![](https://img-blog.csdnimg.cn/20201014180756925.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
Storage System
文章平均质量分 61
Kinges
科技改变世界,科技引领未来。
展开
-
ALUA --- Asymmetric Logic Unit Access
New failover mode on VNX: ALUA or Asymmetric Active/Active(ALUA --- Asymmetric Logic Unit Access)Based on ALUA(part of SCSI SPC-3 specification). In dual SP storage system, I/O can be routed throu转载 2013-02-04 11:04:07 · 4286 阅读 · 0 评论 -
SCSI锁 详解
何为SCSI锁?在一个共享存储的环境下,多台主机可能会同时访问同一台存储设备,如果此时多台主机在同一时点上对一个Lun进行写的操作,那么可想而知这个Lun将不知道哪个数据先写,哪个数据后写。为了防止这种情况发生而导致的数据损坏,于是就引入了SCSI锁的概念。如下图中HostA对Lun进行读写时,对Lun加上SCSI锁,此时HostB将无法对该Lun进行访问。原创 2013-12-25 08:15:28 · 12005 阅读 · 0 评论 -
SMI-S 存储管理 (1)
接下来的一段时间,我都会聚焦在这个技术上面,结合目前实际使用环境,把所有存储的配置信息和性能信息都拉取到服务器上,做分析。如果有这方的技术专家,可以与我联系,做出业界最专业的平台。++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++原创 2014-01-21 15:01:45 · 3860 阅读 · 3 评论 -
How dose SMI-S work?(2)
SMI-S use standard XML based communication methods to facilitate exchange between the client application, the SMI-S provider, and the storage device.How dose SMI-S work?SMI-S use sta原创 2014-01-22 10:51:26 · 1102 阅读 · 0 评论 -
How to set the I/O Queue depth on VMware ESX servers?
Product: CLARiiON CX4 Series, VNX Series Description: Performance analysis on the CLARiiON or VNX shows "Queue full" issues occurring on the FC ports and there is poor response time in VMw原创 2014-04-15 15:50:57 · 1148 阅读 · 0 评论 -
Server lost ASM luns with scsi edc_status message.
最近在linux主机上看到很多这样的报错:Sep 17 20:30:57 localhost kernel: scsi(4): The edc_status node should no longer be used.Sep 17 20:30:57 localhost kernel: scsi(4): The edc_status node should no longer be used原创 2014-06-27 22:40:41 · 2779 阅读 · 2 评论 -
Linux Host "Abort command issued"
I still investigate this issue, and it now narrow down after we hard work.Thanks my team mate.Something we alred原创 2014-09-15 16:29:33 · 5496 阅读 · 1 评论 -
Buffer I/O Error in /var/log/messages
主机报错信息:原创 2014-10-24 12:58:02 · 8519 阅读 · 0 评论 -
Brocade MAPS Description
1. It should support the hardwareplatforms as below:•Fixed-port swtich- Brocade300 switch- Brocade5100 switch- Brocade5300 switch- Brocade5410 embedded switch- Brocade5424 embedded sw原创 2014-10-10 11:07:54 · 1257 阅读 · 0 评论 -
Brocade MAPS Overview
Monitoring and Alerting Policy Suite原创 2014-10-04 21:27:51 · 1350 阅读 · 0 评论 -
Linux高并发导致(HDS)HNAS NODE Reset
最近接到了一个很奇怪的CASE,希望能在这里描述一下。NFS_Volume_01 挂载在NODE1上面,然后会有接近20台主机挂载了这个卷。当有大量并发访问该卷的时候,Node2出现了Reset。这个应该是SMU做出的判断,因为这个时候心跳出现了问题。证据如下:Warning: Cluster: Heart beating over high speed interconnect原创 2014-11-27 19:21:27 · 1855 阅读 · 0 评论 -
vmware workstation 命令行
最近做一个项目,需要用到workstation,但是为了提高效率,研究了一下命令脚本,分享一下我的所得有错误之处,还望指正:我是在windows下面的做的实验,首先要切换到对应的目录下面c:/Program Files/VMware/VMware Workstation下面有两个文件比较关键,一个是vmare.exe,一个是vmrun.exe两个命令的用途可以见插图原创 2015-05-14 18:48:23 · 6432 阅读 · 0 评论 -
Understanding SCSI Sense
This page is about decoding and interpreting the SCSI sense buffer in order totroubleshoot a disk or storage device problem.A SCSI sense buffer is the error reporting facility in SCSI. It reports th转载 2015-10-20 14:19:51 · 2419 阅读 · 0 评论 -
NPV 和 NPIV之间的区别
Two technologies that seem to have come to the fore recently are NPIV (N_Port ID Virtualization) and NPV (N_Port Virtualization). Judging just by the names, you might think that these two technologies原创 2014-01-01 22:37:38 · 6823 阅读 · 0 评论 -
How do I set up break reserves in parallel on AIX HACMP?
在AIX环境中,HACMP+Powerpath的情况下面,尤其是比较老的版本5.3,经常会碰到一些客户说HA切换时间很长,有的长达20多分钟才可以切换完成。显然这是不正常的,经过一些research发现,当primary的机器宕机时,secondary机器需要对之前的reservation lock做一个清除动作,但是这个工具之前是比较土的,一个一个的清除,导致磁盘过多的情况下,清除的非常缓慢原创 2013-12-10 08:03:10 · 1063 阅读 · 0 评论 -
HPUX LINUX AIX下的VG相关操作
HP UX将存储磁盘映射到HP UX主机使用ioscan命令扫描新增加的磁盘:#ioscan -fnCdisk如果是多路径的放,使用以下命令查看磁盘名与物理路径对应关系#ioscan -m dsf确定新建VG的磁盘:建VG(建议使用聚合后盘符,不要使用物理路径)1.建 pvpvcreate /dev/rdsk/disk314或者nodeA#[/]pvcr转载 2013-11-14 20:06:15 · 2947 阅读 · 0 评论 -
一些storage 的概念以及与VMware的关系
Active-Passive/ActiveThe default owner refers to which storage processor owns a LUN and is responsible for sending IOs to the backend disk. This is a critical differentiator to mention behind an en转载 2013-02-04 11:06:07 · 1183 阅读 · 0 评论 -
NetAPP proposed File service for OpenStack
NetApp (NASDAQ: NTAP) today announced it has submitted a prototype and proposal for a file share service capability for consideration by the OpenStack Foundation Technical Committee and community at l原创 2013-04-27 13:35:24 · 845 阅读 · 0 评论 -
Why do I have trespassed LUNs or all LUNs on one SP? --- Clinton Kitson
This post is going to focus on discussing different trespassing in a mid-range array and how it relates to ensuring an optimal storage configuration for ESX/i. In a VMware environment, storage is a c转载 2013-04-27 11:59:23 · 2312 阅读 · 0 评论 -
Veritas DMP and PowerPath configration in the same host [LINUX]
I have reference these doc for this topic.https://support.emc.com/docu42959_PowerPath-Linux-5.7-Installation-and-Administration-Guide.pdf?language=en_UShttp://sfdoccentral.symantec.com/sf/5.0/so原创 2013-05-14 09:29:30 · 1343 阅读 · 0 评论 -
Symmetrix Gatekeeper device 详解
1. What are the most important things to know about Gatekeepers?If the system selects and uses a data or system device as a Gatekeeper, applications on the application host can be impacted! EMC ST原创 2013-06-04 16:16:06 · 3362 阅读 · 0 评论 -
What is Device Pinning?
How do I prevent the movement of data related to thin devices under FAST VP control?EMC SW: Fully Automated Storage Tiering for Virtual Pools (FAST VP)Enginuity: 5875 Pinning a原创 2013-06-25 09:53:08 · 953 阅读 · 0 评论 -
Powerpath and VxVM work together mechanism
The below OPT 409550 could be a very good example for us to understand how Powerpath and VxVM are designed to work together from Engineering’s point of view. 10/30/2012 9:29:18 AM Sibel KamerThe原创 2013-07-23 14:28:20 · 1880 阅读 · 0 评论 -
LUNZ详解
LUNZ在日常运维中经常简单,也碰到少客户有碰到类似的问题,不知道如何处理。LUNZ,是在主机和存储之间还没有建立连接的时候,建立沟通桥梁的工具。(个人认为这句话已经是高度提炼过了)当存储有一个LUN 0 的设备MAP给主机的时候,LUNZ就可以功成身退了。另外,如果客户没有使用LUN0的设备,则需要disable arraycommpath。当然,disable这个参数是有代价的,还需要原创 2013-08-02 07:33:08 · 3545 阅读 · 0 评论 -
What does arraycommpath do?
当我们不需要CLARIION VNX存储与主机连接的时候,可以disable arraycompath 这个参数,这样在主机侧就不会有LUNZ的设备当需要有数据盘过去的时候,可以enable这个参数,这时候用一个LUN0的设备取代,主机侧也就不会有LUNZ的设备The arraycommpath option enables or disables a communication path原创 2013-08-02 06:50:01 · 1600 阅读 · 0 评论 -
Reservation policy from IBM
No Reserve reservationpolicy (不设置任何锁)If you set MPIO deviceswith this reserve policy, there is no reserve being made on MPIO devices. Adevice without reservation can be accessed by any initiators at原创 2013-08-29 07:08:13 · 774 阅读 · 0 评论 -
How to rename the powerpath pseudo disk name using "emcpadm"?
Please refer the Picture.原创 2013-11-01 07:49:05 · 1734 阅读 · 0 评论 -
Introuduce all the Powerpath Policy
Please refer the picture:if you have any quetions, please leave message.原创 2013-11-21 13:50:43 · 807 阅读 · 0 评论 -
Brocade SAN Switch CFG backup and recover
通常,我们在执行SAN交换机变更之前,需要先对SAN交换机的配置做一次备份,尤其是在删除ZONE配置,或者一些其他重大变更。那么本文主要探讨如何来做SAN交换机的备份和恢复。1. 备份switch:admin> configuploadProtocol (scp or ftp) [ftp]: ftpServer Name or IP Address [host]:原创 2015-12-30 21:00:39 · 1506 阅读 · 0 评论