在进行源码讲解关于prometheus还有一些配置和使用，需要解释一下。首先是API的使用，prometheus提供了一套HTTP的接口
curl http://localhost:9090 /api/v1/query ?query =go_goroutines|python -m json.tool
{
"data" : {
"result" : [
{
"metric" : {
"__name__" : "go_goroutines" ,
"instance" : "localhost:9090" ,
"job" : "prometheus"
} ,
"value" : [
1493347106.901 ,
"119"
]
} ,
{
"metric" : {
"__name__" : "go_goroutines" ,
"instance" : "10.39.0.45:9100" ,
"job" : "node"
} ,
"value" : [
1493347106.901 ,
"13"
]
} ,
{
"metric" : {
"__name__" : "go_goroutines" ,
"instance" : "10.39.0.53:9100" ,
"job" : "node"
} ,
"value" : [
1493347106.901 ,
"11"
]
}
],
"resultType" : "vector"
} ,
"status" : "success"
} 上面演示一个查询go_goroutines这一个监控指标的数据。让然也可以基于开始时间和截止时间查询，但更强大的功能应该是支持OR查询
[root@slave3 ~]# curl -g 'http://localhost:9090/api/v1/series?match[]=up&match[]=process_start_time_seconds{job="prometheus"}' |python -m json.tool
{
"data" : [
{
"__name__" : "up" ,
"instance" : "10.39.0.53:9100" ,
"job" : "node"
},
{
"__name__" : "up" ,
"instance" : "localhost:9090" ,
"job" : "prometheus"
},
{
"__name__" : "up" ,
"instance" : "10.39.0.45:9100" ,
"job" : "node"
},
{
"__name__" : "process_start_time_seconds" ,
"instance" : "localhost:9090" ,
"job" : "prometheus"
}
],
"status" : "success"
}查询一个系列的数据，当然还可以通过DELETE去删除系列。还记得上一篇说的设置job和targets了吗？也可以通过API查询
curl http: //localhost:9090/api /v1/label /job/values
{"status" :"success" ,"data" : ["node" ,"prometheus" ]}当然有哪些监控对象也可以查询
curl http: //localhost:9090/api /v1/targets |python -m json.tool
{
"data" : {
"activeTargets" : [
{
"discoveredLabels" : {
"__address__" : "10.39.0.53:9100" ,
"__metrics_path__" : "/metrics" ,
"__scheme__" : "http" ,
"job" : "node"
},
"health" : "up" ,
"labels" : {
"instance" : "10.39.0.53:9100" ,
"job" : "node"
},
"lastError" : "" ,
"lastScrape" : "2017-04-28T02:47:40.871586825Z" ,
"scrapeUrl" : "http://10.39.0.53:9100/metrics"
},
{
"discoveredLabels" : {
"__address__" : "10.39.0.45:9100" ,
"__metrics_path__" : "/metrics" ,
"__scheme__" : "http" ,
"job" : "node"
},
"health" : "up" ,
"labels" : {
"instance" : "10.39.0.45:9100" ,
"job" : "node"
},
"lastError" : "" ,
"lastScrape" : "2017-04-28T02:47:45.144032466Z" ,
"scrapeUrl" : "http://10.39.0.45:9100/metrics"
},
{
"discoveredLabels" : {
"__address__" : "localhost:9090" ,
"__metrics_path__" : "/metrics" ,
"__scheme__" : "http" ,
"job" : "prometheus"
},
"health" : "up" ,
"labels" : {
"instance" : "localhost:9090" ,
"job" : "prometheus"
},
"lastError" : "" ,
"lastScrape" : "2017-04-28T02:47:44.079111193Z" ,
"scrapeUrl" : "http://localhost:9090/metrics"
}
]
},
"status" : "success"
}查询这些target。alertmanagers也是通过/api/v1/alertmanagers可以查询的。对应prometheus的本地存储还有一些关键的配置需要注意：
prometheus还另一个高级应用就是集群联邦，通过定义slave，这样就可以在每个数据中心部署一个，然后通过联邦汇聚。
- scrape_config:
- job_name: dc_prometheus
honor_labels: true
metrics_path: /federate
params:
match[]:
- '{__name__=~"^job:.*"}'
static_configs:
- targets:
- dc1-prometheus: 9090
- dc2-prometheus: 9090 当然如果存储量不够还可以通过分片去采集，
global:
external_labels:
slave: 1
scrape_configs:
- job_name: some_job
relabel_configs:
- source _labels: [__address__]
modulus: 4
target_label: __tmp_hash
action: hashmod
- source _labels: [__tmp_hash ]
regex: ^1 $
action: keep上面定义hash的方式去决定每个prometheus负责的targe他。
- scrape_config:
- job_name: slaves
honor_labels: true
metrics_path: /federate
params:
match[]:
- '{__name__=~"^slave:.*"}'
static_configs:
- targets:
- slave0: 9090
- slave1: 9090
- slave3: 9090
- slave4: 9090 下面定义了多个slave。这样数据就可以分片存储了。
转播
