keith-turner commented on issue #3078: URL: https://github.com/apache/accumulo/issues/3078#issuecomment-1315930089
Digging around in the hadoop code I think it creates an output stream per output block in the DN and calls fadvise on its file descriptor. So it does seem like its tightly scoped to the clients output stream, but not completely sure, got a bit lost, below are some things I was looking at. Did not look at the input path. https://github.com/apache/hadoop/blob/branch-3.3.5/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/BlockReceiver.java#L928 https://github.com/apache/hadoop/blob/5ca626e3e3ea29c2c90632129a57e73e3a1a420a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/fsdataset/ReplicaOutputStreams.java#L157 https://github.com/apache/hadoop/blob/5ca626e3e3ea29c2c90632129a57e73e3a1a420a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/io/nativeio/NativeIO.java#L407 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
