Merge pull request #167 from ClickHouse/glaredb

alexey-milovidov · web-flow · commit 27b2caff7ea2 · 2024-02-05T19:33:48.000+01:00
GlareDB
diff --git a/README.md b/README.md
@@ -229,6 +229,7 @@ We also introduced the [Hardware Benchmark](https://benchmark.clickhouse.com/har
 - [x] Hydra
 - [ ] Impala
 - [ ] Hyper
+- [x] Umbra
 - [x] SQLite
 - [x] Redshift
 - [x] Redshift Serverless
@@ -253,7 +254,7 @@ We also introduced the [Hardware Benchmark](https://benchmark.clickhouse.com/har
 - [ ] ScyllaDB
 - [x] Elasticsearch
 - [ ] Apache Ignite
-- [ ] Motherduck
+- [x] Motherduck
 - [x] Infobright
 - [ ] Actian Vector
 - [ ] Manticore Search
@@ -275,11 +276,11 @@ We also introduced the [Hardware Benchmark](https://benchmark.clickhouse.com/har
 - [ ] Boilingdata
 - [x] Byteconity
 - [ ] DolphinDB
-- [ ] Oxla
+- [x] Oxla
 - [ ] Quickwit
 - [x] AlloyDB
 - [x] ParadeDB
-- [ ] GlareDB
+- [x] GlareDB
 - [ ] Seafowl
 - [ ] Sneller
 
diff --git a/glaredb/benchmark.sh b/glaredb/benchmark.sh
@@ -0,0 +1,20 @@
+#!/bin/bash
+
+# Install
+
+sudo apt-get install -y unzip
+curl https://glaredb.com/install.sh | sh
+
+wget https://clickhouse-public-datasets.s3.eu-central-1.amazonaws.com/hits_compatible/athena/hits.parquet
+
+cat queries.sql | while read query
+do
+    sync
+    echo 3 | sudo tee /proc/sys/vm/drop_caches
+
+    for i in $(seq 1 3); do
+        ./glaredb --timing --query "${query}"
+    done;
+done 2>&1 | tee log.txt
+
+cat log.txt | grep -oP 'Time: \d+\.\d+s|Error' | sed -r -e 's/Time: ([0-9]+\.[0-9]+)s/\1/; s/Error/null/' | awk '{ if (i % 3 == 0) { printf "[" }; printf $1; if (i % 3 != 2) { printf "," } else { print "]," }; ++i; }'
diff --git a/glaredb/queries.sql b/glaredb/queries.sql
@@ -0,0 +1,43 @@
+SELECT COUNT(*) FROM 'hits.parquet';
+SELECT COUNT(*) FROM 'hits.parquet' WHERE "AdvEngineID" <> 0;
+SELECT SUM("AdvEngineID"), COUNT(*), AVG("ResolutionWidth") FROM 'hits.parquet';
+SELECT AVG("UserID") FROM 'hits.parquet';
+SELECT COUNT(DISTINCT "UserID") FROM 'hits.parquet';
+SELECT COUNT(DISTINCT "SearchPhrase") FROM 'hits.parquet';
+SELECT MIN("EventDate"), MAX("EventDate") FROM 'hits.parquet';
+SELECT "AdvEngineID", COUNT(*) FROM 'hits.parquet' WHERE "AdvEngineID" <> 0 GROUP BY "AdvEngineID" ORDER BY COUNT(*) DESC;
+SELECT "RegionID", COUNT(DISTINCT "UserID") AS u FROM 'hits.parquet' GROUP BY "RegionID" ORDER BY u DESC LIMIT 10;
+SELECT "RegionID", SUM("AdvEngineID"), COUNT(*) AS c, AVG("ResolutionWidth"), COUNT(DISTINCT "UserID") FROM 'hits.parquet' GROUP BY "RegionID" ORDER BY c DESC LIMIT 10;
+SELECT "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM 'hits.parquet' WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
+SELECT "MobilePhone", "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM 'hits.parquet' WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhone", "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
+SELECT "SearchPhrase", COUNT(*) AS c FROM 'hits.parquet' WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT "SearchPhrase", COUNT(DISTINCT "UserID") AS u FROM 'hits.parquet' WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY u DESC LIMIT 10;
+SELECT "SearchEngineID", "SearchPhrase", COUNT(*) AS c FROM 'hits.parquet' WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT "UserID", COUNT(*) FROM 'hits.parquet' GROUP BY "UserID" ORDER BY COUNT(*) DESC LIMIT 10;
+SELECT "UserID", "SearchPhrase", COUNT(*) FROM 'hits.parquet' GROUP BY "UserID", "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
+SELECT "UserID", "SearchPhrase", COUNT(*) FROM 'hits.parquet' GROUP BY "UserID", "SearchPhrase" LIMIT 10;
+SELECT "UserID", extract(minute FROM arrow_cast("EventTime", 'Timestamp(Second, None)')) AS m, "SearchPhrase", COUNT(*) FROM 'hits.parquet' GROUP BY "UserID", m, "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
+SELECT "UserID" FROM 'hits.parquet' WHERE "UserID" = 435090932899640449;
+SELECT COUNT(*) FROM 'hits.parquet' WHERE "URL" LIKE '%google%';
+SELECT "SearchPhrase", MIN("URL"), COUNT(*) AS c FROM 'hits.parquet' 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.parquet' WHERE "Title" LIKE '%Google%' AND "URL" NOT LIKE '%.google.%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT * FROM 'hits.parquet' WHERE "URL" LIKE '%google%' ORDER BY "EventTime" LIMIT 10;
+SELECT "SearchPhrase" FROM 'hits.parquet' WHERE "SearchPhrase" <> '' ORDER BY "EventTime" LIMIT 10;
+SELECT "SearchPhrase" FROM 'hits.parquet' WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;
+SELECT "SearchPhrase" FROM 'hits.parquet' WHERE "SearchPhrase" <> '' ORDER BY "EventTime", "SearchPhrase" LIMIT 10;
+SELECT "CounterID", AVG(length("URL")) AS l, COUNT(*) AS c FROM 'hits.parquet' 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.parquet' 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.parquet';
+SELECT "SearchEngineID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM 'hits.parquet' WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM 'hits.parquet' WHERE "SearchPhrase" <> '' GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM 'hits.parquet' GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "URL", COUNT(*) AS c FROM 'hits.parquet' GROUP BY "URL" ORDER BY c DESC LIMIT 10;
+SELECT 1, "URL", COUNT(*) AS c FROM 'hits.parquet' GROUP BY 1, "URL" ORDER BY c DESC LIMIT 10;
+SELECT "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3, COUNT(*) AS c FROM 'hits.parquet' GROUP BY "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3 ORDER BY c DESC LIMIT 10;
+SELECT "URL", COUNT(*) AS "PageViews" FROM 'hits.parquet' 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;
+SELECT "Title", COUNT(*) AS "PageViews" FROM 'hits.parquet' 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;
+SELECT "URL", COUNT(*) AS "PageViews" FROM 'hits.parquet' 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;
+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.parquet' 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;
+SELECT "URLHash", "EventDate", COUNT(*) AS "PageViews" FROM 'hits.parquet' 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;
+SELECT "WindowClientWidth", "WindowClientHeight", COUNT(*) AS "PageViews" FROM 'hits.parquet' 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;
+SELECT DATE_TRUNC('minute', arrow_cast("EventTime", 'Timestamp(Second, None)')) AS M, COUNT(*) AS "PageViews" FROM 'hits.parquet' WHERE "CounterID" = 62 AND "EventDate" >= '2013-07-14' AND "EventDate" <= '2013-07-15' AND "IsRefresh" = 0 AND "DontCountHits" = 0 GROUP BY DATE_TRUNC('minute', arrow_cast("EventTime", 'Timestamp(Second, None)')) ORDER BY M LIMIT 10 OFFSET 1000;
diff --git a/glaredb/results/c6a.4xlarge.json b/glaredb/results/c6a.4xlarge.json
@@ -0,0 +1,55 @@
+{
+    "system": "GlareDB",
+    "date": "2024-02-02",
+    "machine": "c6a.4xlarge, 500gb gp2",
+    "cluster_size": 1,
+    "comment": "",
+    "tags": ["Rust", "serverless"],
+    "load_time": 0,
+    "data_size": 14779976446,
+    "result": [
+[0.221,0.070,0.069],
+[0.509,0.425,0.424],
+[0.569,0.462,0.466],
+[0.787,0.483,0.470],
+[1.339,1.220,1.200],
+[1.800,1.644,1.649],
+[0.490,0.418,0.410],
+[0.509,0.423,0.423],
+[2.009,1.880,1.920],
+[3.383,3.134,3.147],
+[0.950,0.695,0.702],
+[0.891,0.743,0.721],
+[1.787,1.646,1.654],
+[4.032,3.007,2.974],
+[1.911,1.746,1.762],
+[1.538,1.321,1.360],
+[3.746,3.335,3.327],
+[3.611,3.064,2.993],
+[7.835,6.293,6.414],
+[0.882,0.469,0.470],
+[9.903,1.943,1.947],
+[11.653,2.182,2.172],
+[22.503,4.410,4.416],
+[56.481,11.754,11.769],
+[3.039,0.925,0.917],
+[1.132,0.854,0.855],
+[2.939,0.991,0.973],
+[9.958,2.688,2.695],
+[9.431,5.639,5.614],
+[1.027,0.872,0.814],
+[2.611,1.508,1.497],
+[6.177,1.887,1.960],
+[9.675,9.095,8.891],
+[12.268,7.139,7.063],
+[12.675,7.661,7.671],
+[2.418,2.250,2.210],
+[9.998,2.095,2.066],
+[9.273,2.782,2.722],
+[10.015,2.085,2.079],
+[18.876,3.284,3.317],
+[2.963,0.939,0.917],
+[2.165,0.973,0.936],
+[1.380,0.901,0.864]
+    ]
+}
diff --git a/glaredb/results/c6a.metal.json b/glaredb/results/c6a.metal.json
@@ -0,0 +1,55 @@
+{
+    "system": "GlareDB",
+    "date": "2024-02-02",
+    "machine": "c6a.metal, 500gb gp2",
+    "cluster_size": 1,
+    "comment": "",
+    "tags": ["Rust", "serverless"],
+    "load_time": 0,
+    "data_size": 14779976446,
+    "result": [
+[0.213,0.070,0.071],
+[4.066,4.060,3.978],
+[3.994,3.812,4.046],
+[4.287,4.122,4.218],
+[6.016,6.482,6.210],
+[5.260,5.308,5.242],
+[3.968,4.054,4.054],
+[4.013,3.961,4.045],
+[7.124,6.742,6.934],
+[5.632,5.625,5.433],
+[4.546,4.463,4.577],
+[4.540,4.616,4.675],
+[5.438,5.302,5.243],
+[6.286,6.115,6.202],
+[5.460,5.259,5.531],
+[6.064,6.451,6.458],
+[7.461,7.655,7.337],
+[6.920,7.538,7.684],
+[11.688,11.362,11.378],
+[4.264,4.085,4.092],
+[12.973,4.585,4.449],
+[14.739,4.562,4.676],
+[25.511,5.088,5.323],
+[59.374,8.895,8.542],
+[6.076,4.352,4.324],
+[4.305,4.233,4.334],
+[6.083,4.450,4.398],
+[12.983,4.812,4.721],
+[11.651,5.245,5.281],
+[4.275,4.214,4.175],
+[5.561,5.378,5.630],
+[9.220,5.983,6.112],
+[17.147,15.575,15.934],
+[14.016,9.356,8.974],
+[14.274,9.454,9.371],
+[6.675,6.473,6.510],
+[13.348,4.684,4.587],
+[12.473,4.655,4.580],
+[13.153,4.471,4.637],
+[21.939,4.932,4.951],
+[6.033,4.320,4.282],
+[5.181,4.242,4.286],
+[4.503,4.312,4.215]
+    ]
+}
