Replicated database distribution for workload balancing after cluster reconfiguration

Abstract

A computer-implemented method for distributing a plurality of data partitions among a cluster of computer nodes includes dividing a database into a plurality of primary partitions, storing the primary partitions on a plurality of nodes associated with a computer network, duplicating the primary partitions to create a plurality of secondary partitions and storing the secondary partitions on the nodes, wherein the primary and secondary partitions are substantially evenly distributed among the nodes, each secondary partition is stored on a different node than its corresponding primary partition, diversity exists with respect to each secondary partition and the node where it is stored, the primary partitions are available to serve a system workload, and one or more secondary partitions corresponding to one or more primary partitions of a failed node are available to be upgraded to primary status to maintain workload balancing and data availability after one of the computer nodes fails.

Description

[0001] Related Applications Cross Application [0002] This application claims prior application priority to U.S. Nonprovisional Patent Application No. 14 / 577,629, filed December 19, 2014, entitled "Replicated Database Distribution for Workload Balancing After Cluster Reconfiguration" , the content of this prior application is incorporated herein by reference. technical field [0003] The present invention relates generally to distributed databases, and more particularly to the layout of replicated partitions of distributed relational databases on network computer nodes. Background technique [0004] Databases are used to store information and relationships between pieces of information. Some databases are stored in a distributed file system on multiple computers by a single network or by multiple interconnected networks. Typically, a database is divided into partitions of equal, similar, or unequal size, and one or more partitions of informational data are stored in memor...

AI Technical Summary

Problems solved by technology

Similarly, when a new node is attached to the ring, that node only shares the workload of adjacent servers in the ring, resulting in an unbalanced workload

While such an unbalanced workload can be reasonably tolerated in a cluster comprising tens of thousands of nodes, the same level of workload imbalance can have a large negative impact on performance in an MPP database

Since both throughput and latency are of considerable importance, it turns out that some existing file allocation methods have disadvantages when used in MPP database systems

Images