in_kafka: boost throughput #9625
Open
+29
−3
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
coreidcc
requested review from
edsiper,
leonardo-albertovich,
fujimotos and
koleini
as code owners
|
Documentation is here: fluent/fluent-bit-docs#1520 |
| rd_kafka_commit(ctx->kafka.rk, NULL, 0); | ||
|
|
||
| if(!ctx->enable_auto_commit) { | ||
| /* TO-DO: commit the record based on `ret` */ |
There was a problem hiding this comment.
I think we need to sort all TODOs, we can't just leave them in there. I know it was in the original but we should attempt to sort or add more info.
There was a problem hiding this comment.
Well i din't introduce the TO-DO. It existed before. It just went into the if statement. Unfortunately github shows to little context so you can't see it.
plugins/in_kafka/in_kafka.c
Outdated
| { | ||
| FLB_CONFIG_MAP_BOOL, "enable_auto_commit", FLB_IN_KAFKA_ENABLE_AUTO_COMMIT, | ||
| 0, FLB_TRUE, offsetof(struct flb_in_kafka_config, enable_auto_commit), | ||
| "Relay on kafka auto-commit and commit messages in batches" |
There was a problem hiding this comment.
I think this is a typo and should be rely
| /* TO-DO: commit the record based on `ret` */ | ||
| rd_kafka_commit(ctx->kafka.rk, NULL, 0); | ||
|
|
||
| if(!ctx->enable_auto_commit) { |
There was a problem hiding this comment.
Current behaviour is to have auto-commit false but the default below is now true which means we are not maintaining the old behaviour by default.
coreidcc
force-pushed
the
master
branch
2 times, most recently
from
56a331a
to
713453e
Compare
Polling every 1ms and committing each message individually results in rather pure performance in high volume Kafka clusters. Commiting in batches (relay on auto-commit of kafka) drastically improves performance. Signed-off-by: CoreidCC <sws-github@coreid.cc>
having 1ms timeout might make sense if the input plugin is running in the main thread (not introducing delay for others). but if we run in our very own thread then we should not over- ride the fetch.wait.max.ms configuration value from the kafka-consumer. this in conjuntion with using autocommit again boosts the throuhput significantly. Signed-off-by: CoreidCC <sws-github@coreid.cc>
Signed-off-by: CoreidCC <sws-github@coreid.cc>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
We have a Kafka cluster with about 40k messages and 25MB of data per seconds. Fluent-bit stands no change to keep up with this load in its current state where it
a) commits each message individually
b) a poll-timeout of just one 1ms (this completely overrides fetch.wait.max.ms from kafka)
Even Logstash is faster and vector is just consuming all these messages with ease.
probably related to "Batch processing is required in in_kafka. #8030"
Enter
[N/A]in the box, if an item is not applicable to your change.Testing
Before we can approve your change; please submit the following in a comment:
To activate the changes one need to
[INPUT]
Name kafka
threaded true -> sets timeout so that it will be limited by fetch.wait.max.ms in any practical scenario
enable_auto_commit true -> disable explicit commit call
-> The change doesn't do any dynamic allocations at all and therefore cant introduce any mem-leaks
-> The change has no impact on packaging at all
Documentation
Backporting
Fluent Bit is licensed under Apache 2.0, by submitting this pull request I understand that this code will be released under the terms of that license.