gpfs 多路径问题

gpfs4.1,centos7.3 初始化的时候就是不好用,错误如下

[root@gpfs ~]#  mmcrfs fpofs0 -F /etc/gpfsdisk_profile -B 1m -n 16 -m2 -M2 -r2 -R2 -T /gpfs/fpofs0 -A yes -i 4096 -S relatime -E no

The following disks of fpofs0 will be formatted on node gpfs.node2.com:

    fpo_linux1_NSD_Data_11: size 614400 MB

    fpo_linux1_NSD_Data_22: size 614400 MB

Formatting file system ...

Disks up to size 5.2 TB can be added to storage pool system.

Creating Inode File



日志提示:

Jan 24 15:49:22 gpfs multipathd: gpfs_a: remaining active paths: 1

Jan 24 15:49:22 gpfs kernel: device-mapper: multipath: Failing path 8:96.

Jan 24 15:49:22 gpfs kernel: device-mapper: multipath: Reinstating path 8:112.

Jan 24 15:49:22 gpfs kernel: blk_cloned_rq_check_limits: over max size limit.

Jan 24 15:49:22 gpfs multipathd: gpfs_b: sdh - tur checker reports path is up

Jan 24 15:49:22 gpfs kernel: device-mapper: multipath: Failing path 8:112.

Jan 24 15:49:22 gpfs multipathd: 8:112: reinstated

Jan 24 15:49:22 gpfs multipathd: gpfs_b: remaining active paths: 1

Jan 24 15:49:22 gpfs multipathd: sdg: mark as failed

Jan 24 15:49:22 gpfs multipathd: gpfs_a: remaining active paths: 0

Jan 24 15:49:22 gpfs multipathd: sdh: mark as failed

Jan 24 15:49:22 gpfs multipathd: gpfs_b: remaining active paths: 0

Jan 24 15:49:23 gpfs kernel: device-mapper: multipath: Reinstating path 8:16.

Jan 24 15:49:23 gpfs kernel: blk_cloned_rq_check_limits: over max size limit.

Jan 24 15:49:23 gpfs multipathd: gpfs_a: sdb - tur checker reports path is up

Jan 24 15:49:23 gpfs multipathd: 8:16: reinstated

Jan 24 15:49:23 gpfs multipathd: gpfs_a: remaining active paths: 1

Jan 24 15:49:23 gpfs kernel: device-mapper: multipath: Failing path 8:16.

Jan 24 15:49:23 gpfs multipathd: sdb: mark as failed

Jan 24 15:49:23 gpfs multipathd: gpfs_a: remaining active paths: 0

Jan 24 15:49:24 gpfs multipathd: gpfs_b: sdc - tur checker reports path is up

Jan 24 15:49:24 gpfs kernel: device-mapper: multipath: Reinstating path 8:32.

Jan 24 15:49:24 gpfs kernel: blk_cloned_rq_check_limits: over max size limit.

Jan 24 15:49:24 gpfs multipathd: 8:32: reinstated

Jan 24 15:49:24 gpfs kernel: device-mapper: multipath: Failing path 8:32.

Jan 24 15:49:24 gpfs multipathd: gpfs_b: remaining active paths: 1

Jan 24 15:49:25 gpfs multipathd: sdc: mark as failed

Jan 24 15:49:25 gpfs multipathd: gpfs_b: remaining active paths: 0

参与11

6同行回答

chinesezzqiangchinesezzqiang课题专家组信息技术经理M
安装多路径软件。显示全部

安装多路径软件。

收起
IT其它 · 2020-05-07
浏览2820
zwz99999zwz99999系统工程师dcits
安装hds的多路径软件hdlm 显示全部

安装hds的多路径软件hdlm

收起
系统集成 · 2017-02-06
浏览5882
menkeyimenkeyi技术经理睿智大数据
这个东西还需驱动么?显示全部

这个东西还需驱动么?

收起
系统集成 · 2017-01-24
浏览5791
jiaxu2000jiaxu2000系统工程师沈阳医学院附属中心医院
HITACHI的存储?没用过,找找文档吧,可能需要rdac或日立其他的驱动显示全部

HITACHI的存储?没用过,找找文档吧,可能需要rdac或日立其他的驱动

收起
事业单位 · 2017-01-24
浏览5881
menkeyimenkeyi技术经理睿智大数据
fc-san  2台机器共享一个LUN   ,不知道为什么执行这个命令,multipath的状态就是失败了failed ready running[root@gpfs ~]# multipath -llgpfs_b (360060e8010352240057f1cf400000027) dm-6 HITACHI ,DF600F     size=600G featur...显示全部

fc-san  2台机器共享一个LUN   ,不知道为什么执行这个命令,multipath的状态就是失败了failed ready running


[root@gpfs ~]# multipath -ll

gpfs_b (360060e8010352240057f1cf400000027) dm-6 HITACHI ,DF600F     

size=600G features=\'1 queue_if_no_path\' hwhandler=\'0\' wp=rw

`-+- policy=\'service-time 0\' prio=1 status=enabled

  |- 1:0:0:1 sdc 8:32  failed ready running

  `- 1:0:1:1 sdh 8:112 failed ready running

gpfs_a (360060e8010352240057f1cf400000026) dm-5 HITACHI ,DF600F     

size=600G features=\'1 queue_if_no_path\' hwhandler=\'0\' wp=rw

`-+- policy=\'service-time 0\' prio=0 status=enabled

  |- 1:0:0:0 sdb 8:16  failed ready running

  `- 1:0:1:0 sdg 8:96  failed ready running

收起
系统集成 · 2017-01-24
浏览5870
jiaxu2000jiaxu2000系统工程师沈阳医学院附属中心医院
fpo架构还是传统架构?看提示好像是node2不能访问node1上的磁盘显示全部

fpo架构还是传统架构?看提示好像是node2不能访问node1上的磁盘

收起
事业单位 · 2017-01-24
浏览5880

提问者

menkeyi
技术经理睿智大数据
擅长领域: 服务器分布式系统双活

相关问题

相关资料

相关文章

问题状态

  • 发布时间:2017-01-24
  • 关注会员:4 人
  • 问题浏览:10073
  • 最近回答:2020-05-07
  • X社区推广