Kubernetes 应注意哪种公制织网?
暴露了以下几点 以下警报看起来正确吗?对于这些指标的哪些值,我们应该提高警惕以监控网络健康状况Kubernetes 应注意哪种公制织网?,kubernetes,prometheus,weave,Kubernetes,Prometheus,Weave,暴露了以下几点 以下警报看起来正确吗?对于这些指标的哪些值,我们应该提高警惕以监控网络健康状况 WeaveNoFastDP Weavenu流量[5m]>0 WeaviePamUnreachable weave\u ipam\u unreachable\u百分比>0 WeavePampendingAllocates weave\u ipam\u pending\u分配>0 WeavePendingClaims weave_ipam_PendingClaims>0 WeaveConnectEM编
- WeaveNoFastDP Weavenu流量[5m]>0
- WeaviePamUnreachable weave\u ipam\u unreachable\u百分比>0
- WeavePampendingAllocates weave\u ipam\u pending\u分配>0
- WeavePendingClaims weave_ipam_PendingClaims>0
- WeaveConnectEM编织连接终端总数>300
{
“团体”:[
{
“名称”:“节点代理”,
“规则”:[
{
“警报”:“不健康节点”,
“expr”:“更改(中心节点数:节点数、路由数[3m])>0”,
“用于”:“1m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“群集中不健康的节点。有关详细信息,请转到下面的prometheus链接。”,
“描述”:“可操作:查找节点不健康的原因并修复它。”
}
}
]
},
{
“名称”:“编织网”,
“规则”:[
{
“警报”:“WeaveNetIPAMSPlitBrain”,
“expr”:“最大值(织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入/织入百分比)>0”,
“for”:“3m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“概要”:“WeaveNetIPAM有一个分裂的大脑。有关详细信息,请访问下面的普罗米修斯链接。”,
“描述”:“可操作:每个节点都应看到相同的不可访问性百分比。请检查并修复其原因。”
}
},
{
“警报”:“WeavenetiPamunReach”,
“expr”:“织物/ipam/无法达到/百分比[10m]>25”,
“用于”:“10m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“WeaveNetIPAM不可访问百分比高于阈值。有关详细信息,请访问下面的prometheus链接。”,
“描述”:“可操作:查找无法访问阈值高于阈值的原因并修复它。WeaveNet负责控制它。WeaveNet rm对等部署可以帮助清理问题。”
}
},
{
“警报”:“WeaveNetIPAMPendingAllocates”,
“expr”:“总和(编织ipam未决分配)>0”,
“for”:“3m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“WeaveNet IPAM具有挂起的分配。有关详细信息,请转到下面的prometheus链接。”,
“描述”:“可操作:查找IPAM分配处于挂起状态的原因并修复它。”
}
},
{
“警报”:“WeaveNetIPAMPendingClaims”,
“expr”:“总金额(未决索赔)>0”,
“for”:“3m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“WeaveNet IPAM有未决索赔。有关详细信息,请访问以下普罗米修斯链接。”,
“说明”:“可采取行动:查找IPAM声明处于挂起状态的原因并进行修复。”
}
},
{
“警报”:“WeavenetFastdFlowSlow”,
“expr”:“总流量(weave_flows)<15000”,
“for”:“3m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“WeaveNet FastDP总流量低于阈值。有关详细信息,请访问下面的prometheus链接。”,
“说明”:“可操作:查找快速dp流降至阈值以下的原因。”
}
},
{
“警报”:“WeavenetFastdFlowsof”,
“expr”:“总和(weave_flows==bool 0)>0”,
“for”:“3m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“WeaveNet FastDP流未在部分或所有节点中发生。有关详细信息,请转到下面的prometheus链接。”,
“说明”:“可操作:查找快速dp关闭的原因。”
}
},
{
“警报”:“WeaveNetHighConnectionTerminationRate”,
“expr”:“速率(编织连接端接总数[5m])>0.1”,
“用于”:“5m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“许多连接正在被终止。有关详细信息,请访问下面的普罗米修斯链接。”,
“描述”:“可操作:找到高连接终止率的原因并修复它。”
}
},
{
“警报”:“WeavenetConnectionsConnections”,
“expr”:“和(weave_连接{state='connecting'})>0”,
“for”:“3m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“许多连接处于连接状态。有关详细信息,请访问下面的普罗米修斯链接。”,
“说明”:“可操作:找到原因并修复它。”
}
},
{
“警报”:“WeavenetConnectionsReing”,
“expr”:“和(weave_连接{state='retrying'})>0”,
“for”:“3m”,
“标签”:{
“严重性”:“严重”
},
“注释”:{
“摘要”:“许多连接处于重试状态。有关详细信息,请转到下面的prometheus链接。”,
“说明”:“可操作:找到原因并修复它。”
}
},
{
“警报”:“WeavenetConnection支出”,
“expr”:“和(weave_连接{state='pending'})>0”,
“for”:“3m”,
{
"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."
}
}
]
}
]
}