Performance Regression or Improvement: gbk_python_batch_load_test_fanout_4_times_with_2GB_10byte_records_total:runtime

[github-actions]

Performance change found in the
test: gbk_python_batch_load_test_fanout_4_times_with_2GB_10byte_records_total for the metric: runtime.

For more information on how to triage the alerts, please look at
Triage performance alert issues section of the README.

Test description: GroupByKey Python Load test - fanout 4 times with 2GB 10-byte records total
python | GBK | Fanout 4
Test Dashboard - http://metrics.beam.apache.org/d/UYZ-oJ3Zk/gbk-load-tests?orgId=1&var-processingType=batch&var-sdk=python&from=now-90d&to=now&viewPanel=5
Test link -

beam/.test-infra/jenkins/job_LoadTests_GBK_Python.groovy

Line 106 in 5e38dec

test : 'apache_beam.testing.load_tests.group_by_key_test',

timestamp: Sat Nov 29 16:59:46 2025, metric_value: 49.00
timestamp: Fri Nov 28 17:04:38 2025, metric_value: 56.00
timestamp: Thu Nov 27 17:01:30 2025, metric_value: 38.00
timestamp: Wed Nov 26 17:05:23 2025, metric_value: 65.00
timestamp: Tue Nov 25 17:06:03 2025, metric_value: 53.00
timestamp: Mon Nov 24 17:08:54 2025, metric_value: 43.00 <---- Anomaly
timestamp: Sun Nov 23 17:03:07 2025, metric_value: 80.00
timestamp: Sat Nov 22 17:00:46 2025, metric_value: 88.00
timestamp: Fri Nov 21 16:59:45 2025, metric_value: 58.00
timestamp: Thu Nov 20 17:01:30 2025, metric_value: 57.00
timestamp: Wed Nov 19 17:21:24 2025, metric_value: 46.00
timestamp: Tue Nov 18 17:18:18 2025, metric_value: 62.00
timestamp: Mon Nov 17 17:09:09 2025, metric_value: 75.00
timestamp: Sun Nov 16 17:06:06 2025, metric_value: 84.00
timestamp: Sat Nov 15 17:10:42 2025, metric_value: 54.00
timestamp: Fri Nov 14 17:18:11 2025, metric_value: 73.00

[claudevdm]

Noise