http://hadoop.apache.org/docs/r1.2.1/hdfs_design.html
Staging A client request to create a file does not reach the NameNode immediately. In fact, initially the HDFS client caches the file data into a temporary local file. Application writes are transparently redirected to this temporary local file. 2014-03-24 17:01 GMT+08:00 Azuryy Yu <azury...@gmail.com>: > Can you give the URL where you looked at? > > > On Mon, Mar 24, 2014 at 4:49 PM, 张建伟 <connerlyzh...@gmail.com> wrote: > >> hi, >> >> In the apache site,I find a document said : >> >> "A client request to create a file does not reach the NameNode >> immediately. In fact, initially the HDFS client caches the file data into a >> temporary local file. Application writes are transparently redirected to >> this temporary local file. When the local file accumulates data worth over >> one HDFS block size, the client contacts the NameNode. " >> >> does it still right in 2.2.0 and 1.2.1 version? why write a file like >> this? >> > >
