AS models FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;

benchmarks/sql_benchmarks/clickbench_extended/benchmarks/q14.benchmark

@@ -0,0 +1,22 @@
+name Q14
+group clickbench_extended
+subgroup ${CLICKBENCH_TYPE:-single}
+
+init sql_benchmarks/clickbench/init/set_config.sql
+
+load sql_benchmarks/clickbench/init/load-${CLICKBENCH_TYPE:-single}.sql
+
+assert I
+SELECT COUNT(*) > 0 from hits;
+----
+true
+
+run
+SELECT "SearchPhrase", COUNT(*) AS c, COUNT(DISTINCT "MobilePhoneModel") AS models
+FROM hits
+WHERE "SearchPhrase" <> ''
+GROUP BY "SearchPhrase"
+ORDER BY c DESC
+LIMIT 10;
+
+result sql_benchmarks/clickbench_extended/results/q14.csv

datafusion/sqllogictest/test_files/clickbench_extended.slt

@@ -61,6 +61,76 @@ SELECT COUNT(*) AS ShareCount FROM hits WHERE "IsMobile" = 1 AND "MobilePhoneMod
 ----
 0
 
+query IIII
+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;
+----
+9110818468285196899 0 0 0
+8924809397503602651 0 0 0
+8740403056911509777 0 0 0
+8156744413230856864 0 0 0
+8120543446287442873 0 0 0
+6864353419233967042 0 0 0
+6635790769678439148 0 0 0
+6308646140879811077 0 0 0
+5206346422301499756 0 0 0
+4894690465724379622 0 0 0
+
+query III??
+SELECT "RegionID", "UserAgent", "OS", AVG(to_timestamp("ResponseEndTiming")-to_timestamp("ResponseStartTiming")) as avg_response_time, AVG(to_timestamp("ResponseEndTiming")-to_timestamp("ConnectTiming")) as avg_latency FROM hits GROUP BY "RegionID", "UserAgent", "OS" ORDER BY avg_latency DESC limit 10;
+----
+229 3 44 0 days 0 hours 0 mins 0.000000000 secs 0 days 0 hours 0 mins 0.000000000 secs
+197 7 39 0 days 0 hours 0 mins 0.000000000 secs 0 days 0 hours 0 mins 0.000000000 secs
+839 3 2 0 days 0 hours 0 mins 0.000000000 secs 0 days 0 hours 0 mins 0.000000000 secs
+839 0 0 0 days 0 hours 0 mins 0.000000000 secs 0 days 0 hours 0 mins 0.000000000 secs
+39 7 2 0 days 0 hours 0 mins 0.000000000 secs 0 days 0 hours 0 mins 0.000000000 secs
+
+query I
+SELECT MAX(len) FROM (
+    SELECT LENGTH(FIRST_VALUE("URL" ORDER BY "EventTime")) as len
+    FROM hits
+    GROUP BY "UserID"
+);
+----
+72
+
+query I
+SELECT MAX(len) FROM (
+    SELECT LENGTH(FIRST_VALUE("URL" ORDER BY "EventTime")) as len
+    FROM hits
+    GROUP BY "OS"
+);
+----
+57
+
+query I
+SELECT MAX(fv) FROM (
+    SELECT FIRST_VALUE("WatchID" ORDER BY "EventTime") as fv
+    FROM hits
+    GROUP BY "UserID"
+);
+----
+9110818468285196899
+
+query I
+SELECT MAX(fv) FROM (
+    SELECT FIRST_VALUE("WatchID" ORDER BY "EventTime") as fv
+    FROM hits
+    GROUP BY "OS"
+);
+----
+9110818468285196899
+
+query I
+SELECT SUM("CounterID") AS counter_id_sum
+FROM hits
+WHERE "URL" < 'zzzz';
+----
+173
+
+query TII
+SELECT "SearchPhrase", COUNT(*) AS c, COUNT(DISTINCT "MobilePhoneModel") AS models FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
+----
+
 
 statement ok
 drop table hits;