Hi Lewis, Sorry to hear that you're having trouble running the wordcount example with Celeborn.
Based on the information you shared, I would suggest you run MapReduce with Celeborn on a Hadoop cluster instead of pseudo-disturb mode. Celeborn client in MapReduce needs to write a config file into the Hadoop file system. If that doesn't resolve the issue, please let me know and I'll be happy to help you troubleshoot further. Celeborn has a Slack workspace if you are convenient to join. ( https://join.slack.com/t/apachecelebor-kw08030/shared_invite/zt-1ju3hd5j8-4Z5keMdzpcVMspe4UJzF4Q ) Best regards, Ethan Feng lewis john mcgibbney <lewi...@apache.org> 于2023年10月18日周三 12:19写道: > > Hi user@, > > I cloned Celeborn (0.4.0-Incubating) > 69defcad7f9423c9c24d2d22ead856b4225671c6 today and built it with the > -Pmr profile. > > openjdk version "11.0.20.1" 2023-08-24 > OpenJDK Runtime Environment Homebrew (build 11.0.20.1+0) > OpenJDK 64-Bit Server VM Homebrew (build 11.0.20.1+0, mixed mode) > > Apache Hadoop 3.3.4 running in pseudo-distrib mode. > > I made an attempt to start MapReduce with Celeborn as documented at > https://celeborn.apache.org/docs/latest/#start-mapreduce-with-celeborn > > Everything goes good until it fails when I attempt to run the > wordcount example. The exceptions and stack traces are available at > https://paste.apache.org/3vvy6. > > Is it likely that this has to do with the Hadoop version or is this a > known issue? > > Thanks in advance for any help. > lewismc > > -- > http://home.apache.org/~lewismc/ > http://people.apache.org/keys/committer/lewismc