Skip to content

Adding Billing Rates to the config.py and rewriting references #159

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

Open
jimmysway wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Adding Billing Rates to the config.py and rewriting references #159

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2967310
Addresses CCI-MOC#144, Part 2: Adding Billing Rates to the config.py …
jimmysway Oct 8, 2025
d7d27cc
Merge remote-tracking branch 'upstream/main' into fix/144-consolidati…
jimmysway Nov 11, 2025
938dfd6
Resolved merge conflicts
jimmysway Dec 9, 2025
7fe5f96
Merge branch 'main' into fix/144-consolidating-config
jimmysway Dec 15, 2025
43098ff
Merge remote-tracking branch 'upstream/main' into fix/144-consolidati…
jimmysway Jan 22, 2026
4833009
GPU_A100_RATE and the SU/RESOURCE lists are removed from config.
jimmysway Jan 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions openshift_metrics/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,5 +14,19 @@
S3_SECRET_ACCESS_KEY = os.getenv("S3_OUTPUT_SECRET_ACCESS_KEY")
S3_INVOICE_BUCKET = os.getenv("S3_INVOICE_BUCKET", "nerc-invoicing")
S3_METRICS_BUCKET = os.getenv("S3_METRICS_BUCKET", "openshift_metrics")

# Billing Configuration

# Rate Configuration
USE_NERC_RATES = os.getenv("USE_NERC_RATES", "false").lower() == "true"
# Individual rates (used when USE_NERC_RATES=false)
RATE_CPU_SU = os.getenv("RATE_CPU_SU")
RATE_GPU_V100_SU = os.getenv("RATE_GPU_V100_SU")
RATE_GPU_A100SXM4_SU = os.getenv("RATE_GPU_A100SXM4_SU")
RATE_GPU_A100_SU = os.getenv("RATE_GPU_A100_SU")
RATE_GPU_H100_SU = os.getenv("RATE_GPU_H100_SU")


# Prometheus Query Configuration
PROM_QUERY_INTERVAL_MINUTES = int(os.getenv("PROM_QUERY_INTERVAL_MINUTES", 15))
assert PROM_QUERY_INTERVAL_MINUTES >= 1, "Query interval must be at least 1 minute"
58 changes: 36 additions & 22 deletions openshift_metrics/merge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,16 @@

from openshift_metrics import utils, invoice
from openshift_metrics.metrics_processor import MetricsProcessor
from openshift_metrics.config import S3_INVOICE_BUCKET, PROM_QUERY_INTERVAL_MINUTES
from openshift_metrics.config import (
S3_INVOICE_BUCKET,
USE_NERC_RATES,
RATE_CPU_SU,
RATE_GPU_V100_SU,
RATE_GPU_A100SXM4_SU,
RATE_GPU_A100_SU,
RATE_GPU_H100_SU,
PROM_QUERY_INTERVAL_MINUTES,
)

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
Expand Down Expand Up @@ -90,16 +99,6 @@ def main():
nargs="*",
help="List of timestamp ranges in UTC to ignore in the format 'YYYY-MM-DDTHH:MM:SS,YYYY-MM-DDTHH:MM:SS'",
)
parser.add_argument(
"--use-nerc-rates",
action="store_true",
help="Use rates from the nerc-rates repo",
)
parser.add_argument("--rate-cpu-su", type=Decimal)
parser.add_argument("--rate-gpu-v100-su", type=Decimal)
parser.add_argument("--rate-gpu-a100sxm4-su", type=Decimal)
parser.add_argument("--rate-gpu-a100-su", type=Decimal)
parser.add_argument("--rate-gpu-h100-su", type=Decimal)

args = parser.parse_args()
files = args.files
Expand Down Expand Up @@ -165,7 +164,7 @@ def main():
datetime.strptime(report_start_date, "%Y-%m-%d"), "%Y-%m"
)

if args.use_nerc_rates:
if USE_NERC_RATES:
logger.info("Using nerc rates for rates and outages")
rates_data = rates.load_from_url()
invoice_rates = invoice.Rates(
Expand All @@ -182,12 +181,23 @@ def main():
report_start_date, report_end_date, cluster_name
)
else:
if RATE_CPU_SU is None:
raise ValueError("RATE_CPU_SU environment variable must be set")
if RATE_GPU_V100_SU is None:
raise ValueError("RATE_GPU_V100_SU environment variable must be set")
if RATE_GPU_A100SXM4_SU is None:
raise ValueError("RATE_GPU_A100SXM4_SU environment variable must be set")
if RATE_GPU_A100_SU is None:
raise ValueError("RATE_GPU_A100_SU environment variable must be set")
if RATE_GPU_H100_SU is None:
raise ValueError("RATE_GPU_H100_SU environment variable must be set")

Comment on lines +184 to +194
Copy link
Collaborator

@QuanMPhm QuanMPhm Dec 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In the upstream version of the code, an error is already raised by the Rates dataclass if the SU rates are None. I suppose these a bit more informative, but I would argue they are not entirely necessary and leads to more maintenance burden down the line.

Copy link
Contributor Author

@jimmysway jimmysway Jan 22, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just tapping back into this issue sorry about the delay. I don't see where the Rates dataclass validates? But yeah all the other comments I think I've addressed

invoice_rates = invoice.Rates(
cpu=Decimal(args.rate_cpu_su),
gpu_a100=Decimal(args.rate_gpu_a100_su),
gpu_a100sxm4=Decimal(args.rate_gpu_a100sxm4_su),
gpu_v100=Decimal(args.rate_gpu_v100_su),
gpu_h100=Decimal(args.rate_gpu_h100_su),
cpu=Decimal(RATE_CPU_SU),
gpu_a100=Decimal(RATE_GPU_A100_SU),
gpu_a100sxm4=Decimal(RATE_GPU_A100SXM4_SU),
gpu_v100=Decimal(RATE_GPU_V100_SU),
gpu_h100=Decimal(RATE_GPU_H100_SU),
)
ignore_hours = args.ignore_hours

Expand All @@ -210,15 +220,19 @@ def main():
else:
pod_report_file = f"Pod NERC OpenShift {report_month}.csv"

report_start_date = datetime.strptime(report_start_date, "%Y-%m-%d").replace(
report_start_date_dt = datetime.strptime(report_start_date, "%Y-%m-%d").replace(
tzinfo=UTC
)
report_end_date = datetime.strptime(report_end_date, "%Y-%m-%d").replace(tzinfo=UTC)

logger.info(
f"Generating report from {report_start_date} to {report_end_date + timedelta(days=1)} for {cluster_name}"
report_end_date_dt = datetime.strptime(report_end_date, "%Y-%m-%d").replace(
tzinfo=UTC
)

if report_start_date_dt.month != report_end_date_dt.month:
logger.warning("The report spans multiple months")

report_start_date = report_start_date_dt
report_end_date = report_end_date_dt

condensed_metrics_dict = processor.condense_metrics(
["cpu_request", "memory_request", "gpu_request", "gpu_type"]
)
Expand Down