def test_consolidate_dataframe(capsys, data):
bundle = dtr.discover(data["analyze-files-gromacs"])
version = VersionFactory(categories=bundle.categories).version_class
df = utils.parse_bundle(
bundle, columns=version.analyze_categories, sort_values_by=version.analyze_sort,
)
test_output = utils.consolidate_dataframe(
df, columns=version.consolidate_categories
)
print_dataframe(
test_output[version.generate_printing[1:]],
columns=map_columns(
map_dict=version.category_mapping, columns=version.generate_printing[1:],
),
)
expected_output = (
"Setting up...\n\n"
"+----------------+---------+--------------+---------+--------+-----------+-------------+-------------------+\n",
"| Module | Nodes | Time (min) | GPUs? | Host | # ranks | # threads | Hyperthreading? |\n",
"|----------------+---------+--------------+---------+--------+-----------+-------------+-------------------|\n",
"| gromacs/2016.3 | 1-5 | 15 | False | draco | nan | nan | nan |\n",
"+----------------+---------+--------------+---------+--------+-----------+-------------+-------------------+\n\n",
)
out, _ = capsys.readouterr()
assert "\n".join(out.split("\n")) == "".join(expected_output)
def test_analyze_with_errors(cli_runner, tmpdir, capsys, data):
"""Test that we warn the user of errors in the output files. Also test that we
show a question mark instead of a float in the corresponding cell.
"""
with tmpdir.as_cwd():
result = cli_runner.invoke(cli, [
"analyze", "--directory={}".format(data["analyze-files-w-errors"])
])
version = Version2Categories()
bundle = dtr.discover(data["analyze-files-w-errors"])
df = parse_bundle(
bundle,
columns=version.analyze_categories,
sort_values_by=version.analyze_sort,
)
df = df.iloc[:, :-1]
df = df.replace(np.nan, "?")
print_dataframe(
df,
columns=map_columns(version.category_mapping,
version.analyze_printing),
)
out, _ = capsys.readouterr()
out = "Setting up...\n" + out
assert result.exit_code == 0
assert result.output == "\n".join(out.split("\n"))
def test_submit_test_prompt_no(cli_runner, tmpdir, data):
"""Test whether prompt answer no works."""
benchmark_version = Version2Categories()
with tmpdir.as_cwd():
result = cli_runner.invoke(
cli,
[
"submit",
"--directory={}".format(data["analyze-files-gromacs-one-unstarted"]),
],
input="n\n",
)
df = pd.read_csv(data["gromacs/test_prompt.csv"], index_col=0)
print_dataframe(
df,
columns=map_columns(
map_dict=benchmark_version.category_mapping,
columns=benchmark_version.generate_printing[1:],
),
)
assert result.exit_code == 1
assert (
result.output.split("\n")[-2] == "ERROR Exiting. No benchmarks submitted."
)
def test_print_dataframe(capsys, data):
df = pd.read_csv(data["analyze-files-gromacs.csv"])
version = Version2Categories()
utils.print_dataframe(df, version.analyze_printing + ["version"])
expected_output = tabulate.tabulate(
df, headers="keys", tablefmt="psql", showindex=False
)
expected_output = "\n" + expected_output + "\n\n"
out, _ = capsys.readouterr()
assert "\n".join(out.split("\n")) == expected_output
def do_analyze(directory, save_csv):
"""Analyze benchmarks."""
bundle = dtr.discover(directory)
version = VersionFactory(categories=bundle.categories).version_class
df = parse_bundle(
bundle,
columns=version.analyze_categories,
sort_values_by=version.analyze_sort,
)
# Remove the versions column from the DataFrame
columns_to_drop = ["version"]
df = df.drop(columns=columns_to_drop)
if save_csv is not None:
if not save_csv.endswith(".csv"):
save_csv = "{}.csv".format(save_csv)
df.to_csv(save_csv, index=False)
console.success("Successfully benchmark data to {}.", save_csv)
# Reformat NaN values nicely into question marks.
# move this to the bundle function!
df = df.replace(np.nan, "?")
if df.isnull().values.any():
console.warn(
"We were not able to gather informations for all systems. "
"Systems marked with question marks have either crashed or "
"were not started yet.")
# Warn user that we are going to print more than 50 benchmark results to the console
if df.shape[0] > 50:
if click.confirm(
"We are about to print the results of {} benchmarks to the console. Continue?"
.format(click.style(str(df.shape[0]), bold=True))):
pass
else:
console.error("Exiting.")
# Print the data to the console
print_dataframe(
df,
columns=map_columns(version.category_mapping,
version.analyze_printing),
)
def test_submit_resubmit(cli_runner, monkeypatch, tmpdir, data):
"""Test that we cannot submit a benchmark system that was already submitted,
unless we force it.
"""
with tmpdir.as_cwd():
# Test that we get an error if we try to point the submit function to
# an non-existent path.
result = cli_runner.invoke(cli, ["submit", "--directory=look_here/"], "--yes")
assert result.exit_code == 1
assert result.output == "ERROR No benchmarks found.\n"
# Test that we get an error if we try to start benchmarks that were
# already started once.
result = cli_runner.invoke(
cli,
["submit", "--directory={}".format(data["analyze-files-gromacs"]), "--yes"],
)
df = pd.read_csv(data["analyze-files-gromacs-consolidated.csv"], index_col=0)
s = print_dataframe(df, False)
output = "ERROR All generated benchmarks were already started once. You can force a restart with --force.\n"
assert result.exit_code == 1
assert result.output == output
# Test that we can force restart already run benchmarks.
# Monkeypatch a few functions
monkeypatch.setattr("subprocess.call", lambda x: True)
monkeypatch.setattr(
"mdbenchmark.cli.submit.get_batch_command", lambda: "sbatch"
)
monkeypatch.setattr(
"mdbenchmark.cli.submit.detect_md_engine", lambda x: gromacs
)
monkeypatch.setattr(
"mdbenchmark.submit.cleanup_before_restart", lambda engine, sim: True
)
output = (
"Benchmark Summary:\n"
+ s
+ "\nThe above benchmarks will be submitted.\n"
+ "Submitting a total of 5 benchmarks.\n"
+ "Submitted all benchmarks. Run mdbenchmark analyze once they are finished to get the results.\n"
)
result = cli_runner.invoke(
cli,
[
"submit",
"--directory={}".format(data["analyze-files-gromacs"]),
"--force",
"--yes",
],
)
assert result.exit_code == 0
assert result.output == output
def test_analyze_gromacs(cli_runner, tmpdir, capsys, data):
"""Test that the output is OK when all outputs are fine."""
with tmpdir.as_cwd():
result = cli_runner.invoke(cli, [
"analyze", "--directory={}".format(data["analyze-files-gromacs"])
])
df = pd.read_csv(data["analyze-files-gromacs.csv"])
df = df.iloc[:, :-1]
df = df.replace(np.nan, "?")
version = Version2Categories()
print_dataframe(
df,
columns=map_columns(version.category_mapping,
version.analyze_printing),
)
out, _ = capsys.readouterr()
out = "Setting up...\n" + out
assert result.exit_code == 0
assert result.output == "\n".join(out.split("\n"))
def test_analyze_namd(cli_runner, tmpdir, capsys, data):
with tmpdir.as_cwd():
result = cli_runner.invoke(
cli,
["analyze", "--directory={}".format(data["analyze-files-namd"])])
version = Version2Categories()
bundle = dtr.discover(data["analyze-files-namd"])
df = parse_bundle(
bundle,
columns=version.analyze_categories,
sort_values_by=version.analyze_sort,
)
df = df.iloc[:, :-1]
df = df.replace(np.nan, "?")
print_dataframe(
df,
columns=map_columns(version.category_mapping,
version.analyze_printing),
)
out, _ = capsys.readouterr()
out = "Setting up...\n" + out
assert result.exit_code == 0
assert result.output == "\n".join(out.split("\n"))
def test_submit_test_prompt_yes(cli_runner, tmpdir, data, monkeypatch):
"""Test whether promt answer no works."""
with tmpdir.as_cwd():
# Test that we can force restart already run benchmarks.
# Monkeypatch a few functions
monkeypatch.setattr("subprocess.call", lambda x: True)
monkeypatch.setattr(
"mdbenchmark.cli.submit.get_batch_command", lambda: "sbatch"
)
monkeypatch.setattr(
"mdbenchmark.cli.submit.detect_md_engine", lambda x: gromacs
)
monkeypatch.setattr(
"mdbenchmark.cli.submit.cleanup_before_restart", lambda engine, sim: True
)
result = cli_runner.invoke(
cli,
[
"submit",
"--directory={}".format(data["analyze-files-gromacs-one-unstarted"]),
],
input="y\n",
)
df = pd.read_csv(data["gromacs/test_prompt.csv"], index_col=0)
s = print_dataframe(df, False)
output = (
"Benchmark Summary:\n"
+ s
+ "\nThe above benchmarks will be submitted. Continue? [y/N]: y\n"
+ "Submitting a total of 1 benchmarks.\n"
+ "Submitted all benchmarks. Run mdbenchmark analyze once they are finished to get the results.\n"
)
assert result.exit_code == 0
assert result.output == output
# Lazy way of resetting the value of `started` to `false`.
# TODO: We need to clean up all of our unit tests...
treant = dtr.Bundle(data["analyze-files-gromacs-one-unstarted"] + "/1")
treant.categories["started"] = False
def do_submit(directory, force_restart, yes):
"""Submit the benchmarks."""
bundle = dtr.discover(directory)
# Exit if no bundles were found in the current directory.
if not bundle:
console.error("No benchmarks found.")
grouped_bundles = bundle.categories.groupby("started")
try:
bundles_not_yet_started = grouped_bundles[False]
except KeyError:
bundles_not_yet_started = None
if not bundles_not_yet_started and not force_restart:
console.error(
"All generated benchmarks were already started once. "
"You can force a restart with {}.",
"--force",
)
# Start all benchmark simulations if a restart was requested. Otherwise
# only start the ones that were not run yet.
bundles_to_start = bundle
if not force_restart:
bundles_to_start = bundles_not_yet_started
benchmark_version = VersionFactory(
categories=bundles_to_start.categories).version_class
df = parse_bundle(
bundles_to_start,
columns=benchmark_version.submit_categories,
sort_values_by=benchmark_version.analyze_sort,
discard_performance=True,
)
# Reformat NaN values nicely into question marks.
df_to_print = df.replace(np.nan, "?")
columns_to_drop = ["ncores", "version"]
df_to_print = df.drop(columns=columns_to_drop)
# Consolidate the data by grouping on the number of nodes and print to the
# user as an overview.
consolidated_df = consolidate_dataframe(
df_to_print, columns=benchmark_version.consolidate_categories)
print_dataframe(
consolidated_df,
columns=map_columns(
map_dict=benchmark_version.category_mapping,
columns=benchmark_version.generate_printing[1:],
),
)
# Ask the user to confirm whether they want to submit the benchmarks
if yes:
console.info("The above benchmarks will be submitted.")
elif not click.confirm(
"The above benchmarks will be submitted. Continue?"):
console.error("Exiting. No benchmarks submitted.")
batch_cmd = get_batch_command()
console.info("Submitting a total of {} benchmarks.", len(bundles_to_start))
for sim in bundles_to_start:
# Remove files generated by previous mdbenchmark run
if force_restart:
engine = detect_md_engine(sim.categories["module"])
cleanup_before_restart(engine=engine, sim=sim)
sim.categories["started"] = True
os.chdir(sim.abspath)
subprocess.call([batch_cmd, "bench.job"])
console.info(
"Submitted all benchmarks. Run {} once they are finished to get the results.",
"mdbenchmark analyze",
)
def do_generate(
name,
cpu,
gpu,
module,
host,
min_nodes,
max_nodes,
time,
skip_validation,
job_name,
yes,
physical_cores,
logical_cores,
number_of_ranks,
enable_hyperthreading,
multidir,
):
"""Generate a bunch of benchmarks."""
# Instantiate the version we are going to use
benchmark_version = Version3Categories()
# Validate the CPU and GPU flags
validate_cpu_gpu_flags(cpu, gpu)
# Validate the number of nodes
validate_number_of_nodes(min_nodes=min_nodes, max_nodes=max_nodes)
if logical_cores < physical_cores:
console.error(
"The number of logical cores cannot be smaller than the number of physical cores."
)
if physical_cores and not logical_cores:
console.warn("Assuming logical_cores = 2 * physical_cores")
logical_cores = 2 * physical_cores
if physical_cores and logical_cores:
processor = Processor(physical_cores=physical_cores,
logical_cores=logical_cores)
else:
processor = Processor()
# Hyperthreading check
if enable_hyperthreading and not processor.supports_hyperthreading:
console.error(
"The processor of this machine does not support hyperthreading.")
if not number_of_ranks:
number_of_ranks = (processor.physical_cores, )
# Validate number of simulations
validate_number_of_simulations(multidir, min_nodes, max_nodes,
number_of_ranks)
# Grab the template name for the host. This should always work because
# click does the validation for us
template = utils.retrieve_host_template(host)
# Warn the user that NAMD support is still experimental.
if any(["namd" in m for m in module]):
console.warn(NAMD_WARNING, "--gpu")
# Stop if we cannot find any modules. If the user specified multiple
# modules, we will continue with only the valid ones.
modules = mdengines.normalize_modules(module, skip_validation)
if not modules:
console.error("No requested modules available!")
# Check if all needed files exist. Throw an error if they do not.
validate_required_files(name=name, modules=modules)
# Validate that we can use the number of ranks and threads.
# We can continue, if no ValueError is thrown
for ranks in number_of_ranks:
try:
processor.get_ranks_and_threads(
ranks, with_hyperthreading=enable_hyperthreading)
except ValueError as e:
console.error(e)
# Create all benchmark combinations and put them into a DataFrame
data = construct_generate_data(
name,
job_name,
modules,
host,
template,
cpu,
gpu,
time,
min_nodes,
max_nodes,
processor,
number_of_ranks,
enable_hyperthreading,
multidir,
)
df = pd.DataFrame(data, columns=benchmark_version.generate_categories)
# Consolidate the data by grouping on the number of nodes and print to the
# user as an overview.
consolidated_df = consolidate_dataframe(
df, columns=benchmark_version.consolidate_categories)
print_dataframe(
consolidated_df[benchmark_version.generate_printing],
columns=map_columns(
map_dict=benchmark_version.category_mapping,
columns=benchmark_version.generate_printing,
),
)
# Save the number of benchmarks for later printing
number_of_benchmarks = df.shape[0]
# Ask the user for confirmation to generate files.
# If the user defined `--yes`, we will skip the confirmation immediately.
if yes:
console.info(
"We will generate {} " +
"{benchmark}.".format(benchmark="benchmark" if number_of_benchmarks
== 1 else "benchmarks"),
number_of_benchmarks,
)
elif not click.confirm("We will generate {} benchmarks. Continue?".format(
number_of_benchmarks)):
console.error("Exiting. No benchmarks were generated.")
# Generate the benchmarks
with click.progressbar(
df.iterrows(),
length=number_of_benchmarks,
show_pos=True,
label="Generating benchmarks",
) as bar:
for _, row in bar:
relative_path, file_basename = os.path.split(row["name"])
mappings = benchmark_version.generate_mapping
kwargs = {"name": file_basename, "relative_path": relative_path}
for key, value in mappings.items():
kwargs[value] = row[key]
write_benchmark(**kwargs)
# Finish up by telling the user how to submit the benchmarks
console.info(
"Finished! You can submit the jobs with {}.",
"mdbenchmark submit",
)
