From 2ec92186bc7bef257a2da43c6028411f2e1a9146 Mon Sep 17 00:00:00 2001 From: Dima Arnautov Date: Thu, 21 Nov 2024 18:26:58 +0100 Subject: [PATCH 1/3] fallback to lazy nodes count to determine if ml autoscaling is enabled --- x-pack/plugins/ml/server/lib/node_utils.ts | 2 +- x-pack/plugins/ml/server/routes/system.ts | 11 ++++++++--- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/x-pack/plugins/ml/server/lib/node_utils.ts b/x-pack/plugins/ml/server/lib/node_utils.ts index d8098e3c43f42..9c5c0348f03da 100644 --- a/x-pack/plugins/ml/server/lib/node_utils.ts +++ b/x-pack/plugins/ml/server/lib/node_utils.ts @@ -33,7 +33,7 @@ export async function getMlNodeCount(client: IScopedClusterClient): Promise { const body = await client.asInternalUser.cluster.getSettings( { include_defaults: true, diff --git a/x-pack/plugins/ml/server/routes/system.ts b/x-pack/plugins/ml/server/routes/system.ts index d4127a7428397..150fc3c75a109 100644 --- a/x-pack/plugins/ml/server/routes/system.ts +++ b/x-pack/plugins/ml/server/routes/system.ts @@ -14,7 +14,7 @@ import { mlLog } from '../lib/log'; import { capabilitiesProvider } from '../lib/capabilities'; import { spacesUtilsProvider } from '../lib/spaces_utils'; import type { RouteInitialization, SystemRouteDeps } from '../types'; -import { getMlNodeCount } from '../lib/node_utils'; +import { getLazyMlNodeCount, getMlNodeCount } from '../lib/node_utils'; /** * System routes @@ -187,10 +187,15 @@ export function systemRoutes( let isMlAutoscalingEnabled = false; try { - await client.asInternalUser.autoscaling.getAutoscalingPolicy({ name: 'ml' }); + // kibana_system user does not have the manage_autoscaling cluster privilege. + // perform this check as a current user. + await client.asCurrentUser.autoscaling.getAutoscalingPolicy({ name: 'ml' }); isMlAutoscalingEnabled = true; } catch (e) { - // If doesn't exist, then keep the false + // If ml autoscaling policy doesn't exist or the user does not have privileges to fetch it, + // check the number of lazy ml nodes to determine if autoscaling is enabled. + const lazyMlNodeCount = await getLazyMlNodeCount(client); + isMlAutoscalingEnabled = lazyMlNodeCount > 0; } return response.ok({ From 37ee9356ad3bb73f5d42432a6911ea6f723e785e Mon Sep 17 00:00:00 2001 From: Dima Arnautov Date: Mon, 25 Nov 2024 13:29:27 +0100 Subject: [PATCH 2/3] fix resolving levels from api params --- .../deployment_params_mapper.test.ts | 291 ++++++++++++++++++ .../deployment_params_mapper.ts | 25 +- 2 files changed, 309 insertions(+), 7 deletions(-) diff --git a/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.test.ts b/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.test.ts index 34875b893a867..4193251d76f3a 100644 --- a/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.test.ts +++ b/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.test.ts @@ -627,6 +627,297 @@ describe('DeploymentParamsMapper', () => { }, }); }); + + describe('mapApiToUiDeploymentParams', () => { + it('should map API params to UI correctly', () => { + // Optimized for search + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 16, + number_of_allocations: 2, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: false, + vCPUUsage: 'medium', + }); + + // Lower value + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 16, + number_of_allocations: 1, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: false, + vCPUUsage: 'medium', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 8, + number_of_allocations: 2, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: false, + vCPUUsage: 'medium', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 2, + number_of_allocations: 1, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: false, + vCPUUsage: 'low', + }); + + // Exact match + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 16, + number_of_allocations: 8, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: false, + vCPUUsage: 'high', + }); + + // Higher value + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 16, + number_of_allocations: 12, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: false, + vCPUUsage: 'high', + }); + + // Lower value + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 16, + number_of_allocations: 5, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: false, + vCPUUsage: 'high', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 16, + number_of_allocations: 6, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: false, + vCPUUsage: 'high', + }); + + // Optimized for ingest + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 1, + number_of_allocations: 1, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForIngest', + adaptiveResources: false, + vCPUUsage: 'low', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 1, + number_of_allocations: 2, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForIngest', + adaptiveResources: false, + vCPUUsage: 'low', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 1, + number_of_allocations: 6, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForIngest', + adaptiveResources: false, + vCPUUsage: 'medium', + }); + }); + + it('should map API params to UI correctly with adaptive resources', () => { + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 8, + adaptive_allocations: { + enabled: true, + min_number_of_allocations: 2, + max_number_of_allocations: 2, + }, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: true, + vCPUUsage: 'medium', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 2, + adaptive_allocations: { + enabled: true, + min_number_of_allocations: 2, + max_number_of_allocations: 2, + }, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: true, + vCPUUsage: 'medium', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 1, + adaptive_allocations: { + enabled: true, + min_number_of_allocations: 1, + max_number_of_allocations: 1, + }, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForIngest', + adaptiveResources: true, + vCPUUsage: 'low', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 2, + adaptive_allocations: { + enabled: true, + min_number_of_allocations: 0, + max_number_of_allocations: 1, + }, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: true, + vCPUUsage: 'low', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 1, + adaptive_allocations: { + enabled: true, + min_number_of_allocations: 0, + max_number_of_allocations: 64, + }, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForIngest', + adaptiveResources: true, + vCPUUsage: 'high', + }); + + expect( + mapper.mapApiToUiDeploymentParams({ + model_id: modelId, + deployment_id: 'test-deployment', + priority: 'normal', + threads_per_allocation: 16, + adaptive_allocations: { + enabled: true, + min_number_of_allocations: 0, + max_number_of_allocations: 12, + }, + } as unknown as MlTrainedModelAssignmentTaskParametersAdaptive) + ).toEqual({ + deploymentId: 'test-deployment', + optimized: 'optimizedForSearch', + adaptiveResources: true, + vCPUUsage: 'high', + }); + }); + }); }); }); }); diff --git a/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.ts b/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.ts index ecb8a06198b1c..d873386adf7d7 100644 --- a/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.ts +++ b/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.ts @@ -6,6 +6,7 @@ */ import type { MlStartTrainedModelDeploymentRequest } from '@elastic/elasticsearch/lib/api/typesWithBodyKey'; +import { pick } from 'lodash'; import type { NLPSettings } from '../../../common/constants/app'; import type { TrainedModelDeploymentStatsResponse } from '../../../common/types/trained_models'; import type { CloudInfo } from '../services/ml_server_info'; @@ -25,7 +26,7 @@ type VCPUBreakpoints = Record< max: number; /** * Static value is used for the number of vCPUs when the adaptive resources are disabled. - * Not allowed in certain environments. + * Not allowed in certain environments, Obs and Security serverless projects. */ static?: number; } @@ -89,6 +90,7 @@ export class DeploymentParamsMapper { ) { /** * Initial value can be different for serverless and ESS with autoscaling. + * Also not available with 0 ML active nodes. */ const maxSingleMlNodeProcessors = this.mlServerLimits.max_single_ml_node_processors; @@ -236,18 +238,27 @@ export class DeploymentParamsMapper { ? input.adaptive_allocations!.max_number_of_allocations! : input.number_of_allocations); + // The deployment can be created via API with a number of allocations that do not exactly match our vCPU ranges. + // In this case, we should find the closest vCPU range that does not exceed the max or static value of the range. const [vCPUUsage] = Object.entries(this.vCpuBreakpoints) - .reverse() - .find(([key, val]) => vCPUs >= val.min) as [ - DeploymentParamsUI['vCPUUsage'], - { min: number; max: number } - ]; + .filter((range) => { + const comparedRange = (adaptiveResources ? range[1].max : range[1].static) as number; + return vCPUs <= comparedRange; + }) + .reduce((curr, prev) => { + const comparedRangePrev = (adaptiveResources ? prev[1].max : prev[1].static) as number; + const comparedRangeCurr = (adaptiveResources ? curr[1].max : curr[1].static) as number; + + return Math.abs(vCPUs - comparedRangePrev) <= Math.abs(vCPUs - comparedRangeCurr) + ? prev + : curr; + }, Object.entries(pick(this.vCpuBreakpoints, 'high'))[0]); return { deploymentId: input.deployment_id, optimized, adaptiveResources, - vCPUUsage, + vCPUUsage: vCPUUsage as DeploymentParamsUI['vCPUUsage'], }; } } From c5b821de43e412a9d67faa43d9300b6616906b85 Mon Sep 17 00:00:00 2001 From: Dima Arnautov Date: Mon, 25 Nov 2024 13:35:46 +0100 Subject: [PATCH 3/3] refactor --- .../deployment_params_mapper.ts | 23 ++++++++----------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.ts b/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.ts index d873386adf7d7..96ba5f0755caa 100644 --- a/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.ts +++ b/x-pack/plugins/ml/public/application/model_management/deployment_params_mapper.ts @@ -6,7 +6,6 @@ */ import type { MlStartTrainedModelDeploymentRequest } from '@elastic/elasticsearch/lib/api/typesWithBodyKey'; -import { pick } from 'lodash'; import type { NLPSettings } from '../../../common/constants/app'; import type { TrainedModelDeploymentStatsResponse } from '../../../common/types/trained_models'; import type { CloudInfo } from '../services/ml_server_info'; @@ -241,18 +240,16 @@ export class DeploymentParamsMapper { // The deployment can be created via API with a number of allocations that do not exactly match our vCPU ranges. // In this case, we should find the closest vCPU range that does not exceed the max or static value of the range. const [vCPUUsage] = Object.entries(this.vCpuBreakpoints) - .filter((range) => { - const comparedRange = (adaptiveResources ? range[1].max : range[1].static) as number; - return vCPUs <= comparedRange; - }) - .reduce((curr, prev) => { - const comparedRangePrev = (adaptiveResources ? prev[1].max : prev[1].static) as number; - const comparedRangeCurr = (adaptiveResources ? curr[1].max : curr[1].static) as number; - - return Math.abs(vCPUs - comparedRangePrev) <= Math.abs(vCPUs - comparedRangeCurr) - ? prev - : curr; - }, Object.entries(pick(this.vCpuBreakpoints, 'high'))[0]); + .filter(([, range]) => vCPUs <= (adaptiveResources ? range.max : range.static!)) + .reduce( + (prev, curr) => { + const prevValue = adaptiveResources ? prev[1].max : prev[1].static!; + const currValue = adaptiveResources ? curr[1].max : curr[1].static!; + return Math.abs(vCPUs - prevValue) <= Math.abs(vCPUs - currValue) ? prev : curr; + }, + // in case allocation params exceed the max value of the high range + ['high', this.vCpuBreakpoints.high] + ); return { deploymentId: input.deployment_id,