[openib-general] [PATCH] OpenSM: Set retries to 0 if RMPP

Hal Rosenstock halr at voltaire.com
Tue Jun 7 16:27:51 PDT 2005


On Tue, 2005-06-07 at 18:37, Tom Duffy wrote:
> On Tue, 2005-06-07 at 15:21 -0700, Tom Duffy wrote:
> > On Tue, 2005-06-07 at 18:12 -0400, Hal Rosenstock wrote:
> > > With this change, able to interoperate with Solaris 10 SA client (which
> > > uses RMPP) with OpenSM
> > 
> > Cool.  I will give it a try.  What do you mean by interop?  Were you
> > able to bring up IPoIB and ping?
> 
> Nevermind.  Just tried it with Solaris Nevada build 16 and it works
> too!  
> 
> Albeit with some minor caveats.  For instance, a broadcast ping from
> Linux does not see the Solaris node:
> 
> This is a linux system:
> 
> [root at sins-stinger-10 ~]# ping 192.168.0.0 -b
> WARNING: pinging broadcast address
> PING 192.168.0.0 (192.168.0.0) 56(84) bytes of data.
> 64 bytes from 192.168.0.233: icmp_seq=0 ttl=64 time=0.054 ms
> 64 bytes from 192.168.0.26: icmp_seq=0 ttl=64 time=0.159 ms (DUP!)
> 64 bytes from 192.168.0.233: icmp_seq=1 ttl=64 time=0.016 ms
> 64 bytes from 192.168.0.26: icmp_seq=1 ttl=64 time=0.114 ms (DUP!)

I didn't try broadcast but the limited broadcast (192.168.0.255_ and it
worked. Does it for you ? I will try this next time. Not sure this is an
OpenSM issue.

> From the Solaris system:
> 
> [root at nisus ~]# ping -s 192.168.0.0
> PING 192.168.0.0: 56 data bytes
> 64 bytes from 192.168.0.78: icmp_seq=0. time=0.501 ms
> 64 bytes from 192.168.0.233: icmp_seq=0. time=5.95 ms
> 64 bytes from 192.168.0.26: icmp_seq=0. time=10.4 ms
> 
> Solaris 10 was unhappy:
> 
> [root at blissom ~]# ifconfig ibd0 plumb
> ifconfig: SIOCSLIFNAME for ip: ibd0: no such interface
> Jun  7 15:29:02 blissom.SFBay.Sun.COM ip: ibd0: DL_ATTACH_REQ failed: DL_BADPPA
> Jun  7 15:29:02 blissom.SFBay.Sun.COM ip: ibd0: DL_BIND_REQ failed: DL_OUTSTATE
> Jun  7 15:29:02 blissom.SFBay.Sun.COM ip: ibd0: DL_PHYS_ADDR_REQ failed: DL_OUTSTATE
> Jun  7 15:29:02 blissom.SFBay.Sun.COM ip: ibd0: DL_UNBIND_REQ failed: DL_OUTSTATE
> 
> Which made my Nevada box unhappy:
> 
> < from dmesg >
> interface ibd0 to 192.168.0.78 broken: in=3 ierr=0 out=5 oerr=2

It needs a little more work. Unfortunately I could not capture IB traces
today for analysis. Was this with Sean's latest RMPP change or not ?

Thanks.

-- Hal




More information about the general mailing list