[ http://issues.apache.org/jira/browse/HADOOP-692?page=comments#action_12448867 ] Doug Cutting commented on HADOOP-692: -------------------------------------
I think that at this point what we want is a declarative description of the cluster topology, provided by the administrator, rather than a distance function. For example, we could extend the format of the slaves file to list all of the network levels that a node lives at: <hostname> <rackswitchname> <clusterswitchname> <datacentername>, etc. This can be used not just to compute the distance between any two nodes, but also to quickly list nodes that are close to a node. The latter is hard with a distance function without pre-computing all inter-node distances. With 10k nodes, that's 100M distances, which is expensive. > Rack-aware Replica Placement > ---------------------------- > > Key: HADOOP-692 > URL: http://issues.apache.org/jira/browse/HADOOP-692 > Project: Hadoop > Issue Type: Improvement > Components: dfs > Affects Versions: 0.8.0 > Reporter: Hairong Kuang > Assigned To: Hairong Kuang > Fix For: 0.9.0 > > > This issue assumes that HDFS runs on a cluster of computers that spread > across many racks. Communication between two nodes on different racks needs > to go through switches. Bandwidth in/out of a rack may be less than the total > bandwidth of machines in the rack. The purpose of rack-aware replica > placement is to improve data reliability, availability, and network bandwidth > utilization. The basic idea is that each data node determines to which rack > it belongs at the startup time and notifies the name node of the rack id upon > registration. The name node maintains a rackid-to-datanode map and tries to > place replicas across racks. -- This message is automatically generated by JIRA. - If you think it was sent incorrectly contact one of the administrators: http://issues.apache.org/jira/secure/Administrators.jspa - For more information on JIRA, see: http://www.atlassian.com/software/jira
