Server node data cache method based on limited data consistency state

Abstract

The invention discloses a server node data cache method based on a limited data consistency state, which comprises the following steps of 1), sending out memory information, and judging whether a memory address index is matched correctly, and whether a data consistency authority meets an access requirement, 2), reading far end data or local data of a consistency monopolization state, a sharing state and a forwarding state from a far end data cache or a local data cache of a node controller of a requested party, and 3), only writing the far end data or the local data of the consistency monopolization state, the sharing state and the forwarding state into a far end data cache or a local data cache of a node controller of a requesting party. The method can effectively reduce across node access frequency and avoid extra overhead arising from node data cache replacement, can achieve balance control of the redundancy and the performance, and can avoid replacement crosstalk in a unified catalogue, so that the system performance of a server is improved greatly.

Description

technical field [0001] The invention relates to the field of computer architecture, in particular to a server node data caching method based on limited data consistency state. Background technique [0002] Due to the limitation of the number of interconnection ports of server processors, it is difficult to build a large-scale CC-NUMA computer system through direct connection of processors; therefore, large-scale CC-NUMA computer systems are usually based on node clusters (clump or node) unit. Each node cluster is composed of 2-4 server processors and 1-2 node controllers. The node controllers are first interconnected with each server processor to form the first-level interconnection domain and cache coherency domain, and then the node control The second-level interconnection domain and cache coherency domain are formed by direct connection between the processors or interconnection through node routers; the limitation of the processor itself can be overcome through the two-l...

AI Technical Summary

Problems solved by technology

[0006] At the same time, the data cache consistency state of the node controller cache has a certain impact on the performance of the node controller. If the cached data state is a modified state, if the processor in the node has a copy of the modified state data, it is likely to be updated again. is modified, so that the data in the node data cache is not the latest value, resulting in data invalidation. On the one hand, this reduces the effectiveness of the node data cache, and on the other hand, it requires additional logic to judge the effectiveness of the modified status data in the cache.

In addition, due to the limited capacity of the node data cache, even if the modified state data cached by the node is the latest copy, it may be replaced. During the replacement process, complex logic is required to ensure that the modified state data is written back to the root processor, while ensuring that the new data is Correctly written, at this time the system logic is likely to need to be executed serially, thereby reducing the efficiency of the system

Images