微信公众号：运维开发故事，作者：华仔

一、前言

为什么想到要用golang来编写metrics呢？这主要是我们的一个客户那里，k8s网络使用了ovs，并且做了bond，即bond0和bond1，每个bond下面2张网卡。在上了生产后，让我每天都要检查一下网卡是否正常，因为之前就有网卡DOWN了。而我呢，比较懒，不想手动去检查。想着通过prometheus最终展示到grafana，我就在grafana上看看有没有处于异常的网卡就好了。其次呢，我最近刚好在学习go，也想练练手；同时也问了一下研发同学，说很简单，叫我试试，遇到困难时也愿意帮助我。所以，我就打算试试了。

二、环境

组件	版本	备注
k8s	v1.14
ovs	v2.9.5
go	1.14.1

三、目标

目标就是要通过prometheus去拉取我的ovs bond的网卡状态指标，那么这里我需要编写一个go程序去获取我主机的ovs bond信息，并最终以metrics方式暴露供prometheus来拉取，在grafana上展示。示例如下：

# 现获取当前bond信息
[root@test~]$ ovs-appctl  bond/show |grep '^slave' |grep -v grep  |awk '{print $2""$3}'
a1-b1:enabled
a2-b2:enabled
a3-b3:enabled
a4-b4:disabled
# 最终组件暴露的数据如下 5代表获取bond信息的命令执行执行失败了，0-4表示有几张处于disabled状态的网卡
curl http://$IP:$PORT/metrics 
ovs_bond_status{component="ovs"} 5
ovs_bond_status{component="ovs","a1b1"="enabled","a2b2"="disabled","a3b3"="enabled",a4b4="disabled“} 2

四、构想

1. 由于要通过prometheus来抓取指标，所以bond 信息肯定要以metrics格式进行暴露。metrics格式可以参考prometheus官网。

2. bond有两个，每个下面有两张网卡，每张网卡的状态只有enabled和disabled，因此用数字0-4来告诉用户有几张网卡disabled了，用数字5来表示命令执行有问题或没有bond，需要人工介入。可以通过命令去获取bond信息，因此还是采取命令方式去获取。

3. 要对执行命令获取的输出结果进行处理并放到metrics中去。注：metrics的label不能有【-】。

4. shell命令返回的bond正确信息用map去接收，key为网卡名，value为网卡状态

5. 可以参考client_golang/prometheus

五、实践

先执行shell命令去获取bond信息

# 现获取当前bond信息
[root@test~]$ ovs-appctl  bond/show |grep '^slave' |grep -v grep  |awk '{print $2""$3}'
a1-b1:enabled
a2-b2:enabled
a3-b3:enabled
a4-b4:disabled

要针对shell的输出结果进行处理

# 执行shell命令，并对输出进行处理，记录相关日志
// return map 
// 一种是执行命令错误，一种是执行命令成功，但是返回null
func getBondStatus() (m map[string]string) {
	result, err := exec.Command("bash", "-c", "ovs-appctl bond/show | grep '^slave' | grep -v grep | awk '{print $2\"\"$3}'").Output()
	if err != nil {
		log.Error("result: ", string(result))
		log.Error("command failed: ", err.Error())
		m = make(map[string]string)
		m["msg"] = "failure"
		return m
	} else if len(result) == 0 {
		log.Error("command exec failed, result is null")
		m = make(map[string]string)
		m["msg"] = "return null"
		return m
	}
// 对结果进行进行处理，先去除两边空格
	ret := strings.TrimSpace(string(result))
    // 通过换行符切割
	tt := strings.Split(ret, "\n")
	//tt := []string{"a1-b1:enabled","a2-b2:disabled"}
    //如果key带有【-】，则需要去掉
	var nMap = make(map[string]string)
	for i := 0; i < len(tt); i++ {
		// if key contains "-"
		if strings.Contains(tt[i], "-") == true {
			nKey := strings.Split(strings.Split(tt[i], ":")[0], "-")
			nMap[strings.Join(nKey, "")] = (strings.Split(tt[i], ":"))[1]
		} else {
			nMap[(strings.Split(tt[i], ":"))[0]] = (strings.Split(tt[i], ":"))[1]
		}
	}
	return nMap
}

定义metrics指标

// define a struct
type ovsCollector struct {
    // 可以定义多个
	ovsMetric *prometheus.Desc
}

func (collector *ovsCollector) Describe(ch chan<- *prometheus.Desc) {
	ch <- collector.ovsMetric
}

// 网卡名
var vLable = []string{}
// 网卡状态
var vValue = []string{}
// 固定label，表明是ovs
var constLabel = prometheus.Labels{"component": "ovs"}

// define metric
func newOvsCollector() *ovsCollector {
	var rm = make(map[string]string)
	rm = getBondStatus()
	if _, ok := rm["msg"]; ok {
		log.Error("command execute failed：", rm["msg"])
	} else {
        //只获取网卡名
		for k, _ := range rm {
			// get the net
			vLable = append(vLable, k)
		}
	}
    // metric
	return &ovsCollector{
		ovsMetric: prometheus.NewDesc("ovs_bond_status",
			"Show ovs bond status", vLable,
			constLabel),
	}
}

指标对应值

// 命令执行正确则将对应的网卡、网卡状态以及处于异常的网卡数量注入到到metrics中去
func (collector *ovsCollector) Collect(ch chan<- prometheus.Metric) {
	var metricValue float64
	var rm = make(map[string]string)
	rm = getBondStatus()
	if _, ok := rm["msg"]; ok {
		log.Error("command exec failed")
		metricValue = 5
		ch <- prometheus.MustNewConstMetric(collector.ovsMetric, prometheus.CounterValue, metricValue)
	} else {
		vValue = vValue[0:0]
        //只取value
		for _, v := range rm {
			// get the net
			vValue = append(vValue, v)
            // 针对disabled计数
			if v == "disabled" {
				metricValue++
			}
		}
		ch <- prometheus.MustNewConstMetric(collector.ovsMetric, prometheus.CounterValue, metricValue, vValue...)
	}
}

程序入口

func main() {
	ovs := newOvsCollector()
	prometheus.MustRegister(ovs)

	http.Handle("/metrics", promhttp.Handler())

	log.Info("begin to server on port 8080")
	// listen on port 8080
	log.Fatal(http.ListenAndServe(":8080", nil))
}

完整代码

package main

import (
	"github.com/prometheus/client_golang/prometheus"
	"github.com/prometheus/client_golang/prometheus/promhttp"
	log "github.com/sirupsen/logrus"
	"net/http"
	"os/exec"
	"strings"
)

// define a struct   from prometheus's struct  named Desc
type ovsCollector struct {
	ovsMetric *prometheus.Desc
}

func (collector *ovsCollector) Describe(ch chan<- *prometheus.Desc) {
	ch <- collector.ovsMetric
}

var vLable = []string{}
var vValue = []string{}
var constLabel = prometheus.Labels{"component": "ovs"}

//  get the value of the metric from a function who would execute a command and return a float64 value
func (collector *ovsCollector) Collect(ch chan<- prometheus.Metric) {
	var metricValue float64
	var rm = make(map[string]string)
	rm = getBondStatus()
	if _, ok := rm["msg"]; ok {
		log.Error("command exec failed")
		metricValue = 5
		ch <- prometheus.MustNewConstMetric(collector.ovsMetric, prometheus.CounterValue, metricValue)
	} else {
		vValue = vValue[0:0]
		for _, v := range rm {
			// get the net
			vValue = append(vValue, v)
			if v == "disabled" {
				metricValue++
			}
		}


		ch <- prometheus.MustNewConstMetric(collector.ovsMetric, prometheus.CounterValue, metricValue, vValue...)
	}
}

// define metric's name、help
func newOvsCollector() *ovsCollector {
	var rm = make(map[string]string)
	rm = getBondStatus()
	if _, ok := rm["msg"]; ok {
		log.Error("command execute failed：", rm["msg"])
	} else {
		for k, _ := range rm {
			// get the net
			vLable = append(vLable, k)
		}
	}
	return &ovsCollector{
		ovsMetric: prometheus.NewDesc("ovs_bond_status",
			"Show ovs bond status", vLable,
			constLabel),
	}
}

func getBondStatus() (m map[string]string) {
	result, err := exec.Command("bash", "-c", "ovs-appctl bond/show | grep '^slave' | grep -v grep | awk '{print $2\"\"$3}'").Output()
	if err != nil {
		log.Error("result: ", string(result))
		log.Error("command failed: ", err.Error())
		m = make(map[string]string)
		m["msg"] = "failure"
		return m
	} else if len(result) == 0 {
		log.Error("command exec failed, result is null")
		m = make(map[string]string)
		m["msg"] = "return null"
		return m
	}
	ret := strings.TrimSpace(string(result))
	tt := strings.Split(ret, "\n")
	var nMap = make(map[string]string)
	for i := 0; i < len(tt); i++ {
		// if key contains "-"
		if strings.Contains(tt[i], "-") == true {
			nKey := strings.Split(strings.Split(tt[i], ":")[0], "-")
			nMap[strings.Join(nKey, "")] = (strings.Split(tt[i], ":"))[1]
		} else {
			nMap[(strings.Split(tt[i], ":"))[0]] = (strings.Split(tt[i], ":"))[1]
		}
	}
	return nMap
}

func main() {
	ovs := newOvsCollector()
	prometheus.MustRegister(ovs)

	http.Handle("/metrics", promhttp.Handler())

	log.Info("begin to server on port 8080")
	// listen on port 8080
	log.Fatal(http.ListenAndServe(":8080", nil))
}

六、部署

因为最终要部署到k8s环境中，
先构建镜像，参考如下Dockerfile

FROM golang:1.14.1 AS builder
WORKDIR /go/src
COPY ./ .
RUN go build -o ovs_check main.go

# runtime
FROM centos:7.7
COPY --from=builder /go/src/ovs_check /xiyangxixia/ovs_check
ENTRYPOINT ["/xiyangxixia/ovs_check"]

我这里部署使用的yaml如下所示：

---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: ovs-agent
  namespace: kube-system
spec:
  minReadySeconds: 5
  selector:
    matchLabels:
      name: ovs-agent
  template:
    metadata:
      annotations:
      # 这里三个都要加上，告诉promethue抓取路径
        prometheus.io/scrape: "true"
        prometheus.io/port: "8080"
        prometheus.io/path: "/metrics"
      labels:
        name: ovs-agent
    spec:
      containers:
      - name: ovs-agent
        image: ovs_bond:v1
        imagePullPolicy: IfNotPresent
        resources:
            limits:
              cpu: 100m
              memory: 200Mi
            requests:
              cpu: 100m
              memory: 200Mi
        securityContext:
          privileged: true
          procMount: Default
        volumeMounts:
        - mountPath: /lib/modules
          name: lib-modules
          readOnly: true
        - mountPath: /var/run/openvswitch
          name: ovs-run
        - mountPath: /usr/bin/ovs-appctl
          name: ovs-bin
          subPath: ovs-appctl
      serviceAccountName: xiyangxixia
      hostPID: true
      hostIPC: true
      volumes:
      - hostPath:
          path: /lib/modules
          type: ""
        name: lib-modules
      - hostPath:
          path: /var/run/openvswitch
          type: ""
        name: ovs-run
      - hostPath:
          path: /usr/bin/
          type: ""
        name: ovs-bin
  updateStrategy:
    type: RollingUpdate

七、测试

[root@test ~]$ kubectl get po -n kube-system -o wide  |grep ovs
ovs-agent-h8zc6    1/1     Running     0    2d14h   10.211.55.41   master-1   <none>           <none>
[root@test ~]$ curl 10.211.55.41:8080/metrics |grep ovs_bond
# HELP ovs_bond_status Show ovs bond status
# TYPE ovs_bond_status counter
ovs_bond_status{component="ovs",a1b1="enabled",a2b2="enabled",a3b3="enabled",a4b4="enabled"} 0

八、总结

以上就是这篇文章的所有了，原谅我学艺不精只能粗糙的介绍一下。感谢一直以来关注公众号的朋友们！