Method and system of fast breakdown location of multiple extensible memories based on BMC control

Abstract

The invention discloses a method and system of fast breakdown location of multiple extensible memories based on BMC control. The method comprises the steps that a BMC chip is selected as a master control chip, wherein the BMC chip is connected to a multi-channel selection chip through an I2C-bus, and the multi-channel selection chip is connected to an LED lamp through a GPIO signal; when a memory bank breaks down, breakdown information is sent to a CPU; a PCH South Bridge obtains information of all memory banks through a DMI, and then the information is sent to the BMC chip through an LPC-bus; the BMC chip collects and organizes information data of the broken-down memory bank; a monitor button is connected to an outer pin of the BMC chip, when the monitor button is pressed, an instruction of checking the broken-down memory bank is sent to the BMC chip, and then the BMC chip controls and turns on the LED lamp. According to the method and system of the fast breakdown location of the multiple extensible memories based on the BMC control, the efficiency of broken-down memory location is greatly improved, not only is hardware space saved, but also the labor cost is saved to some extent, the efficiency is improved, and thus the production cost is reduced to some extent.

Description

technical field [0001] The invention relates to the technical field of computer data storage, in particular to a method and system for rapidly locating multi-memory faults based on BMC control. Background technique [0002] With the continuous development of information technology, the application of servers is more extensive, and higher requirements are put forward for the performance configuration of servers. The number of memory cards that can be supported by a single board of a server has reached dozens. Quickly locate the fault location of the detected memory card slot, so as to replace or maintain the memory module. [0003] Traditional memory fault detection mainly relies on two methods: one is to rely on memory pressure testing. After the preliminary judgment is that it is a memory fault, it is necessary to locate which memory has a fault from more than a dozen memories, and use memory pressure testing tools to test the system platform. Batch testing with the memory...

AI Technical Summary

Problems solved by technology

The limitation of this method is that the content of the generated log files is complicated, and the staff needs to carefully study the contents of the error log, and browse a large number of log files to find the log information of each memory one by one. Locating the exact location of the faulty memory

Images