RHEL5.8 下Infiniband驱动安装(3)

日期：2020-05-31 栏目：程序人生浏览：次

rpm -e --allmatches --nodeps kmod-mlnx-ofa_kernel-xen-1.5.3-OFED.1.5.3.4.0.42.g3cb72fe.rhel5u8libnes-1.1.1mlnx1-1 libcxgb3-1.3.1-1 libmverbs-0.1.0-3.15.gd28970elibibmad-1.3.8.MLNX_20120424-0.1 libmthca-1.0.6mlnx1-0.1.gbe5eef3 libibumad-1.3.7.MLNX_20130110_ff06102-0.1libibverbs-1.1.5mlnx2-1 libmlx4-1.0.2mlnx6-1 librdmacm-1.0.15-1kernel-mft-2.7.1-2.6.18_308.el5 libmverbs-0.1.0-3.15.gd28970elibipathverbs-1.2mlnx1-1 libibmad-1.3.8.MLNX_20120424-0.1mlnx-ofa_kernel-1.5.3-OFED.1.5.3.4.0.42.g3cb72fe.rhel5u8libibverbs-utils-1.1.5mlnx2-1 libcxgb3-1.3.1-1 mstflint-1.4mlnx4-1.21.gd948dddlibmlx4-1.0.2mlnx6-1 librdmacm-1.0.15-1 libmthca-1.0.6mlnx1-0.1.gbe5eef3libibumad-1.3.7.MLNX_20130110_ff06102-0.1 libibverbs-1.1.5mlnx2-1 librdmacm-utils-1.0.15-1mlnxofed-docs-1.5.3-4.0.42 libipathverbs-1.2mlnx1-1kmod-mlnx-ofa_kernel-1.5.3-OFED.1.5.3.4.0.42.g3cb72fe.rhel5u8libnes-1.1.1mlnx1-1 kernel-mft-2.7.1-2.6.18_308.el5ofed-scripts-1.5.3-OFED.1.5.3.4.0.42 mft-2.7.1a-1

Uninstall finished successfully

[root@node33 ~]#rm –rf/etc/infiniband

[root@node33 ~]#

4 排错

4.1 查看IB工作状态

[root@node33 ~]# ibstat

CA 'mlx4_0'

CAtype: MT26428

Numberof ports: 1

Firmwareversion: 2.9.1000

Hardwareversion: b0

NodeGUID: 0x0002c903000cc00e

Systemimage GUID: 0x0002c903000cc011

Port 1:

State:Active

Physicalstate: LinkUp

Rate:40

Baselid: 1

LMC:0

SMlid: 1

Capabilitymask: 0x0251086a

PortGUID: 0x0002c903000cc00f

Linklayer: InfiniBand

[root@node33 ~]#

4.2 查看hosts信息

[root@node33 ~]# ibhosts

Ca :0x0002c903000cc00a ports 1 "node34 HCA-1"

Ca :0x0002c903000cc00e ports 1 "node33 HCA-1"

[root@node33 ~]#

4.3 查看switch信息

[root@node33 ~]# ibswitches

Switch :0x0002c9020042bcc0 ports 36 "MF0;switch-1140a2:IS5030/U1" enhancedport 0 lid 4 lmc 0

[root@node33 ~]#

4.4 查看拓扑信息

[root@node33 ~]#ibnetdiscover

# Topology file: generated on Sun Mar 8 19:53:35 2015

# Initiated from node 0002c903000cc00e port0002c903000cc00f

vendid=0x2c9

devid=0xbd36

sysimgguid=0x2c9020042bcc3

switchguid=0x2c9020042bcc0(2c9020042bcc0)

Switch 36"S-0002c9020042bcc0" #"MF0;switch-1140a2:IS5030/U1" enhanced port 0 lid 4 lmc 0

[30] "H-0002c903000cc00e"[1](2c903000cc00f) # "node33 HCA-1" lid 14xQDR

[31] "H-0002c903000cc00a"[1](2c903000cc00b) # "node34HCA-1" lid 7 4xQDR

vendid=0x2c9

devid=0x673c

sysimgguid=0x2c903000cc00d

caguid=0x2c903000cc00a

Ca 1"H-0002c903000cc00a" #"node34 HCA-1"

[1](2c903000cc00b) "S-0002c9020042bcc0"[31] # lid 7 lmc 0"MF0;switch-1140a2:IS5030/U1" lid 4 4xQDR

vendid=0x2c9

devid=0x673c

sysimgguid=0x2c903000cc011

caguid=0x2c903000cc00e

Ca 1"H-0002c903000cc00e" #"node33 HCA-1"

[1](2c903000cc00f) "S-0002c9020042bcc0"[30] # lid 1 lmc 0"MF0;switch-1140a2:IS5030/U1" lid 4 4xQDR

[root@node33 ~]#

4.5 查看报错统计信息

[root@node33 ~]# ibdiagnet -Pall=1

Loading IBDIAGNET from:/opt/ibutils/lib64/ibdiagnet1.5.7

-W- Topology file is not specified.

Reportsregarding cluster links will use direct routes.

Loading IBDM from: /opt/ibutils/lib64/ibdm1.5.7

-I- Using port 1 as the local port.

-I- Discovering ... 3 nodes (1 Switches & 2 CA-s)discovered.