Clean up

elastic · Oct 3, 2023 · e666f07 · e666f07
1 parent 12d2bd8
commit e666f07
Show file tree

Hide file tree

Showing 19 changed files with 85 additions and 101 deletions.
diff --git a/...api/detection_engine/rule_monitoring/detection_engine_health/model/cluster_health.mock.ts b/...api/detection_engine/rule_monitoring/detection_engine_health/model/cluster_health.mock.ts
@@ -10,13 +10,13 @@ import { healthStatsMock } from './health_stats.mock';
 
 const getEmptyClusterHealthSnapshot = (): ClusterHealthSnapshot => {
   return {
-    stats_at_the_moment: healthStatsMock.getEmptyRuleStats(),
-    stats_over_interval: healthStatsMock.getEmptyRuleExecutionStats(),
+    state_at_the_moment: healthStatsMock.getEmptyHealthOverviewState(),
+    stats_over_interval: healthStatsMock.getEmptyHealthOverviewStats(),
     history_over_interval: {
       buckets: [
         {
           timestamp: '2023-05-15T16:12:14.967Z',
-          stats: healthStatsMock.getEmptyRuleExecutionStats(),
+          stats: healthStatsMock.getEmptyHealthOverviewStats(),
         },
       ],
     },

diff --git a/...mmon/api/detection_engine/rule_monitoring/detection_engine_health/model/cluster_health.ts b/...mmon/api/detection_engine/rule_monitoring/detection_engine_health/model/cluster_health.ts
@@ -6,7 +6,7 @@
  */
 
 import type { HealthParameters, HealthSnapshot } from './health_metadata';
-import type { RuleExecutionStats, RuleStats, StatsHistory } from './health_stats';
+import type { HealthOverviewStats, HealthOverviewState, HealthHistory } from './health_stats';
 
 /**
  * Health calculation parameters for the whole cluster.
@@ -18,27 +18,27 @@ export type ClusterHealthParameters = HealthParameters;
  */
 export interface ClusterHealthSnapshot extends HealthSnapshot {
   /**
-   * Health stats at the moment of the calculation request.
+   * Health state at the moment of the calculation request.
    */
-  stats_at_the_moment: ClusterHealthStatsAtTheMoment;
+  state_at_the_moment: ClusterHealthState;
 
   /**
    * Health stats calculated over the interval specified in the health parameters.
    */
-  stats_over_interval: ClusterHealthStatsOverInterval;
+  stats_over_interval: ClusterHealthStats;
 
   /**
    * History of change of the same health stats during the interval.
    */
-  history_over_interval: StatsHistory<ClusterHealthStatsOverInterval>;
+  history_over_interval: HealthHistory<ClusterHealthStats>;
 }
 
 /**
- * Health stats at the moment of the calculation request.
+ * Health state at the moment of the calculation request.
  */
-export type ClusterHealthStatsAtTheMoment = RuleStats;
+export type ClusterHealthState = HealthOverviewState;
 
 /**
  * Health stats calculated over a given interval.
  */
-export type ClusterHealthStatsOverInterval = RuleExecutionStats;
+export type ClusterHealthStats = HealthOverviewStats;
diff --git a/...n/api/detection_engine/rule_monitoring/detection_engine_health/model/health_stats.mock.ts b/...n/api/detection_engine/rule_monitoring/detection_engine_health/model/health_stats.mock.ts
@@ -7,12 +7,12 @@
 
 import type {
   AggregatedMetric,
-  RuleExecutionStats,
-  RuleStats,
+  HealthOverviewStats,
+  HealthOverviewState,
   TotalEnabledDisabled,
 } from './health_stats';
 
-const getEmptyRuleStats = (): RuleStats => {
+const getEmptyHealthOverviewState = (): HealthOverviewState => {
   return {
     number_of_rules: {
       all: getZeroTotalEnabledDisabled(),
@@ -34,7 +34,7 @@ const getZeroTotalEnabledDisabled = (): TotalEnabledDisabled => {
   };
 };
 
-const getEmptyRuleExecutionStats = (): RuleExecutionStats => {
+const getEmptyHealthOverviewStats = (): HealthOverviewStats => {
   return {
     number_of_executions: {
       total: 0,
@@ -70,18 +70,15 @@ const getEmptyRuleExecutionStats = (): RuleExecutionStats => {
 const getZeroAggregatedMetric = (): AggregatedMetric<number> => {
   return {
     percentiles: {
-      '1.0': 0,
-      '5.0': 0,
-      '25.0': 0,
       '50.0': 0,
-      '75.0': 0,
       '95.0': 0,
       '99.0': 0,
+      '99.9': 0,
     },
   };
 };
 
 export const healthStatsMock = {
-  getEmptyRuleStats,
-  getEmptyRuleExecutionStats,
+  getEmptyHealthOverviewState,
+  getEmptyHealthOverviewStats,
 };
diff --git a/...common/api/detection_engine/rule_monitoring/detection_engine_health/model/health_stats.ts b/...common/api/detection_engine/rule_monitoring/detection_engine_health/model/health_stats.ts
@@ -10,7 +10,7 @@ import type { RuleLastRunOutcomes } from '@kbn/alerting-plugin/common';
 import type { LogLevel } from '../../model';
 
 // -------------------------------------------------------------------------------------------------
-// Stats history (date histogram)
+// History of health stats (date histogram)
 
 /**
  * History of change of a set of stats over a time interval. The interval is split into discreet buckets,
@@ -19,14 +19,14 @@ import type { LogLevel } from '../../model';
  * This model corresponds to the `date_histogram` aggregation of Elasticsearch:
  * https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-bucket-datehistogram-aggregation.html
  */
-export interface StatsHistory<TStats> {
-  buckets: Array<StatsBucket<TStats>>;
+export interface HealthHistory<TStats> {
+  buckets: Array<HealthBucket<TStats>>;
 }
 
 /**
  * Sub-interval with stats calculated over it.
  */
-export interface StatsBucket<TStats> {
+export interface HealthBucket<TStats> {
   /**
    * Start timestamp of the sub-interval.
    */
@@ -39,23 +39,15 @@ export interface StatsBucket<TStats> {
 }
 
 // -------------------------------------------------------------------------------------------------
-// Rule stats
-
-// TODO: https://github.com/elastic/kibana/issues/125642 Add more stats, such as:
-// - number of Kibana instances
-// - number of Kibana spaces
-// - number of rules with exceptions
-// - number of rules with notification actions (total, normal, legacy)
-// - number of rules with response actions
-// - top X last failed status messages + rule ids for each status
-// - top X last partial failure status messages + rule ids for each status
-// - top X slowest rules by any metrics (last total execution time, search time, indexing time, etc)
-// - top X rules with the largest schedule delay (drift)
+// Health overview state
+
+// TODO: https://github.com/elastic/kibana/issues/125642 Add more data, see health_data.md
 
 /**
- * "Static" stats calculated for a set of rules, such as number of enabled and disabled rules, etc.
+ * "Static" health state at the moment of the API call. Calculated for a set of rules.
+ * Example: number of enabled and disabled rules.
  */
-export interface RuleStats {
+export interface HealthOverviewState {
   /**
    * Various counts of different rules.
    */
@@ -108,19 +100,15 @@ export interface TotalEnabledDisabled {
 }
 
 // -------------------------------------------------------------------------------------------------
-// Rule execution stats
+// Health overview stats
 
-// TODO: https://github.com/elastic/kibana/issues/125642 Add more stats, such as:
-// - number of detected alerts (source event "hits")
-// - number of created alerts (those we wrote to the .alerts-* index)
-// - number of times rule hit cirquit breaker, number of not created alerts because of that
-// - number of triggered actions
-// - top gaps
+// TODO: https://github.com/elastic/kibana/issues/125642 Add more data, see health_data.md
 
 /**
- * "Dynamic" rule execution stats. Can be calculated either for a set of rules or for a single rule.
+ * "Dynamic" health stats over a specified "health interval". Can be calculated either
+ * for a set of rules or for a single rule.
  */
-export interface RuleExecutionStats {
+export interface HealthOverviewStats {
   /**
    * Number of rule executions.
    */
@@ -242,13 +230,10 @@ export interface AggregatedMetric<T> {
  * Distribution of values of an aggregated metric represented by a set of discreet percentiles.
  * @example
  * {
- *   '1.0': 27,
- *   '5.0': 150,
- *   '25.0': 240,
  *   '50.0': 420,
- *   '75.0': 700,
  *   '95.0': 2500,
  *   '99.0': 7800,
+ *   '99.9': 10000,
  * }
  */
 export type Percentiles<T> = Record<string, T>;

diff --git a/...on/api/detection_engine/rule_monitoring/detection_engine_health/model/rule_health.mock.ts b/...on/api/detection_engine/rule_monitoring/detection_engine_health/model/rule_health.mock.ts
@@ -11,15 +11,15 @@ import type { RuleHealthSnapshot } from './rule_health';
 
 const getEmptyRuleHealthSnapshot = (): RuleHealthSnapshot => {
   return {
-    stats_at_the_moment: {
+    state_at_the_moment: {
       rule: getRulesSchemaMock(),
     },
-    stats_over_interval: healthStatsMock.getEmptyRuleExecutionStats(),
+    stats_over_interval: healthStatsMock.getEmptyHealthOverviewStats(),
     history_over_interval: {
       buckets: [
         {
           timestamp: '2023-05-15T16:12:14.967Z',
-          stats: healthStatsMock.getEmptyRuleExecutionStats(),
+          stats: healthStatsMock.getEmptyHealthOverviewStats(),
         },
       ],
     },

diff --git a/.../common/api/detection_engine/rule_monitoring/detection_engine_health/model/rule_health.ts b/.../common/api/detection_engine/rule_monitoring/detection_engine_health/model/rule_health.ts
@@ -7,7 +7,7 @@
 
 import type { RuleResponse } from '../../../model';
 import type { HealthParameters, HealthSnapshot } from './health_metadata';
-import type { RuleExecutionStats, StatsHistory } from './health_stats';
+import type { HealthOverviewStats, HealthHistory } from './health_stats';
 
 /**
  * Health calculation parameters for a given rule.
@@ -24,25 +24,25 @@ export interface RuleHealthParameters extends HealthParameters {
  */
 export interface RuleHealthSnapshot extends HealthSnapshot {
   /**
-   * Health stats at the moment of the calculation request.
+   * Health state at the moment of the calculation request.
    */
-  stats_at_the_moment: RuleHealthStatsAtTheMoment;
+  state_at_the_moment: RuleHealthState;
 
   /**
    * Health stats calculated over the interval specified in the health parameters.
    */
-  stats_over_interval: RuleHealthStatsOverInterval;
+  stats_over_interval: RuleHealthStats;
 
   /**
    * History of change of the same health stats during the interval.
    */
-  history_over_interval: StatsHistory<RuleHealthStatsOverInterval>;
+  history_over_interval: HealthHistory<RuleHealthStats>;
 }
 
 /**
- * Health stats at the moment of the calculation request.
+ * Health state at the moment of the calculation request.
  */
-export interface RuleHealthStatsAtTheMoment {
+export interface RuleHealthState {
   /**
    * Rule object including its current execution summary.
    */
@@ -52,4 +52,4 @@ export interface RuleHealthStatsAtTheMoment {
 /**
  * Health stats calculated over a given interval.
  */
-export type RuleHealthStatsOverInterval = RuleExecutionStats;
+export type RuleHealthStats = HealthOverviewStats;
diff --git a/...n/api/detection_engine/rule_monitoring/detection_engine_health/model/space_health.mock.ts b/...n/api/detection_engine/rule_monitoring/detection_engine_health/model/space_health.mock.ts
@@ -10,13 +10,13 @@ import type { SpaceHealthSnapshot } from './space_health';
 
 const getEmptySpaceHealthSnapshot = (): SpaceHealthSnapshot => {
   return {
-    stats_at_the_moment: healthStatsMock.getEmptyRuleStats(),
-    stats_over_interval: healthStatsMock.getEmptyRuleExecutionStats(),
+    state_at_the_moment: healthStatsMock.getEmptyHealthOverviewState(),
+    stats_over_interval: healthStatsMock.getEmptyHealthOverviewStats(),
     history_over_interval: {
       buckets: [
         {
           timestamp: '2023-05-15T16:12:14.967Z',
-          stats: healthStatsMock.getEmptyRuleExecutionStats(),
+          stats: healthStatsMock.getEmptyHealthOverviewStats(),
         },
       ],
     },

diff --git a/...common/api/detection_engine/rule_monitoring/detection_engine_health/model/space_health.ts b/...common/api/detection_engine/rule_monitoring/detection_engine_health/model/space_health.ts
@@ -6,7 +6,7 @@
  */
 
 import type { HealthParameters, HealthSnapshot } from './health_metadata';
-import type { RuleExecutionStats, RuleStats, StatsHistory } from './health_stats';
+import type { HealthOverviewStats, HealthOverviewState, HealthHistory } from './health_stats';
 
 /**
  * Health calculation parameters for the current Kibana space.
@@ -18,27 +18,27 @@ export type SpaceHealthParameters = HealthParameters;
  */
 export interface SpaceHealthSnapshot extends HealthSnapshot {
   /**
-   * Health stats at the moment of the calculation request.
+   * Health state at the moment of the calculation request.
    */
-  stats_at_the_moment: SpaceHealthStatsAtTheMoment;
+  state_at_the_moment: SpaceHealthState;
 
   /**
    * Health stats calculated over the interval specified in the health parameters.
    */
-  stats_over_interval: SpaceHealthStatsOverInterval;
+  stats_over_interval: SpaceHealthStats;
 
   /**
    * History of change of the same health stats during the interval.
    */
-  history_over_interval: StatsHistory<SpaceHealthStatsOverInterval>;
+  history_over_interval: HealthHistory<SpaceHealthStats>;
 }
 
 /**
- * Health stats at the moment of the calculation request.
+ * Health state at the moment of the calculation request.
  */
-export type SpaceHealthStatsAtTheMoment = RuleStats;
+export type SpaceHealthState = HealthOverviewState;
 
 /**
  * Health stats calculated over a given interval.
  */
-export type SpaceHealthStatsOverInterval = RuleExecutionStats;
+export type SpaceHealthStats = HealthOverviewStats;
diff --git a/...ule_monitoring/api/detection_engine_health/get_cluster_health/get_cluster_health_route.ts b/...ule_monitoring/api/detection_engine_health/get_cluster_health/get_cluster_health_route.ts
@@ -26,7 +26,7 @@ import { validateGetClusterHealthRequest } from './get_cluster_health_request';
 /**
  * Get health overview of the whole cluster. Scope: all detection rules in all Kibana spaces.
  * Returns:
- * - health stats at the moment of the API call
+ * - health state at the moment of the API call
  * - health stats over a specified period of time ("health interval")
  * - health stats history within the same interval in the form of a histogram
  *   (the same stats are calculated over each of the discreet sub-intervals of the whole interval)

diff --git a/...gine/rule_monitoring/api/detection_engine_health/get_rule_health/get_rule_health_route.ts b/...gine/rule_monitoring/api/detection_engine_health/get_rule_health/get_rule_health_route.ts
@@ -23,7 +23,7 @@ import { validateGetRuleHealthRequest } from './get_rule_health_request';
 /**
  * Get health overview of a rule. Scope: a given detection rule in the current Kibana space.
  * Returns:
- * - health stats at the moment of the API call (rule and its execution summary)
+ * - health state at the moment of the API call (rule and its execution summary)
  * - health stats over a specified period of time ("health interval")
  * - health stats history within the same interval in the form of a histogram
  *   (the same stats are calculated over each of the discreet sub-intervals of the whole interval)

diff --git a/...ne/rule_monitoring/api/detection_engine_health/get_space_health/get_space_health_route.ts b/...ne/rule_monitoring/api/detection_engine_health/get_space_health/get_space_health_route.ts
@@ -26,7 +26,7 @@ import { validateGetSpaceHealthRequest } from './get_space_health_request';
 /**
  * Get health overview of the current Kibana space. Scope: all detection rules in the space.
  * Returns:
- * - health stats at the moment of the API call
+ * - health state at the moment of the API call
  * - health stats over a specified period of time ("health interval")
  * - health stats history within the same interval in the form of a histogram
  *   (the same stats are calculated over each of the discreet sub-intervals of the whole interval)

diff --git a/...on_engine/rule_monitoring/logic/detection_engine_health/detection_engine_health_client.ts b/...on_engine/rule_monitoring/logic/detection_engine_health/detection_engine_health_client.ts
@@ -44,7 +44,7 @@ export const createDetectionEngineHealthClient = (
           const statsBasedOnEventLog = await eventLogHealthClient.calculateRuleHealth(args);
 
           return {
-            stats_at_the_moment: statsBasedOnRuleObjects.stats_at_the_moment,
+            state_at_the_moment: statsBasedOnRuleObjects.state_at_the_moment,
             stats_over_interval: statsBasedOnEventLog.stats_over_interval,
             history_over_interval: statsBasedOnEventLog.history_over_interval,
             debug: {
@@ -76,7 +76,7 @@ export const createDetectionEngineHealthClient = (
           ]);
 
           return {
-            stats_at_the_moment: statsBasedOnRuleObjects.stats_at_the_moment,
+            state_at_the_moment: statsBasedOnRuleObjects.state_at_the_moment,
             stats_over_interval: statsBasedOnEventLog.stats_over_interval,
             history_over_interval: statsBasedOnEventLog.history_over_interval,
             debug: {
@@ -107,7 +107,7 @@ export const createDetectionEngineHealthClient = (
           ]);
 
           return {
-            stats_at_the_moment: statsBasedOnRuleObjects.stats_at_the_moment,
+            state_at_the_moment: statsBasedOnRuleObjects.state_at_the_moment,
             stats_over_interval: statsBasedOnEventLog.stats_over_interval,
             history_over_interval: statsBasedOnEventLog.history_over_interval,
             debug: {