[ewg] ofa_1_5_kernel 20091019-0200 daily build status

2009-10-19 Thread Vladimir Sokolovsky (Mellanox)
This email was generated automatically, please do not reply git_url: git://git.openfabrics.org/ofed_1_5/linux-2.6.git git_branch: ofed_kernel_1_5 Common build parameters: Passed: Passed on i686 with linux-2.6.18 Passed on i686 with linux-2.6.19 Passed on i686 with linux-2.6.21.1 Passed on

Re: [ewg] Agenda for EWG/OFED meeting on next Monday

2009-10-19 Thread Moni Shoua
Voltaire intends to test with OFED-RDMAoE release. The following setup are used in our QA while each setup consists of 2 machines. Arch|OS / Kernel | HCA|SM +-+--+--- x86_64 | RH4 up6 *| ConnectX QDR | OpenSM

[ewg] mvapich2 srpm uploaded

2009-10-19 Thread Jonathan Perkins
Hi all: I've recently uploaded an mvapich2 srpm to the openfabrics server. The version uploaded is not the 1.4 release but can be used to start the Q/A process. The source rpm can be found at ~perkinjo/ofed_1_5/mvapich2-r3510-1.src.rpm and future uploads can be identified by

[ewg] RE: Agenda for EWG/OFED meeting on next Monday

2009-10-19 Thread Tung, Chien Tin
We test nes content in OFED 1.5 with the following: OS: - RHEL4: up6, up7, up8 - RHEL5: up2, up3, up4 - FC9 - SLES10 SP2 - SLES11 - OEL4 up7 - OEL5 up2 - CentOS5: up2, up3 - Kernel.org: 2.6.29, 2.6.30 Arch: - ia32 - x86_64

[ewg] RE: Agenda for EWG/OFED meeting on next Monday

2009-10-19 Thread Tziporet Koren
Mellanox testing for OFED 1.5 == Mellanox test OFED-RDMA package on most systems, and only few machines on OFED. We test All Mellanox HCAs with main focus on ConnectX and ConnectX-2 with QDR OS: - RHEL4: up6, up7, up8 - RHEL5: up2, up3, up4 -

Re: [ewg] mvapich2 srpm uploaded

2009-10-19 Thread Vladimir Sokolovsky
Jonathan Perkins wrote: Hi all: I've recently uploaded an mvapich2 srpm to the openfabrics server. The version uploaded is not the 1.4 release but can be used to start the Q/A process. The source rpm can be found at ~perkinjo/ofed_1_5/mvapich2-r3510-1.src.rpm and future uploads can be

Re: [ewg] mvapich2 srpm uploaded

2009-10-19 Thread Steve Wise
I'm getting a build failure with today's latest ofed build on centos 5.3/x64: Failed to build mvapich2 RPM See /tmp/OFED.17691.logs/mvapich2.rpmbuild.log [r...@hpc-cn3 OFED-1.5-20091019-0811]# more /tmp/OFED.17691.logs/mvapich2.rpmbuild.log Running rpmbuild --rebuild --define '_topdir /var

[ewg] RE: Agenda for EWG/OFED meeting on next Monday

2009-10-19 Thread Woodruff, Robert J
For my team, we have been testing the following on small clusters, 16 nodes or less. OS - RHEL 5.3 and 5.4 Arch: - X86_64, ia64 ULPs OpenSM, Intel MPI over IPoIB, Intel MPI over uDAPL, ibutils and management tools IHVs Mellanox, mthca and mlx4 Intel

Re: [ewg] mvapich2 srpm uploaded

2009-10-19 Thread Jonathan Perkins
On Mon, Oct 19, 2009 at 06:17:04PM +0200, Vladimir Sokolovsky wrote: Jonathan Perkins wrote: Hi all: I've recently uploaded an mvapich2 srpm to the openfabrics server. The version uploaded is not the 1.4 release but can be used to start the Q/A process. The source rpm can be found at

Re: [ewg] mvapich2 srpm uploaded

2009-10-19 Thread Jonathan Perkins
On Mon, Oct 19, 2009 at 11:56:10AM -0500, Steve Wise wrote: I'm getting a build failure with today's latest ofed build on centos 5.3/x64: Failed to build mvapich2 RPM See /tmp/OFED.17691.logs/mvapich2.rpmbuild.log [r...@hpc-cn3 OFED-1.5-20091019-0811]# more /tmp/OFED.17691.logs/mvapich2

Re: [ewg] mvapich2 srpm uploaded

2009-10-19 Thread Jonathan Perkins
...@hpc-cn3 OFED-1.5-20091019-0811]# more /tmp/OFED.17691.logs/mvapich2.rpmbuild.log Running rpmbuild --rebuild --define '_topdir /var/tmp/OFED_topdir' --define 'd ist %{nil}' --target x86_64 --define '_name mvapich2_gcc' --define 'impl ofa' -- define 'rdma --with-rdma=gen2

RE: [ewg] Re: Possible process deadlock in RMPP flow

2009-10-19 Thread Sean Hefty
Thanks Or. This one is already in OFED 1.4.2 but apparently this is a different problem. Once I have information whether the patch Roland posted fixed it I will update the list. Eli, did you find a commit that fixes the problem you reported on? Or. Not yet :-( I can't find anything off in

[ewg] [PATCH] link-local address fix for rdma_resolve_addr

2009-10-19 Thread David J. Wilder
::2 (server side started with rping -s -P -v -a ::0) Tested against ofed build OFED-1.5-20091019-0811 and kernel 2.6.30. Signed-off-by: David Wilder dwil...@us.ibm.com -- drivers/infiniband/core/addr.c | 25 ++--- 1 files

[ewg] Re: [PATCH] link-local address fix for rdma_resolve_addr

2009-10-19 Thread Jason Gunthorpe
On Mon, Oct 19, 2009 at 03:47:09PM -0700, David J. Wilder wrote: +++ b/drivers/infiniband/core/addr.c @@ -278,6 +278,21 @@ static int addr6_resolve_remote(struct sockaddr_in6 *src_in, fl.nl_u.ip6_u.daddr = dst_in-sin6_addr; fl.nl_u.ip6_u.saddr = src_in-sin6_addr; + if

[ewg] RE: [PATCH] link-local address fix for rdma_resolve_addr

2009-10-19 Thread Sean Hefty
@@ -393,7 +393,7 @@ static int addr_resolve_local(struct sockaddr *src_in, for_each_netdev(init_net, dev) if (ipv6_chk_addr(init_net, - ((struct sockaddr_in6 *) addr)- sin6_addr, +

[ewg] Re: [PATCH] link-local address fix for rdma_resolve_addr

2009-10-19 Thread Jason Gunthorpe
On Mon, Oct 19, 2009 at 04:47:59PM -0700, Sean Hefty wrote: @@ -393,7 +393,7 @@ static int addr_resolve_local(struct sockaddr *src_in, for_each_netdev(init_net, dev) if (ipv6_chk_addr(init_net, - ((struct