Link Search Menu Expand Document Documentation Menu
Documentation

This version of the OpenSearch documentation is no longer maintained. For the latest version, see the current documentation. For information about OpenSearch version maintenance, see Release Schedule and Maintenance Policy.

Top N queries

Monitoring the top N queries in query insights features can help you gain real-time insights into the top queries with high latency within a certain time frame (for example, the last hour).

Getting started

To enable monitoring of the top N queries, configure the following dynamic settings:

It’s important to exercise caution when enabling this feature because it can consume system resources.

For detailed information about enabling and configuring this feature, see the following sections.

Enabling the top N queries feature

After installing the query-insights plugin, you can enable the top N queries feature (which is disabled by default) by using the following dynamic setting. This setting enables the corresponding collectors and aggregators in the running cluster:

PUT _cluster/settings
{
  "persistent" : {
    "search.insights.top_queries.latency.enabled" : true
  }
}

Configuring window size

You can configure the window size for the top N queries by latency with search.insights.top_queries.latency.window_size. For example, a cluster with the following configuration will collect top N queries in a 60-minute window:

PUT _cluster/settings
{
  "persistent" : {
    "search.insights.top_queries.latency.window_size" : "60m"
  }
}

Configuring the value of N

You can configure the value of N in the search.insights.top_queries.latency.top_n_size parameter. For example, a cluster with the following configuration will collect the top 10 queries in the specified window size:

PUT _cluster/settings
{
  "persistent" : {
    "search.insights.top_queries.latency.top_n_size" : 10
  }
}

Monitoring the top N queries

You can use the Insights API endpoint to obtain top N queries by latency:

GET /_insights/top_queries

Specify a metric type to filter the response by metric type (latency is the only supported type as of 2.12):

GET /_insights/top_queries?type=latency

350 characters left

Have a question? .

Want to contribute? or .