HADOOP-18106: Handle memory fragmentation in S3A Vectored IO. #4445
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
…tation. part of HADOOP-18103. Handling memoroy fragmentation in S3A vectored IO implementation by allocating smaller user range requested size buffers and directly filling them from the remote S3 stream and skipping undesired data in between ranges. This patch also adds aborting active vectored reads when stream is closed or unbuffer is called.
4 tasks
|
🎊 +1 overall
This message was automatically generated. |
steveloughran
approved these changes
Jun 20, 2022
...oop-common/src/test/java/org/apache/hadoop/fs/contract/AbstractContractVectoredReadTest.java
Outdated
Show resolved
Hide resolved
| @@ -47,7 +47,7 @@ | |||
| import org.apache.hadoop.fs.LocalFileSystem; | |||
| import org.apache.hadoop.conf.Configuration; | |||
| import org.apache.hadoop.fs.FileRange; | |||
| import org.apache.hadoop.fs.FileRangeImpl; | |||
| import org.apache.hadoop.fs.impl.FileRangeImpl; | |||
There was a problem hiding this comment.
shouldn't be needed now
There was a problem hiding this comment.
it is required actually.
| } catch (Exception ex) { | ||
| LOG.warn("Exception occurred while reading combined range from file {}", pathStr, ex); | ||
| LOG.warn("Exception while reading a range {} from path {} ", combinedFileRange, pathStr, ex); |
There was a problem hiding this comment.
will we log noisily on an EOFException? as that probably doesn't need a stack trace & can just be logged at DEBUG
There was a problem hiding this comment.
Okay changing to debug.
Or do you think it is better to separate EOF exception in a different catch clause?
|
🎊 +1 overall
This message was automatically generated. |
mukund-thakur
added a commit
that referenced
this pull request
Jun 21, 2022
part of HADOOP-18103. Handling memory fragmentation in S3A vectored IO implementation by allocating smaller user range requested size buffers and directly filling them from the remote S3 stream and skipping undesired data in between ranges. This patch also adds aborting active vectored reads when stream is closed or unbuffer() is called. Contributed By: Mukund Thakur
|
on the EOF exception
should all be tested in the contract tests, if not done already |
All these will cause EOF because we validate ranges in the start only. Tests are there but not exactly like these. I can add some more next time. |
asfgit
pushed a commit
that referenced
this pull request
Jun 22, 2022
part of HADOOP-18103. Handling memory fragmentation in S3A vectored IO implementation by allocating smaller user range requested size buffers and directly filling them from the remote S3 stream and skipping undesired data in between ranges. This patch also adds aborting active vectored reads when stream is closed or unbuffer() is called. Contributed By: Mukund Thakur
mukund-thakur
added a commit
that referenced
this pull request
Jun 27, 2022
part of HADOOP-18103. Handling memory fragmentation in S3A vectored IO implementation by allocating smaller user range requested size buffers and directly filling them from the remote S3 stream and skipping undesired data in between ranges. This patch also adds aborting active vectored reads when stream is closed or unbuffer() is called. Contributed By: Mukund Thakur Conflicts: hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/RawLocalFileSystem.java
HarshitGupta11
pushed a commit
to HarshitGupta11/hadoop
that referenced
this pull request
Nov 28, 2022
…#4445) part of HADOOP-18103. Handling memory fragmentation in S3A vectored IO implementation by allocating smaller user range requested size buffers and directly filling them from the remote S3 stream and skipping undesired data in between ranges. This patch also adds aborting active vectored reads when stream is closed or unbuffer() is called. Contributed By: Mukund Thakur
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.
Rebased the feature branch. Old pr link #4427
Description of PR
part of HADOOP-18103.
Handling memoroy fragmentation in S3A vectored IO implementation by
allocating smaller user range requested size buffers and directly
filling them from the remote S3 stream and skipping undesired
data in between ranges.
This patch also adds aborting active vectored reads when stream is
closed or unbuffer is called.
How was this patch tested?
Added new test and re-ran existing tests.
For code changes:
LICENSE,LICENSE-binary,NOTICE-binaryfiles?