Prometheus

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: monitoring
data:
  prometheus.yml: |
    global:
      scrape_interval:     15s
      evaluation_interval: 15s
    scrape_configs:
      - job_name: 'prometheus'
        static_configs:
        - targets: ['localhost:9090']
     # 采集node exporter监控数据
     - job_name: 'node'
       static_configs:
       - targets: ['localhost:9100']    

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42

global:
  # How frequently to scrape targets by default.
  [ scrape_interval: <duration> | default = 1m ]

  # How long until a scrape request times out.
  [ scrape_timeout: <duration> | default = 10s ]

  # How frequently to evaluate rules.
  [ evaluation_interval: <duration> | default = 1m ]

  # The labels to add to any time series or alerts when communicating with
  # external systems (federation, remote storage, Alertmanager).
  external_labels:
    [ <labelname>: <labelvalue> ... ]

  # File to which PromQL queries are logged.
  # Reloading the configuration will reopen the file.
  [ query_log_file: <string> ]

# Rule files specifies a list of globs. Rules and alerts are read from
# all matching files.
rule_files:
  [ - <filepath_glob> ... ]

# A list of scrape configurations.
scrape_configs:
  [ - <scrape_config> ... ]

# Alerting specifies settings related to the Alertmanager.
alerting:
  alert_relabel_configs:
    [ - <relabel_config> ... ]
  alertmanagers:
    [ - <alertmanager_config> ... ]

# Settings related to the remote write feature.
remote_write:
  [ - <remote_write> ... ]

# Settings related to the remote read feature.
remote_read:
  [ - <remote_read> ... ]

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  labels:
    name: prometheus
  name: prometheus
  namespace: monitoring
spec:
  replicas: 1
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      containers:
      - name: prometheus
        image: prom/prometheus:v2.19.0
        command:
        - /bin/prometheus
        args:
        - --config.file=/etc/config/prometheus.yml
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/config
          name: prometheus-config
      volumes:
      - name: prometheus-config
        configMap:
          name: prometheus-config

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitoring
  labels:
    name: prometheus
spec:
  ports:
  - name: prometheus
    protocol: TCP
    port: 9090
    targetPort: 9090
  selector:
    app: prometheus

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: prometheus
  namespace: monitoring
  annotations:
    kubernetes.io/ingress.class: traefik
spec:
  rules:
  - host: prometheus.houmin
    http:
      paths:
      - path: /
        backend:
          serviceName: prometheus
          servicePort: prometheus

1
2
3
4
5
6
7

  ^
  │   . . . . . . . . . . . . . . . . .   . .   node_cpu{cpu="cpu0",mode="idle"}
  │     . . . . . . . . . . . . . . . . . . .   node_cpu{cpu="cpu0",mode="system"}
  │     . . . . . . . . . .   . . . . . . . .   node_load1{}
  │     . . . . . . . . . . . . . . . .   . .
  v
    <------------------ 时间 ---------------->

1
2
3
4
5
6
7
8
9

<--------------- metric ---------------------><-timestamp -><-value->
http_request_total{status="200", method="GET"}@1434417560938 => 94355
http_request_total{status="200", method="GET"}@1434417561287 => 94334

http_request_total{status="404", method="GET"}@1434417560938 => 38473
http_request_total{status="404", method="GET"}@1434417561287 => 38544

http_request_total{status="200", method="POST"}@1434417560938 => 4748
http_request_total{status="200", method="POST"}@1434417561287 => 4785

1

<metric name>{<label name>=<label value>, ...}

1
2
3
4
5

type Metric LabelSet

type LabelSet map[LabelName]LabelValue
type LabelName string
type LabelValue string

1
2
3
4

- <basename>_bucket{le="<upper inclusive bound>"}
- <basename>_bucket{le="+Inf"}
- <basename>_sum
- <basename>_count

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

# HELP prometheus_tsdb_compaction_chunk_range Final time range of chunks on their first compaction
# TYPE prometheus_tsdb_compaction_chunk_range histogram
prometheus_tsdb_compaction_chunk_range_bucket{le="100"} 0
prometheus_tsdb_compaction_chunk_range_bucket{le="400"} 0
prometheus_tsdb_compaction_chunk_range_bucket{le="1600"} 0
prometheus_tsdb_compaction_chunk_range_bucket{le="6400"} 0
prometheus_tsdb_compaction_chunk_range_bucket{le="25600"} 0
prometheus_tsdb_compaction_chunk_range_bucket{le="102400"} 0
prometheus_tsdb_compaction_chunk_range_bucket{le="409600"} 0
prometheus_tsdb_compaction_chunk_range_bucket{le="1.6384e+06"} 260
prometheus_tsdb_compaction_chunk_range_bucket{le="6.5536e+06"} 780
prometheus_tsdb_compaction_chunk_range_bucket{le="2.62144e+07"} 780
prometheus_tsdb_compaction_chunk_range_bucket{le="+Inf"} 780
prometheus_tsdb_compaction_chunk_range_sum 1.1540798e+09
prometheus_tsdb_compaction_chunk_range_count 780

1
2
3
4
5
6
7

# HELP prometheus_tsdb_wal_fsync_duration_seconds Duration of WAL fsync.
# TYPE prometheus_tsdb_wal_fsync_duration_seconds summary
prometheus_tsdb_wal_fsync_duration_seconds{quantile="0.5"} 0.012352463
prometheus_tsdb_wal_fsync_duration_seconds{quantile="0.9"} 0.014458005
prometheus_tsdb_wal_fsync_duration_seconds{quantile="0.99"} 0.017316173
prometheus_tsdb_wal_fsync_duration_seconds_sum 2.888716127000002
prometheus_tsdb_wal_fsync_duration_seconds_count 216

1

http_requests_total

1
2

http_requests_total{code="200",handler="alerts",instance="localhost:9090",job="prometheus",method="get"}=(20889@1518096812.326)
http_requests_total{code="200",handler="graph",instance="localhost:9090",job="prometheus",method="get"}=(21287@1518096812.326)

1

http_requests_total{instance="localhost:9090"}

1

http_requests_total{instance!="localhost:9090"}

1

http_requests_total{environment=~"staging|testing|development",method!="GET"}

1

http_requests_total{}[5m]

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

http_requests_total{code="200",handler="alerts",instance="localhost:9090",job="prometheus",method="get"}=[
    1@1518096812.326
    1@1518096817.326
    1@1518096822.326
    1@1518096827.326
    1@1518096832.326
    1@1518096837.325
]
http_requests_total{code="200",handler="graph",instance="localhost:9090",job="prometheus",method="get"}=[
    4@1518096812.326
    4@1518096817.326
    4@1518096822.326
    4@1518096827.326
    4@1518096832.326
    4@1518096837.325
]

1
2

http_request_total{} # 瞬时向量表达式，选择当前最新的数据
http_request_total{}[5m] # 区间向量表达式，选择以当前时间为基准，5分钟内的数据

1
2

http_request_total{} offset 5m
http_request_total{}[1d] offset 1d

1

sum(http_requests_total{method="GET"} offset 5m) // GOOD.

1

sum(http_requests_total{method="GET"}) offset 5m // INVALID.

1

node_memory_free_bytes_total / (1024 * 1024)

1

node_disk_bytes_written + node_disk_bytes_read

1
2

{device="sda",instance="localhost:9100",job="node_exporter"}=>1634967552@1518146427.807 + 864551424@1518146427.807
{device="sdb",instance="localhost:9100",job="node_exporter"}=>0@1518146427.807 + 1744384@1518146427.807

1

(node_memory_bytes_total - node_memory_free_bytes_total) / node_memory_bytes_total

1

(node_memory_bytes_total - node_memory_free_bytes_total) / node_memory_bytes_total > 0.95

1

100 * (1 - avg (irate(node_cpu{mode='idle'}[5m])) by(job) )

1

vector1 <operator> vector2

1
2

<vector expr> <bin-op> ignoring(<label list>) <vector expr>
<vector expr> <bin-op> on(<label list>) <vector expr>

1
2
3
4
5
6
7
8
9

method_code:http_errors:rate5m{method="get", code="500"}  24
method_code:http_errors:rate5m{method="get", code="404"}  30
method_code:http_errors:rate5m{method="put", code="501"}  3
method_code:http_errors:rate5m{method="post", code="500"} 6
method_code:http_errors:rate5m{method="post", code="404"} 21

method:http_requests:rate5m{method="get"}  600
method:http_requests:rate5m{method="del"}  34
method:http_requests:rate5m{method="post"} 120

1

method_code:http_errors:rate5m{code="500"} / ignoring(code) method:http_requests:rate5m

1
2

{method="get"}  0.04            //  24 / 600
{method="post"} 0.05            //   6 / 120

1
2
3
4

<vector expr> <bin-op> ignoring(<label list>) group_left(<label list>) <vector expr>
<vector expr> <bin-op> ignoring(<label list>) group_right(<label list>) <vector expr>
<vector expr> <bin-op> on(<label list>) group_left(<label list>) <vector expr>
<vector expr> <bin-op> on(<label list>) group_right(<label list>) <vector expr>

1

method_code:http_errors:rate5m / ignoring(code) group_left method:http_requests:rate5m

1
2
3
4

{method="get", code="500"}  0.04            //  24 / 600
{method="get", code="404"}  0.05            //  30 / 600
{method="post", code="500"} 0.05            //   6 / 120
{method="post", code="404"} 0.175           //  21 / 120

1
2
3
4
5
6
7
8

# 查询系统所有http请求的总量
sum(http_request_total)

# 按照mode计算主机CPU的平均使用时间
avg(node_cpu) by (mode)

# 按照主机查询各个主机的CPU使用率
sum(sum(irate(node_cpu{mode!='idle'}[5m])) / sum(irate(node_cpu[5m]))) by (instance)

1

<aggr-op>([parameter,] <vector expression>) [without|by (<label list>)]

1

sum(http_requests_total) without (instance)

1

sum(http_requests_total) by (code,handler,job,method)

1

quantile(0.5, http_requests_total)

1

increase(node_cpu[2m]) / 120

1

rate(node_cpu[2m])

1

irate(node_cpu[2m])

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

# HELP http_request_duration_seconds request duration histogram
# TYPE http_request_duration_seconds histogram
http_request_duration_seconds_bucket{le="0.5"} 0
http_request_duration_seconds_bucket{le="1"} 1
http_request_duration_seconds_bucket{le="2"} 2
http_request_duration_seconds_bucket{le="3"} 3
http_request_duration_seconds_bucket{le="5"} 3
http_request_duration_seconds_bucket{le="+Inf"} 3
http_request_duration_seconds_sum 6
http_request_duration_seconds_count 3

1
2
3

up{instance="localhost:8080",job="cadvisor"}    1
up{instance="localhost:9090",job="prometheus"}    1
up{instance="localhost:9100",job="node"}    1

1
2
3

up{host="localhost",instance="localhost:8080",job="cadvisor"}    1
up{host="localhost",instance="localhost:9090",job="prometheus"}    1
up{host="localhost",instance="localhost:9100",job="node"} 1

1
2
3
4
5
6
7
8

{
  "status": "success" | "error",
  "data": <data>,

  // 为error时，有如下报错信息
  "errorType": "<string>",
  "error": "<string>"
}

1

$ curl 'http://localhost:9090/api/v1/query?query=up&time=2015-07-01T20:10:51.781Z'

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

{
   "status" : "success",
   "data" : {
      "resultType" : "vector",
      "result" : [
         {
            "metric" : {
               "__name__" : "up",
               "job" : "prometheus",
               "instance" : "localhost:9090"
            },
            "value": [ 1435781451.781, "1" ]
         },
         {
            "metric" : {
               "__name__" : "up",
               "job" : "node",
               "instance" : "localhost:9100"
            },
            "value" : [ 1435781451.781, "0" ]
         }
      ]
   }
}

1

$ curl 'http://localhost:9090/api/v1/query_range?query=up&start=2015-07-01T20:10:30.781Z&end=2015-07-01T20:11:00.781Z&step=15s'

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

{
   "status" : "success",
   "data" : {
      "resultType" : "matrix",
      "result" : [
         {
            "metric" : {
               "__name__" : "up",
               "job" : "prometheus",
               "instance" : "localhost:9090"
            },
            "values" : [
               [ 1435781430.781, "1" ],
               [ 1435781445.781, "1" ],
               [ 1435781460.781, "1" ]
            ]
         },
         {
            "metric" : {
               "__name__" : "up",
               "job" : "node",
               "instance" : "localhost:9091"
            },
            "values" : [
               [ 1435781430.781, "0" ],
               [ 1435781445.781, "0" ],
               [ 1435781460.781, "1" ]
            ]
         }
      ]
   }
}

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161

# The job name assigned to scraped metrics by default.
job_name: <job_name>

# How frequently to scrape targets from this job.
[ scrape_interval: <duration> | default = <global_config.scrape_interval> ]

# Per-scrape timeout when scraping this job.
[ scrape_timeout: <duration> | default = <global_config.scrape_timeout> ]

# The HTTP resource path on which to fetch metrics from targets.
[ metrics_path: <path> | default = /metrics ]

# honor_labels controls how Prometheus handles conflicts between labels that are
# already present in scraped data and labels that Prometheus would attach
# server-side ("job" and "instance" labels, manually configured target
# labels, and labels generated by service discovery implementations).
#
# If honor_labels is set to "true", label conflicts are resolved by keeping label
# values from the scraped data and ignoring the conflicting server-side labels.
#
# If honor_labels is set to "false", label conflicts are resolved by renaming
# conflicting labels in the scraped data to "exported_<original-label>" (for
# example "exported_instance", "exported_job") and then attaching server-side
# labels.
#
# Setting honor_labels to "true" is useful for use cases such as federation and
# scraping the Pushgateway, where all labels specified in the target should be
# preserved.
#
# Note that any globally configured "external_labels" are unaffected by this
# setting. In communication with external systems, they are always applied only
# when a time series does not have a given label yet and are ignored otherwise.
[ honor_labels: <boolean> | default = false ]

# honor_timestamps controls whether Prometheus respects the timestamps present
# in scraped data.
#
# If honor_timestamps is set to "true", the timestamps of the metrics exposed
# by the target will be used.
#
# If honor_timestamps is set to "false", the timestamps of the metrics exposed
# by the target will be ignored.
[ honor_timestamps: <boolean> | default = true ]

# Configures the protocol scheme used for requests.
[ scheme: <scheme> | default = http ]

# Optional HTTP URL parameters.
params:
  [ <string>: [<string>, ...] ]

# Sets the `Authorization` header on every scrape request with the
# configured username and password.
# password and password_file are mutually exclusive.
basic_auth:
  [ username: <string> ]
  [ password: <secret> ]
  [ password_file: <string> ]

# Sets the `Authorization` header on every scrape request with
# the configured bearer token. It is mutually exclusive with `bearer_token_file`.
[ bearer_token: <secret> ]

# Sets the `Authorization` header on every scrape request with the bearer token
# read from the configured file. It is mutually exclusive with `bearer_token`.
[ bearer_token_file: <filename> ]

# Configures the scrape request's TLS settings.
tls_config:
  [ <tls_config> ]

# Optional proxy URL.
[ proxy_url: <string> ]

# List of Azure service discovery configurations.
azure_sd_configs:
  [ - <azure_sd_config> ... ]

# List of Consul service discovery configurations.
consul_sd_configs:
  [ - <consul_sd_config> ... ]

# List of DigitalOcean service discovery configurations.
digitalocean_sd_configs:
  [ - <digitalocean_sd_config> ... ]

# List of Docker Swarm service discovery configurations.
dockerswarm_sd_configs:
  [ - <dockerswarm_sd_config> ... ]

# List of DNS service discovery configurations.
dns_sd_configs:
  [ - <dns_sd_config> ... ]

# List of EC2 service discovery configurations.
ec2_sd_configs:
  [ - <ec2_sd_config> ... ]

# List of Eureka service discovery configurations.
eureka_sd_configs:
  [ - <eureka_sd_config> ... ]

# List of file service discovery configurations.
file_sd_configs:
  [ - <file_sd_config> ... ]

# List of GCE service discovery configurations.
gce_sd_configs:
  [ - <gce_sd_config> ... ]

# List of Hetzner service discovery configurations.
hetzner_sd_configs:
  [ - <hetzner_sd_config> ... ]

# List of Kubernetes service discovery configurations.
kubernetes_sd_configs:
  [ - <kubernetes_sd_config> ... ]

# List of Marathon service discovery configurations.
marathon_sd_configs:
  [ - <marathon_sd_config> ... ]

# List of AirBnB's Nerve service discovery configurations.
nerve_sd_configs:
  [ - <nerve_sd_config> ... ]

# List of OpenStack service discovery configurations.
openstack_sd_configs:
  [ - <openstack_sd_config> ... ]

# List of Zookeeper Serverset service discovery configurations.
serverset_sd_configs:
  [ - <serverset_sd_config> ... ]

# List of Triton service discovery configurations.
triton_sd_configs:
  [ - <triton_sd_config> ... ]

# List of labeled statically configured targets for this job.
static_configs:
  [ - <static_config> ... ]

# List of target relabel configurations.
relabel_configs:
  [ - <relabel_config> ... ]

# List of metric relabel configurations.
metric_relabel_configs:
  [ - <relabel_config> ... ]

# Per-scrape limit on number of scraped samples that will be accepted.
# If more than this number of samples are present after metric relabeling
# the entire scrape will be treated as failed. 0 means no limit.
[ sample_limit: <int> | default = 0 ]

# Per-scrape config limit on number of unique targets that will be
# accepted. If more than this number of targets are present after target
# relabeling, Prometheus will mark the targets as failed without scraping them.
# 0 means no limit. This is an experimental feature, this behaviour could
# change in the future.
[ target_limit: <int> | default = 0 ]

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56

# The information to access the Kubernetes API.

# The API server addresses. If left empty, Prometheus is assumed to run inside
# of the cluster and will discover API servers automatically and use the pod's
# CA certificate and bearer token file at /var/run/secrets/kubernetes.io/serviceaccount/.
[ api_server: <host> ]

# The Kubernetes role of entities that should be discovered.
# One of endpoints, service, pod, node, or ingress.
role: <string>

# Optional authentication information used to authenticate to the API server.
# Note that `basic_auth`, `bearer_token` and `bearer_token_file` options are
# mutually exclusive.
# password and password_file are mutually exclusive.

# Optional HTTP basic authentication information.
basic_auth:
  [ username: <string> ]
  [ password: <secret> ]
  [ password_file: <string> ]

# Optional bearer token authentication information.
[ bearer_token: <secret> ]

# Optional bearer token file authentication information.
[ bearer_token_file: <filename> ]

# Optional proxy URL.
[ proxy_url: <string> ]

# TLS configuration.
tls_config:
  [ <tls_config> ]

# Optional namespace discovery. If omitted, all namespaces are used.
namespaces:
  names:
    [ - <string> ]

# Optional label and field selectors to limit the discovery process to a subset of available resources.
# See https://kubernetes.io/docs/concepts/overview/working-with-objects/field-selectors/
# and https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ to learn more about the possible
# filters that can be used. Endpoints role supports pod, service and endpoints selectors, other roles
# only support selectors matching the role itself (e.g. node role can only contain node selectors).

# Note: When making decision about using field/label selector make sure that this
# is the best approach - it will prevent Prometheus from reusing single list/watch
# for all scrape configs. This might result in a bigger load on the Kubernetes API,
# because per each selector combination there will be additional LIST/WATCH. On the other hand,
# if you just want to monitor small subset of pods in large cluster it's recommended to use selectors.
# Decision, if selectors should be used or not depends on the particular situation.
[ selectors:
  [ - role: <string>
    [ label: <string> ]
    [ field: <string> ] ]]

1
2
3
4
5
6

__meta_kubernetes_node_name: The name of the node object.
__meta_kubernetes_node_label_<labelname>: Each label from the node object.
__meta_kubernetes_node_labelpresent_<labelname>: true for each label from the node object.
__meta_kubernetes_node_annotation_<annotationname>: Each annotation from the node object.
__meta_kubernetes_node_annotationpresent_<annotationname>: true for each annotation from the node object.
__meta_kubernetes_node_address_<address_type>: The first address for each node address type, if it exists.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36

scrape_configs:
# Scrape config for nodes (kubelet).
#
# Rather than connecting directly to the node, the scrape is proxied though the
# Kubernetes apiserver.  This means it will work if Prometheus is running out of
# cluster, or can't connect to nodes for some other reason (e.g. because of
# firewalling).
- job_name: 'kubernetes-nodes'

  # Default to scraping over https. If required, just disable this or change to
  # `http`.
  scheme: https

  # This TLS & bearer token file config is used to connect to the actual scrape
  # endpoints for cluster components. This is separate to discovery auth
  # configuration because discovery & scraping are two separate concerns in
  # Prometheus. The discovery auth config is automatic if Prometheus runs inside
  # the cluster. Otherwise, more config options have to be provided within the
  # <kubernetes_sd_config>.
  tls_config:
    ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
    # If your node certificates are self-signed or use a different CA to the
    # master CA, then disable certificate verification below. Note that
    # certificate verification is an integral part of a secure infrastructure
    # so this should only be disabled in a controlled environment. You can
    # disable certificate verification by uncommenting the line below.
    #
    # insecure_skip_verify: true
  bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token

  kubernetes_sd_configs:
  - role: node

  relabel_configs:
  - action: labelmap
    regex: __meta_kubernetes_node_label_(.+)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50

scrape_configs:
# Scrape config for Kubelet cAdvisor.
#
# This is required for Kubernetes 1.7.3 and later, where cAdvisor metrics
# (those whose names begin with 'container_') have been removed from the
# Kubelet metrics endpoint.  This job scrapes the cAdvisor endpoint to
# retrieve those metrics.
#
# In Kubernetes 1.7.0-1.7.2, these metrics are only exposed on the cAdvisor
# HTTP endpoint; use the "/metrics" endpoint on the 4194 port of nodes. In
# that case (and ensure cAdvisor's HTTP server hasn't been disabled with the
# --cadvisor-port=0 Kubelet flag).
#
# This job is not necessary and should be removed in Kubernetes 1.6 and
# earlier versions, or it will cause the metrics to be scraped twice.
- job_name: 'kubernetes-cadvisor'

  # Default to scraping over https. If required, just disable this or change to
  # `http`.
  scheme: https

  # Starting Kubernetes 1.7.3 the cAdvisor metrics are under /metrics/cadvisor.
  # Kubernetes CIS Benchmark recommends against enabling the insecure HTTP
  # servers of Kubernetes, therefore the cAdvisor metrics on the secure handler
  # are used.
  metrics_path: /metrics/cadvisor

  # This TLS & bearer token file config is used to connect to the actual scrape
  # endpoints for cluster components. This is separate to discovery auth
  # configuration because discovery & scraping are two separate concerns in
  # Prometheus. The discovery auth config is automatic if Prometheus runs inside
  # the cluster. Otherwise, more config options have to be provided within the
  # <kubernetes_sd_config>.
  tls_config:
    ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
    # If your node certificates are self-signed or use a different CA to the
    # master CA, then disable certificate verification below. Note that
    # certificate verification is an integral part of a secure infrastructure
    # so this should only be disabled in a controlled environment. You can
    # disable certificate verification by uncommenting the line below.
    #
    # insecure_skip_verify: true
  bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token

  kubernetes_sd_configs:
  - role: node

  relabel_configs:
  - action: labelmap
    regex: __meta_kubernetes_node_label_(.+)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

__meta_kubernetes_namespace: The namespace of the service object.
__meta_kubernetes_service_annotation_<annotationname>: Each annotation from the service object.
__meta_kubernetes_service_annotationpresent_<annotationname>: "true" for each annotation of the service object.
__meta_kubernetes_service_cluster_ip: The cluster IP address of the service. (Does not apply to services of type ExternalName)
__meta_kubernetes_service_external_name: The DNS name of the service. (Applies to services of type ExternalName)
__meta_kubernetes_service_label_<labelname>: Each label from the service object.
__meta_kubernetes_service_labelpresent_<labelname>: true for each label of the service object.
__meta_kubernetes_service_name: The name of the service object.
__meta_kubernetes_service_port_name: Name of the service port for the target.
__meta_kubernetes_service_port_protocol: Protocol of the service port for the target.
__meta_kubernetes_service_type: The type of the service.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

scrape_configs:

- job_name: 'kubernetes-service-endpoints'

  kubernetes_sd_configs:
  - role: endpoints

  relabel_configs:
  # Example relabel to scrape only endpoints that have
  # "example.io/should_be_scraped = true" annotation.
  #  - source_labels: [__meta_kubernetes_service_annotation_example_io_should_be_scraped]
  #    action: keep
  #    regex: true
  #
  # Example relabel to customize metric path based on endpoints
  # "example.io/metric_path = <metric path>" annotation.
  #  - source_labels: [__meta_kubernetes_service_annotation_example_io_metric_path]
  #    action: replace
  #    target_label: __metrics_path__
  #    regex: (.+)
  #
  # Example relabel to scrape only single, desired port for the service based
  # on endpoints "example.io/scrape_port = <port>" annotation.
  #  - source_labels: [__address__, __meta_kubernetes_service_annotation_example_io_scrape_port]
  #    action: replace
  #    regex: ([^:]+)(?::\d+)?;(\d+)
  #    replacement: $1:$2
  #    target_label: __address__
  #
  # Example relabel to configure scrape scheme for all service scrape targets
  # based on endpoints "example.io/scrape_scheme = <scheme>" annotation.
  #  - source_labels: [__meta_kubernetes_service_annotation_example_io_scrape_scheme]
  #    action: replace
  #    target_label: __scheme__
  #    regex: (https?)
  - action: labelmap
    regex: __meta_kubernetes_service_label_(.+)
  - source_labels: [__meta_kubernetes_namespace]
    action: replace
    target_label: kubernetes_namespace
  - source_labels: [__meta_kubernetes_service_name]
    action: replace
    target_label: kubernetes_name

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28

scrape_configs:

- job_name: 'kubernetes-services'

  metrics_path: /probe
  params:
    module: [http_2xx]

  kubernetes_sd_configs:
  - role: service

  relabel_configs:
  # Example relabel to probe only some services that have "example.io/should_be_probed = true" annotation
  #  - source_labels: [__meta_kubernetes_service_annotation_example_io_should_be_probed]
  #    action: keep
  #    regex: true
  - source_labels: [__address__]
    target_label: __param_target
  - target_label: __address__
    replacement: blackbox-exporter.example.com:9115
  - source_labels: [__param_target]
    target_label: instance
  - action: labelmap
    regex: __meta_kubernetes_service_label_(.+)
  - source_labels: [__meta_kubernetes_namespace]
    target_label: kubernetes_namespace
  - source_labels: [__meta_kubernetes_service_name]
    target_label: kubernetes_name

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

__meta_kubernetes_namespace: The namespace of the pod object.
__meta_kubernetes_pod_name: The name of the pod object.
__meta_kubernetes_pod_ip: The pod IP of the pod object.
__meta_kubernetes_pod_label_<labelname>: Each label from the pod object.
__meta_kubernetes_pod_labelpresent_<labelname>: truefor each label from the pod object.
__meta_kubernetes_pod_annotation_<annotationname>: Each annotation from the pod object.
__meta_kubernetes_pod_annotationpresent_<annotationname>: true for each annotation from the pod object.
__meta_kubernetes_pod_container_init: true if the container is an InitContainer
__meta_kubernetes_pod_container_name: Name of the container the target address points to.
__meta_kubernetes_pod_container_port_name: Name of the container port.
__meta_kubernetes_pod_container_port_number: Number of the container port.
__meta_kubernetes_pod_container_port_protocol: Protocol of the container port.
__meta_kubernetes_pod_ready: Set to true or false for the pod's ready state.
__meta_kubernetes_pod_phase: Set to Pending, Running, Succeeded, Failed or Unknown in the lifecycle.
__meta_kubernetes_pod_node_name: The name of the node the pod is scheduled onto.
__meta_kubernetes_pod_host_ip: The current host IP of the pod object.
__meta_kubernetes_pod_uid: The UID of the pod object.
__meta_kubernetes_pod_controller_kind: Object kind of the pod controller.
__meta_kubernetes_pod_controller_name: Name of the pod controller.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40

scrape_configs:
# Example scrape config for pods
#
# The relabeling allows the actual pod scrape to be configured
# for all the declared ports (or port-free target if none is declared)
# or only some ports.
- job_name: 'kubernetes-pods'

  kubernetes_sd_configs:
  - role: pod

  relabel_configs:
  # Example relabel to scrape only pods that have
  # "example.io/should_be_scraped = true" annotation.
  #  - source_labels: [__meta_kubernetes_pod_annotation_example_io_should_be_scraped]
  #    action: keep
  #    regex: true
  #
  # Example relabel to customize metric path based on pod
  # "example.io/metric_path = <metric path>" annotation.
  #  - source_labels: [__meta_kubernetes_pod_annotation_example_io_metric_path]
  #    action: replace
  #    target_label: __metrics_path__
  #    regex: (.+)
  #
  # Example relabel to scrape only single, desired port for the pod
  # based on pod "example.io/scrape_port = <port>" annotation.
  #  - source_labels: [__address__, __meta_kubernetes_pod_annotation_example_io_scrape_port]
  #    action: replace
  #    regex: ([^:]+)(?::\d+)?;(\d+)
  #    replacement: $1:$2
  #    target_label: __address__
  - action: labelmap
    regex: __meta_kubernetes_pod_label_(.+)
  - source_labels: [__meta_kubernetes_namespace]
    action: replace
    target_label: kubernetes_namespace
  - source_labels: [__meta_kubernetes_pod_name]
    action: replace
    target_label: kubernetes_pod_name

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

scrape_configs:
  - job_name: 'kubernetes-pods'
    metrics_path: /metrics
    kubernetes_sd_configs:
    - role: pod
      namespaces:
        names:
          - default
      selectors:
        - role: pod
          label: "app:abc-123"

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

- __meta_kubernetes_namespace: The namespace of the endpoints object.
- __meta_kubernetes_endpoints_name: The names of the endpoints object.
- For all targets discovered directly from the endpoints list (those not additionally inferred from underlying pods), the following labels are attached:
  - __meta_kubernetes_endpoint_hostname: Hostname of the endpoint.
  - __meta_kubernetes_endpoint_node_name: Name of the node hosting the endpoint.
  - __meta_kubernetes_endpoint_ready: Set to true or false for the endpoint's ready state.
  - __meta_kubernetes_endpoint_port_name: Name of the endpoint port.
  - __meta_kubernetes_endpoint_port_protocol: Protocol of the endpoint port.
  - __meta_kubernetes_endpoint_address_target_kind: Kind of the endpoint address target.
  - __meta_kubernetes_endpoint_address_target_name: Name of the endpoint address target.
- If the endpoints belong to a service, all labels of the role: service discovery are attached.
- For all targets backed by a pod, all labels of the role: pod discovery are attached.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34

scrape_configs:
- job_name: 'kubernetes-apiservers'

  kubernetes_sd_configs:
  - role: endpoints

  # Default to scraping over https. If required, just disable this or change to
  # `http`.
  scheme: https

  # This TLS & bearer token file config is used to connect to the actual scrape
  # endpoints for cluster components. This is separate to discovery auth
  # configuration because discovery & scraping are two separate concerns in
  # Prometheus. The discovery auth config is automatic if Prometheus runs inside
  # the cluster. Otherwise, more config options have to be provided within the
  # <kubernetes_sd_config>.
  tls_config:
    ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
    # If your node certificates are self-signed or use a different CA to the
    # master CA, then disable certificate verification below. Note that
    # certificate verification is an integral part of a secure infrastructure
    # so this should only be disabled in a controlled environment. You can
    # disable certificate verification by uncommenting the line below.
    #
    # insecure_skip_verify: true
  bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token

  # Keep only the default/kubernetes service endpoints for the https port. This
  # will add targets for each API server which Kubernetes adds an endpoint to
  # the default/kubernetes service.
  relabel_configs:
  - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
    action: keep
    regex: default;kubernetes;https

1
2
3
4
5
6
7
8

__meta_kubernetes_namespace: The namespace of the ingress object.
__meta_kubernetes_ingress_name: The name of the ingress object.
__meta_kubernetes_ingress_label_<labelname>: Each label from the ingress object.
__meta_kubernetes_ingress_labelpresent_<labelname>: true for each label from the ingress object.
__meta_kubernetes_ingress_annotation_<annotationname>: Each annotation from the ingress object.
__meta_kubernetes_ingress_annotationpresent_<annotationname>: true for each annotation from the ingress object.
__meta_kubernetes_ingress_scheme: Protocol scheme of ingress, https if TLS config is set. Defaults to http.
__meta_kubernetes_ingress_path: Path from ingress spec. Defaults to /.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29

scrape_configs:
- job_name: 'kubernetes-ingresses'

  metrics_path: /probe
  params:
    module: [http_2xx]

  kubernetes_sd_configs:
  - role: ingress

  relabel_configs:
  # Example relabel to probe only some ingresses that have "example.io/should_be_probed = true" annotation
  #  - source_labels: [__meta_kubernetes_ingress_annotation_example_io_should_be_probed]
  #    action: keep
  #    regex: true
  - source_labels: [__meta_kubernetes_ingress_scheme,__address__,__meta_kubernetes_ingress_path]
    regex: (.+);(.+);(.+)
    replacement: ${1}://${2}${3}
    target_label: __param_target
  - target_label: __address__
    replacement: blackbox-exporter.example.com:9115
  - source_labels: [__param_target]
    target_label: instance
  - action: labelmap
    regex: __meta_kubernetes_ingress_label_(.+)
  - source_labels: [__meta_kubernetes_namespace]
    target_label: kubernetes_namespace
  - source_labels: [__meta_kubernetes_ingress_name]
    target_label: kubernetes_name

1

node_cpu{cpu="cpu0",instance="localhost:9100",job="node",mode="idle"} 93970.8203125

1

node_cpu{cpu="cpu0",instance="localhost:9100",job="node",mode="idle", dc="dc1"} 93970.8203125

1
2
3
4
5
6
7
8
9

scrape_configs:
  - job_name: node_exporter
    consul_sd_configs:
      - server: localhost:8500
        services:
          - node_exporter
    relabel_configs:
    - source_labels:  ["__meta_consul_dc"]
      target_label: "dc"

1

node_cpu{cpu="cpu0",dc="dc1",instance="172.21.0.6:9100",job="consul_sd",mode="guest"}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

__address__="192.168.99.100:10250"
__meta_kubernetes_node_address_Hostname="minikube"
__meta_kubernetes_node_address_InternalIP="192.168.99.100"
__meta_kubernetes_node_annotation_alpha_kubernetes_io_provided_node_ip="192.168.99.100"
__meta_kubernetes_node_annotation_node_alpha_kubernetes_io_ttl="0"
__meta_kubernetes_node_annotation_volumes_kubernetes_io_controller_managed_attach_detach="true"
__meta_kubernetes_node_label_beta_kubernetes_io_arch="amd64"
__meta_kubernetes_node_label_beta_kubernetes_io_os="linux"
__meta_kubernetes_node_label_kubernetes_io_hostname="minikube"
__meta_kubernetes_node_name="minikube"
__metrics_path__="/metrics"
__scheme__="https"
instance="minikube"
job="kubernetes-nodes"

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

# The source labels select values from existing labels. Their content is concatenated
# using the configured separator and matched against the configured regular expression
# for the replace, keep, and drop actions.
[ source_labels: '[' <labelname> [, ...] ']' ]

# Separator placed between concatenated source label values.
[ separator: <string> | default = ; ]

# Label to which the resulting value is written in a replace action.
# It is mandatory for replace actions. Regex capture groups are available.
[ target_label: <labelname> ]

# Regular expression against which the extracted value is matched.
[ regex: <regex> | default = (.*) ]

# Modulus to take of the hash of the source label values.
[ modulus: <int> ]

# Replacement value against which a regex replace is performed if the
# regular expression matches. Regex capture groups are available.
[ replacement: <string> | default = $1 ]

# Action to perform based on regex matching.
[ action: <relabel_action> | default = replace ]

1
2
3
4
5
6

- job_name: 'kubernetes-nodes'
  kubernetes_sd_configs:
  - role: node
  relabel_configs:
  - action: labelmap
    regex: __meta_kubernetes_node_label_(.+)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

scrape_configs:
  - job_name: node_exporter
    consul_sd_configs:
      - server: localhost:8500
        services:
          - node_exporter
    relabel_configs:
    - source_labels:  ["__meta_consul_dc"]
      regex: "dc1"
      action: keep

1
2
3

relabel_configs:
  - regex: label_should_drop_(.+)
    action: labeldrop

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

groups:
- name: example
  rules:
  - alert: HighErrorRate
    expr: job:request_latency_seconds:mean5m{job="myjob"} > 0.5
    for: 10m
    labels:
      severity: page
    annotations:
      summary: High request latency
      description: description info

1
2

rule_files:
  [ - <filepath_glob> ... ]

1
2

global:
  [ evaluation_interval: <duration> | default = 1m ]

1
2
3
4

# To insert a firing element's label values:
{{ $labels.<labelname> }}
# To insert the numeric expression value of the firing element:
{{ $value }}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

groups:
- name: example
  rules:
  # Alert for any instance that is unreachable for >5 minutes.
  - alert: InstanceDown
    expr: up == 0
    for: 5m
    labels:
      severity: page
    annotations:
      summary: "Instance {{ $labels.instance }} down"
      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."

  # Alert for any instance that has a median request latency >1s.
  - alert: APIHighRequestLatency
    expr: api_http_request_latencies_second{quantile="0.5"} > 1
    for: 10m
    annotations:
      summary: "High request latency on {{ $labels.instance }}"
      description: "{{ $labels.instance }} has a median request latency above 1s (current value: {{ $value }}s)"

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: monitoring
data:
  prometheus.yml: |
    global:
      scrape_interval:     15s
      evaluation_interval: 15s
    rule_files:
    - /etc/config/recording_rules.yml
    - /etc/config/alerting_rules.yml
    - /etc/config/rules
    - /etc/config/alerts
    scrape_configs:
      - job_name: 'prometheus'
        static_configs:
        - targets: ['localhost:9090']
      - job_name: 'node'
        static_configs:
        - targets: ['node-exporter:9100']
      - job_name: 'container'
        static_configs:
        - targets: ['cadvisor:8080']    
  alerting_rules.yml: |
    groups:
    - name: hostStatsAlert
      rules:
      - alert: hostMemUsageAlert
        expr: (sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes + node_memory_Buffers_bytes+node_memory_Cached_bytes)) / sum(node_memory_MemTotal_bytes) > 0.55
        for: 1m
        labels:
          severity: page
        annotations:
            summary: "Instance {{ $labels.instance }} MEM usgae high"
            description: "{{ $labels.instance }} MEM usage above 85% (current value: {{ $value }})"    
  alerts: |
        {}
  recording_rules.yml: |
        {}
  rules: |
        {}

1
2

rule_files:
  [ - <filepath_glob> ... ]

1
2

groups:
  [ - <rule_group> ]

1
2
3
4
5

groups:
  - name: example
    rules:
    - record: job:http_inprogress_requests:sum
      expr: sum(http_inprogress_requests) by (job)

1
2
3
4
5
6
7
8

# The name of the group. Must be unique within a file.
name: <string>

# How often rules in the group are evaluated.
[ interval: <duration> | default = global.evaluation_interval ]

rules:
  [ - <rule> ... ]

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

# The name of the time series to output to. Must be a valid metric name.
record: <string>

# The PromQL expression to evaluate. Every evaluation cycle this is
# evaluated at the current time, and the result recorded as a new set of
# time series with the metric name as given by 'record'.
expr: <string>

# Labels to add or overwrite before storing the result.
labels:
  [ <labelname>: <labelvalue> ]

1
2

global:
  [ evaluation_interval: <duration> | default = 1m ]