✅ Validation Results: - PPO training: 24.2s (1 epoch, 950 samples, dim=225) - Feature extraction: 105μs/bar (9.5x faster than target) - Model checkpoint: 293KB (147KB actor + 146KB critic) - GPU memory: 145MB used (96.4% headroom) - Zero dimension mismatches 📊 Success Criteria (5/5): ✅ Feature dimension = 225 (Wave C 201 + Wave D 24) ✅ Model state_dim = 225 ✅ Training completed without errors ✅ Checkpoint saved successfully ✅ No dimension mismatch errors 📁 Training Data Ready: - ES.FUT: 2.9MB, 180 days - NQ.FUT: 4.4MB, 180 days - 6E.FUT: 2.8MB, 180 days - ZN.FUT: 65KB, 90 days (clean) 🚀 Next: Full production model retraining (4 models, ~10min GPU time) 🤖 Generated with Claude Code (https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
77 lines
2.2 KiB
JSON
77 lines
2.2 KiB
JSON
{
|
|
"version": "1.0.0",
|
|
"description": "Performance baselines for ML Training Service stress tests",
|
|
"baselines": {
|
|
"batch_creation": {
|
|
"description": "Concurrent batch creation performance",
|
|
"p95_latency_ms": 10.0,
|
|
"throughput_ops_per_sec": 1000.0,
|
|
"max_concurrent": 1000,
|
|
"acceptable_failure_rate_percent": 1.0
|
|
},
|
|
"streaming": {
|
|
"description": "gRPC streaming performance",
|
|
"throughput_msg_per_sec_per_stream": 1000.0,
|
|
"max_concurrent_streams": 100,
|
|
"backpressure_handling": true,
|
|
"message_loss_rate_percent": 0.1
|
|
},
|
|
"state_transitions": {
|
|
"description": "State transition performance",
|
|
"p95_latency_ms": 5.0,
|
|
"throughput_updates_per_sec": 1000.0,
|
|
"deadlock_free": true,
|
|
"rollback_correctness": true
|
|
},
|
|
"file_discovery": {
|
|
"description": "Data file discovery performance",
|
|
"discovery_time_100_files_ms": 100.0,
|
|
"discovery_time_10k_files_ms": 1000.0,
|
|
"concurrent_requests": 20,
|
|
"cache_invalidation": true
|
|
},
|
|
"memory_leak": {
|
|
"description": "Memory leak detection thresholds",
|
|
"max_rss_growth_percent_per_hour": 1.0,
|
|
"max_leak_after_cleanup_percent": 5.0,
|
|
"stream_cleanup_leak_percent": 3.0,
|
|
"connection_leak_percent": 2.0
|
|
}
|
|
},
|
|
"system_requirements": {
|
|
"min_cpu_cores": 4,
|
|
"min_ram_gb": 8,
|
|
"min_disk_gb": 20,
|
|
"postgres_connections": 20,
|
|
"recommended_environment": "Dedicated hardware, no CI/CD"
|
|
},
|
|
"test_execution": {
|
|
"concurrent_batch_creation": {
|
|
"min_duration_secs": 10,
|
|
"max_duration_secs": 30
|
|
},
|
|
"streaming_load": {
|
|
"min_duration_secs": 10,
|
|
"max_duration_secs": 60
|
|
},
|
|
"state_transition_storm": {
|
|
"min_duration_secs": 5,
|
|
"max_duration_secs": 30
|
|
},
|
|
"file_discovery": {
|
|
"min_duration_secs": 1,
|
|
"max_duration_secs": 10
|
|
},
|
|
"memory_leak": {
|
|
"short_test_duration_secs": 300,
|
|
"long_test_duration_secs": 3600
|
|
}
|
|
},
|
|
"regression_thresholds": {
|
|
"latency_p95_degradation_percent": 20.0,
|
|
"throughput_degradation_percent": 15.0,
|
|
"memory_growth_degradation_percent": 50.0,
|
|
"failure_rate_increase_percent": 100.0
|
|
}
|
|
}
|