abiba-bot/prose-contracts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

prose: annotate infrastructure-monitoring with current deployment status

Browse Source 
- Core stack (Prometheus + Grafana + pve/node/docker exporters) already
  deployed by proxmox-monitor contract (Jul 2)
- GPU exporters (.8/.110/.15) NOT yet live — gpu-exporter crash-loops,
  sidecars never deployed
- Strike nginx /monitoring/ proxy suggestion (sub-path pattern already
  tried and reverted for /grafana/ per proxmox-monitor)
- Add cross-reference: this contract defines target state, proxmox-monitor
  is the as-built
This commit is contained in:
root
2026-07-04 21:55:43 +00:00
parent 0a3b62a598
commit 0d0215e9dd
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
infrastructure-monitoring.prose.md
+7 -3
View File
@@ -5,8 +5,12 @@ description: >
Deploys Prometheus + GPU exporters + Grafana to monitor the entire Deploys Prometheus + GPU exporters + Grafana to monitor the entire
inference fleet (3 GPU hosts + LiteLLM) from CT 116. GPU metrics inference fleet (3 GPU hosts + LiteLLM) from CT 116. GPU metrics
from nvidia-smi (.8, .110) and amdgpu_top (.15). LiteLLM metrics from nvidia-smi (.8, .110) and amdgpu_top (.15). LiteLLM metrics
via existing /metrics Prometheus endpoint. Replaces the deprecated via existing /metrics Prometheus endpoint.
harness-dashboard with a production-grade monitoring stack.
STATUS: Core stack (Prometheus + Grafana + pve/node/docker exporters)
already deployed by proxmox-monitor contract. GPU exporters (.8/.110/.15)
NOT yet live — gpu-exporter crash-loops on .15, sidecars never deployed.
This contract defines the target state; proxmox-monitor is the as-built.
version: 1.0.0 version: 1.0.0
--- ---
@@ -129,7 +133,7 @@ GPU .8 (RTX 3090) GPU .110 (RTX 5070) GPU .15 (Strix Halo)
2. Verify Prometheus targets all UP at :9090/targets 2. Verify Prometheus targets all UP at :9090/targets
3. Verify Grafana accessible at :3001 with dashboards 3. Verify Grafana accessible at :3001 with dashboards
4. Verify LiteLLM metrics flowing to Prometheus 4. Verify LiteLLM metrics flowing to Prometheus
5. Update nginx to proxy `/monitoring/` → Grafana (optional) 5. ~~Update nginx to proxy `/monitoring/` → Grafana~~ (NOT recommended — nginx sub-path was tried for /grafana/ and reverted per proxmox-monitor; direct :3001 access is the standard)
## Verification Commands ## Verification Commands