• UCS内存问题排查


    UCS使用双列直插式内存模块(Dual In-line Memory Module (DIMM) )作为RAM模块。

    根据文档介绍,主要有如下部分:
    1、Memory placement 《内存放置》
    2、Troubleshoot DIMM’s via UCSM and CLI 《通过UCSM和CLI来排查DIMM》
    3、Logs to check in tech support 《登录检查tech-support>

    来自 <https://www.cisco.com/c/en/us/support/docs/servers-unified-computing/ucs-b-series-blade-servers/200775-Troubleshoot-DIMM-memory-issues-in-UCS.html>

    一些术语和关键词:

    Memory Placement

    内存放置可能是UCS中最值得注意的物理方面之一。通常,UCS附带了预先填充了请求数量的内存。
    安装方面,可以参考安装指南:
    https://www.cisco.com/c/en/us/td/docs/unified_computing/ucs/hw/blade-servers/install/B200.html#wp1035141

    有关内存填充规则,请参阅B系列特定平台的技术规范,如下是B系列技术规格的链接:
    http://www.cisco.com/c/en/us/products/servers-unified-computing/ucs-b-series-blade-servers/datasheet-listing.html

    Memory Error

    Correctable vs. Uncorrectable Errors》》》可纠正与不可纠正的错误

    Whether a particular error is correctable or uncorrectable depends on the strength of the ECC code employed within the memory system. Dedicated hardware is able to fix correctable errors when they occur with no impact on program execution.

    The DIMMs with correctable error are not disabled and are available for the OS to use. The Total Memory and Effective Memory be the same (taking memory mirroring into account). These correctable errors reported in UCSM operability state as Degraded while overall operability Operable with correctable errors.

    Uncorrectable errors generally cannot be fixed, and may make it impossible for the application or operating system to continue execution. The DIMMs with uncorrectable error is disabled and OS does not see that memory. UCSM operState change to ""Inoperable"" in this case.

    特定错误是可纠正还是不可纠正取决于存储器系统内采用的ECC代码的强度。 专用硬件能够在发生错误时修复可纠正的错误,而不会影响程序执行。
    具有可纠正错误的DIMM未禁用,可供操作系统使用。 总内存和有效内存相同(考虑内存镜像)。 在UCSM可操作性状态中报告的这些可纠正错误为Degraded,而总体可操作性可操作且具有可纠正的错误。
    通常不能修复无法纠正的错误,并且可能使应用程序或操作系统无法继续执行。 具有无法纠正错误的DIMM被禁用,操作系统看不到该内存。 在这种情况下,UCSM operState更改为“Inoperable ”。

    通过UCSM和CLI来排查DIMM

    通过GUI检查Errors:

    为了获取统计视图:
    Equipment > Chassis > Server > Inventory > Memory 然后针对对应的memory右击,选择 show navigator.

    通过CLI来检查errors:

    scope server x/y -> show memory detail
    scope server x/y -> show memory-array detail
    scope server x/y -> scope memory-array x -> show stats history memory-array-env-stats detail

    Eg:
    UCS-A# scope server 1/3
    UCS-A /chassis/server # show memory detail
    UCS-A /chassis/server # show memory-array detail
    UCS-A /chassis/server # scope memory-array x 
    UCS-A /chassis/server #show stats history memory-array-env-stats detail

    还可以访问DIMM:
    UCS-A# scope server 1/3
    UCS-A /chassis/server # scope memory-array x 
    UCS-A /chassis/server/memory-array #scope DIMM x 

    然后,您可以从中获取每DIMM统计信息或重置错误计数。
    bdsol-6248-06-B /chassis/server/memory-array/dimm # reset-errors
    bdsol-6248-06-B /chassis/server/memory-array/dimm* # commit-buffer
    bdsol-6248-06-B /chassis/server/memory-array/dimm # show stats memory-error-state

    好好学习,天天向上!
  • 相关阅读:
    Linux内核中的红黑树
    研究UEVENT相关东西,看到2篇优秀的博文,转载与此
    Nor Nand OneNand
    Linux设备模型(总线、设备、驱动程序和类)
    linux驱动的入口函数module_init的加载和释放(转)
    hwclock(Linux)
    Linux块设备驱动
    pdflush内核线程池及其中隐含的竞争
    Nand Flash与Nor Flash
    linux内核I2C体系结构(注意结构体原型)
  • 原文地址:https://www.cnblogs.com/MomentsLee/p/10006505.html
Copyright © 2020-2023  润新知