[GitHub] [hadoop-ozone] bshashikant edited a comment on issue #40: HDDS-2285. GetBlock and ReadChunk command from the client should be s…

[GitBox <gi...@apache.org>]

bshashikant edited a comment on issue #40: HDDS-2285. GetBlock and ReadChunk command from the client should be s…
URL: https://github.com/apache/hadoop-ozone/pull/40#issuecomment-544884381
 
 
   Thanks @hanishakoneru for working on this. I am thinking of a case where, let's say two threads trying to read two different blocks using the same XceiverClientGrpc object as it is shared object, one thread issues a getBlock for block1 to dn1, dn1 got cached and further read chunk calls for all chunks for all blocks(block1 and block2) will go the same dn. The idea of shuffling the datanodes was basically to distribute the load across the datanodes in a pipeline, but for the same block it should always be tried on the same order of datanodes. I think the patch won't address both these concerns here. What do you think?

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org