# 数据拉取配置 scrape_configs 主要用于配置拉取数据节点，每一个拉取配置主要包含以下参数： - job_name：任务名称 - honor_labels： 用于解决拉取数据标签有冲突，当设置为 true, 以拉取数据为准，否则以服务配置为准 - params：数据拉取访问时带的请求参数 - scrape_interval： 拉取时间间隔 - scrape_timeout: 拉取超时时间 - metrics_path： 拉取节点的 metric 路径 - scheme： 拉取数据访问协议 - sample_limit： 存储的数据标签个数限制，如果超过限制，该数据将被忽略，不入存储；默认值为0，表示没有限制 - relabel_configs： 拉取数据重置标签配置 - metric_relabel_configs：metric 重置标签配置 其代码结构体定义为： ``` // ScrapeConfig configures a scraping unit for Prometheus. type ScrapeConfig struct { // The job name to which the job label is set by default. JobName string `yaml:"job_name"` // Indicator whether the scraped metrics should remain unmodified. HonorLabels bool `yaml:"honor_labels,omitempty"` // A set of query parameters with which the target is scraped. Params url.Values `yaml:"params,omitempty"` // How frequently to scrape the targets of this scrape config. ScrapeInterval model.Duration `yaml:"scrape_interval,omitempty"` // The timeout for scraping targets of this config. ScrapeTimeout model.Duration `yaml:"scrape_timeout,omitempty"` // The HTTP resource path on which to fetch metrics from targets. MetricsPath string `yaml:"metrics_path,omitempty"` // The URL scheme with which to fetch metrics from targets. Scheme string `yaml:"scheme,omitempty"` // More than this many samples post metric-relabelling will cause the scrape to fail. SampleLimit uint `yaml:"sample_limit,omitempty"` // We cannot do proper Go type embedding below as the parser will then parse // values arbitrarily into the overflow maps of further-down types. ServiceDiscoveryConfig ServiceDiscoveryConfig `yaml:",inline"` HTTPClientConfig HTTPClientConfig `yaml:",inline"` // List of target relabel configurations. RelabelConfigs []*RelabelConfig `yaml:"relabel_configs,omitempty"` // List of metric relabel configurations. MetricRelabelConfigs []*RelabelConfig `yaml:"metric_relabel_configs,omitempty"` // Catches all undefined fields and must be empty after parsing. XXX map[string]interface{} `yaml:",inline"` } ``` 以上配置定义中还包含 ServiceDiscoveryConfig，它的代码定义为： ``` // ServiceDiscoveryConfig configures lists of different service discovery mechanisms. type ServiceDiscoveryConfig struct { // List of labeled target groups for this job. StaticConfigs []*TargetGroup `yaml:"static_configs,omitempty"` // List of DNS service discovery configurations. DNSSDConfigs []*DNSSDConfig `yaml:"dns_sd_configs,omitempty"` // List of file service discovery configurations. FileSDConfigs []*FileSDConfig `yaml:"file_sd_configs,omitempty"` // List of Consul service discovery configurations. ConsulSDConfigs []*ConsulSDConfig `yaml:"consul_sd_configs,omitempty"` // List of Serverset service discovery configurations. ServersetSDConfigs []*ServersetSDConfig `yaml:"serverset_sd_configs,omitempty"` // NerveSDConfigs is a list of Nerve service discovery configurations. NerveSDConfigs []*NerveSDConfig `yaml:"nerve_sd_configs,omitempty"` // MarathonSDConfigs is a list of Marathon service discovery configurations. MarathonSDConfigs []*MarathonSDConfig `yaml:"marathon_sd_configs,omitempty"` // List of Kubernetes service discovery configurations. KubernetesSDConfigs []*KubernetesSDConfig `yaml:"kubernetes_sd_configs,omitempty"` // List of GCE service discovery configurations. GCESDConfigs []*GCESDConfig `yaml:"gce_sd_configs,omitempty"` // List of EC2 service discovery configurations. EC2SDConfigs []*EC2SDConfig `yaml:"ec2_sd_configs,omitempty"` // List of OpenStack service discovery configurations. OpenstackSDConfigs []*OpenstackSDConfig `yaml:"openstack_sd_configs,omitempty"` // List of Azure service discovery configurations. AzureSDConfigs []*AzureSDConfig `yaml:"azure_sd_configs,omitempty"` // List of Triton service discovery configurations. TritonSDConfigs []*TritonSDConfig `yaml:"triton_sd_configs,omitempty"` // Catches all undefined fields and must be empty after parsing. XXX map[string]interface{} `yaml:",inline"` } ``` ServiceDiscoveryConfig 主要用于 target 发现，大体分为两类，静态配置和动态发现。 所以，一份完整的 scrape_configs 配置大致为： ``` # 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. This is useful for use cases such as federation, 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 ] # 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. basic_auth: [ username: <string> ] [ password: <string> ] # Sets the `Authorization` header on every scrape request with # the configured bearer token. It is mutually exclusive with `bearer_token_file`. [ bearer_token: <string> ] # 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: /path/to/bearer/token/file ] # 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 DNS service discovery configurations. dns_sd_configs: [ - <dns_sd_config> ... ] # List of EC2 service discovery configurations. ec2_sd_configs: [ - <ec2_sd_config> ... ] # List of OpenStack service discovery configurations. openstack_sd_configs: [ - <openstack_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 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 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 relabelling # the entire scrape will be treated as failed. 0 means no limit. [ sample_limit: <int> | default = 0 ] ```