Metrics that show the overall operating status for Storm topologies.
|RECORDS||All Tasks Input/Output||
Input Records is the number of input messages executed on all tasks.
Output Records is the number of messages emitted on all tasks.
|All Tasks Acked Tuples||Number of messages acked (completed) on all tasks.|
|All Tasks Failed Tuples||Number of messages failed on all tasks.|
|LATENCY / QUEUE||All Spouts Latency||Average latency on all spout tasks.|
|All Tasks Queue||
Receive Queue Population is the total number of tuples waiting in the receive queue.
Send Queue Population is the total number of tuples waiting in the send queue.
|MEMORY USAGE||All workers memory usage on heap||Used bytes on heap for all workers in topology.|
|All workers memory usage on non-heap||Used bytes on non-heap for all workers in topology.|
|GC||All workers GC count||
PSScavenge count is the number of occurrences for parallel scavenge collector.
PSMarkSweep count is the number of occurrences for parallel scavenge mark and sweep collector.
|All workers GC time||
PSScavenge timeMs is the sum of the time parallel scavenge collector takes (in milliseconds).
PSMarkSweep timeMs is the sum of the time parallel scavenge mark and sweep collector takes (in milliseconds).
Note that GC metrics are provided based on worker GC setting, so these metrics are only available for default GC option for worker.childopts. If you use another GC option for worker, you need to copy the dashboard and update the metric name manually.