组件说明
Prometheus 为开发这提供了客户端工具，用于为自己的中间件开发Exporter，对接Prometheus。目前支持的客户端Go、Java、Python、Ruby。
依赖包的引入
工程结构
[root@node1 data]# tree exporter/
exporter/
├── collector
│ └── node.go
├── go.mod
└── main.go
1 directory, 3 files
引入依赖包
require (
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
github.com/modern-go/reflect2 v1.0.1 // indirect
github.com/prometheus/client_golang v1.1.0
//借助gopsutil 采集主机指标
github.com/shirou/gopsutil v0.0.0-20190731134726-d80c43f9c984
)
main.go
package main
import (
"cloud.io/exporter/collector"
"fmt"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promhttp"
"net/http"
)
func init() {
//注册自身采集器
prometheus.MustRegister(collector.NewNodeCollector())
}
func main() {
http.Handle("/metrics", promhttp.Handler())
if err := http.ListenAndServe(":8080", nil); err != nil {
fmt.Printf("Error occur when start server %v", err)
}
}
为了能看清结果我将默认采集器注释,位置registry.go
func init() {
//MustRegister(NewProcessCollector(ProcessCollectorOpts{}))
//MustRegister(NewGoCollector())
}
/collector/node.go 代码中涵盖了Counter、Gauge、Histogram、Summary四种情况，一起混合使用的情况，具体的说明见一下代码中。
package collector
import (
"github.com/prometheus/client_golang/prometheus"
"github.com/shirou/gopsutil/host"
"github.com/shirou/gopsutil/mem"
"runtime"
"sync"
)
var reqCount int32
var hostname string
type NodeCollector struct {
requestDesc *prometheus.Desc //Counter
nodeMetrics nodeStatsMetrics //混合方式
goroutinesDesc *prometheus.Desc //Gauge
threadsDesc *prometheus.Desc //Gauge
summaryDesc *prometheus.Desc //summary
histogramDesc *prometheus.Desc //histogram
mutex sync.Mutex
}
//混合方式数据结构
type nodeStatsMetrics []struct {
desc *prometheus.Desc
eval func(*mem.VirtualMemoryStat) float64
valType prometheus.ValueType
}
//初始化采集器
func NewNodeCollector() prometheus.Collector {
host,_:= host.Info()
hostname = host.Hostname
return &NodeCollector{
requestDesc: prometheus.NewDesc(
"total_request_count",
"请求数",
[]string{"DYNAMIC_HOST_NAME"}, //动态标签名称
prometheus.Labels{"STATIC_LABEL1":"静态值可以放在这里","HOST_NAME":hostname}),
nodeMetrics: nodeStatsMetrics{
{
desc: prometheus.NewDesc(
"total_mem",
"内存总量",
nil, nil),
valType: prometheus.Gaugevalue,
eval: func(ms *mem.VirtualMemoryStat) float64 { return float64(ms.Total) / 1e9 },
},
{
desc: prometheus.NewDesc(
"free_mem",
"内存空闲",
nil, nil),
valType: prometheus.Gaugevalue,
eval: func(ms *mem.VirtualMemoryStat) float64 { return float64(ms.Free) / 1e9 },
},
},
goroutinesDesc:prometheus.NewDesc(
"goroutines_num",
"协程数.",
nil, nil),
threadsDesc: prometheus.NewDesc(
"threads_num",
"线程数",
nil, nil),
summaryDesc: prometheus.NewDesc(
"summary_http_request_duration_seconds",
"summary类型",
[]string{"code", "method"},
prometheus.Labels{"owner": "example"},
),
histogramDesc: prometheus.NewDesc(
"histogram_http_request_duration_seconds",
"histogram类型",
[]string{"code", "method"},
prometheus.Labels{"owner": "example"},
),
}
}
// Describe returns all descriptions of the collector.
//实现采集器Describe接口
func (n *NodeCollector) Describe(ch chan<- *prometheus.Desc) {
ch <- n.requestDesc
for _, metric := range n.nodeMetrics {
ch <- metric.desc
}
ch <- n.goroutinesDesc
ch <- n.threadsDesc
ch <- n.summaryDesc
ch <- n.histogramDesc
}
// Collect returns the current state of all metrics of the collector.
//实现采集器Collect接口,真正采集动作
func (n *NodeCollector) Collect(ch chan<- prometheus.Metric) {
n.mutex.Lock()
ch <- prometheus.MustNewConstMetric(n.requestDesc,prometheus.CounterValue,0,hostname)
vm, _ := mem.VirtualMemory()
for _, metric := range n.nodeMetrics {
ch <- prometheus.MustNewConstMetric(metric.desc, metric.valType, metric.eval(vm))
}
ch <- prometheus.MustNewConstMetric(n.goroutinesDesc, prometheus.Gaugevalue, float64(runtime.NumGoroutine()))
num, _ := runtime.ThreadCreateProfile(nil)
ch <- prometheus.MustNewConstMetric(n.threadsDesc, prometheus.Gaugevalue, float64(num))
//模拟数据
ch <- prometheus.MustNewConstSummary(
n.summaryDesc,
4711, 403.34,
map[float64]float64{0.5: 42.3, 0.9: 323.3},
"200", "get",
)
//模拟数据
ch <- prometheus.MustNewConstHistogram(
n.histogramDesc,
4711, 403.34,
map[float64]uint64{25: 121, 50: 2403, 100: 3221, 200: 4233},
"200", "get",
)
n.mutex.Unlock()
}
执行的结果http://127.0.0.1:8080/metrics
https://api.github.com/repos/Vonng/pg_exporter/releases/latest
[Prometheus](https://prometheus.io/) [exporter](https://prometheus.io/docs/instrumenting/exporters/) for [PostgreSQL](https://www.postgresql.org) metrics. **Gives you complete insight on your favourate elephant!** PG Exporter is the foundation component for Project [Pigsty](https://pigsty.cc), Which maybe the best **OpenSource** Monitoring Solution for PostgreSQL. Latest binaries & rpms can be found on [release](https://github.com/Vonng/pg_exporter/releases) page. Supported pg version: PostgreSQL 9.4+ & Pgbouncer 1.8+. Default collectors definition is compatible with PostgreSQL 10,11,12,13,14. Latest stable `pg_exporter` version is: `0.3.2` , and latest beta `pg_exporter` version is: `0.4.0beta` .
如何运行
export PG_EXPORTER_URL='postgres://postgres:password@localhost:5432/postgres' export PG_EXPORTER_CONFIG='/path/to/conf/file/or/dir' pg_exporterRun
Parameter could be given via command line arguments or environment variables.
usage: pg_exporter [API] Flags: --help Show context-sensitive help (also try --help-long and --help-man). --url=URL postgres target url --config=ConFIG path to config dir or file --label="" constant lables:comma separated list of label=value pair --tag="" tags,comma separated list of server tag --disable-cache force not using cache --disable-intro disable collector level introspection metrics --auto-discovery automatically scrape all database for given server --exclude-database="template0,template1,postgres" excluded databases when enabling auto-discovery --include-database="" included databases when enabling auto-discovery --namespace="" prefix of built-in metrics, (pg|pgbouncer) by default --fail-fast fail fast instead of waiting during start-up --web.listen-address=":9630" prometheus web server listen address --web.telemetry-path="/metrics" URL path under which to expose metrics. --dry-run dry run and print raw configs --explain explain server planned queries --version Show application version. --log.level="info" only log messages with the given severity or above. Valid levels: [debug, info, warn, error, fatal] --log.format="logger:stderr" Set the log target and format. Example: "logger:syslog?appname=bob&local=7" or "logger:stdout?json=true"
Here are pg_exporter REST APIs
# Fetch metrics (metrics path depends on parameters) curl localhost:9630/metrics # Reload configuration curl localhost:9630/reload # Explain configuration curl localhost:9630/explain # Aliveness health check (200 up, 503 down) curl localhost:9630/up curl localhost:9630/health curl localhost:9630/liveness curl localhost:9630/readiness # traffic route health check ### 200 if not in recovery, 404 if in recovery, 503 if server is down curl localhost:9630/primary curl localhost:9630/leader curl localhost:9630/master curl localhost:9630/read-write curl localhost:9630/rw ### 200 if in recovery, 404 if not in recovery, 503 if server is down curl localhost:9630/replica curl localhost:9630/standby curl localhost:9630/slave curl localhost:9630/read-only curl localhost:9630/ro ### 200 if server is ready for read traffic (including primary), 503 if server is down curl localhost:9630/read主函数
func Run() {
ParseArgs()
// explain config only
if *dryRun {
DryRun()
}
if *configPath == "" {
log.Errorf("no valid config path, exit")
os.Exit(1)
}
// DummyServer will server a constant pg_up
// launch a dummy server to check listen address availability
// and fake a pg_up 0 metrics before PgExporter connecting to target instance
// otherwise, exporter API is not available until target instance online
dummySrv, closeChan := DummyServer()
// create exporter: if target is down, exporter creation will wait until it backup online
var err error
PgExporter, err = NewExporter(
*pgURL,
WithConfig(*configPath),
WithConstLabels(*constLabels),
WithCacheDisabled(*disableCache),
WithFailFast(*failFast),
WithNamespace(*exporterNamespace),
WithAutoDiscovery(*autoDiscovery),
WithExcludeDatabase(*excludeDatabase),
WithIncludeDatabase(*includeDatabase),
WithTags(*serverTags),
)
if err != nil {
log.Fatalf("fail creating pg_exporter: %s", err.Error())
os.Exit(2)
}
// trigger a manual planning before explain
if *explainonly {
PgExporter.server.Plan()
fmt.Println(PgExporter.Explain())
os.Exit(0)
}
prometheus.MustRegister(PgExporter)
defer PgExporter.Close()
// reload conf when receiving SIGHUP or SIGUSR1
sigs := make(chan os.Signal, 1)
signal.Notify(sigs, syscall.SIGHUP)
go func() {
for sig := range sigs {
switch sig {
case syscall.SIGHUP:
log.Infof("%v received, reloading", sig)
_ = Reload()
}
}
}()
// basic
http.HandleFunc("/", TitleFunc)
http.HandleFunc("/version", VersionFunc)
// reload
http.HandleFunc("/reload", ReloadFunc)
// explain
http.HandleFunc("/explain", PgExporter.ExplainFunc)
// alive
http.HandleFunc("/up", PgExporter.UpCheckFunc)
http.HandleFunc("/read", PgExporter.UpCheckFunc)
http.HandleFunc("/health", PgExporter.UpCheckFunc)
http.HandleFunc("/liveness", PgExporter.UpCheckFunc)
http.HandleFunc("/readiness", PgExporter.UpCheckFunc)
// primary
http.HandleFunc("/primary", PgExporter.PrimaryCheckFunc)
http.HandleFunc("/leader", PgExporter.PrimaryCheckFunc)
http.HandleFunc("/master", PgExporter.PrimaryCheckFunc)
http.HandleFunc("/read-write", PgExporter.PrimaryCheckFunc)
http.HandleFunc("/rw", PgExporter.PrimaryCheckFunc)
// replica
http.HandleFunc("/replica", PgExporter.ReplicaCheckFunc)
http.HandleFunc("/standby", PgExporter.ReplicaCheckFunc)
http.HandleFunc("/slave", PgExporter.ReplicaCheckFunc)
http.HandleFunc("/read-only", PgExporter.ReplicaCheckFunc)
http.HandleFunc("/ro", PgExporter.ReplicaCheckFunc)
// metric
_ = dummySrv.Close()
<-closeChan
http.Handle(*metricPath, promhttp.Handler())
log.Infof("pg_exporter for %s start, listen on http://%s%s", shadowDSN(*pgURL), *listenAddress, *metricPath)
log.Fatal(http.ListenAndServe(*listenAddress, nil))
}
