mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-22 01:17:19 +08:00
Publish
This commit is contained in:
samber
parent
080a792777
commit
879436f440
4 changed files with 315 additions and 0 deletions
105
dist/rules/golang/golang-exporter.yml
vendored
Normal file
105
dist/rules/golang/golang-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,105 @@
|
|||
groups:
|
||||
|
||||
- name: GolangExporter
|
||||
|
||||
|
||||
rules:
|
||||
|
||||
# Threshold is a rough default. High-concurrency servers may legitimately run thousands of goroutines. Adjust to match your baseline.
|
||||
- alert: GoGoroutineCountHigh
|
||||
expr: 'go_goroutines > 1000'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go goroutine count high (instance {{ $labels.instance }})
|
||||
description: "Go application has too many goroutines (> 1000), potential goroutine leak\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# quantile="1" is the maximum observed GC pause in the current summary window, not p99.
|
||||
# A single outlier pause can push this above 1s. The for: 5m ensures the max stays elevated.
|
||||
- alert: GoGcDurationHigh
|
||||
expr: 'go_gc_duration_seconds{quantile="1"} > 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go GC duration high (instance {{ $labels.instance }})
|
||||
description: "Go GC pause duration is too high (max > 1s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# go_memstats_sys_bytes is the total memory obtained from the OS by the Go runtime, not total host memory.
|
||||
# This ratio measures Go-internal memory utilization, not system-level memory pressure.
|
||||
- alert: GoMemoryUsageHigh
|
||||
expr: '(go_memstats_heap_alloc_bytes / go_memstats_sys_bytes) * 100 > 90'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go memory usage high (instance {{ $labels.instance }})
|
||||
description: "Go heap allocation is using most of the runtime's reserved memory (> 90%), indicating the process may need more memory or has a leak\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# Threshold is workload-dependent. Applications with heavy CGo or blocking I/O may legitimately use more OS threads. Adjust to match your baseline.
|
||||
- alert: GoThreadCountHigh
|
||||
expr: 'go_threads > 50'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go thread count high (instance {{ $labels.instance }})
|
||||
description: "Go OS thread count is high (> 50), potential blocking syscall or CGo leak\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# Threshold is a rough default. Adjust based on your application's normal object count.
|
||||
- alert: GoHeapObjectsCountHigh
|
||||
expr: 'go_memstats_heap_objects > 10000000'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go heap objects count high (instance {{ $labels.instance }})
|
||||
description: "Go heap has too many live objects (> 10M), high GC pressure\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# go_memstats_gc_cpu_fraction is deprecated since Go 1.20 and may return 0 in newer versions.
|
||||
# Consider using runtime/metrics-based alternatives if running Go >= 1.20.
|
||||
- alert: GoGcCpuFractionHigh
|
||||
expr: 'go_memstats_gc_cpu_fraction > 0.05'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go GC CPU fraction high (instance {{ $labels.instance }})
|
||||
description: "Go GC is consuming too much CPU (> 5%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: GoGoroutineSpike
|
||||
expr: 'deriv(go_goroutines[5m]) > 100'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go goroutine spike (instance {{ $labels.instance }})
|
||||
description: "Go goroutine count is growing rapidly\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: GoHeapFragmentation
|
||||
expr: 'go_memstats_heap_idle_bytes / go_memstats_heap_sys_bytes > 0.9'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go heap fragmentation (instance {{ $labels.instance }})
|
||||
description: "Go heap has high idle ratio (> 90%), indicating memory fragmentation\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: GoMemoryLeak
|
||||
expr: 'rate(go_memstats_alloc_bytes_total[5m]) > 1e9'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go memory leak (instance {{ $labels.instance }})
|
||||
description: "Go application has sustained high allocation rate (> 1GB/s), potential memory leak\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: GoStackMemoryHigh
|
||||
expr: 'go_memstats_stack_inuse_bytes > 1e9'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Go stack memory high (instance {{ $labels.instance }})
|
||||
description: "Go stack memory usage is high (> 1GB), likely excessive goroutines or deep recursion\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
105
dist/rules/jvm/jvm-exporter.yml
vendored
105
dist/rules/jvm/jvm-exporter.yml
vendored
|
|
@ -13,3 +13,108 @@ groups:
|
|||
annotations:
|
||||
summary: JVM memory filling up (instance {{ $labels.instance }})
|
||||
description: "JVM memory is filling up (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# Many JVM configurations leave metaspace unbounded, in which case jvm_memory_max_bytes{area="nonheap"} is -1 and this alert will not fire.
|
||||
# The query filters out max_bytes <= 0 to avoid false negatives.
|
||||
- alert: JvmNon-heapMemoryFillingUp
|
||||
expr: '(sum by (instance)(jvm_memory_used_bytes{area="nonheap"}) / (sum by (instance)(jvm_memory_max_bytes{area="nonheap"}) > 0)) * 100 > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM non-heap memory filling up (instance {{ $labels.instance }})
|
||||
description: "JVM non-heap memory (metaspace/code cache) is filling up (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JvmGcTimeTooHigh
|
||||
expr: 'sum by (instance)(rate(jvm_gc_collection_seconds_sum[5m])) > 0.05'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM GC time too high (instance {{ $labels.instance }})
|
||||
description: "JVM is spending too much time in garbage collection (> 5% of wall clock time)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JvmThreadsDeadlocked
|
||||
expr: 'jvm_threads_deadlocked > 0'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: JVM threads deadlocked (instance {{ $labels.instance }})
|
||||
description: "JVM has deadlocked threads\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JvmThreadCountHigh
|
||||
expr: 'jvm_threads_current > 300'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM thread count high (instance {{ $labels.instance }})
|
||||
description: "JVM thread count is high (> 300), potential thread leak\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JvmThreadsBlocked
|
||||
expr: 'jvm_threads_state{state="BLOCKED"} > 50'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM threads BLOCKED (instance {{ $labels.instance }})
|
||||
description: "JVM has high number of BLOCKED threads, indicating lock contention\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# This regex matches CMS, G1, and Parallel collector names. It will not match ZGC or Shenandoah cycle names.
|
||||
# Adjust the gc label filter if you use a different collector.
|
||||
- alert: JvmOldGenGcFrequency
|
||||
expr: 'rate(jvm_gc_collection_seconds_count{gc=~".*old.*|.*major.*"}[5m]) > 0.3'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM old gen GC frequency (instance {{ $labels.instance }})
|
||||
description: "Frequent old/major GC cycles, indicating memory pressure\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JvmDirectBufferPoolFillingUp
|
||||
expr: '(jvm_buffer_pool_used_bytes / jvm_buffer_pool_capacity_bytes) * 100 > 90'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM direct buffer pool filling up (instance {{ $labels.instance }})
|
||||
description: "JVM direct buffer pool is filling up (> 90%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JvmObjectsPendingFinalization
|
||||
expr: 'jvm_memory_objects_pending_finalization > 1000'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM objects pending finalization (instance {{ $labels.instance }})
|
||||
description: "JVM has objects pending finalization, potential memory leak\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# process_open_fds and process_max_fds are generic metrics from the Prometheus client library, not JVM-specific.
|
||||
# This alert will also fire for Go, Python, or any process exposing these metrics.
|
||||
- alert: JvmFileDescriptorsExhaustion
|
||||
expr: '(process_open_fds / process_max_fds) * 100 > 90'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM file descriptors exhaustion (instance {{ $labels.instance }})
|
||||
description: "JVM process is running out of file descriptors (> 90% used)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JvmClassLoadingAnomaly
|
||||
expr: 'rate(jvm_classes_loaded_total[5m]) > 100'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM class loading anomaly (instance {{ $labels.instance }})
|
||||
description: "Rapid class loading detected, potential classloader leak\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JvmCompilationTimeSpike
|
||||
expr: 'rate(jvm_compilation_time_seconds_total[5m]) > 0.1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM compilation time spike (instance {{ $labels.instance }})
|
||||
description: "Excessive JIT compilation time consuming CPU\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
|
|
|||
53
dist/rules/python/python-exporter.yml
vendored
Normal file
53
dist/rules/python/python-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,53 @@
|
|||
groups:
|
||||
|
||||
- name: PythonExporter
|
||||
|
||||
|
||||
rules:
|
||||
|
||||
- alert: PythonGcObjectsUncollectable
|
||||
expr: 'increase(python_gc_objects_uncollectable_total[5m]) > 0'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Python GC objects uncollectable (instance {{ $labels.instance }})
|
||||
description: "Python has uncollectable objects, potential memory leak via reference cycles\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PythonGcCollectionsHigh
|
||||
expr: 'rate(python_gc_objects_collected_total[5m]) > 10000'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Python GC collections high (instance {{ $labels.instance }})
|
||||
description: "Python GC is collecting too many objects (> 10k/s), high allocation pressure\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# process_open_fds and process_max_fds are generic metrics from the Prometheus client library, not Python-specific.
|
||||
- alert: PythonFileDescriptorsExhaustion
|
||||
expr: '(process_open_fds / process_max_fds) * 100 > 90'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Python file descriptors exhaustion (instance {{ $labels.instance }})
|
||||
description: "Python process is running out of file descriptors (> 90% used)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PythonGcGeneration2CollectionsHigh
|
||||
expr: 'rate(python_gc_collections_total{generation="2"}[5m]) > 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Python GC generation 2 collections high (instance {{ $labels.instance }})
|
||||
description: "Python full GC (generation 2) is running too frequently, indicating memory pressure\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# Threshold is a rough default. Adjust based on your application's expected memory footprint.
|
||||
- alert: PythonVirtualMemoryHigh
|
||||
expr: 'process_virtual_memory_bytes > 4e9'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Python virtual memory high (instance {{ $labels.instance }})
|
||||
description: "Python process virtual memory is high (> 4GB)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
52
dist/rules/ruby/ruby-exporter.yml
vendored
Normal file
52
dist/rules/ruby/ruby-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,52 @@
|
|||
groups:
|
||||
|
||||
- name: RubyExporter
|
||||
|
||||
|
||||
rules:
|
||||
|
||||
# Threshold is a rough default. Adjust based on your application's normal heap size.
|
||||
- alert: RubyHeapLiveSlotsHigh
|
||||
expr: 'ruby_heap_live_slots > 500000'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ruby heap live slots high (instance {{ $labels.instance }})
|
||||
description: "Ruby heap has too many live slots (> 500k), heap bloat\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RubyHeapFreeSlotsHigh
|
||||
expr: 'ruby_heap_free_slots > 500000'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ruby heap free slots high (instance {{ $labels.instance }})
|
||||
description: "Ruby heap has too many free slots (> 500k), memory fragmentation after large allocations\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RubyMajorGcRateHigh
|
||||
expr: 'rate(ruby_major_gc_ops_total[5m]) > 5'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ruby major GC rate high (instance {{ $labels.instance }})
|
||||
description: "Ruby is performing too many major GC cycles, indicating memory pressure\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RubyRssHigh
|
||||
expr: 'ruby_rss > 1e9'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ruby RSS high (instance {{ $labels.instance }})
|
||||
description: "Ruby process RSS is high (> 1GB)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RubyAllocatedObjectsSpike
|
||||
expr: 'rate(ruby_allocated_objects_total[5m]) > 100000'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ruby allocated objects spike (instance {{ $labels.instance }})
|
||||
description: "Ruby is allocating objects at a high rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
Loading…
Reference in a new issue