LLAP

LLAP Dashboard

The LLAP component optimizes the performance of Hive queries. The query processing and execution in LLAP is similar to that of Hive except that LLAP caches the frequently executed queries or data for faster execution and in Hive, all query results are cached. Using Hive with LLAP speeds up query execution and overall performance of Hive.

Click LLAP --> Dashboard in the left pane to access the LLAP dashboard. The dashboard consists of summary panels, a Sankey Diagram, and charts that display information about queries and other related metrics.

Key Performance Indicators (KPI)

KPIs are user-driven analytics criteria to analyze the performance of jobs.

Creating KPIs

To create a KPI for a module, do the following.

1. Click Create KPI.

The Create window is displayed.

2. Do the following in the available indices.

   1. In Metric, click the drop-down and choose one metric from the available list.

   2. (Optional) For time-related or memory-related metrics, you can choose the unit of the resultant KPI value. To do so, click the drop-down that appears in the right and select a unit.

   3. In Operator, click the drop-down and choose the operator to measure the metric you selected.

   4. In Metric * 2.5, click the text box for available metrics or type a value in that text box.

3. In Name, type a name for the KPI you are creating.

4. (Optional) Click the + sign to add another metric to the same KPI.

5. Click Save.

The KPI is created.

Summary Panel

The summary tiles display several aggregated values. You can click the number on each field to view detailed information about that metric.

Context Metric Distributions

The Context Metric distributions panel displays the summary of jobs as a Sankey diagram. You can see the flow of the selected queue to users and to the queries.

The following screenshot is an example of a Context Metric Distributions Sankey chart of the last 24 hours displayed by Duration.

You can gather the following information from the chart.

You can observe the following in Queues.

• 100% of queries are running in default queue.

• From Users category, you can gather the following.

• 71.43% of queries are run by 3 users.

• 14.29% of queries are run by 4 users.

• 8.57% of queries are run by 3 users.

• 5.71% of queries are run by 2 users.

• From Queries category, you can gather the following.

• 25 queries (71.43%) are executed within 6.19 seconds to 10.76 seconds.

• 5 queries (14.29%) are executed within 17.95 seconds to 22.12 seconds.

• 3 queries (8.57%) are executed within 23.12 seconds to 25.83 seconds.

• 2 queries (5.71%) are executed within 11.34 seconds to 12.13 seconds.

Other LLAP Charts

The following charts are also displayed on the LLAP Dashboard.

Failed LLAP Queries

This section displays the following details of LLAP queries that failed execution.