You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by GitBox <gi...@apache.org> on 2020/05/29 10:58:46 UTC
[GitHub] [flink] pnowojski opened a new pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
pnowojski opened a new pull request #12407:
URL: https://github.com/apache/flink/pull/12407
This removes `NextRecordResponse` and inlines `NonSpanningWrapper#getNextRecord` to fix second performance regression that happened on May 19th. This second regression is visible as a difference between results from Mat 19th (before regression) and May 22nd - 29th (period after fixing the first performance regression):
http://codespeed.dak8s.net:8000/timeline/?ben=networkBroadcastThroughput&env=2
It was introduced by the following commit:
> [824100e1460dd2f78f689da72bc5d7b0c9dcbbde] [FLINK-17547][task][hotfix] Extract methods from RecordsDeserializer
`networkBroadcastThroughput` benchmark results are restored from ~1000 to ~1100 ops/ms on the Hetzner worker.
## Verifying this change
Change is covered by existing tests.
## Does this pull request potentially affect one of the following parts:
- Dependencies (does it add or upgrade a dependency): (yes / **no**)
- The public API, i.e., is any changed class annotated with `@Public(Evolving)`: (yes / **no**)
- The serializers: (yes / **no** / don't know)
- The runtime per-record code paths (performance sensitive): (**yes** / no / don't know)
- Anything that affects deployment or recovery: JobManager (and its components), Checkpointing, Kubernetes/Yarn/Mesos, ZooKeeper: (yes / **no** / don't know)
- The S3 file system connector: (yes / **no** / don't know)
## Documentation
- Does this pull request introduce a new feature? (yes / **no**)
- If yes, how is the feature documented? (**not applicable** / docs / JavaDocs / not documented)
----------------------------------------------------------------
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:
users@infra.apache.org
[GitHub] [flink] flinkbot edited a comment on pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
Posted by GitBox <gi...@apache.org>.
flinkbot edited a comment on pull request #12407:
URL: https://github.com/apache/flink/pull/12407#issuecomment-635920790
<!--
Meta data
{
"version" : 1,
"metaDataEntries" : [ {
"hash" : "cc1b0b49d02982ca88dfea41393cbbf34748806b",
"status" : "PENDING",
"url" : "https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=2448",
"triggerID" : "cc1b0b49d02982ca88dfea41393cbbf34748806b",
"triggerType" : "PUSH"
}, {
"hash" : "695516408f92a0dc4138ff2aa046a72eab78827a",
"status" : "UNKNOWN",
"url" : "TBD",
"triggerID" : "695516408f92a0dc4138ff2aa046a72eab78827a",
"triggerType" : "PUSH"
} ]
}-->
## CI report:
* cc1b0b49d02982ca88dfea41393cbbf34748806b Azure: [PENDING](https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=2448)
* 695516408f92a0dc4138ff2aa046a72eab78827a UNKNOWN
<details>
<summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot run travis` re-run the last Travis build
- `@flinkbot run azure` re-run the last Azure build
</details>
----------------------------------------------------------------
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:
users@infra.apache.org
[GitHub] [flink] rkhachatryan commented on a change in pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
Posted by GitBox <gi...@apache.org>.
rkhachatryan commented on a change in pull request #12407:
URL: https://github.com/apache/flink/pull/12407#discussion_r432485048
##########
File path: flink-runtime/src/main/java/org/apache/flink/runtime/io/network/api/serialization/SpillingAdaptiveSpanningRecordDeserializer.java
##########
@@ -101,11 +99,13 @@ public DeserializationResult getNextRecord(T target) throws IOException {
}
private DeserializationResult readNonSpanningRecord(T target) throws IOException {
- NextRecordResponse response = nonSpanningWrapper.getNextRecord(target);
- if (response.result == PARTIAL_RECORD) {
- spanningWrapper.transferFrom(nonSpanningWrapper, response.bytesLeft);
+ int recordLen = nonSpanningWrapper.readInt();
+ if (nonSpanningWrapper.canReadRecord(recordLen)) {
+ return nonSpanningWrapper.readInto(target);
Review comment:
nit: leave a comment that this can't be turned into POJO/Tuple because of performance?
----------------------------------------------------------------
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:
users@infra.apache.org
[GitHub] [flink] rkhachatryan commented on a change in pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
Posted by GitBox <gi...@apache.org>.
rkhachatryan commented on a change in pull request #12407:
URL: https://github.com/apache/flink/pull/12407#discussion_r432485048
##########
File path: flink-runtime/src/main/java/org/apache/flink/runtime/io/network/api/serialization/SpillingAdaptiveSpanningRecordDeserializer.java
##########
@@ -101,11 +99,13 @@ public DeserializationResult getNextRecord(T target) throws IOException {
}
private DeserializationResult readNonSpanningRecord(T target) throws IOException {
- NextRecordResponse response = nonSpanningWrapper.getNextRecord(target);
- if (response.result == PARTIAL_RECORD) {
- spanningWrapper.transferFrom(nonSpanningWrapper, response.bytesLeft);
+ int recordLen = nonSpanningWrapper.readInt();
+ if (nonSpanningWrapper.canReadRecord(recordLen)) {
+ return nonSpanningWrapper.readInto(target);
Review comment:
Leave a comment that this can't be turned into POJO/Tuple because of performance?
----------------------------------------------------------------
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:
users@infra.apache.org
[GitHub] [flink] flinkbot edited a comment on pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
Posted by GitBox <gi...@apache.org>.
flinkbot edited a comment on pull request #12407:
URL: https://github.com/apache/flink/pull/12407#issuecomment-635920790
<!--
Meta data
{
"version" : 1,
"metaDataEntries" : [ {
"hash" : "cc1b0b49d02982ca88dfea41393cbbf34748806b",
"status" : "PENDING",
"url" : "https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=2448",
"triggerID" : "cc1b0b49d02982ca88dfea41393cbbf34748806b",
"triggerType" : "PUSH"
}, {
"hash" : "695516408f92a0dc4138ff2aa046a72eab78827a",
"status" : "PENDING",
"url" : "https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=2461",
"triggerID" : "695516408f92a0dc4138ff2aa046a72eab78827a",
"triggerType" : "PUSH"
} ]
}-->
## CI report:
* cc1b0b49d02982ca88dfea41393cbbf34748806b Azure: [PENDING](https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=2448)
* 695516408f92a0dc4138ff2aa046a72eab78827a Azure: [PENDING](https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=2461)
<details>
<summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot run travis` re-run the last Travis build
- `@flinkbot run azure` re-run the last Azure build
</details>
----------------------------------------------------------------
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:
users@infra.apache.org
[GitHub] [flink] pnowojski merged pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
Posted by GitBox <gi...@apache.org>.
pnowojski merged pull request #12407:
URL: https://github.com/apache/flink/pull/12407
----------------------------------------------------------------
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:
users@infra.apache.org
[GitHub] [flink] flinkbot commented on pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
Posted by GitBox <gi...@apache.org>.
flinkbot commented on pull request #12407:
URL: https://github.com/apache/flink/pull/12407#issuecomment-635920790
<!--
Meta data
{
"version" : 1,
"metaDataEntries" : [ {
"hash" : "cc1b0b49d02982ca88dfea41393cbbf34748806b",
"status" : "UNKNOWN",
"url" : "TBD",
"triggerID" : "cc1b0b49d02982ca88dfea41393cbbf34748806b",
"triggerType" : "PUSH"
} ]
}-->
## CI report:
* cc1b0b49d02982ca88dfea41393cbbf34748806b UNKNOWN
<details>
<summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot run travis` re-run the last Travis build
- `@flinkbot run azure` re-run the last Azure build
</details>
----------------------------------------------------------------
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:
users@infra.apache.org
[GitHub] [flink] flinkbot edited a comment on pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
Posted by GitBox <gi...@apache.org>.
flinkbot edited a comment on pull request #12407:
URL: https://github.com/apache/flink/pull/12407#issuecomment-635920790
<!--
Meta data
{
"version" : 1,
"metaDataEntries" : [ {
"hash" : "cc1b0b49d02982ca88dfea41393cbbf34748806b",
"status" : "PENDING",
"url" : "https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=2448",
"triggerID" : "cc1b0b49d02982ca88dfea41393cbbf34748806b",
"triggerType" : "PUSH"
} ]
}-->
## CI report:
* cc1b0b49d02982ca88dfea41393cbbf34748806b Azure: [PENDING](https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=2448)
<details>
<summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot run travis` re-run the last Travis build
- `@flinkbot run azure` re-run the last Azure build
</details>
----------------------------------------------------------------
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:
users@infra.apache.org
[GitHub] [flink] flinkbot commented on pull request #12407: [FLINK-17842][network] Remove NextRecordResponse to improve deserialisation performance
Posted by GitBox <gi...@apache.org>.
flinkbot commented on pull request #12407:
URL: https://github.com/apache/flink/pull/12407#issuecomment-635911663
Thanks a lot for your contribution to the Apache Flink project. I'm the @flinkbot. I help the community
to review your pull request. We will use this comment to track the progress of the review.
## Automated Checks
Last check on commit cc1b0b49d02982ca88dfea41393cbbf34748806b (Fri May 29 11:00:42 UTC 2020)
**Warnings:**
* No documentation files were touched! Remember to keep the Flink docs up to date!
<sub>Mention the bot in a comment to re-run the automated checks.</sub>
## Review Progress
* ❓ 1. The [description] looks good.
* ❓ 2. There is [consensus] that the contribution should go into to Flink.
* ❓ 3. Needs [attention] from.
* ❓ 4. The change fits into the overall [architecture].
* ❓ 5. Overall code [quality] is good.
Please see the [Pull Request Review Guide](https://flink.apache.org/contributing/reviewing-prs.html) for a full explanation of the review process.<details>
The Bot is tracking the review progress through labels. Labels are applied according to the order of the review items. For consensus, approval by a Flink committer of PMC member is required <summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot approve description` to approve one or more aspects (aspects: `description`, `consensus`, `architecture` and `quality`)
- `@flinkbot approve all` to approve all aspects
- `@flinkbot approve-until architecture` to approve everything until `architecture`
- `@flinkbot attention @username1 [@username2 ..]` to require somebody's attention
- `@flinkbot disapprove architecture` to remove an approval you gave earlier
</details>
----------------------------------------------------------------
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:
users@infra.apache.org