ed7ad49d3a
P3.2 — Multi-node deployment: - Added node-worker service to docker-compose.node1.yml (NODE_ID=noda1) - NCS NODA1 now has NODE_WORKER_URL for metrics collection - Fixed NODE_ID consistency: router NODA1 uses 'noda1' - NODA2 node-worker/NCS gets NCS_REPORT_URL for latency reporting P3.3 — NATS accounts/auth (opt-in config): - config/nats-server.conf with 3 accounts: SYS, FABRIC, APP - Per-user topic permissions (router, ncs, node_worker) - Leafnode listener :7422 with auth - Not yet activated (requires credential provisioning) P3.4 — Prometheus counters: - Router /fabric_metrics: caps_refresh, caps_stale, model_select, offload_total, breaker_state, score_ms histogram - Node Worker /prom_metrics: jobs_total, inflight gauge, latency_ms histogram - NCS /prom_metrics: runtime_health, runtime_p50/p95, node_wait_ms - All bound to 127.0.0.1 (not externally exposed) Made-with: Cursor
51 lines
1.4 KiB
Python
51 lines
1.4 KiB
Python
"""Prometheus metrics for NCS."""
|
|
import logging
|
|
|
|
logger = logging.getLogger("ncs_prom")
|
|
|
|
try:
|
|
from prometheus_client import Gauge, CollectorRegistry, generate_latest
|
|
PROM_AVAILABLE = True
|
|
REGISTRY = CollectorRegistry()
|
|
|
|
runtime_health = Gauge(
|
|
"ncs_runtime_health", "Runtime health (1=ok, 0=down)",
|
|
["runtime"], registry=REGISTRY,
|
|
)
|
|
runtime_p50 = Gauge(
|
|
"ncs_runtime_p50_ms", "Runtime p50 latency",
|
|
["runtime"], registry=REGISTRY,
|
|
)
|
|
runtime_p95 = Gauge(
|
|
"ncs_runtime_p95_ms", "Runtime p95 latency",
|
|
["runtime"], registry=REGISTRY,
|
|
)
|
|
node_wait = Gauge(
|
|
"ncs_node_wait_ms", "Estimated wait for node",
|
|
registry=REGISTRY,
|
|
)
|
|
|
|
except ImportError:
|
|
PROM_AVAILABLE = False
|
|
REGISTRY = None
|
|
|
|
|
|
def update_from_caps(caps: dict):
|
|
if not PROM_AVAILABLE:
|
|
return
|
|
nl = caps.get("node_load", {})
|
|
node_wait.set(nl.get("estimated_wait_ms", 0))
|
|
for rl in caps.get("runtime_load", []):
|
|
rt = rl.get("runtime", "?")
|
|
runtime_health.labels(runtime=rt).set(1 if rl.get("healthy") else 0)
|
|
if rl.get("p50_ms") is not None:
|
|
runtime_p50.labels(runtime=rt).set(rl["p50_ms"])
|
|
if rl.get("p95_ms") is not None:
|
|
runtime_p95.labels(runtime=rt).set(rl["p95_ms"])
|
|
|
|
|
|
def get_metrics_text():
|
|
if PROM_AVAILABLE and REGISTRY:
|
|
return generate_latest(REGISTRY)
|
|
return None
|