【Redis】K8S内基于Prometheus的Redis告警规则整理

拼搏现实的明天。 2023-09-29 17:34 8阅读 0赞

#### 文章目录 ####

*   *  Prometheus rule
     *  Alertmanager config
     *  Webhook

告警规则包含以下几个方面：

*  慢日志
 *  内存使用情况
 *  内存碎片率
 *  持久化耗时
 *  集群状态异常
 *  集群槽位分配异常
 *  从节点同步滞后
 *  Pod拓扑分布违背反亲和条件

### Prometheus rule ###

groups:
        - name: slowlog
          rules:
            - alert: slowlog
              annotations:
                description: 集群发现慢查询
                summary: >-
                  集群 {
        {
        $labels.redis_kun_name}} 一分钟内共出现 {
        {
         printf "%.2f" $value }}
                  次慢查询
              expr: 'delta(redis_slowlog_last_id [5m]) >= 5'
              labels:
                group: xadd-redis
                severity: critical
            - alert: used memory increase too fast
              annotations:
                description: 按照最近10分钟的内存使用增长速度计算，预计20分钟后将会达到配置上限
                summary: '集群 {
        {$labels.redis_kun_name}} 发现内存使用量增长过快'
              expr: >-
                predict_linear(redis_memory_used_bytes [10m], 60 * 20) >
                redis_memory_max_bytes
              labels:
                group: xadd-redis
                severity: critical
            - alert: used memory larger than history peak
              annotations:
                description: 内存使用量超过历史峰值
                summary: >-
                  集群 {
        {
        $labels.redis_kun_name}} 内存使用量超过历史峰值，当前内存使用量为 {
        {
         printf
                  "%.2f" $value }} GB
              expr: >-
                (redis_memory_used_bytes / (1024 * 1024 * 1024)) >=
                (redis_memory_used_peak_bytes / (1024 * 1024 * 1024)) and
                (redis_memory_used_bytes / redis_memory_max_bytes) > 0.8
              labels:
                group: xadd-redis
                severity: critical
            - alert: option-memory usage in hight ratio
              annotations:
                description: 内存使用超过90%，将开启自动扩容
                summary: '集群 {
        {$labels.redis_kun_name}} 内存使用超过redis最大设置内存的90%'
              expr: >-
                (redis_memory_used_bytes / redis_memory_max_bytes) * 100 > 90 and
                redis_memory_max_bytes >= (1024 * 1024 * 1024)
              labels:
                group: xadd-redis
                severity: critical
            - alert: memory usage in high fragmentation ratio
              annotations:
                description: '当前内存碎片率为 {
        { printf "%.2f" $value }}，理想值为1至1.4之间'
                summary: >-
                  集群 {
        {
        $labels.redis_kun_name}} 内存碎片率高，当前内存碎片率为 {
        {
         printf "%.2f"
                  $value }}，理想值为1至1.4之间
              expr: >-
                redis_memory_used_rss_bytes / redis_memory_used_bytes > 1.4 and
                redis_memory_used_bytes >= 1024 * 1024 * 1024
              for: 1w
              labels:
                group: xadd-redis
                severity: warning
            - alert: memory usage in low fragmentation ratio
              annotations:
                description: '当前内存碎片率为 {
        { printf "%.2f" $value }}，理想值为1至1.4之间'
                summary: >-
                  集群 {
        {
        $labels.redis_kun_name}}
                  内存碎片率小于1，redis-server进程可能正在使用swap区，导致响应速度降低
              expr: >-
                redis_memory_used_rss_bytes / redis_memory_used_bytes < 1 and
                redis_memory_used_bytes >= 512 * 1024 * 1024
              for: 1w
              labels:
                group: xadd-redis
                severity: warning
            - alert: rdb bgsave too slow
              annotations:
                description: '最近一次持久化时间为 {
        { $value }} 秒，建议降低该节点内存使用量至4GB以内'
                summary: '集群 {
        {$labels.redis_kun_name}} rdb持久化时间过长，最近一次持久化时间为 {
        { $value }} 秒'
              expr: >-
                redis_rdb_last_bgsave_duration_sec > 120 and time() -
                redis_rdb_last_save_timestamp_seconds < 3600
              labels:
                group: xadd-redis
                severity: critical
            - alert: redis exporter maybe down
              annotations:
                description: 请联系redis平台运维团队检查服务或主机状态
                summary: '集群 {
        {$labels.redis_kun_name}} exporter服务不可用'
              expr: up == 0
              for: 5m
              labels:
                addr: '{
        { $labels.instance }}'
                alias: ''
                group: xadd-redis
                severity: critical
            - alert: redis instance maybe down
              annotations:
                description: redis实例可能出现故障
                summary: >-
                  集群 {
        {
        $labels.redis_kun_name}} 中实例 {
        {
        $labels.kubernetes_pod_name}}
                  宕机
              expr: redis_up == 0
              for: 5s
              labels:
                group: xadd-redis
                severity: critical
            - alert: redis master slave failover
              annotations:
                description: redis集群发生主从切换
                summary: '集群 {
        {$labels.redis_kun_name}} 发生主从切换'
              expr: 'changes(redis_instance_info[5s]) > 1'
              labels:
                group: xadd-redis
                severity: critical
            - alert: state of cluster is unnormal
              annotations:
                description: 集群中发现节点的状态异常，并持续2分钟，触发此告警。
                summary: '检测到集群：{
        {$labels.redis_kun_name}}不可用，已持续2分钟。'
              expr: redis_cluster_state != 1
              for: 2m
              labels:
                group: xadd-redis
                severity: critical
            - alert: slots of cluster assigned unnormally
              annotations:
                description: 发现集群槽位分配小于16384，触发此告警。
                summary: '集群：{
        {$labels.redis_kun_name}} 的槽位未完全分配，当前分配槽位数量为：{
        {$value}}。'
              expr: redis_cluster_slots_assigned < 16384
              for: 2m
              labels:
                group: xadd-redis
                severity: critical
            - alert: slave lag too long
              annotations:
                description: Slave节点滞后时间超过10秒，触发此报警，集群cluster-node-timeout配置的是15秒。
                summary: >-
                  集群：{
        {
        $labels.redis_kun_name}}
                  中Master节点：{
        {
        $labels.kubernetes_pod_name}} 的Slave节点滞后超过10秒，Slave
                  IP为{
        {
        $labels.slave_ip}}。
              expr: redis_connected_slave_lag_seconds > 10
              labels:
                group: xadd-redis
                severity: warning
            - alert: cluster known nodes decreased
              annotations:
                description: 在两分钟内，集群的已知节点数量减少，触发此报警。
                summary: '集群：{
        {$labels.redis_kun_name}} 在两分钟内节点数减少了{
        {$value}}个，请检查集群状态是否正常。'
              expr: redis_cluster_known_nodes offset 2m - redis_cluster_known_nodes > 0
              labels:
                group: xadd-redis
                severity: critical
            - alert: redis exporter maybe down
              annotations:
                description: 2分钟内，若up状态的exporter数量减少，则认为减少的exporter存在宕机可能，触发此告警。
                summary: >-
                  集群：{
        {
        $labels.redis_kun_name}}
                  的exporter可能宕机，exporter实例地址为：{
        {
        $labels.instance}}。
              expr: 'up{namespace="redis"} unless up{namespace="redis"} offset 6m'
              for: 5m
              labels:
                group: xadd-redis
                severity: warning
            - alert: pod of the same master-slave group was deployed in same node
              annotations:
                description: 当集群中同一组Master/Slave部署到相同的Node上，触发该告警
                summary: '{
        {$labels.created_by_name}} 的主从节点部署到了相同的主机，主机IP为：{
        {$labels.node}}'
              expr: >-
                (count by(created_by_name,node)
                (kube_pod_info{
        namespace="redis"}))>1
              labels:
                group: xadd-redis
                severity: critical
            - alert: more than one master of the same cluster was deployed in same node
              annotations:
                description: 当集群中多个Master部署到相同的Node上，触发该告警
                summary: >-
                  发现集群：{
        {
        $labels.redis_kun_name}}
                  有多个Master部署到了相同的主机，主机IP为：{
        {
        $labels.node}}
              expr: >-
                count by (redis_kun_name, node) (kube_pod_info{
        namespace="redis"} *
                on (pod) group_left(redis_kun_name)
                label_replace(redis_instance_info{
        role="master"}, "pod", "$1",
                "kubernetes_pod_name", "(.*)"))>1
              labels:
                group: xadd-redis
                severity: critical

### Alertmanager config ###

global:
      resolve_timeout: 5m
    route:
      group_by: ['alertname','alias']
      group_wait: 10s
      group_interval: 30s
      repeat_interval: 1h
      receiver: 'redis-alert'
      routes:
      - receiver: 'redis-alert'
        group_wait: 30s
        group_interval: 30s
        repeat_interval: 30m
        match:
          group: xadd-redis
    receivers:
    - name: redis-alert
      webhook_configs:
      - url: 'http://172.22.43.230/api/web/alert/webhook'
        send_resolved: false
    inhibit_rules:
      - source_match:
          severity: 'critical'
        target_match:
          severity: 'warning'
        equal: ['alertname', 'dev', 'instance']

### Webhook ###

@ResponseBody
        @RequestMapping(value = "/webhook", method = RequestMethod.POST)
        public void webhook(@RequestBody Object alertInfo) {
        
            log.info("【alert info】：{}.", JSONObject.toJSON(alertInfo));
        }

数据发送到接口后，可以直接用JSON或者Map解析，再根据数据获取指定的标签作为告警信息，也可根据告警级别，选择不同的告警方式。