Quantcast
Channel: Mellanox Interconnect Community: Message List
Viewing all articles
Browse latest Browse all 6148

ibdump unable to capture MPI traffic on MLNX ConnectX-3 FDR HCAs

$
0
0

Hi all,

 

I have been trying to to capture MPI traffic using ibdump for one way latency measurements (at the physical layer).

But all ibdump captures are IPoIB packets interleaved with Subnet monitoring packets such as perfqueries from the UFM/SM sweeps.

Specs:

ibdump, 2.0.0-5, built on Aug 21 2013, 13:09:58. GIT Version: 41a4dd2

I have also tried: ibdump, 2.0.0-8, built on Apr 28 2014, 17:06:51. GIT Version: f8e989d

I have also used --mem-mode and --max-burst to prevent packet dropping but with no luck.

Ofed_info: MLNX_OFED_LINUX-2.0-3.0.0.3 (OFED-2.0-3.0.0)

bash-4.1$ ibv_devinfo

hca_id:    mlx4_0

    transport:            InfiniBand (0)

    fw_ver:                2.30.3200

    node_guid:            0002:c903:0044:e220

    sys_image_guid:            0002:c903:0044:e223

    vendor_id:            0x02c9

    vendor_part_id:            4099

    hw_ver:                0x1

    board_id:            IBM1100110019

    phys_port_cnt:            1

    port:    1

    state:            PORT_ACTIVE (4)

    max_mtu:        4096 (5)

    active_mtu:        4096 (5)

    sm_lid:            1

    port_lid:        15

    port_lmc:        0x00

    link_layer:        InfiniBand

 

Using tshark -r sniffer.pcap| grep -i infiniband to parse the .pcap files, I typically get this:

 

frame #

Elapse timesrc -> destComments
     48       6.469792   LID: 1 -> LID: 35  InfiniBand 290 PERF (PortCountersExtended)
     49       6.469888  LID: 35 -> LID: 1   InfiniBand 290 PERF (PortCounters)
     50       6.469951  LID: 35 -> LID: 1   InfiniBand 290 PERF (PortCountersExtended)
    239      36.492380   LID: 1 -> LID: 35  InfiniBand 290 PERF (PortCounters)
    240      36.492388   LID: 1 -> LID: 35  InfiniBand 290 PERF (PortCountersExtended)
    241      36.492477  LID: 35 -> LID: 1   InfiniBand 290 PERF (PortCounters)
    242      36.492543  LID: 35 -> LID: 1   InfiniBand 290 PERF (PortCountersExtended)
    410      66.514564   LID: 1 -> LID: 35  InfiniBand 290 PERF (PortCounters)
    411      66.514574   LID: 1 -> LID: 35  InfiniBand 290 PERF (PortCountersExtended)
    412      66.514660  LID: 35 -> LID: 1   InfiniBand 290 PERF (PortCounters)
    413      66.514723  LID: 35 -> LID: 1   InfiniBand 290 PERF (PortCountersExtended)
    718      96.551601   LID: 1 -> LID: 35  InfiniBand 290 PERF (PortCounters)
    719      96.551606   LID: 1 -> LID: 35  InfiniBand 290 PERF (PortCountersExtended)
    720      96.551701  LID: 35 -> LID: 1   InfiniBand 290 PERF (PortCounters)
    721      96.551770  LID: 35 -> LID: 1   InfiniBand 290 PERF (PortCountersExtended)

 

cat /etc/modprobe.d/mlnx.conf:

blacklist mlx4_core

blacklist mlx4_en

blacklist mlx5_core

blacklist mlx5_ib

 

I would highly appreciate anyone who can help understand this behavior.

 

Thanks,

Fabrice


Viewing all articles
Browse latest Browse all 6148

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>