Merge pull request #127 from jychen7/datafusion-7108

Datafusion v28

Author: nickitat

datafusion/README.md

@@ -4,24 +4,18 @@ DataFusion is an extensible query execution framework, written in Rust, that use
 
 We use parquet file here and create an external table for it; and then do the queries.
 
+## Generate benchmark results
 
-### To solve
-
-q32 (line 33 in queries.sql) out of memory in my 32GB memory vm, it output null now since it's killed
-
-
-### to generate benchmark results
-
-The benchmark should be completed in under an hour. On-demand pricing is $0.6 per hour while spot pricing is only $0.2 per hour.
+The benchmark should be completed in under an hour. On-demand pricing is $0.6 per hour while spot pricing is only $0.2 to $0.3 per hour (us-east-2).
 
 1. manually start a AWS EC2 instance
     - `c6a.4xlarge`
     - Amazon Linux 2 AMI
     - Root 500GB gp2 SSD
     - no EBS optimized
     - no instance store
-1. wait for status check passed, then ssh to EC2
-1. `sudo yum update -y` and `sudo yum install gcc -y`
+1. wait for status check passed, then ssh to EC2 `ssh ec2-user@{ip}`
+1. `sudo yum update -y` and `sudo yum install gcc git -y`
 1. `git clone https://github.com/ClickHouse/ClickBench`
 1. `cd ClickBench/datafusion`
 1. `vi benchmark.sh` and modify following line to target Datafusion version
@@ -37,7 +31,7 @@ The benchmark should be completed in under an hour. On-demand pricing is $0.6 pe
 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)
+## Generate full human readable results (for debugging)
 
 1. install datafusion-cli
 2. download the parquet ```wget --no-verbose --continue https://datasets.clickhouse.com/hits_compatible/hits.parquet```

datafusion/results/single.json

@@ -1,58 +1,58 @@
 {
-    "system": "DataFusion (single parquet)",
-    "date": "2023-04-11",
+    "system": "DataFusion (Parquet, single)",
+    "date": "2023-07-29",
     "machine": "c6a.4xlarge, 500gb gp2",
     "cluster_size": 1,
-    "comment": "v22.0.0 (34c9bce)",
+    "comment": "v28.0.0 (51b4392)",
 
     "tags": ["Rust", "column-oriented", "embedded", "stateless"],
 
     "load_time": 0,
     "data_size": 14779976446,
 
     "result": [
-[2.646, 0.225, 0.226],
-[0.099, 0.079, 0.079],
-[0.173, 0.138, 0.139],
-[0.349, 0.126, 0.125],
-[2.790, 6.718, 2.717],
-[1.911, 1.753, 1.770],
-[0.090, 0.079, 0.076],
-[0.106, 0.081, 0.081],
-[3.032, 3.054, 3.675],
-[3.634, 3.564, 3.647],
-[0.508, 0.397, 0.402],
-[0.529, 0.424, 0.423],
-[2.100, 2.057, 2.040],
-[4.415, 4.169, 3.707],
-[2.198, 2.143, 2.080],
-[4.043, 3.516, 5.126],
-[5.065, 6.106, 8.249],
-[4.524, 4.420, 4.347],
-[10.981, 11.070, 11.203],
-[0.348, 0.112, 0.116],
-[9.968, 1.594, 1.619],
-[11.178, 1.917, 1.900],
-[22.120, 4.337, 4.352],
-[56.098, 12.159, 12.128],
-[2.581, 0.582, 0.583],
-[0.756, 0.478, 0.475],
-[2.556, 0.604, 0.570],
-[9.592, 2.525, 2.479],
-[9.067, 5.925, 5.927],
-[0.638, 0.563, 0.585],
-[3.278, 3.119, 2.940],
-[7.710, 4.401, 4.398],
-[null, null, null],
-[12.566, 8.695, 8.954],
-[12.827, 9.199, 11.148],
-[3.623, 3.514, 3.526],
-[0.506, 0.413, 0.406],
-[0.245, 0.217, 0.214],
-[0.249, 0.194, 0.194],
-[0.892, 0.772, 0.774],
-[0.175, 0.107, 0.106],
-[0.116, 0.095, 0.093],
-[0.142, 0.112, 0.117]
+[2.641, 0.232, 0.216],
+[0.092, 0.074, 0.073],
+[0.159, 0.121, 0.117],
+[0.351, 0.122, 0.120],
+[1.142, 0.874, 0.869],
+[1.399, 1.303, 1.329],
+[0.096, 0.075, 0.076],
+[0.094, 0.074, 0.076],
+[1.516, 1.481, 1.475],
+[2.711, 2.582, 2.583],
+[0.429, 0.332, 0.327],
+[0.558, 0.357, 0.360],
+[1.374, 1.323, 1.336],
+[3.559, 2.670, 2.733],
+[1.519, 1.487, 1.477],
+[1.041, 0.981, 0.988],
+[3.248, 2.748, 2.801],
+[3.139, 2.696, 2.688],
+[7.014, 5.770, 5.775],
+[0.271, 0.111, 0.109],
+[9.975, 1.558, 1.578],
+[11.163, 1.926, 1.881],
+[22.053, 4.208, 4.194],
+[56.007, 12.132, 12.113],
+[2.559, 0.602, 0.586],
+[0.737, 0.479, 0.489],
+[2.548, 0.589, 0.589],
+[9.550, 2.299, 2.286],
+[9.076, 5.399, 5.388],
+[0.579, 0.568, 0.584],
+[2.214, 1.136, 1.136],
+[5.734, 1.593, 1.598],
+[8.357, 7.896, 8.053],
+[11.556, 7.358, 7.369],
+[12.051, 7.878, 7.956],
+[1.866, 1.820, 1.807],
+[0.448, 0.347, 0.358],
+[0.231, 0.197, 0.195],
+[0.248, 0.198, 0.188],
+[0.843, 0.725, 0.722],
+[0.138, 0.091, 0.095],
+[0.115, 0.089, 0.088],
+[0.124, 0.097, 0.092]
 ]
 }