init

conf/prometheus/alerts/blackbox.yml

@@ -0,0 +1,74 @@
+groups:
+  - name: blackbox
+    rules:
+      - alert: BlackboxProbeFailed
+        expr: probe_success == 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Blackbox probe failed (instance {{ $labels.instance }})
+          description: "Probe failed\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: BlackboxSlowProbe
+        expr: avg_over_time(probe_duration_seconds[1m]) > 5
+        for: 1m
+        labels:
+          severity: warning
+        annotations:
+          summary: Blackbox slow probe (instance {{ $labels.instance }})
+          description: "Blackbox probe took more than 5s to complete\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: BlackboxProbeHttpFailure
+        expr: probe_http_status_code <= 199 OR probe_http_status_code >= 400
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Blackbox probe HTTP failure (instance {{ $labels.instance }})
+          description: "HTTP status code is not 200-399\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: BlackboxSslCertificateWillExpireSoon
+        expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 30
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Blackbox SSL certificate will expire soon (instance {{ $labels.instance }})
+          description: "SSL certificate expires in 30 days\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: BlackboxSslCertificateWillExpireSoon
+        expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 3
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Blackbox SSL certificate will expire soon (instance {{ $labels.instance }})
+          description: "SSL certificate expires in 3 days\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: BlackboxSslCertificateExpired
+        expr: probe_ssl_earliest_cert_expiry - time() <= 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Blackbox SSL certificate expired (instance {{ $labels.instance }})
+          description: "SSL certificate has expired already\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: BlackboxProbeSlowHttp
+        expr: avg_over_time(probe_http_duration_seconds[1m]) > 1
+        for: 1m
+        labels:
+          severity: warning
+        annotations:
+          summary: Blackbox probe slow HTTP (instance {{ $labels.instance }})
+          description: "HTTP request took more than 1s\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: BlackboxProbeSlowPing
+        expr: avg_over_time(probe_icmp_duration_seconds[1m]) > 1
+        for: 1m
+        labels:
+          severity: warning
+        annotations:
+          summary: Blackbox probe slow ping (instance {{ $labels.instance }})
+          description: "Blackbox ping took more than 1s\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

conf/prometheus/alerts/cadvisor.yml

@@ -0,0 +1,68 @@
+groups:
+  - name: cadvisor
+    rules:
+      # This rule can be very noisy in dynamic infra with legitimate container start/stop/deployment.
+      - alert: ContainerKilled
+        expr: time() - container_last_seen > 60
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Container killed (instance {{ $labels.instance }})
+          description: "A container has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      # This rule can be very noisy in dynamic infra with legitimate container start/stop/deployment.
+      - alert: ContainerAbsent
+        expr: absent(container_last_seen)
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: Container absent (instance {{ $labels.instance }})
+          description: "A container is absent for 5 min\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: ContainerCpuUsage
+        expr: (sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) > 80
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: Container CPU usage (instance {{ $labels.instance }})
+          description: "Container CPU usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      # See https://medium.com/faun/how-much-is-too-much-the-linux-oomkiller-and-used-memory-d32186f29c9d
+      - alert: ContainerMemoryUsage
+        expr: (sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: Container Memory usage (instance {{ $labels.instance }})
+          description: "Container Memory usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: ContainerVolumeUsage
+        expr: (1 - (sum(container_fs_inodes_free{name!=""}) BY (instance) / sum(container_fs_inodes_total) BY (instance))) * 100 > 80
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: Container Volume usage (instance {{ $labels.instance }})
+          description: "Container Volume usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: ContainerVolumeIoUsage
+        expr: (sum(container_fs_io_current{name!=""}) BY (instance, name) * 100) > 80
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: Container Volume IO usage (instance {{ $labels.instance }})
+          description: "Container Volume IO usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: ContainerHighThrottleRate
+        expr: rate(container_cpu_cfs_throttled_seconds_total[3m]) > 1
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: Container high throttle rate (instance {{ $labels.instance }})
+          description: "Container is being throttled\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

conf/prometheus/alerts/node.yml

@@ -0,0 +1,308 @@
+groups:
+  - name: Node
+    rules:
+    - alert: HostOutOfMemory
+      expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host out of memory (instance {{ $labels.instance }})
+        description: "Node memory is filling up (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostMemoryUnderMemoryPressure
+      expr: rate(node_vmstat_pgmajfault[1m]) > 1000
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host memory under memory pressure (instance {{ $labels.instance }})
+        description: "The node is under heavy memory pressure. High rate of major page faults\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostUnusualNetworkThroughputIn
+      expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual network throughput in (instance {{ $labels.instance }})
+        description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostUnusualNetworkThroughputOut
+      expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual network throughput out (instance {{ $labels.instance }})
+        description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostUnusualDiskReadRate
+      expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual disk read rate (instance {{ $labels.instance }})
+        description: "Disk is probably reading too much data (> 50 MB/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostUnusualDiskWriteRate
+      expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual disk write rate (instance {{ $labels.instance }})
+        description: "Disk is probably writing too much data (> 50 MB/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    # Please add ignored mountpoints in node_exporter parameters like
+    # "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
+    # Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
+    - alert: HostOutOfDiskSpace
+      expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host out of disk space (instance {{ $labels.instance }})
+        description: "Disk is almost full (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    # Please add ignored mountpoints in node_exporter parameters like
+    # "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
+    # Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
+    - alert: HostDiskWillFillIn24Hours
+      expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
+        description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostOutOfInodes
+      expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host out of inodes (instance {{ $labels.instance }})
+        description: "Disk is almost running out of available inodes (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostInodesWillFillIn24Hours
+      expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{mountpoint="/rootfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host inodes will fill in 24 hours (instance {{ $labels.instance }})
+        description: "Filesystem is predicted to run out of inodes within the next 24 hours at current write rate\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostUnusualDiskReadLatency
+      expr: rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual disk read latency (instance {{ $labels.instance }})
+        description: "Disk latency is growing (read operations > 100ms)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostUnusualDiskWriteLatency
+      expr: rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual disk write latency (instance {{ $labels.instance }})
+        description: "Disk latency is growing (write operations > 100ms)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostHighCpuLoad
+      expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host high CPU load (instance {{ $labels.instance }})
+        description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostCpuStealNoisyNeighbor
+      expr: avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
+        description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    # 1000 context switches is an arbitrary number.
+    # Alert threshold depends on nature of application.
+    # Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
+    - alert: HostContextSwitching
+      expr: (rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 2000
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host context switching (instance {{ $labels.instance }})
+        description: "Context switching is growing on node (> 2000 / s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostSwapIsFillingUp
+      expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host swap is filling up (instance {{ $labels.instance }})
+        description: "Swap is filling up (>80%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostSystemdServiceCrashed
+      expr: node_systemd_unit_state{state="failed"} == 1
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host systemd service crashed (instance {{ $labels.instance }})
+        description: "systemd service crashed\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostPhysicalComponentTooHot
+      expr: node_hwmon_temp_celsius > 75
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host physical component too hot (instance {{ $labels.instance }})
+        description: "Physical hardware component too hot\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostNodeOvertemperatureAlarm
+      expr: node_hwmon_temp_crit_alarm_celsius == 1
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Host node overtemperature alarm (instance {{ $labels.instance }})
+        description: "Physical node temperature alarm triggered\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostRaidArrayGotInactive
+      expr: node_md_state{state="inactive"} > 0
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Host RAID array got inactive (instance {{ $labels.instance }})
+        description: "RAID array {{ $labels.device }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostRaidDiskFailure
+      expr: node_md_disks{state="failed"} > 0
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host RAID disk failure (instance {{ $labels.instance }})
+        description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    #- alert: HostKernelVersionDeviations
+    #  expr: count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 1
+    #  for: 6h
+    #  labels:
+    #    severity: warning
+    #  annotations:
+    #    summary: Host kernel version deviations (instance {{ $labels.instance }})
+    #    description: "Different kernel versions are running\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostOomKillDetected
+      expr: increase(node_vmstat_oom_kill[1m]) > 0
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host OOM kill detected (instance {{ $labels.instance }})
+        description: "OOM kill detected\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostEdacCorrectableErrorsDetected
+      expr: increase(node_edac_correctable_errors_total[1m]) > 0
+      for: 0m
+      labels:
+        severity: info
+      annotations:
+        summary: Host EDAC Correctable Errors detected (instance {{ $labels.instance }})
+        description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostEdacUncorrectableErrorsDetected
+      expr: node_edac_uncorrectable_errors_total > 0
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }})
+        description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostNetworkReceiveErrors
+      expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host Network Receive Errors (instance {{ $labels.instance }})
+        description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostNetworkTransmitErrors
+      expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host Network Transmit Errors (instance {{ $labels.instance }})
+        description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostNetworkInterfaceSaturated
+      expr: (rate(node_network_receive_bytes_total{device!~"^tap.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*"} > 0.8 < 10000
+      for: 1m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host Network Interface Saturated (instance {{ $labels.instance }})
+        description: "The network interface \"{{ $labels.device }}\" on \"{{ $labels.instance }}\" is getting overloaded.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostNetworkBondDegraded
+      expr: (node_bonding_active - node_bonding_slaves) != 0
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host Network Bond Degraded (instance {{ $labels.instance }})
+        description: "Bond \"{{ $labels.device }}\" degraded on \"{{ $labels.instance }}\".\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostConntrackLimit
+      expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host conntrack limit (instance {{ $labels.instance }})
+        description: "The number of conntrack is approaching limit\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostClockSkew
+      expr: (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host clock skew (instance {{ $labels.instance }})
+        description: "Clock skew detected. Clock is out of sync. Ensure NTP is configured correctly on this host.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostClockNotSynchronising
+      expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host clock not synchronising (instance {{ $labels.instance }})
+        description: "Clock not synchronising. Ensure NTP is configured on this host.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostRequiresReboot
+      expr: node_reboot_required > 0
+      for: 4h
+      labels:
+        severity: info
+      annotations:
+        summary: Host requires reboot (instance {{ $labels.instance }})
+        description: "{{ $labels.instance }} requires a reboot.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

conf/prometheus/alerts/prometheus.yml

@@ -0,0 +1,236 @@
+groups:
+  - name: Prometheus
+    rules:
+      - alert: PrometheusJobMissing
+        expr: absent(up{job="prometheus"})
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus job missing (instance {{ $labels.instance }})
+          description: "A Prometheus job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTargetMissing
+        expr: up == 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus target missing (instance {{ $labels.instance }})
+          description: "A Prometheus target has disappeared. An exporter might be crashed.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusAllTargetsMissing
+        expr: count by (job) (up) == 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus all targets missing (instance {{ $labels.instance }})
+          description: "A Prometheus job does not have living target anymore.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusConfigurationReloadFailure
+        expr: prometheus_config_last_reload_successful != 1
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus configuration reload failure (instance {{ $labels.instance }})
+          description: "Prometheus configuration reload error\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTooManyRestarts
+        expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus too many restarts (instance {{ $labels.instance }})
+          description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusAlertmanagerJobMissing
+        expr: absent(up{job="alertmanager"})
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus AlertManager job missing (instance {{ $labels.instance }})
+          description: "A Prometheus AlertManager job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusAlertmanagerConfigurationReloadFailure
+        expr: alertmanager_config_last_reload_successful != 1
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})
+          description: "AlertManager configuration reload error\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusAlertmanagerConfigNotSynced
+        expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus AlertManager config not synced (instance {{ $labels.instance }})
+          description: "Configurations of AlertManager cluster instances are out of sync\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusAlertmanagerE2eDeadManSwitch
+        expr: vector(1)
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus AlertManager E2E dead man switch (instance {{ $labels.instance }})
+          description: "Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusNotConnectedToAlertmanager
+        expr: prometheus_notifications_alertmanagers_discovered < 1
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus not connected to alertmanager (instance {{ $labels.instance }})
+          description: "Prometheus cannot connect the alertmanager\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusRuleEvaluationFailures
+        expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus rule evaluation failures (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTemplateTextExpansionFailures
+        expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus template text expansion failures (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} template text expansion failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusRuleEvaluationSlow
+        expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus rule evaluation slow (instance {{ $labels.instance }})
+          description: "Prometheus rule evaluation took more time than the scheduled interval. It indicates a slower storage backend access or too complex query.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusNotificationsBacklog
+        expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus notifications backlog (instance {{ $labels.instance }})
+          description: "The Prometheus notification queue has not been empty for 10 minutes\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusAlertmanagerNotificationFailing
+        expr: rate(alertmanager_notifications_failed_total[1m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus AlertManager notification failing (instance {{ $labels.instance }})
+          description: "Alertmanager is failing sending notifications\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTargetEmpty
+        expr: prometheus_sd_discovered_targets == 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus target empty (instance {{ $labels.instance }})
+          description: "Prometheus has no target in service discovery\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTargetScrapingSlow
+        expr: prometheus_target_interval_length_seconds{quantile="0.9"} > 60
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus target scraping slow (instance {{ $labels.instance }})
+          description: "Prometheus is scraping exporters slowly\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusLargeScrape
+        expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus large scrape (instance {{ $labels.instance }})
+          description: "Prometheus has many scrapes that exceed the sample limit\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTargetScrapeDuplicate
+        expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 0
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: Prometheus target scrape duplicate (instance {{ $labels.instance }})
+          description: "Prometheus has many samples rejected due to duplicate timestamps but different values\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTsdbCheckpointCreationFailures
+        expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} checkpoint creation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTsdbCheckpointDeletionFailures
+        expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} checkpoint deletion failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTsdbCompactionsFailed
+        expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus TSDB compactions failed (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} TSDB compactions failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTsdbHeadTruncationsFailed
+        expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus TSDB head truncations failed (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} TSDB head truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTsdbReloadFailures
+        expr: increase(prometheus_tsdb_reloads_failures_total[1m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus TSDB reload failures (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} TSDB reload failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTsdbWalCorruptions
+        expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} TSDB WAL corruptions\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+      - alert: PrometheusTsdbWalTruncationsFailed
+        expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})
+          description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

conf/prometheus/prometheus.yml

@@ -0,0 +1,78 @@
+global:
+  scrape_interval: 20s
+
+rule_files:
+  - alerts/*.yml
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+            - alertmanager:9093
+
+scrape_configs:
+  - job_name: "prometheus"
+    scrape_interval: 5s
+    static_configs:
+      - targets: ["localhost:9090"]
+
+  - job_name: "alertmanager"
+    scrape_interval: 5s
+    static_configs:
+      - targets: ["alertmanager:9093"]
+
+  - job_name: "node"
+    static_configs:
+      - targets: ["node-exporter:9100"]
+
+  - job_name: "cadvisor"
+    static_configs:
+      - targets: ["cadvisor:8080"]
+
+  - job_name: "node_nyyu"
+    scheme: https
+    metrics_path: /node/metrics
+    static_configs:
+      - targets: ["nyyu.dev:443"]
+
+  # - job_name: "smokeping"
+  #   static_configs:
+  #     - targets: ["smokeping:9374"]
+
+  - job_name: "blackbox"
+    metrics_path: /probe
+    params:
+      module: [http_2xx]
+    dns_sd_configs:
+      - names:
+          - nyyu.dev
+        type: A
+        port: 443
+    relabel_configs:
+      - source_labels: [__address__]
+        target_label: __param_target
+        replacement: https://$1/
+      - source_labels: [__param_target]
+        target_label: target
+      - target_label: __address__
+        replacement: blackbox:9115
+      - source_labels: [__meta_dns_name]
+        target_label: __param_hostname
+      - source_labels: [__meta_dns_name]
+        target_label: vhost
+
+  - job_name: "blackbox_icmp"
+    metrics_path: /probe
+    params:
+      module: [icmp]
+    static_configs:
+        - targets:
+          - 1.1.1.1
+          - nyyu.dev
+    relabel_configs:
+      - source_labels: [__address__]
+        target_label: __param_target
+      - source_labels: [__param_target]
+        target_label: target
+      - target_label: __address__
+        replacement: blackbox:9115