[
https://issues.apache.org/jira/browse/KAFKA-15609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17782210#comment-17782210
]
Divij Vaidya edited comment on KAFKA-15609 at 11/2/23 4:31 PM:
---------------------------------------------------------------
Thank you for clarifying [~ocadaruma] and thank you for the quick tests. We
actually want to test the condition where we write to a MMap but read using
(non direct) File I/O. We want to validate that even if MMap may not have been
flushed, the data read via File I/O is consistent. Would you have time to
quickly test that?
> Also, in my understanding, page cache is directly mapped to the mmap area so
> even when we try to read the file with ordinary read() call which is written
> by mmap, the content should be consistent.
This is the point about which I am not able to find any concrete information.
Would you happen to have some reference that I can read about this?
was (Author: divijvaidya):
Thank you for clarifying [~ocadaruma] and thank you for the quick tests. We
actually want to test the condition where we write to a MMap but read using
(non direct) File I/O. We want to validate that even if MMap may not have been
flushed, the data read via File I/O is consistent. Would you have time to
quickly test that?
> Also, in my understanding, page cache is directly mapped to the mmap area so
> even when we try to read the file with ordinary read() call which is written
> by mmap, the content should be consistent.
This is the point about which I am not able to find any concrete
implementation. Would you happen to have some reference that I can read about
this?
> Corrupted index uploaded to remote tier
> ---------------------------------------
>
> Key: KAFKA-15609
> URL: https://issues.apache.org/jira/browse/KAFKA-15609
> Project: Kafka
> Issue Type: Bug
> Components: Tiered-Storage
> Affects Versions: 3.6.0
> Reporter: Divij Vaidya
> Priority: Minor
>
> While testing Tiered Storage, we have observed corrupt indexes being present
> in remote tier. One such situation is covered here at
> https://issues.apache.org/jira/browse/KAFKA-15401. This Jira presents another
> such possible case of corruption.
> Potential cause of index corruption:
> We want to ensure that the file we are passing to RSM plugin contains all the
> data which is present in MemoryByteBuffer i.e. we should have flushed the
> MemoryByteBuffer to the file using force(). In Kafka, when we close a
> segment, indexes are flushed asynchronously [1]. Hence, it might be possible
> that when we are passing the file to RSM, the file doesn't contain flushed
> data. Hence, we may end up uploading indexes which haven't been flushed yet.
> Ideally, the contract should enforce that we force flush the content of
> MemoryByteBuffer before we give the file for RSM. This will ensure that
> indexes are not corrupted/incomplete.
> [1]
> [https://github.com/apache/kafka/blob/4150595b0a2e0f45f2827cebc60bcb6f6558745d/core/src/main/scala/kafka/log/UnifiedLog.scala#L1613]
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
