Query execution and optimization with autonomic error recovery from network failures in a parallel computer system with multiple networks

摘要

A database query execution monitor determines if an network error or low performance condition exists and then where possible modifies the query. The query execution monitor then determines an alternate query execution plan to continue execution of the query. The query optimizer can re-optimize the query to use a different network or node. Thus, the query execution monitor allows autonomic error recovery for network failures using an alternate query execution. The alternate query execution could also be determined at the initial optimization time and then this alternate plan used to execute a query in the case of a particular network failure.

主权项

1. A computer implemented method for optimizing a query on a parallel computer system comprising the steps of:
receiving a query to a database; optimizing the query by generating an execution plan that includes using a network of a plurality of independent networks to execute the query; initiating the query execution; monitoring the query execution; monitoring the plurality of independent networks and recording information about network utilization for the plurality of independent networks in a network file; detecting a network failure based on the information in the network file indicating a network resource is below a threshold; and in response to the detected network failure, optimizing to re-optimize the query by generating an alternate execution plan for the query to use a different independent network to execute the query where the different independent network is selected by the query optimizer based on the information in the network file; wherein the network file comprises: network ID, a timestamp; current utilization, future utilization, availability, latency, and retransmits.