* support change shuffle thread num
* support change train thread num
* fix receive shuffle data of each channel
* data norm stop gradient
* add check thread_tensor type and root_tensor type when merge metric
* remove sleep in shuffle, add config
* add config of pslib client to client communication
* fix xbox str
* add data norm op testcase
* add flush in trainer finalize

* support preload thread
* sleep before fleet wrapper exit for pslib core dump
* optimize hdfs log
* fix master+patch bug

* test=develop,  communicator merge add => merge average

* add thread scope stat accurate metrics test=develop

* fix style

* fix style

* fix style

* fix style test=develop

* fix style test=develop

* fix style test=develop

* fix style test=develop

* fix style test=develop

* fix style test=develop

* fix style test=develop

* fix conflict

* fix style

* fix style test=develop

* fix error test=develop

* fix error test=develop

* add get_last_save_xbox_base/get_last_save_xbox
* fix fleet_util bug of load paddle model
* add doc string in fleet api

* fix default value of fleet desc, default values are same with jingpai
* print log when save model

* add fleet util (fleet/utils/fleet_util.py): functions for users' convenience
* add some interface in hdfs util : hdfs is_file、hdfs cat

do some odd jobs, test=develop