// Copyright 2024 Google LLC // // Licensed under the Apache License, Version 2.0 (the "License"); // you may not use this file except in compliance with the License. // You may obtain a copy of the License at // // http://www.apache.org/licenses/LICENSE-2.0 // // Unless required by applicable law or agreed to in writing, software // distributed under the License is distributed on an "AS IS" BASIS, // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. // See the License for the specific language governing permissions and // limitations under the License. syntax = "proto3"; package google.monitoring.v3; import "google/api/field_behavior.proto"; import "google/api/resource.proto"; import "google/monitoring/v3/common.proto"; import "google/monitoring/v3/mutation_record.proto"; import "google/protobuf/duration.proto"; import "google/protobuf/wrappers.proto"; import "google/rpc/status.proto"; option csharp_namespace = "Google.Cloud.Monitoring.V3"; option go_package = "cloud.google.com/go/monitoring/apiv3/v2/monitoringpb;monitoringpb"; option java_multiple_files = true; option java_outer_classname = "AlertProto"; option java_package = "com.google.monitoring.v3"; option php_namespace = "Google\\Cloud\\Monitoring\\V3"; option ruby_package = "Google::Cloud::Monitoring::V3"; // A description of the conditions under which some aspect of your system is // considered to be "unhealthy" and the ways to notify people or services about // this state. For an overview of alert policies, see // [Introduction to Alerting](https://cloud.google.com/monitoring/alerts/). // message AlertPolicy { option (google.api.resource) = { type: "monitoring.googleapis.com/AlertPolicy" pattern: "projects/{project}/alertPolicies/{alert_policy}" pattern: "organizations/{organization}/alertPolicies/{alert_policy}" pattern: "folders/{folder}/alertPolicies/{alert_policy}" pattern: "*" }; // Documentation that is included in the notifications and incidents // pertaining to this policy. message Documentation { // The body of the documentation, interpreted according to `mime_type`. // The content may not exceed 8,192 Unicode characters and may not exceed // more than 10,240 bytes when encoded in UTF-8 format, whichever is // smaller. This text can be [templatized by using // variables](https://cloud.google.com/monitoring/alerts/doc-variables). string content = 1; // The format of the `content` field. Presently, only the value // `"text/markdown"` is supported. See // [Markdown](https://en.wikipedia.org/wiki/Markdown) for more information. string mime_type = 2; // Optional. The subject line of the notification. The subject line may not // exceed 10,240 bytes. In notifications generated by this policy, the // contents of the subject line after variable expansion will be truncated // to 255 bytes or shorter at the latest UTF-8 character boundary. The // 255-byte limit is recommended by [this // thread](https://stackoverflow.com/questions/1592291/what-is-the-email-subject-length-limit). // It is both the limit imposed by some third-party ticketing products and // it is common to define textual fields in databases as VARCHAR(255). // // The contents of the subject line can be [templatized by using // variables](https://cloud.google.com/monitoring/alerts/doc-variables). // If this field is missing or empty, a default subject line will be // generated. string subject = 3 [(google.api.field_behavior) = OPTIONAL]; } // A condition is a true/false test that determines when an alerting policy // should open an incident. If a condition evaluates to true, it signifies // that something is wrong. message Condition { option (google.api.resource) = { type: "monitoring.googleapis.com/AlertPolicyCondition" pattern: "projects/{project}/alertPolicies/{alert_policy}/conditions/{condition}" pattern: "organizations/{organization}/alertPolicies/{alert_policy}/conditions/{condition}" pattern: "folders/{folder}/alertPolicies/{alert_policy}/conditions/{condition}" pattern: "*" }; // Specifies how many time series must fail a predicate to trigger a // condition. If not specified, then a `{count: 1}` trigger is used. message Trigger { // A type of trigger. oneof type { // The absolute number of time series that must fail // the predicate for the condition to be triggered. int32 count = 1; // The percentage of time series that must fail the // predicate for the condition to be triggered. double percent = 2; } } // A condition control that determines how metric-threshold conditions // are evaluated when data stops arriving. // This control doesn't affect metric-absence policies. enum EvaluationMissingData { // An unspecified evaluation missing data option. Equivalent to // EVALUATION_MISSING_DATA_NO_OP. EVALUATION_MISSING_DATA_UNSPECIFIED = 0; // If there is no data to evaluate the condition, then evaluate the // condition as false. EVALUATION_MISSING_DATA_INACTIVE = 1; // If there is no data to evaluate the condition, then evaluate the // condition as true. EVALUATION_MISSING_DATA_ACTIVE = 2; // Do not evaluate the condition to any value if there is no data. EVALUATION_MISSING_DATA_NO_OP = 3; } // A condition type that compares a collection of time series // against a threshold. message MetricThreshold { // Options used when forecasting the time series and testing // the predicted value against the threshold. message ForecastOptions { // Required. The length of time into the future to forecast whether a // time series will violate the threshold. If the predicted value is // found to violate the threshold, and the violation is observed in all // forecasts made for the configured `duration`, then the time series is // considered to be failing. // The forecast horizon can range from 1 hour to 60 hours. google.protobuf.Duration forecast_horizon = 1 [(google.api.field_behavior) = REQUIRED]; } // Required. A // [filter](https://cloud.google.com/monitoring/api/v3/filters) that // identifies which time series should be compared with the threshold. // // The filter is similar to the one that is specified in the // [`ListTimeSeries` // request](https://cloud.google.com/monitoring/api/ref_v3/rest/v3/projects.timeSeries/list) // (that call is useful to verify the time series that will be retrieved / // processed). The filter must specify the metric type and the resource // type. Optionally, it can specify resource labels and metric labels. // This field must not exceed 2048 Unicode characters in length. string filter = 2 [(google.api.field_behavior) = REQUIRED]; // Specifies the alignment of data points in individual time series as // well as how to combine the retrieved time series together (such as // when aggregating multiple streams on each resource to a single // stream for each resource or when aggregating streams across all // members of a group of resources). Multiple aggregations // are applied in the order specified. // // This field is similar to the one in the [`ListTimeSeries` // request](https://cloud.google.com/monitoring/api/ref_v3/rest/v3/projects.timeSeries/list). // It is advisable to use the `ListTimeSeries` method when debugging this // field. repeated Aggregation aggregations = 8; // A [filter](https://cloud.google.com/monitoring/api/v3/filters) that // identifies a time series that should be used as the denominator of a // ratio that will be compared with the threshold. If a // `denominator_filter` is specified, the time series specified by the // `filter` field will be used as the numerator. // // The filter must specify the metric type and optionally may contain // restrictions on resource type, resource labels, and metric labels. // This field may not exceed 2048 Unicode characters in length. string denominator_filter = 9; // Specifies the alignment of data points in individual time series // selected by `denominatorFilter` as // well as how to combine the retrieved time series together (such as // when aggregating multiple streams on each resource to a single // stream for each resource or when aggregating streams across all // members of a group of resources). // // When computing ratios, the `aggregations` and // `denominator_aggregations` fields must use the same alignment period // and produce time series that have the same periodicity and labels. repeated Aggregation denominator_aggregations = 10; // When this field is present, the `MetricThreshold` condition forecasts // whether the time series is predicted to violate the threshold within // the `forecast_horizon`. When this field is not set, the // `MetricThreshold` tests the current value of the timeseries against the // threshold. ForecastOptions forecast_options = 12; // The comparison to apply between the time series (indicated by `filter` // and `aggregation`) and the threshold (indicated by `threshold_value`). // The comparison is applied on each time series, with the time series // on the left-hand side and the threshold on the right-hand side. // // Only `COMPARISON_LT` and `COMPARISON_GT` are supported currently. ComparisonType comparison = 4; // A value against which to compare the time series. double threshold_value = 5; // The amount of time that a time series must violate the // threshold to be considered failing. Currently, only values // that are a multiple of a minute--e.g., 0, 60, 120, or 300 // seconds--are supported. If an invalid value is given, an // error will be returned. When choosing a duration, it is useful to // keep in mind the frequency of the underlying time series data // (which may also be affected by any alignments specified in the // `aggregations` field); a good duration is long enough so that a single // outlier does not generate spurious alerts, but short enough that // unhealthy states are detected and alerted on quickly. google.protobuf.Duration duration = 6; // The number/percent of time series for which the comparison must hold // in order for the condition to trigger. If unspecified, then the // condition will trigger if the comparison is true for any of the // time series that have been identified by `filter` and `aggregations`, // or by the ratio, if `denominator_filter` and `denominator_aggregations` // are specified. Trigger trigger = 7; // A condition control that determines how metric-threshold conditions // are evaluated when data stops arriving. To use this control, the value // of the `duration` field must be greater than or equal to 60 seconds. EvaluationMissingData evaluation_missing_data = 11; } // A condition type that checks that monitored resources // are reporting data. The configuration defines a metric and // a set of monitored resources. The predicate is considered in violation // when a time series for the specified metric of a monitored // resource does not include any data in the specified `duration`. message MetricAbsence { // Required. A // [filter](https://cloud.google.com/monitoring/api/v3/filters) that // identifies which time series should be compared with the threshold. // // The filter is similar to the one that is specified in the // [`ListTimeSeries` // request](https://cloud.google.com/monitoring/api/ref_v3/rest/v3/projects.timeSeries/list) // (that call is useful to verify the time series that will be retrieved / // processed). The filter must specify the metric type and the resource // type. Optionally, it can specify resource labels and metric labels. // This field must not exceed 2048 Unicode characters in length. string filter = 1 [(google.api.field_behavior) = REQUIRED]; // Specifies the alignment of data points in individual time series as // well as how to combine the retrieved time series together (such as // when aggregating multiple streams on each resource to a single // stream for each resource or when aggregating streams across all // members of a group of resources). Multiple aggregations // are applied in the order specified. // // This field is similar to the one in the [`ListTimeSeries` // request](https://cloud.google.com/monitoring/api/ref_v3/rest/v3/projects.timeSeries/list). // It is advisable to use the `ListTimeSeries` method when debugging this // field. repeated Aggregation aggregations = 5; // The amount of time that a time series must fail to report new // data to be considered failing. The minimum value of this field // is 120 seconds. Larger values that are a multiple of a // minute--for example, 240 or 300 seconds--are supported. // If an invalid value is given, an // error will be returned. The `Duration.nanos` field is // ignored. google.protobuf.Duration duration = 2; // The number/percent of time series for which the comparison must hold // in order for the condition to trigger. If unspecified, then the // condition will trigger if the comparison is true for any of the // time series that have been identified by `filter` and `aggregations`. Trigger trigger = 3; } // A condition type that checks whether a log message in the [scoping // project](https://cloud.google.com/monitoring/api/v3#project_name) // satisfies the given filter. Logs from other projects in the metrics // scope are not evaluated. message LogMatch { // Required. A logs-based filter. See [Advanced Logs // Queries](https://cloud.google.com/logging/docs/view/advanced-queries) // for how this filter should be constructed. string filter = 1 [(google.api.field_behavior) = REQUIRED]; // Optional. A map from a label key to an extractor expression, which is // used to extract the value for this label key. Each entry in this map is // a specification for how data should be extracted from log entries that // match `filter`. Each combination of extracted values is treated as a // separate rule for the purposes of triggering notifications. Label keys // and corresponding values can be used in notifications generated by this // condition. // // Please see [the documentation on logs-based metric // `valueExtractor`s](https://cloud.google.com/logging/docs/reference/v2/rest/v2/projects.metrics#LogMetric.FIELDS.value_extractor) // for syntax and examples. map label_extractors = 2; } // A condition type that allows alert policies to be defined using // [Monitoring Query Language](https://cloud.google.com/monitoring/mql). message MonitoringQueryLanguageCondition { // [Monitoring Query Language](https://cloud.google.com/monitoring/mql) // query that outputs a boolean stream. string query = 1; // The amount of time that a time series must violate the // threshold to be considered failing. Currently, only values // that are a multiple of a minute--e.g., 0, 60, 120, or 300 // seconds--are supported. If an invalid value is given, an // error will be returned. When choosing a duration, it is useful to // keep in mind the frequency of the underlying time series data // (which may also be affected by any alignments specified in the // `aggregations` field); a good duration is long enough so that a single // outlier does not generate spurious alerts, but short enough that // unhealthy states are detected and alerted on quickly. google.protobuf.Duration duration = 2; // The number/percent of time series for which the comparison must hold // in order for the condition to trigger. If unspecified, then the // condition will trigger if the comparison is true for any of the // time series that have been identified by `filter` and `aggregations`, // or by the ratio, if `denominator_filter` and `denominator_aggregations` // are specified. Trigger trigger = 3; // A condition control that determines how metric-threshold conditions // are evaluated when data stops arriving. EvaluationMissingData evaluation_missing_data = 4; } // A condition type that allows alert policies to be defined using // [Prometheus Query Language // (PromQL)](https://prometheus.io/docs/prometheus/latest/querying/basics/). // // The PrometheusQueryLanguageCondition message contains information // from a Prometheus alerting rule and its associated rule group. // // A Prometheus alerting rule is described // [here](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/). // The semantics of a Prometheus alerting rule is described // [here](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/#rule). // // A Prometheus rule group is described // [here](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/). // The semantics of a Prometheus rule group is described // [here](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/#rule_group). // // Because Cloud Alerting has no representation of a Prometheus rule // group resource, we must embed the information of the parent rule // group inside each of the conditions that refer to it. We must also // update the contents of all Prometheus alerts in case the information // of their rule group changes. // // The PrometheusQueryLanguageCondition protocol buffer combines the // information of the corresponding rule group and alerting rule. // The structure of the PrometheusQueryLanguageCondition protocol buffer // does NOT mimic the structure of the Prometheus rule group and alerting // rule YAML declarations. The PrometheusQueryLanguageCondition protocol // buffer may change in the future to support future rule group and/or // alerting rule features. There are no new such features at the present // time (2023-06-26). message PrometheusQueryLanguageCondition { // Required. The PromQL expression to evaluate. Every evaluation cycle // this expression is evaluated at the current time, and all resultant // time series become pending/firing alerts. This field must not be empty. string query = 1 [(google.api.field_behavior) = REQUIRED]; // Optional. Alerts are considered firing once their PromQL expression was // evaluated to be "true" for this long. // Alerts whose PromQL expression was not evaluated to be "true" for // long enough are considered pending. // Must be a non-negative duration or missing. // This field is optional. Its default value is zero. google.protobuf.Duration duration = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. How often this rule should be evaluated. // Must be a positive multiple of 30 seconds or missing. // This field is optional. Its default value is 30 seconds. // If this PrometheusQueryLanguageCondition was generated from a // Prometheus alerting rule, then this value should be taken from the // enclosing rule group. google.protobuf.Duration evaluation_interval = 3 [(google.api.field_behavior) = OPTIONAL]; // Optional. Labels to add to or overwrite in the PromQL query result. // Label names [must be // valid](https://prometheus.io/docs/concepts/data_model/#metric-names-and-labels). // Label values can be [templatized by using // variables](https://cloud.google.com/monitoring/alerts/doc-variables). // The only available variable names are the names of the labels in the // PromQL result, including "__name__" and "value". "labels" may be empty. map labels = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. The rule group name of this alert in the corresponding // Prometheus configuration file. // // Some external tools may require this field to be populated correctly // in order to refer to the original Prometheus configuration file. // The rule group name and the alert name are necessary to update the // relevant AlertPolicies in case the definition of the rule group changes // in the future. // // This field is optional. If this field is not empty, then it must // contain a valid UTF-8 string. // This field may not exceed 2048 Unicode characters in length. string rule_group = 5 [(google.api.field_behavior) = OPTIONAL]; // Optional. The alerting rule name of this alert in the corresponding // Prometheus configuration file. // // Some external tools may require this field to be populated correctly // in order to refer to the original Prometheus configuration file. // The rule group name and the alert name are necessary to update the // relevant AlertPolicies in case the definition of the rule group changes // in the future. // // This field is optional. If this field is not empty, then it must be a // [valid Prometheus label // name](https://prometheus.io/docs/concepts/data_model/#metric-names-and-labels). // This field may not exceed 2048 Unicode characters in length. string alert_rule = 6 [(google.api.field_behavior) = OPTIONAL]; } // Required if the condition exists. The unique resource name for this // condition. Its format is: // // projects/[PROJECT_ID_OR_NUMBER]/alertPolicies/[POLICY_ID]/conditions/[CONDITION_ID] // // `[CONDITION_ID]` is assigned by Cloud Monitoring when the // condition is created as part of a new or updated alerting policy. // // When calling the // [alertPolicies.create][google.monitoring.v3.AlertPolicyService.CreateAlertPolicy] // method, do not include the `name` field in the conditions of the // requested alerting policy. Cloud Monitoring creates the // condition identifiers and includes them in the new policy. // // When calling the // [alertPolicies.update][google.monitoring.v3.AlertPolicyService.UpdateAlertPolicy] // method to update a policy, including a condition `name` causes the // existing condition to be updated. Conditions without names are added to // the updated policy. Existing conditions are deleted if they are not // updated. // // Best practice is to preserve `[CONDITION_ID]` if you make only small // changes, such as those to condition thresholds, durations, or trigger // values. Otherwise, treat the change as a new condition and let the // existing condition be deleted. string name = 12; // A short name or phrase used to identify the condition in dashboards, // notifications, and incidents. To avoid confusion, don't use the same // display name for multiple conditions in the same policy. string display_name = 6; // Only one of the following condition types will be specified. oneof condition { // A condition that compares a time series against a threshold. MetricThreshold condition_threshold = 1; // A condition that checks that a time series continues to // receive new data points. MetricAbsence condition_absent = 2; // A condition that checks for log messages matching given constraints. If // set, no other conditions can be present. LogMatch condition_matched_log = 20; // A condition that uses the Monitoring Query Language to define // alerts. MonitoringQueryLanguageCondition condition_monitoring_query_language = 19; // A condition that uses the Prometheus query language to define alerts. PrometheusQueryLanguageCondition condition_prometheus_query_language = 21; } } // Operators for combining conditions. enum ConditionCombinerType { // An unspecified combiner. COMBINE_UNSPECIFIED = 0; // Combine conditions using the logical `AND` operator. An // incident is created only if all the conditions are met // simultaneously. This combiner is satisfied if all conditions are // met, even if they are met on completely different resources. AND = 1; // Combine conditions using the logical `OR` operator. An incident // is created if any of the listed conditions is met. OR = 2; // Combine conditions using logical `AND` operator, but unlike the regular // `AND` option, an incident is created only if all conditions are met // simultaneously on at least one resource. AND_WITH_MATCHING_RESOURCE = 3; } // Control over how the notification channels in `notification_channels` // are notified when this alert fires. message AlertStrategy { // Control over the rate of notifications sent to this alert policy's // notification channels. message NotificationRateLimit { // Not more than one notification per `period`. google.protobuf.Duration period = 1; } // Control over how the notification channels in `notification_channels` // are notified when this alert fires, on a per-channel basis. message NotificationChannelStrategy { // The full REST resource name for the notification channels that these // settings apply to. Each of these correspond to the name field in one // of the NotificationChannel objects referenced in the // notification_channels field of this AlertPolicy. // The format is: // // projects/[PROJECT_ID_OR_NUMBER]/notificationChannels/[CHANNEL_ID] repeated string notification_channel_names = 1; // The frequency at which to send reminder notifications for open // incidents. google.protobuf.Duration renotify_interval = 2; } // Required for alert policies with a `LogMatch` condition. // // This limit is not implemented for alert policies that are not log-based. NotificationRateLimit notification_rate_limit = 1; // If an alert policy that was active has no data for this long, any open // incidents will close google.protobuf.Duration auto_close = 3; // Control how notifications will be sent out, on a per-channel basis. repeated NotificationChannelStrategy notification_channel_strategy = 4; } // An enumeration of possible severity level for an Alert Policy. enum Severity { // No severity is specified. This is the default value. SEVERITY_UNSPECIFIED = 0; // This is the highest severity level. Use this if the problem could // cause significant damage or downtime. CRITICAL = 1; // This is the medium severity level. Use this if the problem could // cause minor damage or downtime. ERROR = 2; // This is the lowest severity level. Use this if the problem is not causing // any damage or downtime, but could potentially lead to a problem in the // future. WARNING = 3; } // Required if the policy exists. The resource name for this policy. The // format is: // // projects/[PROJECT_ID_OR_NUMBER]/alertPolicies/[ALERT_POLICY_ID] // // `[ALERT_POLICY_ID]` is assigned by Cloud Monitoring when the policy // is created. When calling the // [alertPolicies.create][google.monitoring.v3.AlertPolicyService.CreateAlertPolicy] // method, do not include the `name` field in the alerting policy passed as // part of the request. string name = 1; // A short name or phrase used to identify the policy in dashboards, // notifications, and incidents. To avoid confusion, don't use the same // display name for multiple policies in the same project. The name is // limited to 512 Unicode characters. // // The convention for the display_name of a PrometheusQueryLanguageCondition // is "{rule group name}/{alert name}", where the {rule group name} and // {alert name} should be taken from the corresponding Prometheus // configuration file. This convention is not enforced. // In any case the display_name is not a unique key of the AlertPolicy. string display_name = 2; // Documentation that is included with notifications and incidents related to // this policy. Best practice is for the documentation to include information // to help responders understand, mitigate, escalate, and correct the // underlying problems detected by the alerting policy. Notification channels // that have limited capacity might not show this documentation. Documentation documentation = 13; // User-supplied key/value data to be used for organizing and // identifying the `AlertPolicy` objects. // // The field can contain up to 64 entries. Each key and value is limited to // 63 Unicode characters or 128 bytes, whichever is smaller. Labels and // values can contain only lowercase letters, numerals, underscores, and // dashes. Keys must begin with a letter. // // Note that Prometheus {alert name} is a // [valid Prometheus label // names](https://prometheus.io/docs/concepts/data_model/#metric-names-and-labels), // whereas Prometheus {rule group} is an unrestricted UTF-8 string. // This means that they cannot be stored as-is in user labels, because // they may contain characters that are not allowed in user-label values. map user_labels = 16; // A list of conditions for the policy. The conditions are combined by AND or // OR according to the `combiner` field. If the combined conditions evaluate // to true, then an incident is created. A policy can have from one to six // conditions. // If `condition_time_series_query_language` is present, it must be the only // `condition`. // If `condition_monitoring_query_language` is present, it must be the only // `condition`. repeated Condition conditions = 12; // How to combine the results of multiple conditions to determine if an // incident should be opened. // If `condition_time_series_query_language` is present, this must be // `COMBINE_UNSPECIFIED`. ConditionCombinerType combiner = 6; // Whether or not the policy is enabled. On write, the default interpretation // if unset is that the policy is enabled. On read, clients should not make // any assumption about the state if it has not been populated. The // field should always be populated on List and Get operations, unless // a field projection has been specified that strips it out. google.protobuf.BoolValue enabled = 17; // Read-only description of how the alert policy is invalid. This field is // only set when the alert policy is invalid. An invalid alert policy will not // generate incidents. google.rpc.Status validity = 18; // Identifies the notification channels to which notifications should be sent // when incidents are opened or closed or when new violations occur on // an already opened incident. Each element of this array corresponds to // the `name` field in each of the // [`NotificationChannel`][google.monitoring.v3.NotificationChannel] // objects that are returned from the [`ListNotificationChannels`] // [google.monitoring.v3.NotificationChannelService.ListNotificationChannels] // method. The format of the entries in this field is: // // projects/[PROJECT_ID_OR_NUMBER]/notificationChannels/[CHANNEL_ID] repeated string notification_channels = 14; // A read-only record of the creation of the alerting policy. If provided // in a call to create or update, this field will be ignored. MutationRecord creation_record = 10; // A read-only record of the most recent change to the alerting policy. If // provided in a call to create or update, this field will be ignored. MutationRecord mutation_record = 11; // Control over how this alert policy's notification channels are notified. AlertStrategy alert_strategy = 21; // Optional. The severity of an alert policy indicates how important incidents // generated by that policy are. The severity level will be displayed on the // Incident detail page and in notifications. Severity severity = 22 [(google.api.field_behavior) = OPTIONAL]; }