#44, cast varchar as string when no precision. #45
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
Aaaaaaron
force-pushed
the
kyspark-2.4.1.x-4.x-44
branch
from
1c24180 to
787fe88
Compare
7mming7
pushed a commit
that referenced
this pull request
Nov 4, 2020
… more scenarios such as PartitioningCollection
### What changes were proposed in this pull request?
This PR proposes to improve `EnsureRquirement.reorderJoinKeys` to handle the following scenarios:
1. If the keys cannot be reordered to match the left-side `HashPartitioning`, consider the right-side `HashPartitioning`.
2. Handle `PartitioningCollection`, which may contain `HashPartitioning`
### Why are the changes needed?
1. For the scenario 1), the current behavior matches either the left-side `HashPartitioning` or the right-side `HashPartitioning`. This means that if both sides are `HashPartitioning`, it will try to match only the left side.
The following will not consider the right-side `HashPartitioning`:
```
val df1 = (0 until 10).map(i => (i % 5, i % 13)).toDF("i1", "j1")
val df2 = (0 until 10).map(i => (i % 7, i % 11)).toDF("i2", "j2")
df1.write.format("parquet").bucketBy(4, "i1", "j1").saveAsTable("t1")df2.write.format("parquet").bucketBy(4, "i2", "j2").saveAsTable("t2")
val t1 = spark.table("t1")
val t2 = spark.table("t2")
val join = t1.join(t2, t1("i1") === t2("j2") && t1("i1") === t2("i2"))
join.explain
== Physical Plan ==
*(5) SortMergeJoin [i1#26, i1#26], [j2#31, i2#30], Inner
:- *(2) Sort [i1#26 ASC NULLS FIRST, i1#26 ASC NULLS FIRST], false, 0
: +- Exchange hashpartitioning(i1#26, i1#26, 4), true, [id=#69]
: +- *(1) Project [i1#26, j1#27]
: +- *(1) Filter isnotnull(i1#26)
: +- *(1) ColumnarToRow
: +- FileScan parquet default.t1[i1#26,j1#27] Batched: true, DataFilters: [isnotnull(i1#26)], Format: Parquet, Location: InMemoryFileIndex[..., PartitionFilters: [], PushedFilters: [IsNotNull(i1)], ReadSchema: struct<i1:int,j1:int>, SelectedBucketsCount: 4 out of 4
+- *(4) Sort [j2#31 ASC NULLS FIRST, i2#30 ASC NULLS FIRST], false, 0.
+- Exchange hashpartitioning(j2#31, i2#30, 4), true, [id=#79]. <===== This can be removed
+- *(3) Project [i2#30, j2#31]
+- *(3) Filter (((j2#31 = i2#30) AND isnotnull(j2#31)) AND isnotnull(i2#30))
+- *(3) ColumnarToRow
+- FileScan parquet default.t2[i2#30,j2#31] Batched: true, DataFilters: [(j2#31 = i2#30), isnotnull(j2#31), isnotnull(i2#30)], Format: Parquet, Location: InMemoryFileIndex[..., PartitionFilters: [], PushedFilters: [IsNotNull(j2), IsNotNull(i2)], ReadSchema: struct<i2:int,j2:int>, SelectedBucketsCount: 4 out of 4
```
2. For the scenario 2), the current behavior does not handle `PartitioningCollection`:
```
val df1 = (0 until 100).map(i => (i % 5, i % 13)).toDF("i1", "j1")
val df2 = (0 until 100).map(i => (i % 7, i % 11)).toDF("i2", "j2")
val df3 = (0 until 100).map(i => (i % 5, i % 13)).toDF("i3", "j3")
val join = df1.join(df2, df1("i1") === df2("i2") && df1("j1") === df2("j2")) // PartitioningCollection
val join2 = join.join(df3, join("j1") === df3("j3") && join("i1") === df3("i3"))
join2.explain
== Physical Plan ==
*(9) SortMergeJoin [j1#8, i1#7], [j3#30, i3#29], Inner
:- *(6) Sort [j1#8 ASC NULLS FIRST, i1#7 ASC NULLS FIRST], false, 0. <===== This can be removed
: +- Exchange hashpartitioning(j1#8, i1#7, 5), true, [id=#58] <===== This can be removed
: +- *(5) SortMergeJoin [i1#7, j1#8], [i2#18, j2#19], Inner
: :- *(2) Sort [i1#7 ASC NULLS FIRST, j1#8 ASC NULLS FIRST], false, 0
: : +- Exchange hashpartitioning(i1#7, j1#8, 5), true, [id=#45]
: : +- *(1) Project [_1#2 AS i1#7, _2#3 AS j1#8]
: : +- *(1) LocalTableScan [_1#2, _2#3]
: +- *(4) Sort [i2#18 ASC NULLS FIRST, j2#19 ASC NULLS FIRST], false, 0
: +- Exchange hashpartitioning(i2#18, j2#19, 5), true, [id=#51]
: +- *(3) Project [_1#13 AS i2#18, _2#14 AS j2#19]
: +- *(3) LocalTableScan [_1#13, _2#14]
+- *(8) Sort [j3#30 ASC NULLS FIRST, i3#29 ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(j3#30, i3#29, 5), true, [id=#64]
+- *(7) Project [_1#24 AS i3#29, _2#25 AS j3#30]
+- *(7) LocalTableScan [_1#24, _2#25]
```
### Does this PR introduce _any_ user-facing change?
Yes, now from the above examples, the shuffle/sort nodes pointed by `This can be removed` are now removed:
1. Senario 1):
```
== Physical Plan ==
*(4) SortMergeJoin [i1#26, i1#26], [i2#30, j2#31], Inner
:- *(2) Sort [i1#26 ASC NULLS FIRST, i1#26 ASC NULLS FIRST], false, 0
: +- Exchange hashpartitioning(i1#26, i1#26, 4), true, [id=#67]
: +- *(1) Project [i1#26, j1#27]
: +- *(1) Filter isnotnull(i1#26)
: +- *(1) ColumnarToRow
: +- FileScan parquet default.t1[i1#26,j1#27] Batched: true, DataFilters: [isnotnull(i1#26)], Format: Parquet, Location: InMemoryFileIndex[..., PartitionFilters: [], PushedFilters: [IsNotNull(i1)], ReadSchema: struct<i1:int,j1:int>, SelectedBucketsCount: 4 out of 4
+- *(3) Sort [i2#30 ASC NULLS FIRST, j2#31 ASC NULLS FIRST], false, 0
+- *(3) Project [i2#30, j2#31]
+- *(3) Filter (((j2#31 = i2#30) AND isnotnull(j2#31)) AND isnotnull(i2#30))
+- *(3) ColumnarToRow
+- FileScan parquet default.t2[i2#30,j2#31] Batched: true, DataFilters: [(j2#31 = i2#30), isnotnull(j2#31), isnotnull(i2#30)], Format: Parquet, Location: InMemoryFileIndex[..., PartitionFilters: [], PushedFilters: [IsNotNull(j2), IsNotNull(i2)], ReadSchema: struct<i2:int,j2:int>, SelectedBucketsCount: 4 out of 4
```
2. Scenario 2):
```
== Physical Plan ==
*(8) SortMergeJoin [i1#7, j1#8], [i3#29, j3#30], Inner
:- *(5) SortMergeJoin [i1#7, j1#8], [i2#18, j2#19], Inner
: :- *(2) Sort [i1#7 ASC NULLS FIRST, j1#8 ASC NULLS FIRST], false, 0
: : +- Exchange hashpartitioning(i1#7, j1#8, 5), true, [id=#43]
: : +- *(1) Project [_1#2 AS i1#7, _2#3 AS j1#8]
: : +- *(1) LocalTableScan [_1#2, _2#3]
: +- *(4) Sort [i2#18 ASC NULLS FIRST, j2#19 ASC NULLS FIRST], false, 0
: +- Exchange hashpartitioning(i2#18, j2#19, 5), true, [id=#49]
: +- *(3) Project [_1#13 AS i2#18, _2#14 AS j2#19]
: +- *(3) LocalTableScan [_1#13, _2#14]
+- *(7) Sort [i3#29 ASC NULLS FIRST, j3#30 ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(i3#29, j3#30, 5), true, [id=#58]
+- *(6) Project [_1#24 AS i3#29, _2#25 AS j3#30]
+- *(6) LocalTableScan [_1#24, _2#25]
```
### How was this patch tested?
Added tests.
Closes apache#29074 from imback82/reorder_keys.
Authored-by: Terry Kim <yuminkim@gmail.com>
Signed-off-by: Wenchen Fan <wenchen@databricks.com>
7mming7
pushed a commit
to 7mming7/spark
that referenced
this pull request
Nov 17, 2020
### What changes were proposed in this pull request?
Push down filter through expand. For case below:
```
create table t1(pid int, uid int, sid int, dt date, suid int) using parquet;
create table t2(pid int, vs int, uid int, csid int) using parquet;
SELECT
years,
appversion,
SUM(uusers) AS users
FROM (SELECT
Date_trunc('year', dt) AS years,
CASE
WHEN h.pid = 3 THEN 'iOS'
WHEN h.pid = 4 THEN 'Android'
ELSE 'Other'
END AS viewport,
h.vs AS appversion,
Count(DISTINCT u.uid) AS uusers
,Count(DISTINCT u.suid) AS srcusers
FROM t1 u
join t2 h
ON h.uid = u.uid
GROUP BY 1,
2,
3) AS a
WHERE viewport = 'iOS'
GROUP BY 1,
2
```
Plan. before this pr:
```
== Physical Plan ==
*(5) HashAggregate(keys=[years#30, appversion#32], functions=[sum(uusers#33L)])
+- Exchange hashpartitioning(years#30, appversion#32, 200), true, [id=Kyligence#251]
+- *(4) HashAggregate(keys=[years#30, appversion#32], functions=[partial_sum(uusers#33L)])
+- *(4) HashAggregate(keys=[date_trunc('year', CAST(u.`dt` AS TIMESTAMP))Kyligence#45, CASE WHEN (h.`pid` = 3) THEN 'iOS' WHEN (h.`pid` = 4) THEN 'Android' ELSE 'Other' END#46, vs#12], functions=[count(if ((gid#44 = 1)) u.`uid`Kyligence#47 else null)])
+- Exchange hashpartitioning(date_trunc('year', CAST(u.`dt` AS TIMESTAMP))Kyligence#45, CASE WHEN (h.`pid` = 3) THEN 'iOS' WHEN (h.`pid` = 4) THEN 'Android' ELSE 'Other' END#46, vs#12, 200), true, [id=Kyligence#246]
+- *(3) HashAggregate(keys=[date_trunc('year', CAST(u.`dt` AS TIMESTAMP))Kyligence#45, CASE WHEN (h.`pid` = 3) THEN 'iOS' WHEN (h.`pid` = 4) THEN 'Android' ELSE 'Other' END#46, vs#12], functions=[partial_count(if ((gid#44 = 1)) u.`uid`Kyligence#47 else null)])
+- *(3) HashAggregate(keys=[date_trunc('year', CAST(u.`dt` AS TIMESTAMP))Kyligence#45, CASE WHEN (h.`pid` = 3) THEN 'iOS' WHEN (h.`pid` = 4) THEN 'Android' ELSE 'Other' END#46, vs#12, u.`uid`Kyligence#47, u.`suid`Kyligence#48, gid#44], functions=[])
+- Exchange hashpartitioning(date_trunc('year', CAST(u.`dt` AS TIMESTAMP))Kyligence#45, CASE WHEN (h.`pid` = 3) THEN 'iOS' WHEN (h.`pid` = 4) THEN 'Android' ELSE 'Other' END#46, vs#12, u.`uid`Kyligence#47, u.`suid`Kyligence#48, gid#44, 200), true, [id=Kyligence#241]
+- *(2) HashAggregate(keys=[date_trunc('year', CAST(u.`dt` AS TIMESTAMP))Kyligence#45, CASE WHEN (h.`pid` = 3) THEN 'iOS' WHEN (h.`pid` = 4) THEN 'Android' ELSE 'Other' END#46, vs#12, u.`uid`Kyligence#47, u.`suid`Kyligence#48, gid#44], functions=[])
+- *(2) Filter (CASE WHEN (h.`pid` = 3) THEN 'iOS' WHEN (h.`pid` = 4) THEN 'Android' ELSE 'Other' END#46 = iOS)
+- *(2) Expand [ArrayBuffer(date_trunc(year, cast(dt#9 as timestamp), Some(Etc/GMT+7)), CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END, vs#12, uid#7, null, 1), ArrayBuffer(date_trunc(year, cast(dt#9 as timestamp), Some(Etc/GMT+7)), CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END, vs#12, null, suid#10, 2)], [date_trunc('year', CAST(u.`dt` AS TIMESTAMP))Kyligence#45, CASE WHEN (h.`pid` = 3) THEN 'iOS' WHEN (h.`pid` = 4) THEN 'Android' ELSE 'Other' END#46, vs#12, u.`uid`Kyligence#47, u.`suid`Kyligence#48, gid#44]
+- *(2) Project [uid#7, dt#9, suid#10, pid#11, vs#12]
+- *(2) BroadcastHashJoin [uid#7], [uid#13], Inner, BuildRight
:- *(2) Project [uid#7, dt#9, suid#10]
: +- *(2) Filter isnotnull(uid#7)
: +- *(2) ColumnarToRow
: +- FileScan parquet default.t1[uid#7,dt#9,suid#10] Batched: true, DataFilters: [isnotnull(uid#7)], Format: Parquet, Location: InMemoryFileIndex[file:/root/spark-3.0.0-bin-hadoop3.2/spark-warehouse/t1], PartitionFilters: [], PushedFilters: [IsNotNull(uid)], ReadSchema: struct<uid:int,dt:date,suid:int>
+- BroadcastExchange HashedRelationBroadcastMode(List(cast(input[2, int, true] as bigint))), [id=Kyligence#233]
+- *(1) Project [pid#11, vs#12, uid#13]
+- *(1) Filter isnotnull(uid#13)
+- *(1) ColumnarToRow
+- FileScan parquet default.t2[pid#11,vs#12,uid#13] Batched: true, DataFilters: [isnotnull(uid#13)], Format: Parquet, Location: InMemoryFileIndex[file:/root/spark-3.0.0-bin-hadoop3.2/spark-warehouse/t2], PartitionFilters: [], PushedFilters: [IsNotNull(uid)], ReadSchema: struct<pid:int,vs:int,uid:int>
```
Plan. after. this pr. :
```
== Physical Plan ==
AdaptiveSparkPlan isFinalPlan=false
+- HashAggregate(keys=[years#0, appversion#2], functions=[sum(uusers#3L)], output=[years#0, appversion#2, users#5L])
+- Exchange hashpartitioning(years#0, appversion#2, 5), true, [id=Kyligence#71]
+- HashAggregate(keys=[years#0, appversion#2], functions=[partial_sum(uusers#3L)], output=[years#0, appversion#2, sum#22L])
+- HashAggregate(keys=[date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12], functions=[count(distinct uid#7)], output=[years#0, appversion#2, uusers#3L])
+- Exchange hashpartitioning(date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12, 5), true, [id=Kyligence#67]
+- HashAggregate(keys=[date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12], functions=[partial_count(distinct uid#7)], output=[date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12, count#27L])
+- HashAggregate(keys=[date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12, uid#7], functions=[], output=[date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12, uid#7])
+- Exchange hashpartitioning(date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12, uid#7, 5), true, [id=Kyligence#63]
+- HashAggregate(keys=[date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles)) AS date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END AS CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12, uid#7], functions=[], output=[date_trunc(year, cast(dt#9 as timestamp), Some(America/Los_Angeles))Kyligence#23, CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END#24, vs#12, uid#7])
+- Project [uid#7, dt#9, pid#11, vs#12]
+- BroadcastHashJoin [uid#7], [uid#13], Inner, BuildRight, false
:- Filter isnotnull(uid#7)
: +- FileScan parquet default.t1[uid#7,dt#9] Batched: true, DataFilters: [isnotnull(uid#7)], Format: Parquet, Location: InMemoryFileIndex[file:/private/var/folders/4l/7_c5c97s1_gb0d9_d6shygx00000gn/T/warehouse-c069d87..., PartitionFilters: [], PushedFilters: [IsNotNull(uid)], ReadSchema: struct<uid:int,dt:date>
+- BroadcastExchange HashedRelationBroadcastMode(List(cast(input[2, int, false] as bigint)),false), [id=Kyligence#58]
+- Filter ((CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END = iOS) AND isnotnull(uid#13))
+- FileScan parquet default.t2[pid#11,vs#12,uid#13] Batched: true, DataFilters: [(CASE WHEN (pid#11 = 3) THEN iOS WHEN (pid#11 = 4) THEN Android ELSE Other END = iOS), isnotnull..., Format: Parquet, Location: InMemoryFileIndex[file:/private/var/folders/4l/7_c5c97s1_gb0d9_d6shygx00000gn/T/warehouse-c069d87..., PartitionFilters: [], PushedFilters: [IsNotNull(uid)], ReadSchema: struct<pid:int,vs:int,uid:int>
```
### Why are the changes needed?
Improve performance, filter more data.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Added UT
Closes apache#30278 from AngersZhuuuu/SPARK-33302.
Authored-by: angerszhu <angers.zhu@gmail.com>
Signed-off-by: Wenchen Fan <wenchen@databricks.com>
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.
What changes were proposed in this pull request?
(Please fill in changes proposed in this fix)
How was this patch tested?
(Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)
(If this patch involves UI changes, please attach a screenshot; otherwise, remove this)
Please review http://spark.apache.org/contributing.html before opening a pull request.