Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Benchmarks: Add Benchmark - Add IB Loopback performance benchmark. #112

Merged
merged 19 commits into from
Jul 23, 2021
Merged

Benchmarks: Add Benchmark - Add IB Loopback performance benchmark. #112

Changes from 1 commit
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
363d365
add ib loopback benchmark
Jul 16, 2021
f8830a1
lint
Jul 16, 2021
cd7571a
delete message limit, rename commands, rename benchmark name
Jul 19, 2021
b9291fb
add multi size result support
Jul 20, 2021
4c66dba
update according to comments
Jul 21, 2021
2f3c067
fix missing line in config
Jul 21, 2021
66b4d70
remove real test
Jul 21, 2021
9304238
split test
Jul 22, 2021
f8b3969
fix , e.g.,
Jul 22, 2021
6e80748
fix bug of default value of commands in add_parser_arguments
Jul 22, 2021
81a8a87
revise _process_raw_result to remove re.match
Jul 22, 2021
fdc625b
add test for benchmark.commands in test
Jul 22, 2021
fc279b0
update according comments
Jul 22, 2021
0760376
add try-catch for get_arguments_from_env
Jul 22, 2021
cdb6a29
test for get_free_port and get_numa_cores
Jul 23, 2021
0c31ae3
revitest and allow at least 2 numa core
Jul 23, 2021
088057f
resolve conflict
Jul 23, 2021
acd3c02
add test for get_args_from_env
Jul 23, 2021
d81dd29
add test for no ib_device and no numa_core
Jul 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
28 changes: 12 additions & 16 deletions superbench/benchmarks/micro_benchmarks/ib_loopback_performance.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@
"""Module of the IB loopback benchmarks."""

import os
import re
from pathlib import Path

from superbench.common.utils import logger
Expand Down Expand Up @@ -181,13 +180,11 @@ def _process_raw_result(self, cmd_idx, raw_output):

valid = False
content = raw_output.splitlines()
try:
metric_set = set()
for line in content:

metric_set = set()
for line in content:
try:
values = list(filter(None, line.split(' ')))
# Filter useless line
if len(values) != 5 or not re.match(r'\d+', values[0]) or not re.match(r'\d+.\d+', values[-2]):
cp5555 marked this conversation as resolved.
Show resolved Hide resolved
continue
# Extract value from the line
size = int(values[0])
avg_bw = float(values[-2])
Expand All @@ -197,16 +194,15 @@ def _process_raw_result(self, cmd_idx, raw_output):
metric_set.add(metric)
self._result.add_result(metric, avg_bw)
valid = True
except BaseException:
valid = False
finally:
if valid is False:
logger.error(
'The result format is invalid - round: {}, benchmark: {}, raw output: {}.'.format(
self._curr_run_index, self._name, raw_output
)
except BaseException:
pass
if valid is False:
logger.error(
'The result format is invalid - round: {}, benchmark: {}, raw output: {}.'.format(
self._curr_run_index, self._name, raw_output
)
return False
)
return False

return True

Expand Down