My Oracle Support Banner

Exadata IB Switch - "getmaster" returns "No Master SubnetManager seen in the system" (Doc ID 1334834.1)

Last updated on AUGUST 22, 2023

Applies to:

Oracle Exadata Hardware - Version 11.1.0.6 and later
Information in this document applies to any platform.

Symptoms

You have two or more Exadata RACKs connected together.

You run the command "getmaster" to determine which spine switch is the Subnet Master on the Infiniband switches, and the results show "No Master SubnetManager seen in the system" from one of the spine switches.

For example, here is the output from a multi-RACK environment:


exa1-ib1: ibwarn: [12778] mad_rpc: _do_madrpc failed; dport (Lid 2)
exa1-ib1: sminfo: iberror: failed: query
exa1-ib1: Local SM enabled and running
exa1-ib1: 20110519 15:09:16 No Master SubnetManager seen in the system
exa1-ib2: sminfo: sm lid 2 sm guid 0x2128468ce2a0a0, activity count 12727305 priority 14 state 3 SMINFO_MASTER
exa1-ib2: Local SM enabled and running
exa1-ib2: 20110519 15:00:33 Master SubnetManager on sm lid 2 sm guid 0x2128468ce2a0a0 : SUN DCS 36P QDR xxx--ib1.xxxx.com
exa1-ib3: sminfo: sm lid 2 sm guid 0x2128468ce2a0a0, activity count 12727304 priority 14 state 3 SMINFO_MASTER
exa1-ib3: Local SM enabled and running
exa1-ib3: 20110519 15:42:05 Master SubnetManager on sm lid 2 sm guid 0x2128468ce2a0a0 : SUN DCS 36P QDR xxx--ib1.xxxx.com

xxx--ib1: sminfo: sm lid 2 sm guid 0x2128468ce2a0a0, activity count 12727407 priority 14 state 3 SMINFO_MASTER
xxx--ib1: Local SM enabled and running
xxx--ib1: 20110518 10:37:52 Master SubnetManager on sm lid 2 sm guid 0x2128468ce2a0a0 : SUN DCS 36P QDR xxx--ib1.xxxx.com
xxx--ib2: sminfo: sm lid 2 sm guid 0x2128468ce2a0a0, activity count 12727367 priority 14 state 3 SMINFO_MASTER
xxx--ib2: Local SM enabled and running
xxx--ib2: 20110518 11:23:02 Master SubnetManager on sm lid 2 sm guid 0x2128468ce2a0a0 : SUN DCS 36P QDR xxx--ib1.xxxx.com
xxx--ib3: sminfo: sm lid 2 sm guid 0x2128468ce2a0a0, activity count 12727370 priority 14 state 3 SMINFO_MASTER
xxx--ib3: Local SM enabled and running
xxx--ib3: 20110518 14:27:16 Master SubnetManager on sm lid 2 sm guid 0x2128468ce2a0a0 : SUN DCS 36P QDR xxx--ib1.xxxx.com

Cause

To view full details, sign in with your My Oracle Support account.

Don't have a My Oracle Support account? Click to get started!

In this Document
Symptoms
Cause
Solution


My Oracle Support provides customers with access to over a million knowledge articles and a vibrant support community of peers and Oracle experts.