Hello, I know the start-up process in the current hadoop architecture takes 20-30 seconds for the many steps. (Also, I know there are many similar questions like this. <http://www.mail-archive.com/common-user@hadoop.apache.org/msg09919.html>)
But, I am wondering if there is any way to speed-up the job start-up time with some hacking or some pre-processing. (For example, pre-distributing job resources or something.) Regards, Hiroyuki