[CI] Regression Test Configuration (#1157)

* push

* 1111

* 111

* fix

* 222

* 1231231

* 111

* 45458643465

* fix

* fix

* fix

* 4156416

* fix

* path

* 111

* 1231

* 111

* 152554

* fix

* fix

* fix

* fix

* try fix

* change name

* try

* fix

* fix
Co-authored-by: Minjie Wang <minjie.wang@nyu.edu>

asv.conf.json

+{
+    // The version of the config file format.  Do not change, unless
+    // you know what you are doing.
+    "version": 1,
+
+    // The name of the project being benchmarked
+    "project": "dgl",
+
+    // The project's homepage
+    "project_url": "https://github.com/dmlc/dgl",
+
+    // The URL or local path of the source code repository for the
+    // project being benchmarked
+    "repo": "https://github.com/dmlc/dgl.git",
+
+    // The Python project's subdirectory in your repo.  If missing or
+    // the empty string, the project is assumed to be located at the root
+    // of the repository.
+    // "repo_subdir": "",
+
+    // Customizable commands for building, installing, and
+    // uninstalling the project. See asv.conf.json documentation.
+    //
+     "install_command": ["in-dir={env_dir} python -mpip install --pre dgl-cu101"],
+     "build_command": ["python -c \"print('skip')\""],
+    "uninstall_command": ["return-code=any python -mpip uninstall -y dgl-cu101"],
+    // "build_command": [
+    //     "python setup.py build",
+    //     "PIP_NO_BUILD_ISOLATION=false python -mpip wheel --no-deps --no-index -w {build_cache_dir} {build_dir}"
+    // ],
+
+    // List of branches to benchmark. If not provided, defaults to "master"
+    // (for git) or "default" (for mercurial).
+    // "branches": ["master"], // for git
+    // "branches": ["default"],    // for mercurial
+
+    // The DVCS being used.  If not set, it will be automatically
+    // determined from "repo" by looking at the protocol in the URL
+    // (if remote), or by looking for special directories, such as
+    // ".git" (if local).
+    // "dvcs": "git",
+
+    // The tool to use to create environments.  May be "conda",
+    // "virtualenv" or other value depending on the plugins in use.
+    // If missing or the empty string, the tool will be automatically
+    // determined by looking for tools on the PATH environment
+    // variable.
+    // "environment_type": "conda",
+
+    // timeout in seconds for installing any dependencies in environment
+    // defaults to 10 min
+    "install_timeout": 600,
+
+    // the base URL to show a commit for the project.
+    // "show_commit_url": "http://github.com/owner/project/commit/",
+
+    // The Pythons you'd like to test against.  If not provided, defaults
+    // to the current version of Python used to run `asv`.
+    // "pythons": ["2.7", "3.6"],
+
+    // The list of conda channel names to be searched for benchmark
+    // dependency packages in the specified order
+    // "conda_channels": ["conda-forge", "defaults"],
+
+    // The matrix of dependencies to test.  Each key is the name of a
+    // package (in PyPI) and the values are version numbers.  An empty
+    // list or empty string indicates to just test against the default
+    // (latest) version. null indicates that the package is to not be
+    // installed. If the package to be tested is only available from
+    // PyPi, and the 'environment_type' is conda, then you can preface
+    // the package name by 'pip+', and the package will be installed via
+    // pip (with all the conda available packages installed first,
+    // followed by the pip installed packages).
+    //
+    // "matrix": {
+    //     "numpy": ["1.6", "1.7"],
+    //     "six": ["", null],        // test with and without six installed
+    //     "pip+emcee": [""],   // emcee is only available for install with pip.
+    // },
+
+    // Combinations of libraries/python versions can be excluded/included
+    // from the set to test. Each entry is a dictionary containing additional
+    // key-value pairs to include/exclude.
+    //
+    // An exclude entry excludes entries where all values match. The
+    // values are regexps that should match the whole string.
+    //
+    // An include entry adds an environment. Only the packages listed
+    // are installed. The 'python' key is required. The exclude rules
+    // do not apply to includes.
+    //
+    // In addition to package names, the following keys are available:
+    //
+    // - python
+    //     Python version, as in the *pythons* variable above.
+    // - environment_type
+    //     Environment type, as above.
+    // - sys_platform
+    //     Platform, as in sys.platform. Possible values for the common
+    //     cases: 'linux2', 'win32', 'cygwin', 'darwin'.
+    //
+    // "exclude": [
+    //     {"python": "3.2", "sys_platform": "win32"}, // skip py3.2 on windows
+    //     {"environment_type": "conda", "six": null}, // don't run without six on conda
+    // ],
+    //
+    // "include": [
+    //     // additional env for python2.7
+    //     {"python": "2.7", "numpy": "1.8"},
+    //     // additional env if run on windows+conda
+    //     {"platform": "win32", "environment_type": "conda", "python": "2.7", "libpython": ""},
+    // ],
+
+    // The directory (relative to the current directory) that benchmarks are
+    // stored in.  If not provided, defaults to "benchmarks"
+    "benchmark_dir": "tests/regression",
+
+    // The directory (relative to the current directory) to cache the Python
+    // environments in.  If not provided, defaults to "env"
+    // "env_dir": "env",
+
+    // The directory (relative to the current directory) that raw benchmark
+    // results are stored in.  If not provided, defaults to "results".
+    "results_dir": "regression_results",
+
+    // The directory (relative to the current directory) that the html tree
+    // should be written to.  If not provided, defaults to "html".
+    // "html_dir": "html",
+
+    // The number of characters to retain in the commit hashes.
+    // "hash_length": 8,
+
+    // `asv` will cache results of the recent builds in each
+    // environment, making them faster to install next time.  This is
+    // the number of builds to keep, per environment.
+    // "build_cache_size": 2,
+
+    // The commits after which the regression search in `asv publish`
+    // should start looking for regressions. Dictionary whose keys are
+    // regexps matching to benchmark names, and values corresponding to
+    // the commit (exclusive) after which to start looking for
+    // regressions.  The default is to start from the first commit
+    // with results. If the commit is `null`, regression detection is
+    // skipped for the matching benchmark.
+    //
+    // "regressions_first_commits": {
+    //    "some_benchmark": "352cdf",  // Consider regressions only after this commit
+    //    "another_benchmark": null,   // Skip regression detection altogether
+    // },
+
+    // The thresholds for relative change in results, after which `asv
+    // publish` starts reporting regressions. Dictionary of the same
+    // form as in ``regressions_first_commits``, with values
+    // indicating the thresholds.  If multiple entries match, the
+    // maximum is taken. If no entry matches, the default is 5%.
+    //
+    // "regressions_thresholds": {
+    //    "some_benchmark": 0.01,     // Threshold of 1%
+    //    "another_benchmark": 0.5,   // Threshold of 50%
+    // },
+}

tests/regression/__init__.py

+

tests/regression/benchmarks.py

+# Write the benchmarking functions here.
+# See "Writing benchmarks" in the asv docs for more information.
+
+import subprocess
+import os
+from pathlib import Path
+import numpy as np
+import tempfile
+
+base_path = Path("~/regression/dgl/")
+
+
+class GCNBenchmark:
+
+    params = [['pytorch'], ['cora', 'pubmed'], ['0', '-1']]
+    param_names = ['backend', 'dataset', 'gpu_id']
+    timeout = 120
+
+    # def setup_cache(self):
+    #     self.tmp_dir = Path(tempfile.mkdtemp())
+
+    def setup(self, backend, dataset, gpu_id):
+        log_filename = Path("{}_{}_{}.log".format(backend, dataset, gpu_id))
+        if log_filename.exists():
+            return
+        gcn_path = base_path / "examples/{}/gcn/train.py".format(backend)
+        bashCommand = "/opt/conda/envs/{}-ci/bin/python {} --dataset {} --gpu {} --n-epochs 50".format(
+            backend, gcn_path.expanduser(), dataset, gpu_id)
+        process = subprocess.Popen(bashCommand.split(), stdout=subprocess.PIPE,env=dict(os.environ, DGLBACKEND=backend))
+        output, error = process.communicate()
+        print(str(error))
+        log_filename.write_text(str(output))
+
+
+    def track_gcn_time(self, backend, dataset, gpu_id):
+        log_filename = Path("{}_{}_{}.log".format(backend, dataset, gpu_id))
+        lines = log_filename.read_text().split("\\n")
+        time_list = []
+        for line in lines:
+            # print(line)
+            if 'Time' in line:
+                time_str = line.strip().split('|')[1]
+                time = float(time_str.split()[-1])
+                time_list.append(time)
+        return np.array(time_list)[-10:].mean()
+
+    def track_gcn_accuracy(self, backend, dataset, gpu_id):
+        log_filename = Path("{}_{}_{}.log".format(backend, dataset, gpu_id))
+        lines = log_filename.read_text().split("\\n")
+        test_acc = -1
+        for line in lines:
+            if 'Test accuracy' in line:
+                test_acc = float(line.split()[-1][:-1])
+                print(test_acc)
+        return test_acc
+
+
+GCNBenchmark.track_gcn_time.unit = 's'
+GCNBenchmark.track_gcn_accuracy.unit = '%'

tests/regression/publish.sh

+docker run --name dgl-reg --rm --hostname=reg-machine --runtime=nvidia -v dgl-regression:/root/regression -d -it dgllib/dgl-ci-gpu:conda /bin/bash
+docker cp ./tests/regression/run.sh dgl-reg:/root/regression_run.sh
+docker exec dgl-reg bash /root/regression_run.sh
+docker cp dgl-reg:/root/regression/dgl/html /home/ubuntu/reg_prod/html/
+docker stop dgl-reg
\ No newline at end of file

tests/regression/run.sh

+. /opt/conda/etc/profile.d/conda.sh
+
+cd ~
+cd regression
+cd dgl
+# git clone --recursive https://github.com/dmlc/dgl.git 
+git pull 
+git submodule init
+git submodule update --recursive
+
+conda activate base
+pip install asv
+
+for backend in pytorch mxnet tensorflow
+do 
+conda activate "${backend}-ci"
+pip uninstall -y dgl-cu101
+pip install --pre dgl-cu101
+done
+
+conda activate base
+asv machine --yes
+asv run
+asv publish