hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "patrik" <pat...@clipblast.com>
Subject Single point of failure question
Date Sun, 01 Jul 2007 18:12:38 GMT

How are some of dealing with the single point of failure with the /names
directory on the namenode? Rsync to other possible backup nodes? Store it in
the dfs every now and again? I tried bringing up a secondary namenode but
that didn't get a copy of the /names directory.


View raw message