A btop-like monitor in the console, from Prometheus; node exporters discovered and installed
Monitor draws CPU, memory, GPUs, requests, tokens, latency, network and disk as Braille charts over 5m/1h/24h/7d, then per node, card and model sparklines; node and model pages have their own. History is read from monitoring.prometheus through POST /api/v1/metrics/range, or without it from what the console saw. The control plane serves the cluster's machines for Prometheus http_sd at /prometheus/targets on its metrics port, and node add installs prometheus-node-exporter. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
2e55487eca
commit
a1b1663e9d
16 files changed
+1217
-4
No files matched your search
@@ -27,6 +27,17 @@ scrape_configs:
|
||||
labels:
|
||||
instance: control-plane
|
||||
|
||||
# Every machine of the cluster, for its node exporter: network and disk
|
||||
# traffic, filesystems, CPU time. The control plane lists them — nodes,
|
||||
# itself, the store's members — so a node added is a node scraped with
|
||||
# nothing edited here, and each carries its llmgw id as the node label.
|
||||
# `llmgw node add` installs the exporter; on a machine added before that,
|
||||
# apt-get install prometheus-node-exporter.
|
||||
- job_name: nodes
|
||||
http_sd_configs:
|
||||
- url: http://10.0.0.140:9091/prometheus/targets
|
||||
refresh_interval: 1m
|
||||
|
||||
- job_name: prometheus
|
||||
static_configs:
|
||||
- targets: ['localhost:9090']
|
||||
|
||||
Reference in new issue
Block a user