Do you set ip address for these adapters?
Refer to the description of verbsRdmaCm in ‘Command and Programming
Reference':
If RDMA CM is enabled for a node, the node will only be able to establish
RDMA connections
using RDMA CM to other nodes with verbsRdmaCm enabled. RDMA CM enablement
requir
I should have said, here are the package versions:
[root@sgate1 ~]# rpm -qa | grep gpfs
gpfs.gpl-4.2.2-3.noarch
gpfs.docs-4.2.2-3.noarch
gpfs.base-4.2.2-3.x86_64
gpfs.gplbin-3.10.0-514.26.2.el7.x86_64-4.2.2-3.x86_64
nfs-ganesha-gpfs-2.3.2-0.ibm32_2.el7.x86_64
gpfs.ext-4.2.2-3.x86_64
gpfs.msg.en_U
Returning to this thread cause I'm having the same issue as Ilan, above.
I'm working on setting up CES in our environment after finally getting a
blocking bugfix applied. I'm making it further now, but I'm getting an error
when I try to create my export:
---
[root@sgate2 ~]# mmnfs export add /
is ib_read_bw working ?just test it between the two nodes ...
From:
Barry Evans To:
gpfsug main discussion
list Date:
09/20/2017 03:21 AMSubject:
[gpfsug-discuss]
RoCE not playing ballSent by:
gpfsug-discuss-boun...@spectrumscale.orgHi All,Weirdness with a RoCE
Hi Atmane,
In terms of this kind of disk management question, I would like to suggest
to open a PMR to make IBM service help you.
mmdelpdisk command would not need to reboot system to take effect.
Regards, The Spectrum Scale (GPFS) team
-
Hi Kevin,
Let's me try to understand the problem you have. What's the meaning of node
died here. Are you mean that there are some hardware/OS issue which cannot
be fixed and OS cannot be up anymore?
I agree with Bob that you can have a try to disable CCR temporally, restore
cluster configuration
Hi All,
Weirdness with a RoCE interface - verbs is not playing ball and is
complaining about the inet6 address not matching up:
2017-09-02_07:46:01.376+0100: [I] VERBS RDMA starting with verbsRdmaCm=yes
verbsRdmaSend=no verbsRdmaUseMultiCqThreads=yes verbsRdmaUseCompVectors=yes
2017-09-02_07:46:0
OK – I’ve run across this before, and it’s because of a bug (as I recall)
having to do with CCR and quorum. What I think you can do is set the cluster to
non-ccr (mmchcluster –ccr-disable) with all the nodes down, bring it back up
and then re-enable ccr.
I’ll see if I can find this in one of th
Hi All,
We have a small test cluster that is CCR enabled. It only had/has 3 NSD
servers (testnsd1, 2, and 3) and maybe 3-6 clients. testnsd3 died a while
back. I did nothing about it at the time because it was due to be life-cycled
as soon as I finished a couple of higher priority projects.
>> My question is has anyone here set up NFS re-export / proxy with nfs-ganesha?
There are only couple people who test proxy fsal, you may **play** with it. The best place to post this question would to the nfs-ganesha mailing list "nfs-ganesha-de...@lists.sourceforge.net".
Regards, Malahal.
Hello Neil,
While the description below provides a way on how to edit the hostname
parameter, you should not have the need to edit the "hostname" parameter.
Sensors use the hostname() call to get the hostname where the sensor is
running and use this as key in the performance database, which is wha
11 matches
Mail list logo