RE: [RFC] RDMA CM + XRC, take two

2011-05-10 Thread Hefty, Sean
> This is an improved version of my previous patch to add XRC support to > RDMA CM. I would still like to see support merged upstream and into mainline libibverbs before applying this to my tree. > This version now support the newer rdma CM interface. It needs some > polishing but it works. It

Re: [PATCH] librdmacm: define REUSEADDR option

2011-05-10 Thread Ira Weiny
On Fri, 15 Apr 2011 23:48:27 -0700 "Hefty, Sean" wrote: > Support equivalent of SO_REUSEADDR socket option. When specified > the rdma_cm_id will be bound to a reuseable address. This will > allow other users to bind to that same address. This is needed > to support lustre on clusters larger th

Re: [PATCH 2/2] rdma/cm: Support REUSEADDR

2011-05-10 Thread Ira Weiny
On Fri, 15 Apr 2011 23:46:09 -0700 "Hefty, Sean" wrote: > Lustre requires that clients bind to a privileged port number before > connecting to a remote server. On larger clusters (typically more than > about 1000 nodes), the number of privileged ports is exhausted, > resulting in lustre being un

Re: [PATCH 1/2] rdma/cm: fix handling of ipv6 addressing in cma_use_port

2011-05-10 Thread Ira Weiny
On Fri, 15 Apr 2011 23:42:48 -0700 "Hefty, Sean" wrote: > cma_use_port is coded assuming that the sockaddr is an ipv4 address. > Since ipv6 addressing is supported, and also to support other address > families, make the code more generic in its address handling. > > Signed-off-by: Sean Hefty A

RE: [PATCH/RFC] RDMA/iwcm: Get rid of enum iw_cm_event_status

2011-05-10 Thread Latif, Faisal
From: Roland Dreier > > The IW_CM_EVENT_STATUS_xxx values were used in only a couple of places; > cma.c uses -Exxx values instead, and so do the amso1100, cxgb3 and > cxgb4 > drivers -- only nes was using the enum values (with the mild > consequence > that all nes connection failures were treate

Re: [PATCH V4 3/6] IB Core: Run Netlink

2011-05-10 Thread Roland Dreier
> +#include Was the latest version of this actually tested? Patch 1 put this header in as far as I can see, so I don't see how this could even build. - R. -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majord...@vger.kernel.org More majord

Re: [PATCH/RFC] RDMA/iwcm: Get rid of enum iw_cm_event_status

2011-05-10 Thread Steve Wise
On 05/10/2011 12:26 AM, Roland Dreier wrote: From: Roland Dreier The IW_CM_EVENT_STATUS_xxx values were used in only a couple of places; cma.c uses -Exxx values instead, and so do the amso1100, cxgb3 and cxgb4 drivers -- only nes was using the enum values (with the mild consequence that all nes

RE: [PATCH/RFC] RDMA/iwcm: Get rid of enum iw_cm_event_status

2011-05-10 Thread Hefty, Sean
> From: Roland Dreier > > The IW_CM_EVENT_STATUS_xxx values were used in only a couple of > places; > cma.c uses -Exxx values instead, and so do the amso1100, cxgb3 and cxgb4 > drivers -- only nes was using the enum values (with the mild consequence > that all nes connection failures were treated

Re: Building and Installing SDP on existing OFED 1.5.2 install

2011-05-10 Thread bhavinkumar thumar
Hey, Now it's working! I just cleaned up everything and started with fresh installation. Thanks a lot for pointing me /etc/infiniband/info file. Thanks, Bhavin On Tue, May 10, 2011 at 10:55 AM, bhavinkumar thumar wrote: > Thanks a lot for replying. > > I followed your suggestion and issued conf