SIENTIAPDE-1174

pdate metrics tracking to include response time histogram

- Changed PREDICTION_RESPONSE_TIME_MONITOR from Gauge to Histogram for better response time analysis.
- Updated response time observation method in gates.py to utilize the new Histogram functionality.
This commit is contained in:
vitor-aignosi
2025-08-04 16:09:26 -03:00
parent 3cf7b4ec16
commit c92e2f41c3
2 changed files with 4 additions and 3 deletions

View File

@@ -340,4 +340,4 @@ class Gates(BaseActivity):
pod_id=self.pod_id,
model_name=metadata['model_name'],
pipeline_name=metadata['workflow_name']
).set(response_time)
).observe(response_time)

View File

@@ -1,4 +1,4 @@
from prometheus_client import Gauge, Counter
from prometheus_client import Gauge, Counter, Histogram
APP_UP = Gauge(
"app_up",
@@ -20,8 +20,9 @@ PREDICTION_CONFIDENCE_MONITOR = Gauge(
CORE_LABELS,
)
PREDICTION_RESPONSE_TIME_MONITOR = Gauge(
PREDICTION_RESPONSE_TIME_MONITOR = Histogram(
"laborious_prediction_response_time_monitor",
"Current response time of each prediction",
CORE_LABELS,
buckets=[0.01, 0.05, 0.1, 0.2, 0.5, 1.0, 2.0, 5.0, 10.0]
)