ML Commons cluster settings
If , ML Commons tasks and models run machine learning (ML) tasks on ML nodes only. If false
, tasks and models run on ML nodes first. If no ML nodes exist, tasks and models run on data nodes. We recommend that you do not set this value to “false” on production clusters.
Values
- Default value:
true
- Value range:
true
orfalse
Dispatch tasks to ML node
round_robin
dispatches ML tasks to ML nodes using round robin routing. least_load
gathers runtime information from all ML nodes, like JVM heap memory usage and running tasks, and then dispatches the tasks to the ML node with the lowest load.
Setting
plugins.ml_commons.task_dispatch_policy: round_robin
Values
- Dafault value:
round_robin
- Value range:
round_robin
or
Set number of ML tasks per node
Sets the number of ML tasks that can run on each ML node. When set to 0
, no ML tasks run on any nodes.
Setting
plugins.ml_commons.max_ml_task_per_node: 10
Values
- Default value:
10
- Value range: [0, 10,000]
Setting
- Value range: [0, 10,000]
Set sync job intervals
When returning runtime information with the , ML Commons will run a regular job to sync newly loaded or unloaded models on each node. When set to 0
, ML Commons immediately stops sync up jobs.
When returning runtime information with the profile API, ML Commons will run a regular sync up job to sync up newly loaded or unloaded models on each node. When set to 0
, ML Commons immediately stops sync up jobs.
Setting
plugins.ml_commons.sync_up_job_interval_in_seconds: 10
Values
- Default value:
10
- Value range: [0, 86,400]
Predict monitoring requests
Controls how many predict requests are monitored on one node. If set to , OpenSearch clears all monitoring predict requests in cache and does not monitor for new predict requests.
Setting
plugins.ml_commons.monitoring_request_count: 100
Value range
- Default value:
100
- Value range: [0, 10,000,000]
Setting
Values
- Default value:
10
- Value range: [0, 10]
Load model tasks per node
Controls how many load model tasks can run in parallel on one node. If set to 0, you cannot load models to any node.
plugins.ml_commons.max_load_model_tasks_per_node: 10
Values
- Default value:
10
- Value range: [0, 10]
Add trusted URL
The default value allows you to upload a model file from any http/https/ftp/local file. You can change this value to restrict trusted model URLs.
Setting
plugins.ml_commons.trusted_url_regex: ^(https?\|ftp\|file)://[-a-zA-Z0-9+&@#/%?=~_\|!:,.;]*[-a-zA-Z0-9+&@#/%=~_\|]
Values
- Default value:
^(https?\|ftp\|file)://[-a-zA-Z0-9+&@#/%?=~_\|!:,.;]*[-a-zA-Z0-9+&@#/%=~_\|]
- Value range: Java regular expression (regex) string
Assigns how long in seconds an ML task will live. After the timeout, the task will fail.
Setting
Values
- Default value: 600
- Value range: [1, 86,400]
Set native memory threshold
Values are based on the percentage of memory available. When set to 0
, no ML tasks will run. When set to , the circuit breaker closes and no threshold exists.
Setting
plugins.ml_commons.native_memory_threshold: 90
- Default value: 90
- Value range: [0, 100]