Extend monitoring and update portfolio

Add hostmetrics receiver and OTel Collector telemetry, and move
Alertmanager and Blackbox scraping to the collector. Raise collector
memory limits, restrict Blackbox to HTTP 200, and add collector and
Caddy down alerts with inhibition. Update portfolio title and copy.
This commit is contained in:
2026-08-05 19:49:18 +00:00
parent d38b941e0e
commit ede28f6d12
8 changed files with 82 additions and 31 deletions
+43 -3
View File
@@ -3,6 +3,17 @@ receivers:
protocols:
http:
endpoint: 0.0.0.0:4318
hostmetrics:
root_path: /hostfs
collection_interval: 10s
scrapers:
cpu:
memory:
disk:
filesystem:
network:
load:
processes:
prometheus:
config:
scrape_configs:
@@ -18,11 +29,32 @@ receivers:
scrape_interval: 10s
static_configs:
- targets: ['herald:9100']
- job_name: alertmanager
scrape_interval: 10s
static_configs:
- targets: ['alertmanager:9093']
- job_name: blackbox_http
scrape_interval: 10s
metrics_path: /probe
params:
module: [http_2xx]
static_configs:
- targets:
- https://www.qpismont.fr
- https://gitea.qpismont.fr
- https://woodpecker.qpismont.fr
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox_exporter:9115
processors:
memory_limiter:
check_interval: 5s
limit_mib: 200
limit_mib: 400
spike_limit_mib: 50
batch:
timeout: 10s
@@ -35,12 +67,20 @@ exporters:
endpoint: http://tempo:4318
service:
telemetry:
metrics:
readers:
- pull:
exporter:
prometheus:
host: 0.0.0.0
port: 8888
pipelines:
metrics:
receivers: [otlp, prometheus]
receivers: [otlp, prometheus, hostmetrics]
processors: [memory_limiter, batch]
exporters: [prometheusremotewrite]
traces:
receivers: [otlp]
processors: [memory_limiter, batch]
exporters: [otlphttp/tempo]
exporters: [otlphttp/tempo]