Hi, I read codes about hash now and tried to do something. I need some comments to do it properly. Strategy 1 (We used now) Random tokens per node Partition by random token. The partition token is produced by hash function with node IP/port. Strategy 2 Random tokens per node Equal sized partitions. The hash space is divided into Q equally sized partitions. Q is the number of nodes or vnodes. Strategy 3 Random tokens per node Equal sized partitions. When there is node join/leaving, the equal size may be broken to minimize the data movement. For strategy 3, need write hash space to disk. I think I can use the object to record the infomation. Do we need add the strategy 2/3, or there is better strategies? Thanks Haiti -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.wpkg.org/pipermail/sheepdog/attachments/20120504/80543ae5/attachment.html> |