kubernetes - 应该在什么公制编织网上发出警报？

Question

WeaveNet公开了以下Prometheus 指标

以下警报看起来是否正确，可以收到警报？我们应该在这些指标的哪些值上提高警惕以监控编织网的健康状况？

• WeaveNoFastDP weave_flows[5m] > 0
• WeaveIPAMUnreachable weave_ipam_unreachable_percentage > 0
• WeaveIPAMPendingAllocates weave_ipam_pending_allocates > 0
• WeavePendingClaims weave_ipam_pending_claims > 0
• WeaveConnecTerm weave_connection_terminations_total > 300

标签： kubernetesprometheusweave

Answer 1

在编织指标之上制作了 grafana 仪表板。这是仪表板

1. WeaveNet https://grafana.com/grafana/dashboards/11789
2. WeaveNet（集群）https://grafana.com/grafana/dashboards/11804

以下是应监控编织网的有用指标。以下警报为 json 格式。

{
  "groups": [
    {
      "name": "nodeagent",
      "rules": [
        {
          "alert": "UnhealthyNodes",
          "expr": "changes(central_nodeagent:node_route_unhealthy_count[3m]) > 0",
          "for": "1m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "Unhealthy nodes in the cluster. Go to prometheus the below prometheus link for details.",
            "description": "Actionable: Find why the node(s) are unhealthy and fix it."
          }
        }
      ]
    },
    {
      "name": "weave-net",
      "rules": [
        {
          "alert": "WeaveNetIPAMSPlitBrain",
          "expr": "max(weave_ipam_unreachable_percentage) - min(weave_ipam_unreachable_percentage) > 0",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "WeaveNetIPAM has a split brain. Go to the below prometheus link for details.",
            "description": "Actionable: Every node should see same unreachability percentage. Please check and fix why it is not so."
          }
        },
        {
          "alert": "WeaveNetIPAMUnreachable",
          "expr": "weave_ipam_unreachable_percentage[10m] > 25",
          "for": "10m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "WeaveNetIPAM unreachability percentage is above threshold. Go to the below prometheus link for details.",
            "description": "Actionable: Find why the unreachability threshold have increased from threshold and fix it. WeaveNet is responsible to keep it under control. Weave rm peer deployment can help clean things."
          }
        },
        {
          "alert": "WeaveNetIPAMPendingAllocates",
          "expr": "sum(weave_ipam_pending_allocates) > 0",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "WeaveNet IPAM has pending allocates. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason for IPAM allocates to be in pending state and fix it."
          }
        },
        {
          "alert": "WeaveNetIPAMPendingClaims",
          "expr": "sum(weave_ipam_pending_claims) > 0",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "WeaveNet IPAM has pending claims. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason for IPAM claims to be in pending state and fix it."
          }
        },
        {
          "alert": "WeaveNetFastDPFlowsLow",
          "expr": "sum(weave_flows) < 15000",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "WeaveNet total FastDP flows is below threshold. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason for fast dp flows dropping below the threshold."
          }
        },
        {
          "alert": "WeaveNetFastDPFlowsOff",
          "expr": "sum(weave_flows == bool 0) > 0",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "WeaveNet FastDP flows is not happening in some or all nodes. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason for fast dp being off."
          }
        },
        {
          "alert": "WeaveNetHighConnectionTerminationRate",
          "expr": "rate(weave_connection_terminations_total[5m]) > 0.1",
          "for": "5m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "A lot of connections are getting terminated. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason for high connection termination rate and fix it."
          }
        },
        {
          "alert": "WeaveNetConnectionsConnecting",
          "expr": "sum(weave_connections{state='connecting'}) > 0",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "A lot of connections are in connecting state. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason and fix it."
          }
        },
        {
          "alert": "WeaveNetConnectionsRetying",
          "expr": "sum(weave_connections{state='retrying'}) > 0",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "A lot of connections are in retrying state. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason and fix it."
          }
        },
        {
          "alert": "WeaveNetConnectionsPending",
          "expr": "sum(weave_connections{state='pending'}) > 0",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "A lot of connections are in pending state. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason and fix it."
          }
        },
        {
          "alert": "WeaveNetConnectionsFailed",
          "expr": "sum(weave_connections{state='failed'}) > 0",
          "for": "3m",
          "labels": {
            "severity": "critical"
          },
          "annotations": {
            "summary": "A lot of connections are in failed state. Go to the below prometheus link for details.",
            "description": "Actionable: Find the reason and fix it."
          }
        }
      ]
    }
  ]
}