AHRW pre-aggregates input objects into specified number of slots and only then distributes these slots across provided nodes. It allows memoization of calculations made for each slot and makes rendezvous hashing practical for large numbers of nodes (or shares of capacity for weighted case) and/or high request rates.
-
Notifications
You must be signed in to change notification settings - Fork 0
Aggregated Highest Random Weight Hashing / Aggregated Rendezvous Hashing
License
SenseUnit/ahrw
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Aggregated Highest Random Weight Hashing / Aggregated Rendezvous Hashing