[ https://issues.apache.org/jira/browse/HDFS-5639?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13843234#comment-13843234 ]
Daryn Sharp commented on HDFS-5639: ----------------------------------- This patch seems excessively large to me - compounded by unnecessary changes such as using Thread.getCurrentThread when "this" is already a thread. Although conceptually different to some degree, it appears to overlap with HADOOP-9640. Hiding a scheduler behind a custom BlockingQueue implementation may be a bit less intrusive. Would you please work with Chris Li to see if there's enough similarity to combine these efforts (although still via separate jiras). > rpc scheduler abstraction > ------------------------- > > Key: HDFS-5639 > URL: https://issues.apache.org/jira/browse/HDFS-5639 > Project: Hadoop HDFS > Issue Type: Improvement > Reporter: Ming Ma > Attachments: HDFS-5639-2.patch, HDFS-5639.patch > > > We have run into various issues in namenode and hbase w.r.t. rpc handling in > multi-tenant clusters. The examples are > https://issues.apache.org/jira/i#browse/HADOOP-9640 > https://issues.apache.org/jira/i#browse/HBASE-8836 > There are different ideas on how to prioritize rpc requests. It could be > based on user id, or whether it is read request or write request, or it could > use specific rule like datanode's RPC is more important than client RPC. > We want to enable people to implement and experiiment different rpc > schedulers. -- This message was sent by Atlassian JIRA (v6.1.4#6159)