Merge pull request #301 from pmcgleenon/datafusion-44

rschu1ze · web-flow · commit 1f734ba087ac · 2025-02-07T11:04:59.000+01:00
diff --git a/datafusion/README.md b/datafusion/README.md
@@ -20,7 +20,7 @@ The benchmark should be completed in under an hour. On-demand pricing is $0.6 pe
 1. `cd ClickBench/datafusion`
 1. `vi benchmark.sh` and modify following line to target Datafusion version
     ```
-    git checkout 43.0.0
+    git checkout 44.0.0
     ```
 1. `bash benchmark.sh`
 
diff --git a/datafusion/benchmark.sh b/datafusion/benchmark.sh
@@ -14,7 +14,7 @@ sudo yum install gcc -y
 # Install DataFusion main branch
 git clone https://github.com/apache/arrow-datafusion.git
 cd arrow-datafusion/datafusion-cli
-git checkout 43.0.0
+git checkout 44.0.0
 CARGO_PROFILE_RELEASE_LTO=true RUSTFLAGS="-C codegen-units=1" cargo build --release
 export PATH="`pwd`/target/release:$PATH"
 cd ../..
diff --git a/datafusion/queries.sql b/datafusion/queries.sql
@@ -26,7 +26,7 @@ SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY to_timestamp
 SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;
 SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY to_timestamp_seconds("EventTime"), "SearchPhrase" LIMIT 10;
 SELECT "CounterID", AVG(length("URL")) AS l, COUNT(*) AS c FROM hits WHERE "URL" <> '' GROUP BY "CounterID" HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
-SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\.)?([^/]+)/.*$', '\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 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;
diff --git a/datafusion/results/partitioned.json b/datafusion/results/partitioned.json
@@ -3,56 +3,56 @@
     "date": "2024-11-15",
     "machine": "c6a.4xlarge, 500gb gp2",
     "cluster_size": 1,
-    "comment": "v43.0.0 (88f58bf)",
+    "comment": "v44.0.0 (3cc3fca)",
 
     "tags": ["Rust", "column-oriented", "embedded", "stateless"],
 
     "load_time": 0,
     "data_size": 14779976446,
 
     "result": [
-[0.051, 0.019, 0.019],
-[0.091, 0.035, 0.035],
-[0.189, 0.085, 0.088],
-[0.383, 0.081, 0.077],
-[1.071, 0.811, 0.803],
-[0.944, 0.801, 0.805],
-[0.078, 0.030, 0.030],
-[0.103, 0.037, 0.037],
-[1.313, 1.205, 1.201],
-[1.357, 1.034, 1.025],
-[0.511, 0.255, 0.253],
-[0.634, 0.295, 0.301],
-[1.016, 0.856, 0.879],
-[2.615, 1.421, 1.374],
-[1.131, 0.931, 0.918],
-[1.051, 0.952, 0.958],
-[2.672, 2.031, 2.066],
-[2.592, 1.879, 1.887],
-[5.549, 4.226, 4.335],
-[0.254, 0.078, 0.075],
-[9.967, 1.098, 1.092],
-[11.248, 1.329, 1.327],
-[21.868, 2.820, 2.818],
-[55.458, 10.286, 10.609],
-[2.678, 0.488, 0.486],
-[0.802, 0.352, 0.354],
-[2.672, 0.507, 0.498],
-[9.614, 1.513, 1.507],
-[8.368, 3.394, 3.521],
-[0.535, 0.418, 0.439],
-[2.362, 0.854, 0.861],
-[5.957, 0.910, 0.914],
-[4.780, 3.806, 3.871],
-[10.168, 3.654, 3.586],
-[10.090, 3.645, 3.546],
-[1.775, 1.644, 1.660],
-[0.364, 0.199, 0.183],
-[0.183, 0.078, 0.075],
-[0.290, 0.128, 0.123],
-[0.619, 0.376, 0.376],
-[0.148, 0.053, 0.044],
-[0.142, 0.042, 0.042],
-[0.155, 0.065, 0.053]
+[0.061, 0.018, 0.018],
+[0.108, 0.036, 0.033],
+[0.188, 0.084, 0.085],
+[2.097, 0.078, 0.079],
+[2.648, 0.830, 0.817],
+[2.707, 0.802, 0.803],
+[0.081, 0.030, 0.029],
+[0.102, 0.037, 0.036],
+[2.493, 0.899, 0.910],
+[3.445, 1.039, 1.043],
+[2.078, 0.259, 0.244],
+[2.470, 0.295, 0.270],
+[2.916, 0.850, 0.858],
+[5.908, 1.347, 1.340],
+[2.918, 0.802, 0.810],
+[2.081, 0.961, 0.973],
+[5.740, 1.737, 1.739],
+[5.654, 1.632, 1.643],
+[10.074, 3.593, 3.575],
+[1.433, 0.072, 0.073],
+[20.760, 1.050, 1.078],
+[23.608, 1.293, 1.335],
+[45.123, 2.632, 2.540],
+[111.820, 9.779, 10.107],
+[6.605, 0.441, 0.437],
+[2.607, 0.355, 0.351],
+[6.611, 0.506, 0.516],
+[20.174, 1.486, 1.484],
+[17.954, 9.277, 9.326],
+[0.499, 0.416, 0.417],
+[5.743, 0.767, 0.780],
+[13.208, 0.924, 0.906],
+[10.116, 3.444, 3.523],
+[20.379, 3.615, 3.595],
+[20.457, 3.616, 3.621],
+[1.437, 1.192, 1.204],
+[0.327, 0.183, 0.182],
+[0.172, 0.076, 0.074],
+[0.250, 0.114, 0.111],
+[0.569, 0.338, 0.337],
+[0.154, 0.043, 0.045],
+[0.130, 0.040, 0.040],
+[0.137, 0.052, 0.053]
 ]
 }
diff --git a/datafusion/results/single.json b/datafusion/results/single.json
@@ -3,56 +3,56 @@
     "date": "2024-11-15",
     "machine": "c6a.4xlarge, 500gb gp2",
     "cluster_size": 1,
-    "comment": "v43.0.0 (88f58bf)",
+    "comment": "v44.0.0 (3cc3fca)",
 
     "tags": ["Rust", "column-oriented", "embedded", "stateless"],
 
     "load_time": 0,
     "data_size": 14779976446,
 
     "result": [
-[0.093, 0.055, 0.056],
-[0.138, 0.070, 0.070],
-[0.206, 0.120, 0.117],
-[0.346, 0.118, 0.114],
-[0.979, 0.867, 0.871],
-[1.030, 0.902, 0.904],
-[0.125, 0.064, 0.077],
-[0.143, 0.083, 0.078],
-[1.304, 1.169, 1.240],
-[1.533, 1.104, 1.100],
-[0.475, 0.272, 0.278],
-[0.562, 0.309, 0.315],
-[1.165, 0.931, 0.965],
-[2.643, 1.402, 1.490],
-[1.143, 0.997, 0.983],
-[1.106, 0.991, 0.993],
-[2.727, 2.161, 2.098],
-[2.578, 1.954, 1.947],
-[5.530, 4.311, 4.253],
-[0.319, 0.105, 0.107],
-[9.732, 1.155, 1.149],
-[11.337, 1.468, 1.407],
-[22.055, 3.678, 3.663],
-[55.942, 10.017, 10.014],
-[2.561, 0.557, 0.577],
-[0.809, 0.510, 0.519],
-[2.579, 0.634, 0.620],
-[9.630, 1.618, 1.655],
-[8.645, 3.565, 3.699],
-[0.584, 0.493, 0.485],
-[2.285, 0.978, 0.991],
-[5.690, 1.046, 1.006],
-[4.468, 3.833, 3.885],
-[10.123, 3.663, 3.654],
-[10.114, 3.672, 3.685],
-[1.743, 1.597, 1.659],
-[0.389, 0.242, 0.230],
-[0.266, 0.155, 0.170],
-[0.369, 0.161, 0.180],
-[0.659, 0.446, 0.416],
-[0.190, 0.084, 0.085],
-[0.177, 0.078, 0.079],
-[0.164, 0.103, 0.088]
+[0.094, 0.065, 0.057],
+[0.143, 0.070, 0.071],
+[0.220, 0.120, 0.114],
+[1.794, 0.118, 0.117],
+[2.429, 0.883, 0.860],
+[2.616, 0.907, 0.906],
+[0.119, 0.077, 0.065],
+[0.136, 0.082, 0.083],
+[2.404, 0.953, 0.932],
+[3.222, 1.093, 1.099],
+[1.920, 0.278, 0.268],
+[2.293, 0.312, 0.310],
+[2.759, 0.932, 0.939],
+[5.665, 1.363, 1.361],
+[2.813, 0.895, 0.886],
+[1.992, 0.982, 1.004],
+[5.626, 1.856, 1.870],
+[5.548, 1.707, 1.715],
+[9.787, 3.610, 3.623],
+[1.394, 0.109, 0.107],
+[20.622, 1.145, 1.168],
+[23.507, 1.449, 1.522],
+[45.338, 3.505, 3.571],
+[112.371, 10.242, 10.180],
+[6.294, 0.574, 0.555],
+[2.560, 0.509, 0.522],
+[6.269, 0.628, 0.646],
+[20.105, 1.590, 1.599],
+[19.270, 10.050, 9.949],
+[0.530, 0.458, 0.445],
+[5.463, 0.914, 0.895],
+[12.601, 1.037, 0.996],
+[9.671, 3.516, 3.500],
+[20.402, 3.748, 3.752],
+[20.388, 3.791, 3.799],
+[1.392, 1.247, 1.227],
+[0.389, 0.231, 0.229],
+[0.237, 0.154, 0.160],
+[0.312, 0.164, 0.160],
+[0.600, 0.418, 0.394],
+[0.181, 0.083, 0.081],
+[0.163, 0.077, 0.080],
+[0.182, 0.087, 0.121]
 ]
 }
