Systems and methods for trap monitoring in multi-core and cluster systems
US9294381B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 12, 2013 |
| Grant date | Mar 22, 2016 |
| Priority date | — |
| Expiry date | Mar 22, 2034 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L41/0609
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
In a multi-core device or clustered system, instead of snmpd polling for configured monitoring values of an entity to determine if reached a threshold, each core in a multi-core system or node in a clustered system triggers information to the snmpd about entities that may be or are generating SNMP traps. A configured threshold T is distributed among the cores or nodes, as the case may be, based on the number of cores or nodes. If there are ‘n’ cores in a multi-core device, and the configured threshold is ‘T’, then each core checks for a per-core threshold value ‘T/n’. If there are ‘n’ nodes in a clustered system, and the configured threshold is ‘T’, then each node checks for a per-node threshold value ‘T/n’. According to the pigeonhole principle, if an entity has reached or exceeded the threshold ‘T’, then the entity must have reached or exceeded a value of ‘T/n’ on at least one core or node. Upon the entity crossing a ‘T/n’ value on any core or node, the core or node informs snmpd about this entity. Snmpd then gathers information about this entity from all the cores and checks for the threshold ‘T’.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.