pnowojski commented on a change in pull request #11877:
URL: https://github.com/apache/flink/pull/11877#discussion_r667798432
##########
File path:
docs/layouts/shortcodes/generated/all_taskmanager_network_section.html
##########
@@ -30,7 +30,7 @@
<td><h5>taskmanager.network.memory.buffers-per-channel</h5></td>
<td style="word-wrap: break-word;">2</td>
<td>Integer</td>
- <td>Number of exclusive network buffers to use for each
outgoing/incoming channel (subpartition/inputchannel) in the credit-based flow
control model. It should be configured at least 2 for good performance. 1
buffer is for receiving in-flight data in the subpartition and 1 buffer is for
parallel serialization.</td>
+ <td>Number of exclusive network buffers to use for each
outgoing/incoming channel (subpartition/input channel) in the credit-based flow
control model. It should be configured at least 2 for good performance. 1
buffer is for receiving in-flight data in the subpartition and 1 buffer is for
parallel serialization. The minimum valid value can be configured is 0 and when
0 is configured, the exclusive network buffers used per downstream incoming
channel will be 0, but for each upstream outgoing channel, max(1, configured
value) will be used which means that at least one buffer is needed and this
behavior is for performance. If it's not guaranteed that each outgoing channel
can get at least one buffer, more partial buffers with little data will be
outputted to network/disk and recycled to be used by other channels which can
not get a buffer for data caching.</td>
Review comment:
Maybe a minor reword to:
> The minimum valid value that can be configured is 0. When 0
buffers-per-channel is configured, the exclusive network buffers used per
downstream incoming channel will be 0, but for each upstream outgoing channel,
max(1, configured value) will be used. In other words we ensure that, for
performance reasons, there is at least one buffer per outgoing channel
regardless of the configuration.
--
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: issues-unsubscr...@flink.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
