[Pkg-ofed-devel] discovery of InfiniBand ports sometimes fails after firmware update

[Nitin Yadav]

Hi Roland,
 Thanks for quick reply .
    Actually I am using Debian kernel(3.2), could you please let me know
which OFED package I will use for Debian kernel.
Currently I am trying to install OFED 1.5.3 package but I getting some
errors like :

/var/tmp/OFED_topdir/BUILD/ofa_kernel-1.5.4.1/drivers/infiniband/core/ad
dr.c:49: error: expected declaration specifiers or '...' before string
constant
/var/tmp/OFED_topdir/BUILD/ofa_kernel-1.5.4.1/drivers/infiniband/core/ad
dr.c:192: error: 'struct flowi' has no member named 'nl_u'

Please suggest me proper OFED package for Debian kernel.

Thanks,
Nitin

-----Original Message-----
From: Roland Dreier [mailto:roland at digitalvampire.org] 
Sent: Wednesday, December 05, 2012 10:34 PM
To: Nitin Yadav
Cc: Pkg-ofed-devel at lists.alioth.debian.org
Subject: Re: [Pkg-ofed-devel] discovery of InfiniBand ports sometimes
fails after firmware update
Importance: High

I would resend your question to linux-rdma at vger.kernel.org, it's much
more likely to be a driver issue than a packaging problem.

With that said, in the cases where ib1 doesn't come up, I would do:

    grep . /sys/class/infiniband/mlx4*/ports/*/link_layer

(I'm assuming you only have one ConnectX adapter in the system), and see
if the output looks like

    /sys/class/infiniband/mlx4_0/ports/1/link_layer:InfiniBand
    /sys/class/infiniband/mlx4_0/ports/2/link_layer:InfiniBand

I've seen cases where one port gets mis-negotiated as Ethernet.

 - R.


From: Nitin Yadav 
Sent: Wednesday, December 05, 2012 3:06 PM
To: 'Pkg-ofed-devel at lists.alioth.debian.org'
Subject: discovery of InfiniBand ports sometimes fails after firmware
update

Description of problem:
After installing the latest firmware release for the Mellanox ConnectX-2
HCA (Mellanox Technologies MT26428 [ConnectX VPI PCIe 2.0 5GT/s - IB QDR
/ 10GigE] (rev b0)),
I've noticed that the second port (ib1) is sometimes not discovered at
system
boot.

According to the installation instructions, this firmware has a
prerequisite
of OFED 1.5.3 or later , this firmware should be correct.

The firmware file is: fw-ConnectX2-2_9_1200-592520-B21.bin.

The issue seems most likely to occur after a "reboot -f".


Version or Release number of selected component (if n/a, use `uname
-a`):
Linux dl380g7-2 3.2 kernel  #1 SMP Tue Jul 31 18:13:05 UTC 2012 x86_64
GNU/Linux
fw-ConnectX2-2_9_1200-592520-B21.bin

Could anyone suggest some pointer ?

Thanks,
Nitin


Information transmitted by this e-mail is proprietary to MphasiS, its associated companies and/ or its customers and is intended 
for use only by the individual or entity to which it is addressed, and may contain information that is privileged, confidential or 
exempt from disclosure under applicable law. If you are not the intended recipient or it appears that this mail has been forwarded 
to you without proper authority, you are notified that any use or dissemination of this information in any manner is strictly 
prohibited. In such cases, please notify us immediately at mailmaster at mphasis.com and delete this mail from your records.