Created
April 25, 2019 01:36
-
-
Save bvaradar/6eba5c0fab7a0ab630206d64367d6cde to your computer and use it in GitHub Desktop.
This file contains 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
#Apply patch to add DFS properties | |
https://github.com/bvaradar/hudi/commit/a4f79a7ab6955503e3cca0a36876305a544991ee | |
Instead of Step (1) in demo | |
varadarb-C02SH0P1G8WL:hudi varadarb$ docker exec -it adhoc-2 /bin/bash | |
# Creating DFS Root Directory | |
root@adhoc-2:/opt#hadoop fs -mkdir -p /var/data/input_batch/ | |
## Copy batch_1 to DFS | |
root@adhoc-2:/opt# hadoop fs -copyFromLocal /var/hoodie/ws/docker/demo/data/batch_1.json /var/data/input_batch/. | |
## FOr delta-streamer invocations, change --source-class and --props | |
spark-submit --class com.uber.hoodie.utilities.deltastreamer.HoodieDeltaStreamer $HUDI_UTILITIES_BUNDLE --storage-type COPY_ON_WRITE --source-class com.uber.hoodie.utilities.sources.JsonDFSSource --source-ordering-field ts --target-base-path /user/hive/warehouse/stock_ticks_cow --target-table stock_ticks_cow --props /var/demo/config/dfs-source.properties --schemaprovider-class com.uber.hoodie.utilities.schema.FilebasedSchemaProvider | |
# Do similar changes instead of Step 5 http://hudi.incubator.apache.org/docker_demo.html#step-5-upload-second-batch-to-kafka-and-run-deltastreamer-to-ingest | |
## Copy batch_2 to DFS | |
root@adhoc-2:/opt# hadoop fs -copyFromLocal /var/hoodie/ws/docker/demo/data/batch_2.json /var/data/input_batch/. | |
## Similar changes to delta-streamer invocations |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment