[Gluster-users] Are directory moves cheap?
jayunit100 at gmail.com
Sun Dec 15 23:03:52 UTC 2013
Are move/rename ops over directories in fuse mounted gluster generally fast when there are TBs of data in the underlying dirs?
One of the common operations in hive data manipulation is "load data", where you move a set of files from one place to another when ETLing a data set into a cluster.
In our hadoop implementation (GlusterFileSystem), we use the fuse mount to do renames using local posix commands.
I'm wondering this because In hadoop (hdfs), moving directories is (iirc) a relatively cheap metadata operation.
More information about the Gluster-users