使用edac工具来检测服务器内存故障.

您所在的位置:网站首页 edac培训 使用edac工具来检测服务器内存故障.

使用edac工具来检测服务器内存故障.

2024-06-29 15:43| 来源: 网络整理| 查看: 265

随着虚拟化,Redis,BDB内存数据库等应用的普及,现在越来越多的服务器配置了大容量内存,拿DELL的R620来说在配置双路CPU下,其24个内存插槽,支持的内存高达960GB。对于ECC,REG这些带有纠错功能的内存故障检测是一件很头疼的事情,出现故障,还是可以连续运行几个月甚至几年,但如果运气不好,随时都会挂掉,好在linux中提供了一个edac-utils 内存纠错诊断工具,可以用来检查服务器内存潜在的故障。下面以CentOS为例,介绍下edac-utils 工具的使用.在使用edac-utils 工具之前,需要先了解服务器的硬件架构,以DELL R620为例,(其它如HP DL360P G8,IBM X3650 M4 机型都使用了 E5-2600 系列CPU,C600 系列芯片组.大致相同) 其CPU内存控制器对应通道,内存槽关系,如下所示。

处理器0 (对应一个内存控制器)通道0:内存插槽A1、A5 和A9通道1:内存插槽A2、A6 和A10通道2:内存插槽A3、A7 和A11通道3:内存插槽A4、A8 和A12

处理器1 (对应一个内存控制器)通道0:内存插槽B1、B5 和B9通道1:内存插槽B2、B6 和B10通道2:内存插槽B3、B7 和B11通道3:内存插槽B4、B8 和B12

1.安装 edac-utils 工具

yum install -y libsysfs edac-utils2.执行检测命令,可查看纠错提示如下

edac-util -v

mc0: csrow0: CPU_SrcID#0_Ha#0_Chan#0_DIMM#0: A1mc0: csrow0: CPU_SrcID#0_Ha#0_Chan#1_DIMM#0: A2mc0: csrow0: CPU_SrcID#0_Ha#0_Chan#2_DIMM#0: A3mc0: csrow0: CPU_SrcID#0_Ha#0_Chan#3_DIMM#0: A4mc0: csrow1: CPU_SrcID#0_Ha#0_Chan#0_DIMM#1: A5mc0: csrow1: CPU_SrcID#0_Ha#0_Chan#1_DIMM#1: A6mc0: csrow1: CPU_SrcID#0_Ha#0_Chan#2_DIMM#1: A7mc0: csrow1: CPU_SrcID#0_Ha#0_Chan#3_DIMM#1: A8mc0: csrow2: CPU_SrcID#0_Ha#0_Chan#0_DIMM#2: A9mc0: csrow2: CPU_SrcID#0_Ha#0_Chan#1_DIMM#2: A10mc0: csrow2: CPU_SrcID#0_Ha#0_Chan#2_DIMM#2: A11mc0: csrow2: CPU_SrcID#0_Ha#0_Chan#3_DIMM#2: A12

mc1: csrow0: CPU_SrcID#1_Ha#0_Chan#0_DIMM#0: B1mc1: csrow0: CPU_SrcID#1_Ha#0_Chan#1_DIMM#0: B2mc1: csrow0: CPU_SrcID#1_Ha#0_Chan#2_DIMM#0: B3mc1: csrow0: CPU_SrcID#1_Ha#0_Chan#3_DIMM#0: B4mc1: csrow1: CPU_SrcID#1_Ha#0_Chan#0_DIMM#1: B5mc1: csrow1: CPU_SrcID#1_Ha#0_Chan#1_DIMM#1: B6mc1: csrow1: CPU_SrcID#1_Ha#0_Chan#2_DIMM#1: B7mc1: csrow1: CPU_SrcID#1_Ha#0_Chan#3_DIMM#1: B8mc1: csrow2: CPU_SrcID#1_Ha#0_Chan#0_DIMM#1: B9mc1: csrow2: CPU_SrcID#1_Ha#0_Chan#1_DIMM#1: B10mc1: csrow2: CPU_SrcID#1_Ha#0_Chan#2_DIMM#1: B11mc1: csrow2: CPU_SrcID#1_Ha#0_Chan#3_DIMM#1: B12

其中 mc0 表示 表示内存控制器0, CPU_Src_ID#0表示源CPU0 , Channel#0 表示通道0DIMM#0 标示内存槽0,Corrected Errors 代表已经纠错的次数,根据前面列出的CPU通道和内存槽对应关系即可给edac-utils 返回的信息进行编号。即可得出 A1槽 6312 次纠错,B1槽 6459次纠错,B3槽 535次纠错. 3条内存出现潜在故障,接下来联系供应商进行更换即可。

12条内存的对应关系mc0: csrow0: CPU#0Channel#0_DIMM#0: A1mc0: csrow0: CPU#0Channel#1_DIMM#0: A2mc0: csrow0: CPU#0Channel#2_DIMM#0: A3mc0: csrow1: CPU#0Channel#0_DIMM#1: A4mc0: csrow1: CPU#0Channel#1_DIMM#1: A5mc0: csrow1: CPU#0Channel#2_DIMM#1: A6

mc1: csrow0: CPU#1Channel#0_DIMM#0: B1mc1: csrow0: CPU#1Channel#1_DIMM#0: B2mc1: csrow0: CPU#1Channel#2_DIMM#0: B3mc1: csrow1: CPU#1Channel#0_DIMM#1: B4mc1: csrow1: CPU#1Channel#1_DIMM#1: B5mc1: csrow1: CPU#1Channel#2_DIMM#1: B6

20条内存的对应关系mc0: 0 Uncorrected Errors with no DIMM infomc0: 0 Corrected Errors with no DIMM infomc0: csrow0: 0 Uncorrected Errorsmc0: csrow0: CPU_SrcID#0_Ha#0_Chan#0_DIMM#0: 0 Corrected Errors A1mc0: csrow0: CPU_SrcID#0_Ha#0_Chan#1_DIMM#0: 0 Corrected Errors B1mc0: csrow0: CPU_SrcID#0_Ha#0_Chan#2_DIMM#0: 0 Corrected Errors C1mc0: csrow0: CPU_SrcID#0_Ha#0_Chan#3_DIMM#0: 0 Corrected Errors D1mc0: csrow1: 0 Uncorrected Errorsmc0: csrow1: CPU_SrcID#0_Ha#0_Chan#0_DIMM#1: 0 Corrected Errors A2mc0: csrow1: CPU_SrcID#0_Ha#0_Chan#1_DIMM#1: 0 Corrected Errors B2mc0: csrow1: CPU_SrcID#0_Ha#0_Chan#2_DIMM#1: 0 Corrected Errors C2mc0: csrow1: CPU_SrcID#0_Ha#0_Chan#3_DIMM#1: 0 Corrected Errors D2mc0: csrow2: 0 Uncorrected Errorsmc0: csrow2: CPU_SrcID#0_Ha#0_Chan#0_DIMM#2: 0 Corrected Errors A3mc0: csrow2: CPU_SrcID#0_Ha#0_Chan#1_DIMM#2: 11 Corrected Errors B3mc0: csrow2: CPU_SrcID#0_Ha#0_Chan#2_DIMM#2: 0 Corrected Errors C3mc0: csrow2: CPU_SrcID#0_Ha#0_Chan#3_DIMM#2: 0 Corrected Errors D3mc1: 0 Uncorrected Errors with no DIMM infomc1: 0 Corrected Errors with no DIMM infomc1: csrow0: 0 Uncorrected Errorsmc1: csrow0: CPU_SrcID#1_Ha#0_Chan#0_DIMM#0: 0 Corrected Errors mc1: csrow0: CPU_SrcID#1_Ha#0_Chan#1_DIMM#0: 0 Corrected Errors mc1: csrow0: CPU_SrcID#1_Ha#0_Chan#2_DIMM#0: 0 Corrected Errorsmc1: csrow0: CPU_SrcID#1_Ha#0_Chan#3_DIMM#0: 0 Corrected Errorsmc1: csrow1: 0 Uncorrected Errorsmc1: csrow1: CPU_SrcID#1_Ha#0_Chan#0_DIMM#1: 0 Corrected Errorsmc1: csrow1: CPU_SrcID#1_Ha#0_Chan#1_DIMM#1: 0 Corrected Errorsmc1: csrow1: CPU_SrcID#1_Ha#0_Chan#2_DIMM#1: 0 Corrected Errorsmc1: csrow1: CPU_SrcID#1_Ha#0_Chan#3_DIMM#1: 0 Corrected Errors

4x16关系mc0: csrow0: CPU#0Channel#0_DIMM#0: 0 Corrected Errors 8amc0: csrow0: CPU#0Channel#1_DIMM#0: 0 Corrected Errors 5bmc0: csrow0: CPU#0Channel#2_DIMM#0: 0 Corrected Errors 2cmc0: csrow1: 0 Uncorrected Errorsmc0: csrow1: CPU#0Channel#0_DIMM#1: 1 Corrected Errors 7dmc0: csrow1: CPU#0Channel#1_DIMM#1: 0 Corrected Errors 4emc0: csrow1: CPU#0Channel#2_DIMM#1: 0 Corrected Errors 1fmc0: csrow2: 0 Uncorrected Errorsmc0: csrow2: CPU#0Channel#0_DIMM#2: 0 Corrected Errors 6Gmc0: csrow2: CPU#0Channel#1_DIMM#2: 0 Corrected Errors 3h



【本文地址】


今日新闻


推荐新闻


CopyRight 2018-2019 办公设备维修网 版权所有 豫ICP备15022753号-3