[
https://issues.apache.org/jira/browse/DRILL-7607?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17048158#comment-17048158
]
ASF GitHub Bot commented on DRILL-7607:
---------------------------------------
paul-rogers commented on pull request #2000: DRILL-7607: support dynamic credit
based flow control
URL: https://github.com/apache/drill/pull/2000#discussion_r385997180
##########
File path: protocol/src/main/protobuf/BitData.proto
##########
@@ -50,3 +52,7 @@ message RuntimeFilterBDef{
optional int32 hj_op_id = 7; // the operator id of the HashJoin which
generates this RuntimeFilter
optional int64 rf_identifier = 8; // the runtime filter identifier
}
+
+message AckWithCredit{
Review comment:
Although it is not a good design, Drill clients use the same RPC protocol as
Drillbits. We recently with Drill 1.17 had an issue where we changed a protobuf
in a way that broke the C++ ODBC driver.
At present the project is thinly staffed; we lack C++ expertise and it may
take a while to get the ODBC driver updated. Further, as Drill is rolled out in
organizations, we cannot expect clients to update in sync with each server
release. Also, we may have people using a single client to speak to Drillbits
of different versions.
All of is a preface to asking: is this a safe change? Is it backward
compatible? If not, is there a way to use optional fields in an existing
message to accomplish the same thing without breaking backward compatibility?
I understand hacking the current protocol is not elegant. But, is it
possible to ensure compatibility?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
> Dynamic credit based flow control
> ---------------------------------
>
> Key: DRILL-7607
> URL: https://issues.apache.org/jira/browse/DRILL-7607
> Project: Apache Drill
> Issue Type: New Feature
> Components: Server, Execution - RPC
> Affects Versions: 1.17.0
> Reporter: Weijie Tong
> Assignee: Weijie Tong
> Priority: Major
> Fix For: 1.18.0
>
>
> Drill current has a static credit based flow control between the batch sender
> and receiver. That means ,all the sender send out their batch through the
> DataTunnel by a static 3 semaphore. To the receiver side , there's two cases,
> the UnlimitedRawBatchBuffer has a 6 * fragmentCount receiver semaphore, the
> SpoolingRawBatchBuffer acts as having unlimited receiving semaphore as it
> could flush data to disk.
> The static credit has the following weak points:
> 1. While the send batch data size is low(e.g. it has only one column bigint
> data) and the receiver has larger memory space, the sender still could not
> send out its data rapidly.
> 2. As the static credit assumption does not set the semaphore number
> according to the corresponding receiver memory space, it still have the risk
> to make the receiver OOM.
> 3. As the sender semaphore is small, it could not send its batch
> consecutively due to wait for an Ack to release one semaphore , and then ,
> the sender's corresponding execution pipeline would be halt, also the same to
> its leaf execution nodes.
> The dynamic credit based flow control could solve these problems. It starts
> from the static credit flow control. Then the receiver collects some batch
> datas to calculate the average batch size. According to the receiver side
> memory space, the receiver make a runtime sender credit and receiver side
> total credit. The receiver sends out the runtime sender credit number to the
> sender by the Ack response. The sender change to the runtime sender credit
> number when receives the Ack response with a runtime credit value.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
