templates

var (
	// Templates stores a mapping of template name to registered template. This is used to
	// unmarshal template definitions from their yaml source and to provide users with
	// feedback about what templates this tool supports.
	Templates = map[string]SLO{}

	// TemplateRules implement the translation from the rules produced by each instance of
	// SLO templates into the generic SLO error:ratio<I> format, which then power alerts.
	TemplateRules = []rulefmt.Rule{}

	// AlertWindows are common interval windows we want to precompute
	AlertWindows = []string{"1m", "5m", "30m", "1h", "2h", "6h", "1d", "3d", "7d", "28d"}

	// AlertRules every SLO type produces rules that terminate in job:slo_error:ratio<I> and
	// job:slo_error_budget's. Together, we can use these rules to power generic
	// multi-window SLO error budget burn alerts, and these alert rules are run as the final
	// part of the Pipeline generated RuleGroup.
	AlertRules = []rulefmt.Rule{
		rulefmt.Rule{
			Alert: "SLOErrorBudgetFastBurn",
			For:   model.Duration(time.Minute),
			Labels: map[string]string{
				"severity": "ticket",
			},
			Expr: `
((
  job:slo_error:ratio1h > on(name) group_left() (14.4 * job:slo_error_budget:ratio)
and
  job:slo_error:ratio5m > on(name) group_left() (14.4 * job:slo_error_budget:ratio)
)
or
(
  job:slo_error:ratio6h > on(name) group_left() (6.0 * job:slo_error_budget:ratio)
and
  job:slo_error:ratio30m > on(name) group_left() (6.0 * job:slo_error_budget:ratio)
)) * on(name) group_left(channel) job:slo_labels_info
			`,
		},
		rulefmt.Rule{
			Alert: "SLOErrorBudgetSlowBurn",
			For:   model.Duration(time.Hour),
			Labels: map[string]string{
				"severity": "ticket",
			},
			Expr: `
((
  job:slo_error:ratio1d > on(name) group_left() (3.0 * job:slo_error_budget:ratio)
and
  job:slo_error:ratio2h > on(name) group_left() (3.0 * job:slo_error_budget:ratio)
)
or
(
  job:slo_error:ratio3d > on(name) group_left() (1.0 * job:slo_error_budget:ratio)
and
  job:slo_error:ratio6h > on(name) group_left() (1.0 * job:slo_error_budget:ratio)
)) * on(name) group_left(channel) jobs:slo_labels_info
			`,
		},
	}
)

var (
	// BatchProcessingTemplateRules map from the job:slo_batch_* time series to
	// the SLO-compliant job:slo_error:ratio<I> series that are used to power
	// alerts.
	BatchProcessingTemplateRules = flattenRules(

		rulefmt.Rule{
			Record: "job:slo_batch_error:interval",
			Expr: `
1.0 - clamp_max(
  job:slo_batch_throughput:interval / job:slo_batch_throughput_target:max,
  1.0
)
			`,
		},

		forIntervals(AlertWindows,
			rulefmt.Rule{
				Record: "job:slo_error:ratio%s",
				Expr:   `avg_over_time(job:slo_batch_error:interval[%s])`,
			},
		),
	)
)

var (
	// ErrorRateTemplateRules map from the job:slo_error_rate_total and
	// job:slo_error_rate_errors time series to the SLO-compliant
	// job:slo_error:ratio<I> series that are used to power alerts.
	ErrorRateTemplateRules = flattenRules(

		forIntervals(AlertWindows, rulefmt.Rule{
			Record: "job:slo_error:ratio%s",
			Expr:   `((job:slo_error_rate_errors:rate%[1]s) or (0 * job:slo_error_rate_total:rate%[1]s)) / job:slo_error_rate_total:rate%[1]s`,
		}),
	)
)

var (
	// LatencyTemplateRules map from the job:slo_latency_* time series to the
	// SLO-compliant job:slo_error:ratio<I> series than are used to power
	// alerts.
	LatencyTemplateRules = flattenRules(

		forIntervals(AlertWindows, rulefmt.Rule{
			Record: "job:slo_error:ratio%s",
			Expr:   `(job:slo_latency_total:rate%[1]s - job:slo_latency_observation:rate%[1]s) / job:slo_latency_total:rate%[1]s`,
		}),
	)
)