On Mon, Apr 13, 2009 at 5:50 PM, Chris Worley <[email protected]> wrote:
<snip...> >> Were the ports getting to LinkUp/Active before partitions were configured ? > > Yes, before I started trying to partition, all the nodes could > communicate... except they'd all use just one port on the server and I > couldn't get the throughput I needed. I suspect the switch SMA went south sometime after this. <snip...> >> So no SM initialization is occurring there since they are still just in Init. > > Correct. But, the SM is running. Nothing the SM can do when a device SMA malfunctions like that. <snip...> >>> Partition "part2" with P_Key=2 should connect this client's port 0 to >>> the sever on port 1 of mlx4_1 >> >> Do you really mean port 0 ? > > Nope... in this case I have 0x0002c903000292b0 in part2 in my > partitions file, which is port 1, the second port of the adapter. I'm > hoping to use both ports of all adapters on the server. So you're talking about physical marking on the card rather than actual (logical) port number. <snip...> > After power-cycling the switch, the ports went "active"! Note that I > didn't restart the SM... I just left it running. That should be fine. > So, on one client... the one corresponding to "part2" in the > partitions file, I put the P_Key into the "create child": > > echo 0x2 > /sys/class/net/ib0/create_child > > ... and did likewise on the host, for ib3 (the second port on the > second adapter): > > echo 0x2 > /sys/class/net/ib3/create_child I'm not 100% sure but I think you may need the full member PKey on at least one of them (0x800x). > Still, no ping (the interfaces are setup correctly). Are there still join failure messages on the client and/or server ? What do they say now ? -- Hal > Thanks, > > Chris > <snip> _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
