Re: [ewg] Re: [PATCH 7/9] rdma/cm: fix loopback address support
Pradeep Satyanarayana wrote: > Pradeep Satyanarayana wrote: >> Sean, Thanks a lot for pulling it all together. Can we consider >> including this into OFED-1.5 too? Tziporet, Sure, we will do it. Pradeep, earlier you wanted to hear the rdma-cm maintainer opinion on inclusion of this 2.6.33-rc1 patch set (which isn't finalized by-the-way, Jason still has fixes to submit), any reason to skip it now? Or. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] Re: [PATCH 7/9] rdma/cm: fix loopback address support
Or Gerlitz wrote: Pradeep Satyanarayana wrote: > Pradeep Satyanarayana wrote: >> Sean, Thanks a lot for pulling it all together. Can we consider >> including this into OFED-1.5 too? Tziporet, Sure, we will do it. Pradeep, earlier you wanted to hear the rdma-cm maintainer opinion on inclusion of this 2.6.33-rc1 patch set (which isn't finalized by-the-way, Jason still has fixes to submit), any reason to skip it now? I agree with Or lets have Sean's blessing before we take them to OFED 1.5 Tziporet ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [PATCH] install: Allow ib-bonding to compile on RHEL4.8
--- install.pl.orig 2009-11-23 20:48:49.0 +0200
+++ install.pl 2009-11-23 20:49:35.0 +0200
@@ -1707,7 +1707,7 @@
}
# ib-bonding
-if ($kernel =~
m/2.6.9-67|2.6.9-78|2.6.16.[0-9.]*-[0-9.]*-[A-Za-z0-9.]*|el5|fc6/) {
+if ($kernel =~
m/2.6.9-67|2.6.9-78|2.6.9-89|2.6.16.[0-9.]*-[0-9.]*-[A-Za-z0-9.]*|el5|fc6/) {
$packages_info{'ib-bonding'}{'available'} = 1;
$packages_info{'ib-bonding-debuginfo'}{'available'} = 1;
}
___
ewg mailing list
ewg@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] OFED with MPE
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Jonathan Perkins schrieb: Hello, > It looks like the X11 development headers weren't installed at the time > the mvapich2 rpm was built. In this case certain parts of MPE may > silently fail to build. Can you try building the mvapich2 tarball > (http://mvapich.cse.ohio-state.edu/download/mvapich2/mvapich2-1.4.tgz) > and see if you can get any more diagnostics during the build process? > u...@head:~# ./configure --enable-mpe --with-mpe - --with-ib-include=/opt/include | grep X11 configure: WARNING: Structures containing long doubles may be aligned differently from structures with floats or longs. MVAPICH2 does not handle this case automatically and you should avoid assumed extents for structures containing float types. ./configure: line 3635: enable_ftb-cr=no: command not found configure: WARNING: unrecognized options: --enable-mpe, --with-mpe, - --with-ib-include, --enable-header-caching configure: WARNING: unrecognized options: --enable-mpe, --with-mpe, - --with-ib-include, --enable-header-caching configure: WARNING: unrecognized options: --enable-mpe, --with-mpe, - --with-ib-include, --enable-header-caching configure: WARNING: File locks may not work with NFS. See the Installation and users manual for instructions on testing and if necessary fixing this configure: WARNING: unrecognized options: --enable-mpe, --with-mpe, - --with-ib-include, --enable-header-caching configure: WARNING: unrecognized options: --enable-mpe, --with-mpe, - --with-ib-include, --enable-header-caching configure: WARNING: unrecognized options: --enable-mpe, --with-mpe, - --with-ib-include, --enable-header-caching configure: WARNING: unrecognized options: --enable-mpe, --with-mpe, - --with-ib-include, --enable-header-caching configure: WARNING: unrecognized options: --enable-mpe, --with-mpe, - --with-ib-include, --enable-header-caching config.status: WARNING: 'sbin/mpecheckinstall.in' seems to ignore the - --datarootdir setting configure: WARNING: No Java Virtual Machine can be found anywhere! u...@head:~# But i've a Java VM running. I've Eclipse installed. So, how can i solve this and have i to install a Java VM on all nodes? Regards, Stefan Kuhne -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.10 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iQEcBAEBAgAGBQJLC73OAAoJEOZfOPnHFHyA3EkH/jCiqojtGJZq/5XHm3eqeEnY cg05UNcQdi5UxjXIkqCiYfV+2PVAeU0khaGkX02eu5f63+x2E9/jM5UlBaWtiJqR 5SGrqcQwgQ+2nqtoo/pfSmoVPFNE2lguJmb4bpEyQV2jJaLSmFHD/0/ukuaGr2Ou /nySpNWMCmLvqVTB3GDcX55fNaFJm2f0uNelMgkvX7pxILPtKtWDal+8JjRt/mnI 95U8E3hIhqKtqiEQ+mlXkNTv/FRkh6Hlod8jmtx6yO/rmCOqWJKYKGDI18PUfImH focTioCTFepQZ11XMpMrnp62EtL55FVE5OFGfnCsF9K0rdIkXsi8puX5u/VscAY= =FL7Q -END PGP SIGNATURE- <>___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] ofa_1_5_kernel 20091124-0200 daily build status
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 i686 with linux-2.6.26 Passed on i686 with linux-2.6.24 Passed on i686 with linux-2.6.22 Passed on i686 with linux-2.6.27 Passed on x86_64 with linux-2.6.16.60-0.54.5-smp Passed on x86_64 with linux-2.6.16.60-0.21-smp Passed on x86_64 with linux-2.6.18 Passed on x86_64 with linux-2.6.18-128.el5 Passed on x86_64 with linux-2.6.18-164.el5 Passed on x86_64 with linux-2.6.20 Passed on x86_64 with linux-2.6.19 Passed on x86_64 with linux-2.6.18-93.el5 Passed on x86_64 with linux-2.6.21.1 Passed on x86_64 with linux-2.6.24 Passed on x86_64 with linux-2.6.22 Passed on x86_64 with linux-2.6.26 Passed on x86_64 with linux-2.6.27 Passed on x86_64 with linux-2.6.25 Passed on x86_64 with linux-2.6.27.19-5-smp Passed on x86_64 with linux-2.6.9-89.ELsmp Passed on x86_64 with linux-2.6.9-67.ELsmp Passed on x86_64 with linux-2.6.9-78.ELsmp Passed on ia64 with linux-2.6.21.1 Passed on ia64 with linux-2.6.19 Passed on ia64 with linux-2.6.18 Passed on ia64 with linux-2.6.23 Passed on ia64 with linux-2.6.24 Passed on ia64 with linux-2.6.22 Passed on ia64 with linux-2.6.26 Passed on ia64 with linux-2.6.25 Passed on ppc64 with linux-2.6.18 Passed on ppc64 with linux-2.6.19 Failed: ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: [GIT PULL ofed-1.5] - cxgb3 bug fix
Steve Wise wrote: Vlad, Please pull from: ssh://v...@sofa.openfabrics.org/~swise/scm/ofed_kernel.git ofed_1_5 This pulls in an important upstream bug fix and adjusts the backport files accordingly. Thanks, Steve. Done, Regards, Vladimir ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] OFED with MPE
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Stefan Kuhne schrieb: Hello, > But i've a Java VM running. > I've Eclipse installed. > sorry, it was on my old instalation. Now configure seams to run. I've rebuild OFED and get the same errors on compiling. Should there an own mpe lib or is it in libmpich included? Regards, Stefan Kuhne -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.10 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iQEcBAEBAgAGBQJLC8OFAAoJEOZfOPnHFHyAoQkH/0htSmx7bQDV5RjgmQkttRs8 /WWzFtDq0VRucPTl1Pq6lv8NNHbe6Adh8T8nT0HeZU/nmBV3OQEWcXdWZ00e5fLt zN114XgHmFPqYfn3Sc+GX/SEhh7t+DPIcNKcahc9yCOjcaCQ6Ss+DksMcH3A/cX6 deeK+/SASVF0Qd0INADLOodZOVMF1V5iWtXQHIu0qCtvansxqBTmwAxlWm47xm3K jt3E2E/v4wAR4b3dAE99fLAizskNKhGyuIjEOAif3336UAZKGYaHsW0YUWgM9KNN qZMDLqBkyI7vmh717A7kX8i1Vslz+byQz9l0rwtfzvpoL5sl8GJt8T1LjMjdM6I= =J/Q/ -END PGP SIGNATURE- <>___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] OFED with MPE
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Stefan Kuhne schrieb: > Stefan Kuhne schrieb: > > Hello, > >> But i've a Java VM running. >> I've Eclipse installed. > > sorry, it was on my old instalation. > > Now configure seams to run. > I found this: checking for include flag... no checking for include flag... no checking for include flag... no configure: WARNING: Invalid JNI include dir, exit! I remember, that i had this Problem when i had ried to build mpe whith openmpi. Why are sees errors so hidden? I found: u...@head:/# find / -name jni.h /usr/lib/jvm/java-6-openjdk/include/jni.h u...@head:/# But, how tell i OFED this? Regards, Stefan Kuhne -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.10 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iQEcBAEBAgAGBQJLC8/tAAoJEOZfOPnHFHyAKQ8H/jN5p2DI9RT9g4qJ5twB8xOw hPSmmKMIh1P1ve7GPBb1wIOtPTRtGecUwMMC1LAS3znM/QZpFPuEN8/8llMFeqNM LTw58AzxKr80cQWgAXINbS2icLN1QJynXFi2GNAxqbg7bjlgbcEwVkjsZg3qPjcX 2ghYGfq09wtxaR6XFg4IY9MdZ/9o2JGXS2VxzY0TIHjz+qAwH878BLxSMoUy0dJ6 2afE1SadLF/4SaNbq/ekeQUzoUbZb+ZxT4BfM+8Tvkux2wvyberR/+2xYFekjYI/ +e+HETKqX7Hv4VeIRe129T5/Wnns3lH9/qnRhStx00/VXevt1qhS+p4pKx5A5hk= =4sPy -END PGP SIGNATURE- <>___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] Re: [ofw] SC'09 BOF - Meeting notes
Liran Liss wrote: > LL: Any comments on our low-level driver are more than welcome. I see this code in a patch whose commit log has the following "Date: Mon, 3 Aug 2009 18:29:07 +0300" and "Subject: [PATCH 11/13] mlx4: Add support for RDMAoE - address resolution" +struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr) [...] + /* TBD: need to handle the case when we get called + in an atomic context and there we might sleep. We + don't expect this currently since we're working with + link local addresses which we can translate without + going to sleep */ + ret = create_rdmaoe_ah(pd, ah_attr, ah); are all the addresses which this code will run to serve are link local? also what patch set version is present in the ofed 1.5 rdmaoe branch? this patch is dated back to August where since then couple of newer versions were posted to the lists. Or. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] EWG/OFED meeting minutes for Nov 23, 09
EWG/OFED the meeting minutes for Nov 23, 2009 Meeting summary: * RDMAoE and OFED 1.5: It was decided to include RDMAoE in OFED 1.5.1. * 1.5 RC3 will be released on Wed 11/24/09 * Reminder: We have weekly meetings till OFED 1.5 GA Meeting details: 1. RDMAoE and OFED 1.5: There was a very life discussion on what should we do with the RDMAoE feature, and what is the best fit from all EWG members. Everybody agreed we cannot delay such an important feature for a long period from one hand, and from the other hand OFED process is not to change any core features after RC1. After all the different argument raised, very similar to those on the mail thread so I will not repeat them here, we decided that the best solution will be to have this feature in OFED 1.5.1. Meanwhile the OFED-RDMAoE branch will continue to be available to anyone that wish to test the new feature now. All companies are invited to test this package and report issues. Note: In bugzilla we have two versions: - 1.5 - 1.5-RDMAoE So it is easy to know which bug belong to which package. 2. Decide on RC3 date - RC3 will be released on Wed 25 Nov (I know all US people are on thanks-Giving holiday but some of us are not in US :-) 3. Bugs status - we reviewed bugs and updated status and severity. For now we have 6 critical and 13 major bugs All bug owners: please work on your issues ASAP, and update bug status if it was fixed. 1800 cri RHEL am...@mellanox.co.il iperf sdp on ppc cause to client machine to dead lock 1812cri SLESam...@mellanox.co.ilSDP fails during init_qp 1826cri Otheam...@mellanox.co.ilIperf sdp with more than 50 connections cause to call tra... 1831cri RHELe...@mellanox.co.il ofed-1.5rc2 crashed RHEL5.4 linux kernel running IPoIB bi... 1805cri RHELj...@opengridcomputing.com Kernel panics when NFS server is 32 bit OS & NFS client i... 1811cri RHELj...@opengridcomputing.com OFED-1.5- NFSoverRDMA-"SPECIAL TESTS" of Connectathon too... 1804maj RHELandy.gro...@oracle.com RDS panic 1691maj All arlin.r.da...@intel.com dapl-utils RPM conflicts with compat-dapl-utils on SLES11... 1639maj RHELe...@mellanox.co.il Kernel panic while running udp traffic 1642maj All e...@mellanox.co.il IPoIB has starvation issues under UDP stress. 1839maj SLESe...@mellanox.co.il IPoIB Conneced fails on Multicast latency test 1789maj Centj...@opengridcomputing.com OFED-1.5 kernel panic observed while running iozone & con... 1815maj RHELj...@opengridcomputing.com NFSoRDMA: mount.rnfs on client side does not work 1821maj RHELmo...@voltaire.com Crash in bonding 1833maj Othemo...@voltaire.com Bonding on RH5 up4: rdma_cm does not send an ADDR_CHNAGE ... 1778maj Centsw...@opengridcomputing.com OFED-1.5-IMB tests Alltoall & Alltoallv aborts while runn... 1719maj Othet...@opengridcomputing.com Reconnect path in Linux client can loop indefinitely 1636maj SLESv...@mellanox.co.il SLES10 and SLES11 expect a -32bit suffix for any user spa... 1823maj SLESv...@mellanox.com OFED-1.5-rc2 opensm fails to discover SRP direct connect ... Tziporet ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [ANNOUNCE] ib-bonding release 41
Hi, New ib-bonding is available on the OFA server Change Log: 1. Add backport support to RHEL 4.8 2. Add backport support to SLES 10.3 3. Add support to RHEL 5.4 (only patch to initscripts - driver itself won't be installed) 4. Remove the documentation (exact copy is available in ofed-docs) 5. Remove the script ib-bond Vlad, please take the package from the new path: openfabrics.org:/home/monis/public_html/ofed_1_5 (see latest.txt there) ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] Re: [ofw] SC'09 BOF - Meeting notes
On Tue, Nov 24, 2009 at 04:18:35PM +0200, Or Gerlitz wrote: > > I see this code in a patch whose commit log has the following "Date: Mon, 3 > Aug 2009 18:29:07 +0300" and "Subject: [PATCH 11/13] mlx4: Add support for > RDMAoE - address resolution" > > +struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr) > [...] > + /* TBD: need to handle the case when we get called > + in an atomic context and there we might sleep. We > + don't expect this currently since we're working with > + link local addresses which we can translate without > + going to sleep */ > + ret = create_rdmaoe_ah(pd, ah_attr, ah); > > are all the addresses which this code will run to serve are link local? Addresses (e.g. GIDs) may be either link local or mulitcast; in both cases the translation is immediate. > also what patch set version is present in the ofed 1.5 rdmaoe branch? OFED rdmaoe is based on v6. It has a some fixes in it which I intend to send to the rdma list as distinct patches (on top of v6 rather then sending a v7 series). ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [PATCH] docs: add to ipoib known issues
The additional comment below is to a request from Pradeep Satyanarayana who opened bugzilla 1821. Signed-off-by: Moni Shoua --- diff --git a/ipoib_release_notes.txt b/ipoib_release_notes.txt index 2d1217a..0aba56d 100644 --- a/ipoib_release_notes.txt +++ b/ipoib_release_notes.txt @@ -174,6 +174,11 @@ Usage and configuration: 15. IPoIB multicast support is broken in RH4.x kernels. This is because ndisc_mc_map() does not handle IPOIB hardware addresses. +16. If bonding uses IPoIB slave then unenslaving all slaves (or downing them + with ifdown) followed by unloading the module ib_ipoib might crash the + kernel. To avoid this leave the IPoIB interfaces enslaved when unloading + ib_ipoib. + === 4. IPoIB Configuration Based on DHCP === ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
RE: [ewg] Re: [PATCH 7/9] rdma/cm: fix loopback address support
>> Pradeep, earlier you wanted to hear the rdma-cm maintainer opinion on >> inclusion of this 2.6.33-rc1 patch set (which isn't finalized >> by-the-way, Jason still has fixes to submit), any reason to skip it now? >I agree with Or >lets have Sean's blessing before we take them to OFED 1.5 I have no issue with someone adding it to OFED. I will create a new librdmacm package that corresponds with the changes. - Sean ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: [PATCH 7/9] rdma/cm: fix loopback address support
Sean Hefty wrote: > I will create a new librdmacm package that corresponds with the changes I made all my testing of the patch set with librdmacm 1.0.10 and patched 2.6.32-rc5 kernel, where as I wrote you, I was focusing on AF_INET/PS_TCP and AF_INET/PS_IPOIB. I understand that Dave was covering AF_INET6/PS_TCP with plenty of the ipv6 variations. So what will this new librdmacm package will let cover which wasn't possible so far? do you refer to ipv6 support in mckey? anything else? Or. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] RE: [PATCH 7/9] rdma/cm: fix loopback address support
>So what will this new librdmacm package will let cover which wasn't >possible so far? do you refer to ipv6 support in mckey? anything else? Changes were your changes to mckey, plus changes Dave added to cmatose to support IPv6. The actual library itself hasn't been modified. - Sean ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: [PATCH 7/9] rdma/cm: fix loopback address support
> Changes were your changes to mckey, plus changes Dave added to cmatose to > support IPv6. The actual library itself hasn't been modified. okay, got it. I was under the impression that mckey still misses an option to get from the user an ipv6 multicast address which isn't all zeros nor unmapped, correct? or the -m option will work with both ipv4 and ipv6 addresses? Or. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] RE: [PATCH 7/9] rdma/cm: fix loopback address support
>okay, got it. I was under the impression that mckey still misses an >option to get from the user an ipv6 multicast address which isn't all >zeros nor unmapped, correct? or the -m option will work with both ipv4 >and ipv6 addresses? The -m and -b options work with IPv4 and IPv6 addresses. - Sean ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] [ANNOUNCE] ib-bonding release 41
Moni Shoua wrote: Hi, New ib-bonding is available on the OFA server Change Log: 1. Add backport support to RHEL 4.8 2. Add backport support to SLES 10.3 3. Add support to RHEL 5.4 (only patch to initscripts - driver itself won't be installed) 4. Remove the documentation (exact copy is available in ofed-docs) 5. Remove the script ib-bond Vlad, please take the package from the new path: openfabrics.org:/home/monis/public_html/ofed_1_5 (see latest.txt there) Done, Regards, Vladimir ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] [PATCH] docs: add to ipoib known issues
Moni Shoua wrote: The additional comment below is to a request from Pradeep Satyanarayana who opened bugzilla 1821. Signed-off-by: Moni Shoua --- diff --git a/ipoib_release_notes.txt b/ipoib_release_notes.txt index 2d1217a..0aba56d 100644 --- a/ipoib_release_notes.txt +++ b/ipoib_release_notes.txt @@ -174,6 +174,11 @@ Usage and configuration: 15. IPoIB multicast support is broken in RH4.x kernels. This is because ndisc_mc_map() does not handle IPOIB hardware addresses. +16. If bonding uses IPoIB slave then unenslaving all slaves (or downing them + with ifdown) followed by unloading the module ib_ipoib might crash the + kernel. To avoid this leave the IPoIB interfaces enslaved when unloading + ib_ipoib. + === 4. IPoIB Configuration Based on DHCP === Applied, Regards, Vladimir ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
