You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: deploy-manage/autoscaling/trained-model-autoscaling.md
+7Lines changed: 7 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -32,6 +32,7 @@ The available resources of self-managed deployments are static, so trained model
32
32
{{serverless-full}} Security and Observability projects are only charged for data ingestion and retention. They are not charged for processing power (VCU usage), which is used for more complex operations, like running advanced search models. For example, in Search projects, models such as ELSER require significant processing power to provide more accurate search results.
33
33
34
34
## Enabling autoscaling through APIs - adaptive allocations [enabling-autoscaling-through-apis-adaptive-allocations]
35
+
35
36
$$$nlp-model-adaptive-resources$$$
36
37
37
38
Model allocations are independent units of work for NLP tasks. If you set the numbers of threads and allocations for a model manually, they remain constant even when not all the available resources are fully used or when the load on the model requires more resources. Instead of setting the number of allocations manually, you can enable adaptive allocations to set the number of allocations based on the load on the process. This can help you to manage performance and cost more easily. (Refer to the [pricing calculator](https://cloud.elastic.co/pricing) to learn more about the possible costs.)
@@ -55,6 +56,7 @@ When you create inference endpoints on {{serverless-short}} using Kibana, adapti
55
56
:::
56
57
57
58
### Optimizing for typical use cases [optimizing-for-typical-use-cases]
59
+
58
60
You can optimize your model deployment for typical use cases, such as search and ingest. When you optimize for ingest, the throughput will be higher, which increases the number of {{infer}} requests that can be performed in parallel. When you optimize for search, the latency will be lower during search processes.
59
61
60
62
* If you want to optimize for ingest, set the number of threads to `1` (`"threads_per_allocation": 1`).
@@ -86,6 +88,11 @@ The used resources for trained model deployments depend on three factors:
86
88
* the use case you optimize the model deployment for (ingest or search)
87
89
* whether model autoscaling is enabled with adaptive allocations/resources to have dynamic resources, or disabled for static resources
88
90
91
+
::::{note}
92
+
On {{serverless-short}}, VCUs for {{ml}} are based on the amount of vCPU and memory consumed. For {{ml}}, `1` VCU equals `0.125` of vCPU and `1GB` of memory, where vCPUs are measured by allocations multiplied by threads, and where memory is the amount consumed by trained models or {{ml}} jobs.
93
+
As a math formula, `VCUs = 8 * allocations * threads`, or `1` VCU for every `1GB` of memory consumed, whichever is greater.
94
+
::::
95
+
89
96
If you use a self-managed cluster or ECK, vCPUs level ranges are derived from the `total_ml_processors` and `max_single_ml_node_processors` values. Use the [get {{ml}} info API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-ml-info) to check these values.
90
97
91
98
The following tables show you the number of allocations, threads, and vCPUs available in ECE and ECH when adaptive resources are enabled or disabled.
Copy file name to clipboardExpand all lines: deploy-manage/deploy/elastic-cloud/add-plugins-extensions.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -16,11 +16,11 @@ Plugins extend the core functionality of {{es}}. There are many suitable plugins
16
16
* Analysis plugins, to provide analyzers targeted at languages other than English.
17
17
* Scripting plugins, to provide additional scripting languages.
18
18
19
-
Plugins can come from different sources: the official ones created or at least maintained by Elastic, community-sourced plugins from other users, and plugins that you provide. Some of the official plugins are always provided with our service, and can be [enabled per deployment](elasticsearch://reference/elasticsearch-plugins/cloud/ec-adding-elastic-plugins.md).
19
+
Plugins can come from different sources: the official ones created or at least maintained by Elastic, community-sourced plugins from other users, and plugins that you provide. Some of the official plugins are always provided with our service, and can be [enabled per deployment](elasticsearch://reference/elasticsearch-plugins/plugin-management.md).
20
20
21
21
There are two ways to add plugins to a hosted deployment in {{ecloud}}:
22
22
23
-
*[Enable one of the official plugins already available in {{ecloud}}](elasticsearch://reference/elasticsearch-plugins/cloud/ec-adding-elastic-plugins.md).
23
+
*[Enable one of the official plugins already available in {{ecloud}}](elasticsearch://reference/elasticsearch-plugins/plugin-management.md).
24
24
*[Upload a custom plugin and then enable it per deployment](upload-custom-plugins-bundles.md).
25
25
26
26
Custom plugins can include the official {{es}} plugins not provided with {{ecloud}}, any of the community-sourced plugins, or [plugins that you write yourself](elasticsearch://extend/index.md). Uploading custom plugins is available only to Gold, Platinum, and Enterprise subscriptions. For more information, check [Upload custom plugins and bundles](upload-custom-plugins-bundles.md).
Copy file name to clipboardExpand all lines: deploy-manage/tools/snapshot-and-restore/minio-on-premise-repository.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -65,7 +65,7 @@ How you create the AWS S3 bucket depends on what version of Elasticsearch you ar
65
65
* For version 7.x:
66
66
67
67
1. Using the Minio browser or an S3 client application, create an S3 bucket to store your snapshots.
68
-
2.[Log into the Cloud UI](../../deploy/cloud-enterprise/log-into-cloud-ui.md) and [add the S3 repository plugin](elasticsearch://reference/elasticsearch-plugins/cloud-enterprise/ece-add-plugins.md) to your cluster.
68
+
2.[Log into the Cloud UI](../../deploy/cloud-enterprise/log-into-cloud-ui.md) and [add the S3 repository plugin](elasticsearch://reference/elasticsearch-plugins/plugin-management.md) to your cluster.
69
69
70
70
* For versions 8.0 and later, {{es}} has built-in support for AWS S3 repositories; no repository plugin is needed. Use the Minio browser or an S3 client application to create an S3 bucket to store your snapshots.
Copy file name to clipboardExpand all lines: deploy-manage/users-roles/cluster-or-deployment-auth/kerberos.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -166,7 +166,7 @@ For detailed information of available realm settings, see [Kerberos realm settin
166
166
167
167
::::{tab-item} ECH and ECE
168
168
169
-
1. Create a [custom bundle](elasticsearch://reference/elasticsearch-plugins/cloud-enterprise/ece-add-plugins.md) that contains your `krb5.conf` and `keytab` files, and add it to your cluster.
169
+
1. Create a [custom bundle](elasticsearch://reference/elasticsearch-plugins/plugin-management.md) that contains your `krb5.conf` and `keytab` files, and add it to your cluster.
170
170
171
171
:::{tip}
172
172
You should use these exact filenames for {{ecloud}} to recognize the file in the bundle.
ess-leadin: "You can run Elasticsearch on your own hardware or use our hosted Elasticsearch Service that is available on AWS, GCP, and Azure. https://cloud.elastic.co/registration{ess-utm-params}[Try the Elasticsearch Service for free]."
227
96
ess-leadin-short: "Our hosted Elasticsearch Service is available on AWS, GCP, and Azure, and you can https://cloud.elastic.co/registration{ess-utm-params}[try it for free]."
228
97
ess-icon: "image:https://doc-icons.s3.us-east-2.amazonaws.com/logo_cloud.svg[link=\"https://cloud.elastic.co/registration{ess-utm-params}\", title=\"Supported on Elasticsearch Service\"]"
0 commit comments