Skip to content

Commit bb40359

Browse files
AdamGSAdamGS
committed
Add benchmarks for querying Vortex files with datafusion
1 parent 05d1bdd commit bb40359

File tree

5 files changed

+226
-0
lines changed

5 files changed

+226
-0
lines changed

‎datafusion-vortex/benchmark.sh‎

Lines changed: 32 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,32 @@
1+
#!/bin/bash
2+
3+
set -euo pipefail
4+
5+
# Install Rust
6+
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs > rust-init.sh
7+
bash rust-init.sh -y
8+
source ~/.cargo/env
9+
10+
# Install Dependencies
11+
sudo apt-get update
12+
sudo apt-get install --yes gcc jq build-essential
13+
14+
# Install Vortex from latest release main branch
15+
git clone https://github.com/spiraldb/vortex.git
16+
cd vortex
17+
git checkout 0.29.0
18+
git submodule update --init
19+
# We build a release version of the benchmarking utility using mimalloc, just like the datafusion-cli
20+
CARGO_PROFILE_RELEASE_LTO=true cargo build --release --bin clickbench --package bench-vortex --features mimalloc
21+
export PATH="`pwd`/target/release:$PATH"
22+
cd ..
23+
24+
# Vortex's benchmarking utility generates appropriate Vortex files by itself, so we just run it to make sure they exist before we start measuring.
25+
# This will download parquet files (with time and string columns already converted to the logically correct datatype) and generate Vortex files from them.
26+
clickbench -i 1 --flavor single --formats vortex --display-format gh-json -q 0 --hide-progress-bar --hide-metrics
27+
clickbench -i 1 --flavor partitioned --formats vortex --display-format gh-json -q 0 --hide-progress-bar --hide-metrics
28+
29+
# Run benchmarks for single parquet and partitioned, our CLI generates the relevant vortex files.
30+
./run.sh single
31+
./run.sh partitioned
32+

‎datafusion-vortex/queries.sql‎

Lines changed: 43 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,43 @@
1+
SELECT COUNT(*) FROM hits;
2+
SELECT COUNT(*) FROM hits WHERE "AdvEngineID" <> 0;
3+
SELECT SUM("AdvEngineID"), COUNT(*), AVG("ResolutionWidth") FROM hits;
4+
SELECT AVG("UserID") FROM hits;
5+
SELECT COUNT(DISTINCT "UserID") FROM hits;
6+
SELECT COUNT(DISTINCT "SearchPhrase") FROM hits;
7+
SELECT MIN("EventDate"), MAX("EventDate") FROM hits;
8+
SELECT "AdvEngineID", COUNT(*) FROM hits WHERE "AdvEngineID" <> 0 GROUP BY "AdvEngineID" ORDER BY COUNT(*) DESC;
9+
SELECT "RegionID", COUNT(DISTINCT "UserID") AS u FROM hits GROUP BY "RegionID" ORDER BY u DESC LIMIT 10;
10+
SELECT "RegionID", SUM("AdvEngineID"), COUNT(*) AS c, AVG("ResolutionWidth"), COUNT(DISTINCT "UserID") FROM hits GROUP BY "RegionID" ORDER BY c DESC LIMIT 10;
11+
SELECT "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
12+
SELECT "MobilePhone", "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhone", "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
13+
SELECT "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
14+
SELECT "SearchPhrase", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY u DESC LIMIT 10;
15+
SELECT "SearchEngineID", "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "SearchPhrase" ORDER BY c DESC LIMIT 10;
16+
SELECT "UserID", COUNT(*) FROM hits GROUP BY "UserID" ORDER BY COUNT(*) DESC LIMIT 10;
17+
SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
18+
SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" LIMIT 10;
19+
SELECT "UserID", extract(minute FROM "EventTime") AS m, "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", m, "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
20+
SELECT "UserID" FROM hits WHERE "UserID" = 435090932899640449;
21+
SELECT COUNT(*) FROM hits WHERE "URL" LIKE '%google%';
22+
SELECT "SearchPhrase", MIN("URL"), COUNT(*) AS c FROM hits WHERE "URL" LIKE '%google%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
23+
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;
24+
SELECT * FROM hits WHERE "URL" LIKE '%google%' ORDER BY "EventTime" LIMIT 10;
25+
SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime" LIMIT 10;
26+
SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;
27+
SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime", "SearchPhrase" LIMIT 10;
28+
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;
29+
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;
30+
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;
31+
SELECT "SearchEngineID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "ClientIP" ORDER BY c DESC LIMIT 10;
32+
SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
33+
SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
34+
SELECT "URL", COUNT(*) AS c FROM hits GROUP BY "URL" ORDER BY c DESC LIMIT 10;
35+
SELECT 1, "URL", COUNT(*) AS c FROM hits GROUP BY 1, "URL" ORDER BY c DESC LIMIT 10;
36+
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;
37+
SELECT "URL", COUNT(*) AS PageViews FROM hits 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;
38+
SELECT "Title", COUNT(*) AS PageViews FROM hits 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;
39+
SELECT "URL", COUNT(*) AS PageViews FROM hits 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;
40+
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" >= '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;
41+
SELECT "URLHash", "EventDate", COUNT(*) AS PageViews FROM hits 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;
42+
SELECT "WindowClientWidth", "WindowClientHeight", COUNT(*) AS PageViews FROM hits 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;
43+
SELECT DATE_TRUNC('minute', "EventTime") AS M, COUNT(*) AS PageViews FROM hits 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', M) LIMIT 10 OFFSET 1000;

‎datafusion-vortex/results/partitioned.json‎

Lines changed: 55 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,55 @@
1+
{
2+
"system": "DataFusion (Vortex, partitioned)",
3+
"date": "2024-04-17",
4+
"machine": "c6a.4xlarge, 500gb gp2",
5+
"cluster_size": 1,
6+
"comment": "v46.0.0 (d5ca830) - Vortex 0.28",
7+
"tags": ["Rust", "column-oriented", "embedded", "stateless"],
8+
"load_time": 0,
9+
"data_size": 17429875344,
10+
"result": [
11+
[0.177491197, 0.044042761, 0.048824664],
12+
[0.213918912, 0.063358027, 0.060162445],
13+
[0.255848768, 0.108019413, 0.108818054],
14+
[1.201872124, 0.173740826, 0.175351887],
15+
[1.535135874, 0.884620424, 0.860099844],
16+
[1.177808922, 0.846875606, 0.852574362],
17+
[0.176757403, 0.047089427, 0.047792455],
18+
[0.225963665, 0.067920302, 0.069724298],
19+
[1.990736817, 1.077070849, 1.058614396],
20+
[2.368446918, 1.062228045, 1.020586364],
21+
[1.314844508, 0.191394089, 0.190370773],
22+
[1.366022614, 0.216278299, 0.204868236],
23+
[1.197657245, 0.694905863, 0.705062024],
24+
[3.299013043, 1.050458222, 1.085212044],
25+
[1.315334181, 0.694763283, 0.675104878],
26+
[1.588654976, 1.02234713, 1.037625273],
27+
[3.476392408, 2.026396262, 2.038437003],
28+
[3.436743522, 1.983267876, 1.966019914],
29+
[4.659755321, 3.333448025, 3.414175515],
30+
[0.777088974, 0.100126367, 0.107444365],
31+
[12.9437387, 0.67743915, 0.688230577],
32+
[13.914818211, 0.775697794, 0.780429746],
33+
[19.652743008, 1.199705564, 1.182498892],
34+
[52.274787727, 2.489725982, 2.473551916],
35+
[1.986821249, 0.28269998, 0.267894261],
36+
[1.071196493, 0.26161125, 0.259879355],
37+
[1.991914647, 0.335307829, 0.331277926],
38+
[12.784304397, 1.275405337, 1.280569809],
39+
[11.328221409, 8.773489335, 8.764263094],
40+
[0.728454421, 0.518579239, 0.530639058],
41+
[2.762218054, 0.585901385, 0.589777204],
42+
[5.903817179, 0.664648184, 0.672947348],
43+
[4.619491042, 3.691738021, 3.739215804],
44+
[13.074133867, 3.560469652, 3.566455765],
45+
[13.06496281, 3.54441918, 3.558058879],
46+
[1.614394252, 1.428373048, 1.435121711],
47+
[0.287066525, 0.125555657, 0.117913742],
48+
[0.249696668, 0.084622219, 0.078693006],
49+
[0.234061207, 0.07962823, 0.082994446],
50+
[0.363667078, 0.184651542, 0.201712229],
51+
[0.236301835, 0.063851746, 0.065238932],
52+
[0.222270546, 0.060296695, 0.060399898],
53+
[0.235223316, 0.075434013, 0.077388943]
54+
]
55+
}

‎datafusion-vortex/results/single.json‎

Lines changed: 55 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,55 @@
1+
{
2+
"system": "DataFusion (Vortex, single)",
3+
"date": "2024-04-17",
4+
"machine": "c6a.4xlarge, 500gb gp2",
5+
"cluster_size": 1,
6+
"comment": "v46.0.0 (d5ca830) - Vortex 0.28",
7+
"tags": ["Rust", "column-oriented", "embedded", "stateless"],
8+
"load_time": 0,
9+
"data_size": 21179522704,
10+
"result": [
11+
[0.130124194, 0.009984336, 0.010210231],
12+
[0.188034009, 0.038723903, 0.036273],
13+
[0.437091422, 0.075902825, 0.075908366],
14+
[2.501938257, 0.175294094, 0.174636227],
15+
[2.90350982, 0.854802272, 0.863138485],
16+
[1.272336435, 0.833564188, 0.840789433],
17+
[0.143794935, 0.009995266, 0.010171331],
18+
[0.22275506, 0.04718635, 0.046232066],
19+
[3.719765231, 1.147393681, 1.144027025],
20+
[4.200954794, 1.039005684, 0.984171188],
21+
[2.602204759, 0.188200862, 0.187047802],
22+
[2.652878054, 0.19786146, 0.203732812],
23+
[1.349216446, 0.702125743, 0.70157893],
24+
[4.950455105, 1.136244618, 1.150069093],
25+
[1.565186382, 0.701503112, 0.704413156],
26+
[2.944228792, 1.026852221, 1.039050175],
27+
[5.209962041, 2.112387208, 2.116596341],
28+
[5.147733148, 2.021984301, 2.032144441],
29+
[7.17575736, 3.70162468, 3.713250538],
30+
[1.492772303, 0.087556792, 0.091827562],
31+
[13.713729218, 0.801951626, 0.782477047],
32+
[14.736063257, 0.923154529, 0.919882455],
33+
[15.600566575, 1.243586529, 1.275209121],
34+
[63.649268553, 3.016342428, 2.970124454],
35+
[2.162868607, 0.314535561, 0.304022162],
36+
[1.057531355, 0.55444319, 0.553066285],
37+
[2.178711003, 0.62035057, 0.599688023],
38+
[13.50135998, 1.344686243, 1.330203312],
39+
[10.885841057, 8.406163143, 8.361199302],
40+
[0.732421039, 0.457088488, 0.454738057],
41+
[3.809124114, 0.612400065, 0.592856774],
42+
[6.709282797, 0.66962844, 0.653058846],
43+
[5.07030328, 3.734638791, 3.779009154],
44+
[15.016241109, 3.783654953, 3.781978904],
45+
[14.987624638, 3.759600477, 3.776094661],
46+
[1.645574566, 1.440977185, 1.45292041],
47+
[0.262195322, 0.086342407, 0.090236117],
48+
[0.235458265, 0.06195437, 0.058508672],
49+
[0.234904931, 0.062424852, 0.061702414],
50+
[0.323033144, 0.143941305, 0.142706034],
51+
[0.251677952, 0.047208312, 0.047335245],
52+
[0.238001341, 0.051719968, 0.045787545],
53+
[0.237351073, 0.044735499, 0.043422255]
54+
]
55+
}

‎datafusion-vortex/run.sh‎

Lines changed: 41 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,41 @@
1+
#!/bin/bash
2+
3+
# Check if an argument is provided
4+
if [ "$#" -ne 1 ]; then
5+
echo "Usage: $0 [single|partitioned]"
6+
exit 1
7+
fi
8+
9+
# Set the SQL file based on the argument
10+
if [ "$1" == "single" ] || [ "$1" == "partitioned" ]; then
11+
FLAVOR=$1
12+
echo "Running benchmark for $FLAVOR"
13+
else
14+
echo "Invalid argument. Please use 'single' or 'partitioned'."
15+
exit 1
16+
fi
17+
18+
# clear results file
19+
touch results.csv
20+
> results.csv
21+
22+
TRIES=3
23+
OS=$(uname)
24+
25+
for query_num in $(seq 0 42); do
26+
sync
27+
echo 3 | sudo tee /proc/sys/vm/drop_caches >/dev/null
28+
29+
echo -n "["
30+
for i in $(seq 1 $TRIES); do
31+
# Parse query results out of the JSON output, which reports the time in ns
32+
RES=`RUST_LOG=off clickbench -i 1 --flavor $FLAVOR --formats vortex --display-format gh-json --queries-file ./queries.sql -q $query_num --hide-progress-bar --hide-metrics | jq ".value / 1000000000"`
33+
34+
[[ $RES != "" ]] && \
35+
echo -n "$RES" || \
36+
echo -n "null"
37+
[[ "$i" != $TRIES ]] && echo -n ", "
38+
echo "${query_num},${i},${RES}" >> results.csv
39+
done
40+
echo "],"
41+
done

0 commit comments

Comments
 (0)