Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49892714
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java
---
@@ -103,6 +105,25 @@
Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49893792
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java
---
@@ -0,0 +1,50 @@
+package
Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49894629
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java
---
@@ -0,0 +1,271 @@
+/*
+ *
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172064100
**[Test build #49472 has
started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/49472/consoleFull)**
for PR 10593 at commit
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172064494
**[Test build #49472 has
finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/49472/consoleFull)**
for PR 10593 at commit
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172064506
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172064504
Merged build finished. Test FAILed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172080212
**[Test build #49476 has
started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/49476/consoleFull)**
for PR 10593 at commit
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172117440
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172117435
Merged build finished. Test PASSed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172116685
**[Test build #49476 has
finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/49476/consoleFull)**
for PR 10593 at commit
Github user rxin commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-172144550
Going to merge this. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not
Github user asfgit closed the pull request at:
https://github.com/apache/spark/pull/10593
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49815031
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java
---
@@ -0,0 +1,50 @@
+package
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171815749
**[Test build #49413 has
finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/49413/consoleFull)**
for PR 10593 at commit
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171816015
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171816014
Merged build finished. Test PASSed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your
Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49765499
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedValuesReader.java
---
@@ -0,0 +1,37 @@
+/*
+ *
Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49764984
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java
---
@@ -154,6 +184,45 @@ public float
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49821580
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java
---
@@ -154,6 +184,45 @@ public float
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49821924
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java
---
@@ -0,0 +1,50 @@
+package
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49822085
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java
---
@@ -0,0 +1,271 @@
+/*
+ *
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171876218
**[Test build #2383 has
started](https://amplab.cs.berkeley.edu/jenkins/job/NewSparkPullRequestBuilder/2383/consoleFull)**
for PR 10593 at commit
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49821548
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java
---
@@ -103,6 +105,25 @@
private
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49821596
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java
---
@@ -154,6 +184,45 @@ public float
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49822023
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java
---
@@ -0,0 +1,271 @@
+/*
+ *
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49822045
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java
---
@@ -0,0 +1,271 @@
+/*
+ *
Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49821996
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java
---
@@ -0,0 +1,50 @@
+package
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171894735
**[Test build #2383 has
finished](https://amplab.cs.berkeley.edu/jenkins/job/NewSparkPullRequestBuilder/2383/consoleFull)**
for PR 10593 at commit
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171782602
**[Test build #49413 has
started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/49413/consoleFull)**
for PR 10593 at commit
Github user nongli commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171735222
@maropu I agree. We should probably think about updating the data sources
API to support decoding in batch. I think starting with just parquet will give
us a better
Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49765061
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java
---
@@ -154,6 +184,45 @@ public float
Github user maropu commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171666309
@nongli Great work. One question; we need not have common APIs to realize
batched de-serialization for other data sources like ORC? I know we currently
have no
Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49639656
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java
---
@@ -154,6 +184,45 @@ public float
Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49640021
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedValuesReader.java
---
@@ -0,0 +1,37 @@
+/*
+ *
Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49636533
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetReadBenchmark.scala
---
@@ -87,15 +91,62 @@ object
Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49637590
--- Diff:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java
---
@@ -154,6 +184,45 @@ public float
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171141265
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-171141262
Merged build finished. Test FAILed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your
Github user velvia commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r48991290
--- Diff: core/src/test/scala/org/apache/spark/Benchmark.scala ---
@@ -0,0 +1,102 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under
Github user velvia commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-169412883
@nongli this is awesome. I suppose changes to the logical/physical query
planner are coming also? Is that going to be in a separate PR?
---
If your project is set up
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-169552961
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-169552958
**[Test build #48898 has
finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/48898/consoleFull)**
for PR 10593 at commit
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-169552892
**[Test build #48898 has
started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/48898/consoleFull)**
for PR 10593 at commit
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-169552960
Merged build finished. Test FAILed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your
Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r49035976
--- Diff: core/src/test/scala/org/apache/spark/Benchmark.scala ---
@@ -0,0 +1,102 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under
Github user nongli commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-169470362
@velvia we don't need plan changes to enable this. As soon as we complete
the implementation so this can read all parquet files, the reader will just
always decode this
GitHub user nongli opened a pull request:
https://github.com/apache/spark/pull/10593
[SPARK-12644][SQL] Update parquet reader to be vectorized.
This inlines a few of the Parquet decoders and adds vectorized APIs to
support decoding in batch.
There are a few particulars in the
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-168934496
**[Test build #48749 has
finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/48749/consoleFull)**
for PR 10593 at commit
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-168934501
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-168934499
Merged build finished. Test FAILed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/10593#issuecomment-168934389
**[Test build #48749 has
started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/48749/consoleFull)**
for PR 10593 at commit
Github user kiszk commented on a diff in the pull request:
https://github.com/apache/spark/pull/10593#discussion_r48920875
--- Diff: core/src/test/scala/org/apache/spark/Benchmark.scala ---
@@ -0,0 +1,102 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
53 matches
Mail list logo