Al Chu
For a variety of advanced scenarios, there have been requests to setup hadoop/spark/etc. with a command line tool. In addition, shutdown would be the user's responsibility via the command line...
can be confusing, user may think yes means "I can only run things one time".
Following #269, what if user isn't using hadoop and only using spark & spark scheduler? I bet that if you create the hadoop core files (e.g. core-site.xml) and put it...
request from user as it would be easier. Could be useful in testsuite to generate tests.
the system of "generate all tests" then "delete tests user isn't interested in" isn't working anymore now that there's a huge growth in permutation of tests (i.e. spark 2.2.0 w/...
If log files are logged to a long term place, another job run by a user can analyze the log files of a prior application run. This would be more...
While working on #239 it reminded me of https://issues.apache.org/jira/browse/MAPREDUCE-5528 and the fact that the terasort example doesn't work with "rawnetworkfs". A long time ago I wrote a "lustre" plugin for...
-Xmx1000m and -Xmx512m are passed twice, likely due to scripting logic errors in hadoop-env.sh (512m is set via HADOOP_CLIENT_OPS). This isn't a big deal, but would be nice to clean...
Newer systems may have hyper threading on and core counts are now much larger than before. Estimates for the number of threads daemons should have to handle communications (for example...