[HUDI-3834] Fixing performance hits in reading Column Stats Index#5266
Merged
nsivabalan merged 15 commits intoapache:masterfrom Apr 10, 2022
Merged
[HUDI-3834] Fixing performance hits in reading Column Stats Index#5266nsivabalan merged 15 commits intoapache:masterfrom
nsivabalan merged 15 commits intoapache:masterfrom
Conversation
nsivabalan
reviewed
Apr 8, 2022
Contributor
nsivabalan
left a comment
nsivabalan
left a comment
There was a problem hiding this comment.
Really good job on the finding and the fix.
| * @return Base path | ||
| * @deprecated please use {@link #getBasePathV2()} | ||
| */ | ||
| @Deprecated |
Contributor
There was a problem hiding this comment.
I see we are using getBasePath() in our baseRelation classes. do we need to fix them to getBasePathV2() ?
Contributor
Author
There was a problem hiding this comment.
We should slowly rollover all uses of getBasePath into getBasePathV2 and then rename it
| // reads/writes to references are always atomic (including 64-bit JVMs) | ||
| // https://docs.oracle.com/javase/specs/jls/se8/html/jls-17.html#jls-17.7 | ||
| private volatile String fileName; | ||
| private volatile String s; |
Contributor
|
@alexeykudinkin : there are some CI failures. can you please check it out |
added 15 commits
April 9, 2022 10:05
…d calls punitive `SpecificData.getForSchema` calls
…void memory churn)
…rs to base-/meta-paths to avoid construction of Hadoop's `Path` in the hot-path; Avoid churning `Path` objects
Rebased `HoodieTableMetaClient` onto `SerializablePath`
…to workaround CI issues of building Flink w/ incorrect version of Avro, breaking code-gen)
alexeykudinkin
force-pushed
the
ak/col-stat-perf-fix
branch
from
723c55a to
a87c363
Compare
Contributor
Author
|
@hudi-bot run azure |
xushiyan
pushed a commit
that referenced
this pull request
Apr 14, 2022
) Fixing performance hits in reading Column Stats Index: [HUDI-3834] There's substantial performance degradation in Avro 1.10 default generated Builder classes: they by default rely on SpecificData.getForSchema that load corresponding model's class using reflection, which takes a hit when executed on the hot-path (this was bringing overall runtime to read full Column Stats Index of 800k records to 60s, whereas now it's taking mere 3s) Addressing memory churn by over-used Hadoop's Path creation: Path ctor is not a lightweight sequence and produces quite a bit of memory churn adding pressure on GC. Cleaning such avoidable allocations up to make sure there's no unnecessarily added pressure on GC.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Tips
What is the purpose of the pull request
Fixing performance hits in reading Column Stats Index:
[HUDI-3834] There's substantial performance degradation in Avro 1.10 default generated
Builderclasses: they by default rely onSpecificData.getForSchemathat load corresponding model's class using reflection, which takes a hit when executed on the hot-path (this was bringing overall runtime to read full Column Stats Index of 800k records to 60s, whereas now it's taking mere 3s)Addressing memory churn by over-used Hadoop's
Pathcreation:Pathctor is not a lightweight sequence and produces quite a bit of memory churn adding pressure on GC. Cleaning such avoidable allocations up to make sure there's no unnecessarily added pressure on GC.Brief change log
See above
Verify this pull request
This pull request is already covered by existing tests, such as (please describe tests).
Committer checklist
Has a corresponding JIRA in PR title & commit
Commit message is descriptive of the change
CI is green
Necessary doc changes done or have another open PR
For large changes, please consider breaking it into sub-tasks under an umbrella JIRA.