[SPARK-18679] [SQL] Fix regression in file listing performance for non-catalog tables #16112
Conversation
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
ericl
changed the title
cloud-fan
reviewed
Dec 2, 2016
| } | ||
|
|
||
| test("PartitioningAwareFileIndex listing parallelized with many top level dirs") { | ||
| for ((scale, expectedNumPar) <- Seq((10, 0), (50, 1))) { |
Contributor
There was a problem hiding this comment.
shall we do withSQLConf(SQLConf.PARALLEL_PARTITION_DISCOVERY_THRESHOLD -> "xxx") { test code } to make the test more robust?
Contributor
|
LGTM, @ericl have you run some local benchmark to make sure the performance regression is fixed? |
Contributor
Author
|
Yep
…On Thu, Dec 1, 2016, 8:03 PM Wenchen Fan ***@***.***> wrote:
LGTM, @ericl <https://github.com/ericl> have you run some local benchmark
to make sure the performance regression is fixed?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#16112 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/AAA6SojMWfKRhJ0p_h66YyQZNUkIpYaEks5rD5iJgaJpZM4LCIzn>
.
|
|
Test build #69531 has finished for PR 16112 at commit
|
asfgit
pushed a commit
that referenced
this pull request
Dec 2, 2016
…-catalog tables ## What changes were proposed in this pull request? In Spark 2.1 ListingFileCatalog was significantly refactored (and renamed to InMemoryFileIndex). This introduced a regression where parallelism could only be introduced at the very top of the tree. However, in many cases (e.g. `spark.read.parquet(topLevelDir)`), the top of the tree is only a single directory. This PR simplifies and fixes the parallel recursive listing code to allow parallelism to be introduced at any level during recursive descent (though note that once we decide to list a sub-tree in parallel, the sub-tree is listed in serial on executors). cc mallman cloud-fan ## How was this patch tested? Checked metrics in unit tests. Author: Eric Liang <[email protected]> Closes #16112 from ericl/spark-18679. (cherry picked from commit 294163e) Signed-off-by: Wenchen Fan <[email protected]>
Contributor
|
thanks, merging to master/2.1! |
robert3005
pushed a commit
to palantir/spark
that referenced
this pull request
Dec 15, 2016
…-catalog tables ## What changes were proposed in this pull request? In Spark 2.1 ListingFileCatalog was significantly refactored (and renamed to InMemoryFileIndex). This introduced a regression where parallelism could only be introduced at the very top of the tree. However, in many cases (e.g. `spark.read.parquet(topLevelDir)`), the top of the tree is only a single directory. This PR simplifies and fixes the parallel recursive listing code to allow parallelism to be introduced at any level during recursive descent (though note that once we decide to list a sub-tree in parallel, the sub-tree is listed in serial on executors). cc mallman cloud-fan ## How was this patch tested? Checked metrics in unit tests. Author: Eric Liang <[email protected]> Closes apache#16112 from ericl/spark-18679.
uzadude
pushed a commit
to uzadude/spark
that referenced
this pull request
Jan 27, 2017
…-catalog tables ## What changes were proposed in this pull request? In Spark 2.1 ListingFileCatalog was significantly refactored (and renamed to InMemoryFileIndex). This introduced a regression where parallelism could only be introduced at the very top of the tree. However, in many cases (e.g. `spark.read.parquet(topLevelDir)`), the top of the tree is only a single directory. This PR simplifies and fixes the parallel recursive listing code to allow parallelism to be introduced at any level during recursive descent (though note that once we decide to list a sub-tree in parallel, the sub-tree is listed in serial on executors). cc mallman cloud-fan ## How was this patch tested? Checked metrics in unit tests. Author: Eric Liang <[email protected]> Closes apache#16112 from ericl/spark-18679.
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.
What changes were proposed in this pull request?
In Spark 2.1 ListingFileCatalog was significantly refactored (and renamed to InMemoryFileIndex). This introduced a regression where parallelism could only be introduced at the very top of the tree. However, in many cases (e.g.
spark.read.parquet(topLevelDir)), the top of the tree is only a single directory.This PR simplifies and fixes the parallel recursive listing code to allow parallelism to be introduced at any level during recursive descent (though note that once we decide to list a sub-tree in parallel, the sub-tree is listed in serial on executors).
cc @mallman @cloud-fan
How was this patch tested?
Checked metrics in unit tests.