This article walks through exporting HDFS via FUSE and serving it through Samba so that clients can mount it over CIFS. It shows the configuration on RHEL, how to mount HDFS, how to test read and write performance with rsync and dd, and compares the results to direct SCP transfers. The setup is historical but still useful to understand the trade-offs and overhead of exposing HDFS as a network filesystem. Some years ago I experimented with exposing HDFS to non-Hadoop clients. After playing with libhdfs and NFS and not getting the results I wanted, the next idea was: why not try Samba? Samba 3.x was stable, and most operating systems could mount a CIFS share without additional software. The main goal was to understand the setup and performance characteristics of this scenario, because Samba has many tuning options. The environment used in this experiment was RHEL 5.7 with the stock Samba packages. 1. Environment and packages # rpm -qa | grep samba samba-3.0.33-3.29.el5_7.4....
Fractional Chief Architect for Big Data Systems & Distributed Data Processing