Description
Currently, we consider load of datanode when #chooseTarget for writer, however not consider it for reader. Thus, the process slot of datanode could be occupied by #BlockSender for reader, and disk/network will be busy workload, then meet some slow node exception. IIRC same case is reported times. Based on the fact, I propose to consider load for reader same as it did #chooseTarget for writer.
Attachments
Attachments
Issue Links
- is related to
-
HDFS-15285 The same distance and load nodes don't shuffle when consider DataNode load
- Resolved