Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
When the JobTracker assigns a map task to a TaskTracker, does it need to talk to NameNode? Or it can get the information from the InputSplit itself?
When I look at the code, I see that the InputSplits are packed with BlockLocations. Would the JobTracker go with this information or does it need to work with Namenode?
The client calculates the split informations and writes them with the split info to HDFS.
You can have a look into Hadoop 1.x
JobSplit.SplitMetaInfothere is the serialization implemented that also serializes the locations.The jobtracker just picks up these serializations and schedules them, where the locations are just a hint for faster execution if slots are available.