From ca2d1bd7eccd619173e1d326c9a2ebb1a2d3d502 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 3 Apr 2018 02:25:28 +0000 Subject: actually running hadoop job on cluster --- backfill/README.md | 14 ++++++++++++++ backfill/mrjob.conf | 4 ++++ 2 files changed, 18 insertions(+) create mode 100644 backfill/mrjob.conf diff --git a/backfill/README.md b/backfill/README.md index 6af8f33..2e3dc7a 100644 --- a/backfill/README.md +++ b/backfill/README.md @@ -10,3 +10,17 @@ running on a devbox: --hbase-table wbgrp-journal-extract-0-qa \ --hbase-host bnewbold-dev.us.archive.org +Actual invocation to run on Hadoop cluster (running on an IA devbox, where +hadoop environment is configured): + + # Create tarball of virtualenv + pipenv shell + tar -czf backfill-4OmRI0zZ.tar.gz -C /home/bnewbold/.local/share/virtualenvs/backfill-4OmRI0zZ . + + ./backfill_hbase_from_cdx.py \ + -r hadoop \ + --hbase-host bnewbold-dev.us.archive.org \ + --hbase-table wbgrp-journal-extract-0-qa \ + -c mrjob.conf \ + --archive backfill-4OmRI0zZ.tar.gz#venv \ + hdfs:///user/bnewbold/journal_crawl_cdx/citeseerx_crawl_2017.cdx diff --git a/backfill/mrjob.conf b/backfill/mrjob.conf new file mode 100644 index 0000000..cb286f1 --- /dev/null +++ b/backfill/mrjob.conf @@ -0,0 +1,4 @@ +runners: + hadoop: + setup: + - export PYTHONPATH=$PYTHONPATH:venv/lib/python3.5/site-packages/ -- cgit v1.2.3