SLI plugin

version: "prometheus/v1"
service: "myservice"
labels:
  owner: "myteam"
  repo: "myorg/myservice"
  tier: "2"
slos:
  # We allow failing (5xx and 429) 1 request every 1000 requests (99.9%).
  - name: "requests-availability"
    objective: 99.9
    description: "Common SLO based on availability for HTTP request responses."
    sli:
      plugin:
        id: "getting_started_availability"
        options:
          job: "myservice"
          filter: 'f1="v1",f2="v2"'
    alerting:
      name: MyServiceHighErrorRate
      labels:
        category: "availability"
      annotations:
        # Overwrite default Sloth SLO alert summmary on ticket and page alerts.
        summary: "High error rate on 'myservice' requests responses"
      page_alert:
        labels:
          severity: pageteam
          routing_key: myteam
      ticket_alert:
        labels:
          severity: "slack"
          slack_channel: "#alerts-myteam"

---
# Code generated by Sloth (dev): https://github.com/slok/sloth.
# DO NOT EDIT.

groups:
- name: sloth-slo-sli-recordings-myservice-requests-availability
  rules:
  - record: slo:sli_error:ratio_rate5m
    expr: |-
      (
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice",code=~"(5..|429)" }[5m]))
      /
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice" }[5m])))
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_window: 5m
      tier: "2"
  - record: slo:sli_error:ratio_rate30m
    expr: |-
      (
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice",code=~"(5..|429)" }[30m]))
      /
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice" }[30m])))
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_window: 30m
      tier: "2"
  - record: slo:sli_error:ratio_rate1h
    expr: |-
      (
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice",code=~"(5..|429)" }[1h]))
      /
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice" }[1h])))
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_window: 1h
      tier: "2"
  - record: slo:sli_error:ratio_rate2h
    expr: |-
      (
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice",code=~"(5..|429)" }[2h]))
      /
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice" }[2h])))
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_window: 2h
      tier: "2"
  - record: slo:sli_error:ratio_rate6h
    expr: |-
      (
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice",code=~"(5..|429)" }[6h]))
      /
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice" }[6h])))
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_window: 6h
      tier: "2"
  - record: slo:sli_error:ratio_rate1d
    expr: |-
      (
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice",code=~"(5..|429)" }[1d]))
      /
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice" }[1d])))
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_window: 1d
      tier: "2"
  - record: slo:sli_error:ratio_rate3d
    expr: |-
      (
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice",code=~"(5..|429)" }[3d]))
      /
      sum(rate(http_request_duration_seconds_count{ f1="v1",f2="v2",job="myservice" }[3d])))
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_window: 3d
      tier: "2"
  - record: slo:sli_error:ratio_rate30d
    expr: |
      sum_over_time(slo:sli_error:ratio_rate5m{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"}[30d])
      / ignoring (sloth_window)
      count_over_time(slo:sli_error:ratio_rate5m{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"}[30d])
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_window: 30d
      tier: "2"
- name: sloth-slo-meta-recordings-myservice-requests-availability
  rules:
  - record: slo:objective:ratio
    expr: vector(0.9990000000000001)
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      tier: "2"
  - record: slo:error_budget:ratio
    expr: vector(1-0.9990000000000001)
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      tier: "2"
  - record: slo:time_period:days
    expr: vector(30)
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      tier: "2"
  - record: slo:current_burn_rate:ratio
    expr: |
      slo:sli_error:ratio_rate5m{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"}
      / on(sloth_id, sloth_slo, sloth_service) group_left
      slo:error_budget:ratio{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"}
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      tier: "2"
  - record: slo:period_burn_rate:ratio
    expr: |
      slo:sli_error:ratio_rate30d{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"}
      / on(sloth_id, sloth_slo, sloth_service) group_left
      slo:error_budget:ratio{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"}
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      tier: "2"
  - record: slo:period_error_budget_remaining:ratio
    expr: 1 - slo:period_burn_rate:ratio{sloth_id="myservice-requests-availability",
      sloth_service="myservice", sloth_slo="requests-availability"}
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_service: myservice
      sloth_slo: requests-availability
      tier: "2"
  - record: sloth_slo_info
    expr: vector(1)
    labels:
      cmd: examplesgen.sh
      owner: myteam
      repo: myorg/myservice
      sloth_id: myservice-requests-availability
      sloth_mode: cli-gen-prom
      sloth_objective: "99.9"
      sloth_service: myservice
      sloth_slo: requests-availability
      sloth_spec: prometheus/v1
      sloth_version: dev
      tier: "2"
- name: sloth-slo-alerts-myservice-requests-availability
  rules:
  - alert: MyServiceHighErrorRate
    expr: |
      (
          max(slo:sli_error:ratio_rate5m{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"} > (14.4 * 0.0009999999999999432)) without (sloth_window)
          and
          max(slo:sli_error:ratio_rate1h{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"} > (14.4 * 0.0009999999999999432)) without (sloth_window)
      )
      or
      (
          max(slo:sli_error:ratio_rate30m{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"} > (6 * 0.0009999999999999432)) without (sloth_window)
          and
          max(slo:sli_error:ratio_rate6h{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"} > (6 * 0.0009999999999999432)) without (sloth_window)
      )
    labels:
      category: availability
      routing_key: myteam
      severity: pageteam
      sloth_severity: page
    annotations:
      summary: High error rate on 'myservice' requests responses
      title: (page) {{$labels.sloth_service}} {{$labels.sloth_slo}} SLO error budget
        burn rate is too fast.
  - alert: MyServiceHighErrorRate
    expr: |
      (
          max(slo:sli_error:ratio_rate2h{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"} > (3 * 0.0009999999999999432)) without (sloth_window)
          and
          max(slo:sli_error:ratio_rate1d{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"} > (3 * 0.0009999999999999432)) without (sloth_window)
      )
      or
      (
          max(slo:sli_error:ratio_rate6h{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"} > (1 * 0.0009999999999999432)) without (sloth_window)
          and
          max(slo:sli_error:ratio_rate3d{sloth_id="myservice-requests-availability", sloth_service="myservice", sloth_slo="requests-availability"} > (1 * 0.0009999999999999432)) without (sloth_window)
      )
    labels:
      category: availability
      severity: slack
      slack_channel: '#alerts-myteam'
      sloth_severity: ticket
    annotations:
      summary: High error rate on 'myservice' requests responses
      title: (ticket) {{$labels.sloth_service}} {{$labels.sloth_slo}} SLO error budget
        burn rate is too fast.

package availability

import (
    "bytes"
    "context"
    "fmt"
    "regexp"
    "strings"
    "text/template"
)

const (
    SLIPluginVersion = "prometheus/v1"
    SLIPluginID      = "getting_started_availability"
)

var queryTpl = template.Must(template.New("").Parse(`
sum(rate(http_request_duration_seconds_count{ {{.filter}}job="{{.job}}",code=~"(5..|429)" }[{{"{{.window}}"}}]))
/
sum(rate(http_request_duration_seconds_count{ {{.filter}}job="{{.job}}" }[{{"{{.window}}"}}]))`))

var filterRegex = regexp.MustCompile(`([^=]+="[^=,"]+",)+`)

// SLIPlugin is the getting started plugin example.
//
// It will return an Sloth error ratio raw query that returns the error ratio of HTTP requests based
// on the HTTP response status code, taking 5xx and 429 as error events.
func SLIPlugin(ctx context.Context, meta, labels, options map[string]string) (string, error) {
    // Get job.
    job, ok := options["job"]
    if !ok {
        return "", fmt.Errorf("job options is required")
    }

    // Validate labels.
    err := validateLabels(labels, "owner", "tier")
    if err != nil {
        return "", fmt.Errorf("invalid labels: %w", err)
    }

    // Sanitize filter.
    filter := options["filter"]
    if filter != "" {
        filter = strings.Trim(filter, "{}")
        filter = strings.Trim(filter, ",")
        filter = filter + ","
        match := filterRegex.MatchString(filter)
        if !match {
            return "", fmt.Errorf("invalid prometheus filter: %s", filter)
        }
    }

    // Create query.
    var b bytes.Buffer
    data := map[string]string{
        "job":    job,
        "filter": filter,
    }
    err = queryTpl.Execute(&b, data)
    if err != nil {
        return "", fmt.Errorf("could not execute template: %w", err)
    }

    return b.String(), nil
}

// validateLabels will check the labels exist.
func validateLabels(labels map[string]string, requiredKeys ...string) error {
    for _, k := range requiredKeys {
        v, ok := labels[k]
        if !ok || (ok && v == "") {
            return fmt.Errorf("%q label is required", k)
        }
    }

    return nil
}