[ofa-general] ***SPAM*** new with IB

Podar Valentin totunel at yahoo.com
Fri Aug 22 02:12:24 PDT 2008


Dear all,
I am new to this field and I have some questions.
I run a cluster with IB Mellanox. I have two subnets each with its own opensm (running on different port P1 or P2). mixed hardware MT25204 and MT23108. all are at 4x rate.
mixed drivers IBGold1.8.2 and MLNX_OFED_LINUX-1.3.1-rhel4
when I issue 
ibdiagnet -p 1 -lw 4x I get 
-I- Stages Status Report:
    STAGE                                    Errors Warnings
    Bad GUIDs/LIDs Check                     0      0
    Link State Active Check                  0      0
    Performance Counters Report              0      0
    Specific Link Width Check                0      0
    Partitions Check                         0      0
    IPoIB Subnets Check                      0      16
BUT
-I---------------------------------------------------
-I- IPoIB Subnets Check
-I---------------------------------------------------
-I- Subnet: IPv4 PKey:0x7fff QKey:0x00000b1b MTU:4096Byte rate:120Gbps SL:0x00
-W- Port h1/P1 lid=0x0011 guid=0x dev=23108 can not join due     to rate:10Gbps < group:120Gbps
-W- Port h2/P1 lid=0x0321 guid=0x dev=23108 can not join    due to rate:10Gbps < group:120Gbps
-W- Port h3/P1 lid=0x0069 guid=0x dev=23108 can not join due to    rate:10Gbps < group:120Gbps
-W- Port h4/P1 lid=0x0010 guid=0x dev=23108 can not    join due to rate:10Gbps < group:120Gbps
and so on with all the nodes.
switch type MT47396.

I think the problem is  this line 
Subnet: IPv4 PKey:0x7fff QKey:0x00000b1b MTU:4096Byte rate:120Gbps SL:0x00
but I don't know how to set the Mtu to 2048 and rate to 10G.

more
 /usr/sbin/saquery -d -g

MCMemberRecord group dump:
                MGID....................0xff12401bffff0000 : 0x00000000ffffffff
                Mlid....................0xC000
                Mtu.....................0x5
                pkey....................0xFFFF
                Rate....................0xA
MCMemberRecord group dump:
                MGID....................0xff12401bffff0000 : 0x0000000000000001
                Mlid....................0xC001
                Mtu.....................0x5
                pkey....................0xFFFF
                Rate....................0xA
MCMemberRecord group dump:
                MGID....................0xff12401bffff0000 : 0x0000000000656565
                Mlid....................0xC002
                Mtu.....................0x4
                pkey....................0xFFFF
                Rate....................0x3
MCMemberRecord group dump:
                MGID....................0xff12401bffff0000 : 0x0000000000a847ff
                Mlid....................0xC003
                Mtu.....................0x4
                pkey....................0xFFFF
                Rate....................0x3
MCMemberRecord group dump:
                MGID....................0xff12401bffff0000 : 0x0000000000000000
                Mlid....................0xC007
                Mtu.....................0x4
                pkey....................0xFFFF
                Rate....................0x2
MCMemberRecord group dump:
                MGID....................0xff12401bffff0000 : 0x000000000202c902
                Mlid....................0xC008
                Mtu.....................0x4
                pkey....................0xFFFF
                Rate....................0x2

the question is how can I set the group rate to 10G and not 120G? and the group MTU to 2048 as on some nodes I get " failed to join multicast or setting  MTU>4096 will ...generate...some errors"

thank you very much!
Vali



      
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20080822/929743b0/attachment.html>


More information about the general mailing list