pnowojski commented on a change in pull request #17660:
URL: https://github.com/apache/flink/pull/17660#discussion_r754096460
##########
File path: docs/content.zh/docs/ops/metrics.md
##########
@@ -916,12 +916,17 @@ Metrics related to data exchange between task executors
using netty network comm
<td>Gauge</td>
</tr>
<tr>
- <th rowspan="18">Task</th>
- <td rowspan="4">Shuffle.Netty.Input.Buffers</td>
+ <th rowspan="20">Task</th>
+ <td rowspan="5">Shuffle.Netty.Input.Buffers</td>
<td>inputQueueLength</td>
<td>The number of queued input buffers.</td>
<td>Gauge</td>
</tr>
+ <tr>
+ <td>inputQueueSize</td>
+ <td>The real size of queued input buffers in bytes. The size for local
input channels is only estimated.</td>
Review comment:
On a second thought. Shouldn't we actually ignore local input channels?
1. It would be kind of consistent with the other metrics
2. Otherwise, don't we double account those bytes on the output and on the
input?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
