Reduce thread congestion in HashBuilderOperator #22668
Merged
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
losipiuk
requested review from
dain,
wendigo,
findepi,
dekimir and
raunaqmorarka
wendigo
reviewed
Jul 15, 2024
lib/trino-memory-context/src/main/java/io/trino/memory/context/ThresholdLocalMemoryContext.java
Outdated
Show resolved
Hide resolved
|
|
wendigo
approved these changes
Jul 15, 2024
losipiuk
force-pushed
the
lukaszos/reduce-thread-congestion-in-hashbuilderoperator-f4bee1
branch
from
09d6720
to
11c0340
Compare
Memory management in HashBuilderOperator.addInput caused significant thread congestion. When memory tracking accuracy is traded for calling delegate.setBytes() less frequently, we are getting better performance for queries which tend to process tiny pages in HashBuilder operator.
losipiuk
force-pushed
the
lukaszos/reduce-thread-congestion-in-hashbuilderoperator-f4bee1
branch
from
11c0340
to
32941d5
Compare
updated |
findepi
reviewed
Jul 15, 2024
| public class ThresholdLocalMemoryContext | ||
| implements LocalMemoryContext | ||
| { | ||
| public static final long DEFAULT_SYNC_THRESHOLD = 65536; |
There was a problem hiding this comment.
somewhere (query context? driver context? don't remember) there is already a similar mechanism, with 1 MB threshold (AFAIR)
There was a problem hiding this comment.
There is some guaranteed memory somewhere - do you mean this one?
There was a problem hiding this comment.
Yeah - there is - but it is handled in the AggregatedMemoryContext in the synchronized section already here.
It is just to ensure we are reuturning non-blocked future. The accounting is still 100% correct - so it does not help with thread congestion.
|
CI: #18697 |
|
CI: #21736 |
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.
Memory management in HashBuilderOperator.addInput caused significant
thread congestion. When memory tracking accuracy is traded for calling
delegate.setBytes() less frequently, we are getting better performance
for queries which tend to process tiny pages in HashBuilder operator.
Improvement is very much visible in couple TPC-DS queries run in FTE mode.
Queries run on unpartitioned iceberg, sf1000, 8 nodes cluseter.
Release notes
(x) This is not user-visible or is docs only, and no release notes are required.
( ) Release notes are required. Please propose a release note for me.
( ) Release notes are required, with the following suggested text: