monitoring_task.yml

apiVersion: influxdata.com/v2alpha1
kind: Task
metadata:
    name: failed-tasks-check-1m
spec:
    every: 1m
    name: 00. Failed Tasks Check
    query: |-
        import "strings"
        import "regexp"
        import "influxdata/influxdb/monitor"
        import "influxdata/influxdb/v1"

        task_data = from(bucket: "_tasks")
            |> range(start: -1m, stop: now())
            |> filter(fn: (r) =>
                (r["_measurement"] == "runs"))
            |> filter(fn: (r) =>
                (r["_field"] == "logs"))
            |> map(fn: (r) => ({ r with name: strings.split(v: regexp.findString(r: /option task = \{([^\}]+)/, v: r._value), t: "\\\\\\\"")[1] }))
            |> drop(columns: ["_value", "_start", "_stop"])
            |> group(columns: ["name", "taskID", "status", "_measurement"])
            |> map(fn: (r) =>
                ({r with _value: if r.status == "failed" then 1 else 0}))
            |> last()
        check = {
            _check_id: "00000000ba5eba11",
            _check_name: "Failed Tasks Check",
            _type: "threshold",
            tags: {},
        }
        ok = (r) =>
            (r["logs"] == 0)
        crit = (r) =>
            (r["logs"] == 1)
        messageFn = (r) =>
            ("The task: ${r.taskID} - ${r.name} has a status of ${r.status}")

        task_data
            |> v1["fieldsAsCols"]()
            |> monitor["check"](
                data: check,
                messageFn: messageFn,
                ok: ok,
                crit: crit,
            )