add datafusion

datafusion/README.md

@@ -0,0 +1,27 @@
+# Datafusion
+
+DataFusion is an extensible query execution framework, written in Rust, that uses Apache Arrow as its in-memory format. For more information, please check <https://arrow.apache.org/datafusion/user-guide/introduction.html>
+
+We use parquet file here and create an external table for it; and then do the queries.
+
+
+
+### to generate benchmark results:
+
+```bash
+bash benchmark.sh
+```
+
+
+### Know Issues:
+
+1. importing parquet by `datafusion-cli` doesn't support schema, need to add some casting in quries.sql (e.g. converting EventTime from Int to Timestamp via `to_timestamp_seconds`)
+2. importing parquet by `datafusion-cli` make column name column name case-sensitive, i change all column name in quries.sql to double quoted literal (e.g. `EventTime` -> `"EventTime"`)
+3. `comparing binary with utf-8` and `group by binary` don't work in mac, if you run these quries in mac, you'll get some errors for quries contain binary format apache/arrow-datafusion#3050
+
+
+### to generate full human readable results (for debugging)
+
+1. install datafusion-cli
+2. download the parquet ```wget --continue https://datasets.clickhouse.com/hits_compatible/hits.parquet```
+3. execute it ```datafusion-cli -f create.sh queries.sh``` or ```bash run2.sh```

datafusion/benchmark.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+
+# Install Rust
+curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs > rust-init.sh
+bash rust-init.sh -y
+source ~/.cargo/env
+
+
+# Install Dependencies
+sudo apt update -y
+sudo apt install gcc -y
+
+
+# Install Datafusion
+#cargo install --version 10.0.0 datafusion-cli
+
+# Install Datafusion Master Branch
+git clone https://github.com/apache/arrow-datafusion.git
+cd arrow-datafusion/datafusion-cli && cargo build --release
+export PATH="`pwd`/target/release:$PATH"
+cd ../..
+
+
+# Download benchmark target data
+wget --continue https://datasets.clickhouse.com/hits_compatible/hits.parquet
+
+
+# Run
+bash run.sh

datafusion/create.sql

@@ -0,0 +1,3 @@
+CREATE EXTERNAL TABLE hits
+STORED AS PARQUET
+LOCATION 'hits.parquet';

datafusion/queries.sql

@@ -0,0 +1,43 @@
+SELECT COUNT(*) FROM hits;
+SELECT COUNT(*) FROM hits WHERE "AdvEngineID" <> 0;
+SELECT SUM("AdvEngineID"), COUNT(*), AVG("ResolutionWidth") FROM hits;
+SELECT AVG("UserID") FROM hits;
+SELECT COUNT(DISTINCT "UserID") FROM hits;
+SELECT COUNT(DISTINCT "SearchPhrase") FROM hits;
+SELECT MIN("EventDate"::INT::DATE), MAX("EventDate"::INT::DATE) FROM hits;
+SELECT "AdvEngineID", COUNT(*) FROM hits WHERE "AdvEngineID" <> 0 GROUP BY "AdvEngineID" ORDER BY COUNT(*) DESC;
+SELECT "RegionID", COUNT(DISTINCT "UserID") AS u FROM hits GROUP BY "RegionID" ORDER BY u DESC LIMIT 10;
+SELECT "RegionID", SUM("AdvEngineID"), COUNT(*) AS c, AVG("ResolutionWidth"), COUNT(DISTINCT "UserID") FROM hits GROUP BY "RegionID" ORDER BY c DESC LIMIT 10;
+SELECT "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
+SELECT "MobilePhone", "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhone", "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
+SELECT "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT "SearchPhrase", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY u DESC LIMIT 10;
+SELECT "SearchEngineID", "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT "UserID", COUNT(*) FROM hits GROUP BY "UserID" ORDER BY COUNT(*) DESC LIMIT 10;
+SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
+SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" LIMIT 10;
+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;
+SELECT "UserID" FROM hits WHERE "UserID" = 435090932899640449;
+SELECT COUNT(*) FROM hits WHERE "URL" LIKE '%google%';
+SELECT "SearchPhrase", MIN("URL"), COUNT(*) AS c FROM hits WHERE "URL" LIKE '%google%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
+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;
+SELECT * FROM hits WHERE "URL" LIKE '%google%' ORDER BY to_timestamp_seconds("EventTime") LIMIT 10;
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY to_timestamp_seconds("EventTime") LIMIT 10;
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY to_timestamp_seconds("EventTime"), "SearchPhrase" LIMIT 10;
+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;
+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;
+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 hits;
+SELECT "SearchEngineID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "URL", COUNT(*) AS c FROM hits GROUP BY "URL" ORDER BY c DESC LIMIT 10;
+SELECT 1, "URL", COUNT(*) AS c FROM hits GROUP BY 1, "URL" ORDER BY c DESC LIMIT 10;
+SELECT "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3, COUNT(*) AS c FROM hits GROUP BY "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3 ORDER BY c DESC LIMIT 10;
+SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "URL" <> '' GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10;
+SELECT "Title", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "Title" <> '' GROUP BY "Title" ORDER BY PageViews DESC LIMIT 10;
+SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "IsLink" <> 0 AND "IsDownload" = 0 GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
+SELECT "TraficSourceID", "SearchEngineID", "AdvEngineID", CASE WHEN ("SearchEngineID" = 0 AND "AdvEngineID" = 0) THEN "Referer" ELSE '' END AS Src, "URL" AS Dst, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 GROUP BY "TraficSourceID", "SearchEngineID", "AdvEngineID", Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
+SELECT "URLHash", "EventDate"::INT::DATE, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "TraficSourceID" IN (-1, 6) AND "RefererHash" = 3594120000172545465 GROUP BY "URLHash", "EventDate"::INT::DATE ORDER BY PageViews DESC LIMIT 10 OFFSET 100;
+SELECT "WindowClientWidth", "WindowClientHeight", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "DontCountHits" = 0 AND "URLHash" = 2868770270353813622 GROUP BY "WindowClientWidth", "WindowClientHeight" ORDER BY PageViews DESC LIMIT 10 OFFSET 10000;
+SELECT DATE_TRUNC('minute', to_timestamp_seconds("EventTime")) AS M, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-14' AND "EventDate"::INT::DATE <= '2013-07-15' AND "IsRefresh" = 0 AND "DontCountHits" = 0 GROUP BY DATE_TRUNC('minute', to_timestamp_seconds("EventTime")) ORDER BY DATE_TRUNC('minute', M) LIMIT 10 OFFSET 1000;

datafusion/results/f16s_v2.json

@@ -0,0 +1,58 @@
+{
+    "system": "datafusion",
+    "date": "2022-08-10",
+    "machine": "f16s v2",
+    "cluster_size": 1,
+    "comment": "",
+
+    "tags": ["rust", "column-oriented", "embedded", "stateless"],
+
+    "load_time": 0,
+    "data_size": 14779976446,
+
+    "result": [
+[0.992, 0.567, 0.542],
+[0.468, 0.412, 0.424],
+[1.074, 0.996, 0.983],
+[0.951, 0.650, 0.636],
+[2.506, 2.397, 2.430],
+[4.972, 4.557, 4.570],
+[0.481, 0.508, 0.451],
+[0.459, 0.431, 0.442],
+[3.324, 3.073, 3.085],
+[5.578, 5.204, 5.212],
+[1.904, 1.635, 1.629],
+[2.438, 2.042, 2.122],
+[5.122, 4.989, 5.045],
+[7.142, 6.860, 6.853],
+[5.931, 5.540, 5.645],
+[4.288, 4.154, 4.186],
+[10.123, 9.914, 9.853],
+[8.098, 7.674, 7.705],
+[17.694, 16.997, 16.956],
+[0.734, 0.575, 0.584],
+[11.867, 10.749, 10.736],
+[15.467, 13.738, 13.599],
+[38.945, 35.948, 35.709],
+[114.322, 107.217, 107.070],
+[5.727, 5.125, 5.055],
+[7.367, 7.111, 7.042],
+[9.463, 9.048, 9.134],
+[12.088, 10.382, 10.508],
+[252.422, 254.793, 257.960],
+[2.262, 2.666, 2.655],
+[7.979, 7.210, 7.222],
+[9.422, 8.669, 8.609],
+[0.050, 0.049, 0.048],
+[21.977, 20.811, 20.672],
+[22.026, 20.822, 20.878],
+[4.580, 4.430, 4.469],
+[0.373, 0.330, 0.344],
+[0.311, 0.299, 0.280],
+[0.285, 0.259, 0.257],
+[0.691, 0.634, 0.624],
+[0.131, 0.116, 0.112],
+[0.122, 0.106, 0.108],
+[0.105, 0.095, 0.099]
+]
+}

datafusion/run.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+TRIES=3
+QUERY_NUM=1
+cat queries.sql | while read query; do
+    sync
+    echo 3 | sudo tee /proc/sys/vm/drop_caches >/dev/null
+
+	echo "$query" > /tmp/query.sql
+
+    echo -n "["
+    for i in $(seq 1 $TRIES); do
+		RES=$(datafusion-cli -f create.sql /tmp/query.sql 2>&1 | tail -n 1)
+		[[ "$(echo $RES | awk '{print $5$6}')" == "Querytook" ]] && \
+			echo -n "$(echo $RES | awk '{print $7}')" || \
+			echo -n "null"
+        [[ "$i" != $TRIES ]] && echo -n ", "
+
+		echo "${QUERY_NUM},${i},${RES}" >> result.csv
+    done
+    echo "],"
+
+    QUERY_NUM=$((QUERY_NUM + 1))
+done

datafusion/run2.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+QUERY_NUM=1
+cat queries.sql | while read query; do
+    sync
+    echo 3 | sudo tee /proc/sys/vm/drop_caches >/dev/null
+
+	echo "$query" > /tmp/query.sql
+
+	echo 
+	echo 
+	echo -----------------------------------------
+	echo 
+	echo $QUERY_NUM. "$query"
+	echo 
+	echo -----------------------------------------
+	echo 
+	echo 
+
+
+	datafusion-cli -f create.sql /tmp/query.sql
+
+    QUERY_NUM=$((QUERY_NUM + 1))
+done