monitoring: llama-swap GPU/LLM stack (v250) — PrometheusRule, Grafana dashboard, scrape config, VRAM exporter
This commit is contained in:
73
cluster/applications/monitoring/llama-swap-alerts.yaml
Normal file
73
cluster/applications/monitoring/llama-swap-alerts.yaml
Normal file
@@ -0,0 +1,73 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: llama-swap-alerts
|
||||
namespace: monitoring
|
||||
labels:
|
||||
prometheus: kube-prometheus
|
||||
app.kubernetes.io/part-of: monitoring
|
||||
spec:
|
||||
groups:
|
||||
- name: llama-swap.rules
|
||||
interval: 30s
|
||||
rules:
|
||||
# ====================================================================
|
||||
# CRITICAL: GPU VRAM saturation (OOM risk)
|
||||
# ====================================================================
|
||||
- alert: LlamaSwapVramSaturation
|
||||
expr: llamacpp_vram_used_mib > 24000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
component: llm-inference
|
||||
annotations:
|
||||
summary: "GPU VRAM saturation on {{ $labels.instance }}"
|
||||
description: |
|
||||
GPU VRAM usage is {{ $value | humanize }}MiB (critical threshold: 24000MiB).
|
||||
The system is at risk of out-of-memory (OOM) kernel-kill events.
|
||||
|
||||
# ====================================================================
|
||||
# WARNING: KV-cache spill risk (context cache pressure)
|
||||
# ====================================================================
|
||||
- alert: LlamaSwapKvCacheSpill
|
||||
expr: llamacpp_kv_cache_usage_ratio > 0.92
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
component: llm-inference
|
||||
annotations:
|
||||
summary: "KV-cache spill risk on model {{ $labels.model }}"
|
||||
description: |
|
||||
KV-cache utilization on {{ $labels.model }} is {{ $value | humanizePercentage }}
|
||||
(warning threshold: 92%).
|
||||
|
||||
# ====================================================================
|
||||
# WARNING: Throughput degradation (possible throttling)
|
||||
# ====================================================================
|
||||
- alert: LlamaSwapThroughputDegradation
|
||||
expr: |
|
||||
(rate(llamacpp_tokens_predicted_total[5m]) * 60) < 40
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
component: llm-inference
|
||||
annotations:
|
||||
summary: "Token generation throughput low on {{ $labels.model }}"
|
||||
description: |
|
||||
Token generation rate is {{ $value | humanize }} tokens/min on {{ $labels.model }}
|
||||
(baseline threshold: ~50+ tokens/min).
|
||||
|
||||
# ====================================================================
|
||||
# WARNING: Scrape failures (monitoring health)
|
||||
# ====================================================================
|
||||
- alert: LlamaSwapScrapeFailed
|
||||
expr: up{job="llama-swap"} == 0
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
component: monitoring
|
||||
annotations:
|
||||
summary: "llama-swap Prometheus scrape failed"
|
||||
description: |
|
||||
Prometheus cannot scrape llama-swap's /metrics endpoint.
|
||||
Check: systemctl status llama-swap, curl http://{{ $labels.instance }}/metrics
|
||||
556
cluster/applications/monitoring/llama-swap-dashboard.yaml
Normal file
556
cluster/applications/monitoring/llama-swap-dashboard.yaml
Normal file
@@ -0,0 +1,556 @@
|
||||
---
|
||||
# ------------------------------------------------------------------------------
|
||||
# FILE: cluster/applications/monitoring/llama-swap-dashboard.yaml
|
||||
# DESCRIPTION: Custom Grafana dashboard for llama-swap GPU/LLM monitoring.
|
||||
# Picked up automatically by the Grafana sidecar via label:
|
||||
# grafana_dashboard: "1"
|
||||
# Based on the Ciro Luciotta homelab LLM monitoring pattern.
|
||||
#
|
||||
# USAGE: This ConfigMap is reconciled by ArgoCD. The dashboard JSON is
|
||||
# embedded inline (data key ends in .json).
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: dashboard-llama-swap
|
||||
namespace: monitoring
|
||||
labels:
|
||||
grafana_dashboard: "1"
|
||||
app.kubernetes.io/part-of: monitoring
|
||||
data:
|
||||
llama-swap.json: |
|
||||
{
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": "-- Grafana --",
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"type": "dashboard"
|
||||
}
|
||||
]
|
||||
},
|
||||
"editable": true,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "MiB",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"tooltip": false,
|
||||
"viz": false,
|
||||
"legend": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"max": 24576,
|
||||
"min": 0,
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 23000
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 24000
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "8.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "llamacpp_vram_used_mib{job=\"node\"}",
|
||||
"interval": "",
|
||||
"legendFormat": "VRAM Used",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "GPU VRAM Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"mappings": [],
|
||||
"max": 1,
|
||||
"min": 0,
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 0.8
|
||||
},
|
||||
{
|
||||
"color": "orange",
|
||||
"value": 0.92
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 0.95
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "percentunit"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"options": {
|
||||
"orientation": "auto",
|
||||
"reduceOptions": {
|
||||
"values": false,
|
||||
"fields": "",
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
]
|
||||
},
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"pluginVersion": "8.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "llamacpp_kv_cache_usage_ratio",
|
||||
"interval": "",
|
||||
"legendFormat": "{{ model }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "KV-Cache Utilization (Gauge)",
|
||||
"type": "gauge"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "ms/token",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"tooltip": false,
|
||||
"viz": false,
|
||||
"legend": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": true,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "ms"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"id": 3,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"mean",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "8.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(llamacpp_time_predict_ms_sum[5m]) / rate(llamacpp_time_predict_ms_count[5m])",
|
||||
"interval": "",
|
||||
"legendFormat": "{{ model }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Prediction Latency by Model",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "Queue Size",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"tooltip": false,
|
||||
"viz": false,
|
||||
"legend": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": true,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 3
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 5
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"id": 4,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"mean",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "8.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "llamacpp_queue_size",
|
||||
"interval": "",
|
||||
"legendFormat": "{{ model }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Request Queue Depth",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "tokens/min",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"tooltip": false,
|
||||
"viz": false,
|
||||
"legend": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": true,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"id": 5,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "8.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(llamacpp_tokens_predicted_total[1m]) * 60",
|
||||
"interval": "",
|
||||
"legendFormat": "{{ model }} (tokens/min)",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Token Generation Throughput",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "Tokens",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "bars",
|
||||
"fillOpacity": 100,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"tooltip": false,
|
||||
"viz": false,
|
||||
"legend": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": true,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "normal"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"id": 6,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "8.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, rate(llamacpp_time_predict_ms_bucket[5m]))",
|
||||
"interval": "",
|
||||
"legendFormat": "p95 latency",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, rate(llamacpp_time_predict_ms_bucket[5m]))",
|
||||
"interval": "",
|
||||
"legendFormat": "p99 latency",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Latency Percentiles (p95, p99)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "30s",
|
||||
"schemaVersion": 27,
|
||||
"style": "dark",
|
||||
"tags": [
|
||||
"llm",
|
||||
"llama-swap",
|
||||
"gpu-monitoring",
|
||||
"ciro-luciotta"
|
||||
],
|
||||
"templating": {
|
||||
"list": []
|
||||
},
|
||||
"time": {
|
||||
"from": "now-24h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {},
|
||||
"timezone": "",
|
||||
"title": "llama-swap GPU/LLM Monitoring",
|
||||
"uid": "llama-swap-monitor",
|
||||
"version": 1
|
||||
}
|
||||
@@ -125,7 +125,7 @@ prometheus:
|
||||
- target_label: __address__
|
||||
replacement: snmp-exporter.monitoring.svc.cluster.local:9116
|
||||
|
||||
# usw-pro-aggregation
|
||||
# SNMP – usw-pro-aggregation
|
||||
- job_name: snmp-usw-pro-aggregation
|
||||
scrape_interval: 60s
|
||||
scrape_timeout: 55s
|
||||
@@ -266,31 +266,56 @@ prometheus:
|
||||
# endpoint: astro-orbiter-router
|
||||
# model: Qwen3.6-35B-A3B-UD-Q4_K_S
|
||||
|
||||
- job_name: llama-server-astro-orbiter-llama3
|
||||
scrape_interval: 90s
|
||||
metrics_path: /metrics
|
||||
params:
|
||||
model: ["Meta-Llama-3.1-8B-Instruct-Q4_K_M"]
|
||||
static_configs:
|
||||
- targets:
|
||||
- 10.1.71.130:8002
|
||||
labels:
|
||||
hostname: astro-orbiter
|
||||
endpoint: astro-orbiter-router
|
||||
model: Meta-Llama-3.1-8B-Instruct-Q4_K_M
|
||||
# llama-server-astro-orbiter-llama3 — DEPRECATED (2026-08-18):
|
||||
# Router mode on :8002 replaced by llama-swap on :8001. llama-swap exposes
|
||||
# single /metrics endpoint (not per-model). See llama-swap job below.
|
||||
# - job_name: llama-server-astro-orbiter-llama3
|
||||
# scrape_interval: 90s
|
||||
# metrics_path: /metrics
|
||||
# params:
|
||||
# model: ["Meta-Llama-3.1-8B-Instruct-Q4_K_M"]
|
||||
# static_configs:
|
||||
# - targets:
|
||||
# - 10.1.71.130:8002
|
||||
# labels:
|
||||
# hostname: astro-orbiter
|
||||
# endpoint: astro-orbiter-router
|
||||
# model: Meta-Llama-3.1-8B-Instruct-Q4_K_M
|
||||
|
||||
- job_name: llama-server-astro-orbiter-phi35
|
||||
scrape_interval: 90s
|
||||
metrics_path: /metrics
|
||||
params:
|
||||
model: ["Phi-3.5-mini-instruct-Q8_0"]
|
||||
# llama-server-astro-orbiter-phi35 — DEPRECATED (2026-08-18):
|
||||
# Same as above — router replaced by llama-swap. Use llama-swap /metrics.
|
||||
# - job_name: llama-server-astro-orbiter-phi35
|
||||
# scrape_interval: 90s
|
||||
# metrics_path: /metrics
|
||||
# params:
|
||||
# model: ["Phi-3.5-mini-instruct-Q8_0"]
|
||||
# static_configs:
|
||||
# - targets:
|
||||
# - 10.1.71.130:8002
|
||||
# labels:
|
||||
# hostname: astro-orbiter
|
||||
# endpoint: astro-orbiter-router
|
||||
# model: Phi-3.5-mini-instruct-Q8_0
|
||||
|
||||
# llama-swap (production, since 2026-08-18)
|
||||
# Replaces the per-model /metrics?model=<id> jobs above (all targeting now-deprecated :8002).
|
||||
# llama-swap natively exposes /metrics on its own endpoint with model-labeled metrics.
|
||||
- job_name: llama-swap
|
||||
scrape_interval: 30s
|
||||
scrape_timeout: 10s
|
||||
static_configs:
|
||||
- targets:
|
||||
- 10.1.71.130:8002
|
||||
- 10.1.71.130:8001
|
||||
labels:
|
||||
hostname: astro-orbiter
|
||||
endpoint: astro-orbiter-router
|
||||
model: Phi-3.5-mini-instruct-Q8_0
|
||||
service: llama-swap
|
||||
environment: homelab
|
||||
metrics_path: /metrics
|
||||
honor_labels: true
|
||||
metric_relabel_configs:
|
||||
- source_labels: [__name__]
|
||||
regex: 'llamacpp_.*'
|
||||
action: keep
|
||||
|
||||
# ─── Grafana ──────────────────────────────────────────────────────────────────
|
||||
grafana:
|
||||
|
||||
Reference in New Issue
Block a user