alex-plekhanov commented on a change in pull request #9751:
URL: https://github.com/apache/ignite/pull/9751#discussion_r792597774
##########
File path:
modules/calcite/src/main/java/org/apache/ignite/internal/processors/query/calcite/exec/rel/ScanNode.java
##########
@@ -58,8 +60,20 @@ public ScanNode(ExecutionContext<Row> ctx, RelDataType
rowType, Iterable<Row> sr
requested = rowsCnt;
- if (!inLoop)
- context().execute(this::push, this::onError);
+ if (!inLoop) {
+ if (firstReq) {
Review comment:
Overall throughput can't be changed by this change. The only difference
here: now there is no gap between QueryStartRequest and the first batch from
data source processing. But batch size is relatively small to affect response
time for other queries. If you still think that it's a problem, WDYT about
sending QueryStartResponse in a separate task after the first push task?
--
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]
