1.2.8.3. Hive LLAP - Daemon
Metrics that show operating status for Hive LLAP Daemons.
| Row | Metrics |
Description |
|---|---|---|
|
Executor Metrics |
Total Requests Submitted |
Shows the total number of task requests handled by the daemon. |
|
Total Requests Succeeded | Shows the total number of successful task requests handled by the daemon. | |
| Total Requests Failed | Shows the total number of failed task requests handled by the daemon. | |
| Total Requests Killed | Shows the total number of killed task requests handled by the daemon. | |
| Total Requests Evicted From Wait Queue | Shows the total number of task requests handled by the daemon that were evicted from the wait queue. Tasks are evicted if all of the executor threads are in use by higher priority tasks. | |
| Total Requests Rejected | Shows the total number of task requests handled by the daemon that were rejected by the task executor service. Task are rejected if all of the executor threads are in use and the wait queue is full of tasks that are not eligible for eviction. | |
| Available Execution Slots | Shows the total number of free slots that are available for execution including free executor threads and free slots in the wait queue. | |
| 95th Percentile Pre-emption Time Lost (300s interval) | Shows the 95th percentile latencies for time lost due to pre-emption in 300 second intervals. | |
| Max Pre-emption Time Lost | Shows the maximum time lost due to pre-emption. | |
| 95th Percentile Time to Kill Pre-empted Task (300s interval) | Shows the 95th percentile latencies for time taken to kill tasks due to pre-emption in 300 second intervals. | |
| Max Time To Kill Task Pre-empted Task | Shows the maximum time taken to kill a task due to pre-emption. | |
|
Cache Metrics |
Total Cache Used | Shows the total amount of cache usage (Total, Remaining, and Used) in LLAP daemon cache. |
|
Heap Usage | Shows the amount of memory remaining in LLAP daemon cache. | |
| Average Cache Hit Rate | As the data is released from the cache, the curve should increase. For example, the first query should run at 0, the second at 80-90 seconds, and then the third 10% faster. If, instead, it decreases, there might be a problem in the LLAP daemon. | |
| Total Cache Read Requests | Shows the total number of read requests received by LLAP daemon cache. | |
|
THREAD STATES |
95th Percentile Column Decoding Time (30s interval) |
Shows the 95th percentile latencies for time it takes to decode the column chunk (convert encoded column chunk to column vector batches for processing) in 30 second intervals. The cache comes from IO Elevator. It loads data from HDFS to the cache, and then from the cache to the executor. This metric shows how well the threads are performing and is useful to see that the threads are running. |
|
Max Column Decoding Time | Shows the maximum time taken to decode column chunk (convert encoded column chunk to column vector batches for processing). |