forked from h2oai/db-benchmark
-
Notifications
You must be signed in to change notification settings - Fork 32
181 lines (150 loc) · 4.83 KB
/
regression.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
name: Regression
on:
workflow_dispatch:
repository_dispatch:
pull_request:
paths-ignore:
- '**.md'
- '.github/workflows/**'
- '!.github/workflows/Regression.yml'
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || '' }}-${{ github.base_ref || '' }}-${{ github.ref != 'refs/heads/master' || github.sha }}
cancel-in-progress: true
jobs:
regression-test-benchmark-runner-solo-solutions:
strategy:
fail-fast: false
matrix:
solution: [data.table, collapse, dplyr, pandas, pydatatable, spark, juliadf, juliads, polars, R-arrow, duckdb, datafusion, dask, clickhouse]
name: Regression Tests solo solutions
runs-on: ubuntu-20.04
env:
CC: gcc-10
CXX: g++-10
GEN: ninja
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
- uses: actions/setup-python@v4
with:
python-version: '3.10'
- name: Install libraries
shell: bash
run: ./_utils/setup-small.sh
- name: Generate 500mb datasets
shell: bash
run: ./_utils/generate-data-small.sh
- name: Remove old logs
shell: bash
run: rm time.csv logs.csv
- name: Install all solutions
shell: bash
run: source path.env && python3 _setup_utils/install_all_solutions.py ${{ matrix.solution }}
- name: Turn swap off
shell: bash
run: sudo swapoff -a
# needed because clickhouse for some reason produces an error the first
# time a benchmark is run. The next benchmark run will work and overwrite the
# old benchmark files.
- name: Run mini GroupBy benchmark if clickhouse
shell: bash
if: ${{ matrix.solution == 'clickhouse' || matrix.solution == 'all' }}
run: |
python3 _utils/prep_solutions.py --task=groupby --solution=clickhouse
source path.env
TEST_RUN=true TEST_MOUNT_DIR=$GITHUB_WORKSPACE ./run.sh
- name: Run mini GroupBy benchmark
shell: bash
run: |
python3 _utils/prep_solutions.py --task=groupby --solution=${{ matrix.solution }}
source path.env
TEST_RUN=true TEST_MOUNT_DIR=$GITHUB_WORKSPACE ./run.sh
- name: Run mini Join benchmark
shell: bash
run: |
python3 _utils/prep_solutions.py --task=join --solution=${{ matrix.solution }}
source path.env
TEST_RUN=true TEST_MOUNT_DIR=$GITHUB_WORKSPACE ./run.sh
- name: Validate benchmark results and report generation
shell: bash
run: ./_utils/validate_no_errors.sh
- name: Create Archive
if: always()
shell: bash
run: |
cp *.csv out/
zip -r ${{ matrix.solution }}-out.zip out/
# include this step to see what the latest versions are of every solution
- name: Print latest versions
if: always()
shell: bash
run: tail -n +1 */VERSION
- uses: actions/upload-artifact@v3
if: always()
with:
name: ${{ matrix.solution }}-out.zip
path: ${{ matrix.solution }}-out.zip
if-no-files-found: error
regression-test-benchmark-runner-all-solutions:
needs: regression-test-benchmark-runner-solo-solutions
name: Regression Tests all solutions
runs-on: ubuntu-20.04
env:
CC: gcc-10
CXX: g++-10
GEN: ninja
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
- uses: actions/setup-python@v4
with:
python-version: '3.10'
- name: Install libraries
shell: bash
run: ./_utils/setup-small.sh
- name: Generate 500mb datasets
shell: bash
run: ./_utils/generate-data-small.sh
- name: Remove old logs
shell: bash
run: rm time.csv logs.csv
- name: Install all solutions
shell: bash
run: source path.env && python3 _setup_utils/install_all_solutions.py all
- name: Turn swap off
shell: bash
run: sudo swapoff -a
- name: Run mini GroupBy benchmark
shell: bash
run: |
python3 _utils/prep_solutions.py --task=groupby --solution=all
source path.env
TEST_RUN=true TEST_MOUNT_DIR=$GITHUB_WORKSPACE ./run.sh
- name: Run mini Join benchmark
shell: bash
run: |
python3 _utils/prep_solutions.py --task=join --solution=all
source path.env
TEST_RUN=true TEST_MOUNT_DIR=$GITHUB_WORKSPACE ./run.sh
- name: Validate benchmark results and report generation
shell: bash
run: ./_utils/validate_no_errors.sh
- name: Create Archive
if: always()
shell: bash
run: |
cp *.csv out/
zip -r all-out.zip out/
# include this step to see what the latest versions are of every solution
- name: Print latest versions
if: always()
shell: bash
run: tail -n +1 */VERSION
- uses: actions/upload-artifact@v3
if: always()
with:
name: all-out.zip
path: all-out.zip
if-no-files-found: error