-
Notifications
You must be signed in to change notification settings - Fork 271
Fallback to CPU when Spark pushes down Aggregates (Min/Max/Count) for ORC #4859
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
4b64d77
Aggregate (Min/Max/Count) push down for ORC
amahussein 63114dd
cover all aggregates in the test and parameterize it
amahussein a180080
flaten tests to avoid if/else inside each method
amahussein 36b1a64
avoid overwrite mode while writing ORC file
amahussein File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
47 changes: 47 additions & 0 deletions
47
...n/src/main/301until320-all/scala/com/nvidia/spark/rapids/shims/v2/RapidsOrcScanMeta.scala
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,47 @@ | ||
| /* | ||
| * Copyright (c) 2022, NVIDIA CORPORATION. | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); | ||
| * you may not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package com.nvidia.spark.rapids.shims.v2 | ||
|
|
||
| import com.nvidia.spark.rapids.{DataFromReplacementRule, GpuOrcScanBase, RapidsConf, RapidsMeta, ScanMeta} | ||
|
|
||
| import org.apache.spark.sql.connector.read.Scan | ||
| import org.apache.spark.sql.execution.datasources.v2.orc.OrcScan | ||
|
|
||
| class RapidsOrcScanMeta( | ||
| oScan: OrcScan, | ||
| conf: RapidsConf, | ||
| parent: Option[RapidsMeta[_, _, _]], | ||
| rule: DataFromReplacementRule) | ||
| extends ScanMeta[OrcScan](oScan, conf, parent, rule) { | ||
|
|
||
| override def tagSelfForGpu(): Unit = { | ||
| GpuOrcScanBase.tagSupport(this) | ||
| } | ||
|
|
||
| override def convertToGpu(): Scan = | ||
| GpuOrcScan(oScan.sparkSession, | ||
| oScan.hadoopConf, | ||
| oScan.fileIndex, | ||
| oScan.dataSchema, | ||
| oScan.readDataSchema, | ||
| oScan.readPartitionSchema, | ||
| oScan.options, | ||
| oScan.pushedFilters, | ||
| oScan.partitionFilters, | ||
| oScan.dataFilters, | ||
| conf) | ||
| } |
48 changes: 48 additions & 0 deletions
48
...c/main/301until320-all/scala/com/nvidia/spark/rapids/shims/v2/RapidsParquetScanMeta.scala
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,48 @@ | ||
| /* | ||
| * Copyright (c) 2022, NVIDIA CORPORATION. | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); | ||
| * you may not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package com.nvidia.spark.rapids.shims.v2 | ||
|
|
||
| import com.nvidia.spark.rapids.{DataFromReplacementRule, GpuParquetScanBase, RapidsConf, RapidsMeta, ScanMeta} | ||
|
|
||
| import org.apache.spark.sql.connector.read.Scan | ||
| import org.apache.spark.sql.execution.datasources.v2.parquet.ParquetScan | ||
|
|
||
| class RapidsParquetScanMeta( | ||
| pScan: ParquetScan, | ||
| conf: RapidsConf, | ||
| parent: Option[RapidsMeta[_, _, _]], | ||
| rule: DataFromReplacementRule) | ||
| extends ScanMeta[ParquetScan](pScan, conf, parent, rule) { | ||
|
|
||
| override def tagSelfForGpu(): Unit = { | ||
| GpuParquetScanBase.tagSupport(this) | ||
| } | ||
|
|
||
| override def convertToGpu(): Scan = { | ||
| GpuParquetScan(pScan.sparkSession, | ||
| pScan.hadoopConf, | ||
| pScan.fileIndex, | ||
| pScan.dataSchema, | ||
| pScan.readDataSchema, | ||
| pScan.readPartitionSchema, | ||
| pScan.pushedFilters, | ||
| pScan.options, | ||
| pScan.partitionFilters, | ||
| pScan.dataFilters, | ||
| conf) | ||
| } | ||
| } |
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
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
51 changes: 51 additions & 0 deletions
51
sql-plugin/src/main/320+/scala/com/nvidia/spark/rapids/shims/v2/RapidsCsvScanMeta.scala
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,51 @@ | ||
| /* | ||
| * Copyright (c) 2022, NVIDIA CORPORATION. | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); | ||
| * you may not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package com.nvidia.spark.rapids.shims.v2 | ||
|
|
||
| import com.nvidia.spark.rapids.{DataFromReplacementRule, GpuCSVScan, RapidsConf, RapidsMeta, ScanMeta} | ||
|
|
||
| import org.apache.spark.sql.connector.read.{Scan, SupportsRuntimeFiltering} | ||
| import org.apache.spark.sql.execution.datasources.v2.csv.CSVScan | ||
|
|
||
| class RapidsCsvScanMeta( | ||
| cScan: CSVScan, | ||
| conf: RapidsConf, | ||
| parent: Option[RapidsMeta[_, _, _]], | ||
| rule: DataFromReplacementRule) | ||
| extends ScanMeta[CSVScan](cScan, conf, parent, rule) { | ||
|
|
||
| override def tagSelfForGpu(): Unit = { | ||
| GpuCSVScan.tagSupport(this) | ||
| // we are being overly cautious and that Csv does not support this yet | ||
| if (cScan.isInstanceOf[SupportsRuntimeFiltering]) { | ||
| willNotWorkOnGpu("Csv does not support Runtime filtering (DPP)" + | ||
| " on datasource V2 yet.") | ||
| } | ||
| } | ||
|
|
||
| override def convertToGpu(): Scan = | ||
| GpuCSVScan(cScan.sparkSession, | ||
| cScan.fileIndex, | ||
| cScan.dataSchema, | ||
| cScan.readDataSchema, | ||
| cScan.readPartitionSchema, | ||
| cScan.options, | ||
| cScan.partitionFilters, | ||
| cScan.dataFilters, | ||
| conf.maxReadBatchSizeRows, | ||
| conf.maxReadBatchSizeBytes) | ||
| } |
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.