jeremy/hobbs-iac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: update CLAUDE.md — Coral USB TPU, Onyx redeploy, infra fixes 2026-05-20

Browse Source 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
jeremy
2026-05-20 08:06:05 -05:00
parent 752b8230ed
commit 6f485ff6e5
2 changed files with 15 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stacks/monitoring/alerts.yml
+7 -6
View File
@@ -118,27 +118,28 @@ groups:
summary: "{{ $labels.hostname }} rebooted"
description: "{{ $labels.hostname }} was rebooted less than 10 minutes ago."
# High swap usage
# High swap usage - uses absolute free swap threshold to avoid node-exporter v1.10.x
# SwapTotal double-counting bug on swapfile systems. Triggers when free swap < 1.5GB.
- alert: HighSwapUsage
expr: (node_memory_SwapTotal_bytes > 0) and ((node_memory_SwapTotal_bytes - node_memory_SwapFree_bytes) / node_memory_SwapTotal_bytes * 100 > 50)
expr: (node_memory_SwapTotal_bytes > 0) and (node_memory_SwapFree_bytes < 1.5 * 1024 * 1024 * 1024)
for: 5m
labels:
severity: warning
type: server
annotations:
summary: "{{ $labels.hostname }}: High swap usage"
description: "Swap usage on {{ $labels.hostname }} is above 50% for 5 minutes. Check container memory limits."
description: "Swap usage on {{ $labels.hostname }} is high (free swap below 1.5GB for 5 minutes). Check container memory limits."
# Critical swap usage
# Critical swap usage - triggers when free swap < 512MB
- alert: CriticalSwapUsage
expr: (node_memory_SwapTotal_bytes > 0) and ((node_memory_SwapTotal_bytes - node_memory_SwapFree_bytes) / node_memory_SwapTotal_bytes * 100 > 80)
expr: (node_memory_SwapTotal_bytes > 0) and (node_memory_SwapFree_bytes < 512 * 1024 * 1024)
for: 2m
labels:
severity: critical
type: server
annotations:
summary: "{{ $labels.hostname }}: Critical swap usage"
description: "Swap usage on {{ $labels.hostname }} is above 80%. System may become unresponsive."
description: "Swap usage on {{ $labels.hostname }} is critical (free swap below 512MB). System may become unresponsive."
# NFS mount failure (all data is on NAS - this is critical)
- alert: NFSMountDown