Repository: ambari Updated Branches: refs/heads/branch-2.5 a55172f45 -> 5e60ea646
AMBARI-21377: Add HiveVectorizedORC and JDBC profiles to pxf-profiles.xml Project: http://git-wip-us.apache.org/repos/asf/ambari/repo Commit: http://git-wip-us.apache.org/repos/asf/ambari/commit/5e60ea64 Tree: http://git-wip-us.apache.org/repos/asf/ambari/tree/5e60ea64 Diff: http://git-wip-us.apache.org/repos/asf/ambari/diff/5e60ea64 Branch: refs/heads/branch-2.5 Commit: 5e60ea6462183984a13e09ebc8c1d22f95c86f8f Parents: a55172f Author: lavjain <[email protected]> Authored: Fri Jun 30 12:38:38 2017 -0700 Committer: lavjain <[email protected]> Committed: Fri Jun 30 12:38:38 2017 -0700 ---------------------------------------------------------------------- .../PXF/3.0.0/configuration/pxf-profiles.xml | 23 ++++++++++++++++++++ 1 file changed, 23 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/ambari/blob/5e60ea64/ambari-server/src/main/resources/common-services/PXF/3.0.0/configuration/pxf-profiles.xml ---------------------------------------------------------------------- diff --git a/ambari-server/src/main/resources/common-services/PXF/3.0.0/configuration/pxf-profiles.xml b/ambari-server/src/main/resources/common-services/PXF/3.0.0/configuration/pxf-profiles.xml index a3e587d..27473a1 100644 --- a/ambari-server/src/main/resources/common-services/PXF/3.0.0/configuration/pxf-profiles.xml +++ b/ambari-server/src/main/resources/common-services/PXF/3.0.0/configuration/pxf-profiles.xml @@ -74,6 +74,7 @@ under the License. <description> This profile is suitable for using when connecting to Hive. Supports GPDBWritable output format, as specified in FORMAT header parameter. + It auto-detects actual file storage format and uses an optimized profile (HiveRC, HiveText, HiveORC) if applicable. </description> <plugins> <fragmenter>org.apache.hawq.pxf.plugins.hive.HiveDataFragmenter</fragmenter> @@ -132,6 +133,19 @@ under the License. </plugins> </profile> <profile> + <name>HiveVectorizedORC</name> + <description>This profile is same as HiveORC profile, but operates on batches of rows + instead of one row at a time, leading to faster reading and resolution phases. + </description> + <plugins> + <fragmenter>org.apache.hawq.pxf.plugins.hive.HiveInputFormatFragmenter</fragmenter> + <accessor>org.apache.hawq.pxf.plugins.hive.HiveORCVectorizedAccessor</accessor> + <resolver>org.apache.hawq.pxf.plugins.hive.HiveORCVectorizedResolver</resolver> + <metadata>org.apache.hawq.pxf.plugins.hive.HiveMetadataFetcher</metadata> + <outputFormat>org.apache.hawq.pxf.service.io.GPDBWritable</outputFormat> + </plugins> + </profile> + <profile> <name>HdfsTextSimple</name> <description>This profile is suitable for using when reading delimited single line records from plain text files on HDFS @@ -196,6 +210,15 @@ under the License. <resolver>org.apache.hawq.pxf.plugins.json.JsonResolver</resolver> </plugins> </profile> + <profile> + <name>Jdbc</name> + <description>A profile for reading data into HAWQ via JDBC</description> + <plugins> + <fragmenter>org.apache.hawq.pxf.plugins.jdbc.JdbcPartitionFragmenter</fragmenter> + <accessor>org.apache.hawq.pxf.plugins.jdbc.JdbcReadAccessor</accessor> + <resolver>org.apache.hawq.pxf.plugins.jdbc.JdbcReadResolver</resolver> + </plugins> + </profile> </profiles> ]]></value> <value-attributes>
