RE: [ewg] possible ofed 1.3.1 build issue
I finish checking / building OFED-1.3.1-rc3 on lustre kernel-ib-1.3.1-2.6.18_53.el5 It's look o.k. The source of the errors is in the binary rpm's supplied by Sun. When I build kernel from the kernel sources supplied by Sun , every thing is o.k. Moshe That's what I did - rpm -ivh kernel-lustre-smp-2.6.18-53.1.13.el5_lustre.1.6.4.3.x86_64.rpm rpm -ivh kernel-lustre-source-2.6.18-53.1.13.el5_lustre.1.6.4.3.x86_64.rpm rpm -ivh lustre-modules-1.6.4.3-2.6.18_53.1.13.el5_lustre.1.6.4.3smp.x86_64.rpm lustre-1.6.4.3-2.6.18_53.1.13.el5_lustre.1.6.4.3smp.x86_64.rpm cp -r /usr/src/kernels/2.6.18-53.el5-x86_64/scripts/genksyms/genksyms /usr/src/linux-2.6.18-53.1.13.el5_lustre.1.6.4.3/scripts/genksyms cp -r /usr/src/kernels/2.6.18-53.el5-x86_64/scripts/mod /usr/src/linux-2.6.18-53.1.13.el5_lustre.1.6.4.3/scripts/ cp -r /usr/src/kernels/2.6.18-53.el5-x86_64/scripts/mod /usr/src/linux-2.6.18-53.1.13.el5_lustre.1.6.4.3-obj/x86_64/smp/scripts ++ Here I tried to compile and failed with the error Steve Wise sent. ++ So I build kernel and test again ... cd /usr/src/linux-2.6.18-53.1.13.el5_lustre.1.6.4.3/ cd linux-2.6.18-53.1.13.el5_lustre.1.6.4.3 cp /usr/src/kernels/2.6.18-53.el5-x86_64/.config . make oldconfig make menuconfig # remove the infiniband modules from the kernel build make make modules make modules_install make install reboot tar -zxf OFED-1.3.1-rc3.tgz cd OFED-1.3.1-rc3 ./install.pl --all Good luck Moshe Moshe Katzir | +972-9971-8639 (o) | +972-52-860-6042 (m) Voltaire - The Grid Backbone www.voltaire.com -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Steve Wise Sent: Monday, June 02, 2008 8:39 PM To: Vladimir Sokolovsky; OpenFabrics EWG; Michael Werner Subject: [ewg] possible ofed 1.3.1 build issue Vlad, Building ofed-1.3.1-rc3 against the lustre kernel tree seems to be having some problems: Processing files: kernel-ib-1.3.1-2.6.18_53.el5 error: File not found: /var/tmp/OFED/lib/modules/2.6.18-53.el5/updates/kernel/drivers/net/cxgb3 error: File not found: /var/tmp/OFED/lib/modules/2.6.18-53.el5/updates/kernel/drivers/net/mlx4 Processing files: kernel-ib-devel-1.3.1-2.6.18_53.el5 Requires(interp): /bin/sh /bin/sh /bin/sh Requires(rpmlib): rpmlib(CompressedFileNames) = 3.0.4-1 rpmlib(PayloadFilesHavePrefix) = 4.0-1 Requires(pre): /bin/sh Requires(post): /bin/sh Requires(postun): /bin/sh Requires: /bin/bash kernel-ib Attached is the full log. The command used was: ./install.pl -s /path-to-lustre-kernel-source/ Thanks, Steve. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: [PATCH] OpenSM release notes: add byacc support
Hal Rosenstock wrote: OpenSM release notes: add byacc support as pointed out by Sasha applied Tziporet ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Building OFED1.4 kernel modules
Hi Vald, I'm working on the backports of OFED1.4 I'm trying to test my backports and for doing so I need to build OFED1.4 kernel modules. I'm working by your instruction (for OFED1.3), are they relevant for OFED1.4 also? I did the following steps: 1. git clone -s -n git://git.openfabrics.org/ofed_1_4/linux-2.6.git testbuild 2. cd testbuild 3. git checkout ofed_kernel -- ofed_scripts 4. ./ofed_scripts/ofed_checkout.sh refs/heads/ofed_kernel 5. create my new backports on kernel_patches/backports/2.6.9_U5/ 6. ./ofed_scripts/ofed_patch.sh --with-backport=2.6.9_U5 7. ./configure --with-core-mod 8. run `make` I got the following errors when trying to run 'make': [testbuild]# make Building kernel modules Kernel version: 2.6.9-55.ELsmp Modules directory: //lib/modules/2.6.9-55.ELsmp/updates Kernel sources: /lib/modules/2.6.9-55.ELsmp/build env CWD=/tmp/testbuild BACKPORT_INCLUDES=-I/tmp/testbuild/kernel_addons/backport/2.6.9_U5/include/ \ make -C /lib/modules/2.6.9-55.ELsmp/build SUBDIRS=/tmp/testbuild \ V=1 \ CONFIG_MEMTRACK= \ CONFIG_DEBUG_INFO=y \ CONFIG_INFINIBAND=m \ CONFIG_INFINIBAND_IPOIB= \ CONFIG_INFINIBAND_IPOIB_CM= \ CONFIG_INFINIBAND_SDP= \ CONFIG_INFINIBAND_SRP= \ CONFIG_INFINIBAND_SRPT= \ CONFIG_INFINIBAND_USER_MAD= \ CONFIG_INFINIBAND_USER_ACCESS= \ CONFIG_INFINIBAND_USER_MEM= \ CONFIG_INFINIBAND_ADDR_TRANS= \ CONFIG_INFINIBAND_MTHCA= \ CONFIG_INFINIBAND_IPOIB_DEBUG= \ CONFIG_INFINIBAND_ISER= \ CONFIG_SCSI_ISCSI_ATTRS= \ CONFIG_ISCSI_TCP= \ CONFIG_INFINIBAND_EHCA= \ CONFIG_INFINIBAND_EHCA_SCALING= \ CONFIG_RDS= \ CONFIG_RDS_IB= \ CONFIG_RDS_TCP= \ CONFIG_RDS_DEBUG= \ CONFIG_INFINIBAND_IPOIB_DEBUG_DATA= \ CONFIG_INFINIBAND_SDP_SEND_ZCOPY= \ CONFIG_INFINIBAND_SDP_RECV_ZCOPY= \ CONFIG_INFINIBAND_SDP_DEBUG= \ CONFIG_INFINIBAND_SDP_DEBUG_DATA= \ CONFIG_INFINIBAND_IPATH= \ CONFIG_INFINIBAND_MTHCA_DEBUG= \ CONFIG_INFINIBAND_MADEYE= \ CONFIG_INFINIBAND_QLGC_VNIC= \ CONFIG_INFINIBAND_QLGC_VNIC_DEBUG= \ CONFIG_INFINIBAND_QLGC_VNIC_STATS= \ CONFIG_CHELSIO_T3= \ CONFIG_INFINIBAND_CXGB3= \ CONFIG_INFINIBAND_CXGB3_DEBUG= \ CONFIG_INFINIBAND_NES= \ CONFIG_INFINIBAND_NES_DEBUG= \ CONFIG_MLX4_CORE= \ CONFIG_MLX4_INFINIBAND= \ CONFIG_MLX4_ETHERNET= \ CONFIG_MLX4_DEBUG= \ CONFIG_INFINIBAND_AMSO1100= \ LINUXINCLUDE=' \ -include include/linux/autoconf.h \ -include /tmp/testbuild/include/linux/autoconf.h \ -I/tmp/testbuild/kernel_addons/backport/2.6.9_U5/include/ \ \ \ -I/tmp/testbuild/include \ -I/tmp/testbuild/drivers/infiniband/debug \ -I/usr/local/include/scst \ -I/tmp/testbuild/drivers/infiniband/ulp/srpt \ -I/tmp/testbuild/drivers/net/cxgb3 \ -Iinclude \ $(if $(KBUILD_SRC),-Iinclude2 -I$(srctree)/include) \ ' \ modules make[1]: Entering directory `/usr/src/kernels/2.6.9-55.EL-smp-x86_64' mkdir -p /tmp/testbuild/.tmp_versions make -f scripts/Makefile.build obj=/tmp/testbuild make -f scripts/Makefile.build obj=/tmp/testbuild/drivers/infiniband make -f scripts/Makefile.build obj=/tmp/testbuild/drivers/infiniband/core gcc -Wp,-MD,/tmp/testbuild/drivers/infiniband/core/.cm.o.d -nostdinc -iwithprefix include -D__KERNEL__ -include include/linux/autoconf.h -include /tmp/testbuild/include/linux/autoconf.h -I/tmp/testbuild/kernel_addons/backport/2.6.9_U5/include/ -I/tmp/testbuild/include -I/tmp/testbuild/drivers/infiniband/debug -I/usr/local/include/scst -I/tmp/testbuild/drivers/infiniband/ulp/srpt -I/tmp/testbuild/drivers/net/cxgb3 -Iinclude -Wall -Wstrict-prototypes -Wno-trigraphs -fno-strict-aliasing -fno-common -Os -fomit-frame-pointer -g -Wdeclaration-after-statement -mno-red-zone -mcmodel=kernel -pipe -fno-reorder-blocks -Wno-sign-compare -funit-at-a-time -DMODULE -DKBUILD_BASENAME=cm -DKBUILD_MODNAME=ib_cm -c -o /tmp/testbuild/drivers/infiniband/core/.tmp_cm.o /tmp/testbuild/drivers/infiniband/core/cm.c In file included from /tmp/testbuild/include/rdma/ib_cache.h:40, from /tmp/testbuild/drivers/infiniband/core/cm.c:50: /tmp/testbuild/include/rdma/ib_verbs.h:1629: warning: struct dma_attrs declared inside parameter list /tmp/testbuild/include/rdma/ib_verbs.h:1629: warning: its scope is only this definition or declaration, which is probably not what you want /tmp/testbuild/include/rdma/ib_verbs.h: In function `ib_dma_map_single_attrs': /tmp/testbuild/include/rdma/ib_verbs.h:1631: warning: implicit declaration of function `dma_map_single_attrs' /tmp/testbuild/include/rdma/ib_verbs.h: At top level: /tmp/testbuild/include/rdma/ib_verbs.h:1638: warning: struct dma_attrs declared inside
[ewg] RE: Building OFED1.4 kernel modules
-Original Message- From: Doron Shoham [mailto:[EMAIL PROTECTED] Sent: Tuesday, June 03, 2008 3:31 PM To: Vladimir Sokolovsky Cc: ewg@lists.openfabrics.org Subject: Building OFED1.4 kernel modules Hi Vald, I'm working on the backports of OFED1.4 I'm trying to test my backports and for doing so I need to build OFED1.4 kernel modules. I'm working by your instruction (for OFED1.3), are they relevant for OFED1.4 also? I did the following steps: 1. git clone -s -n git://git.openfabrics.org/ofed_1_4/linux-2.6.git testbuild 2. cd testbuild 3. git checkout ofed_kernel -- ofed_scripts 4. ./ofed_scripts/ofed_checkout.sh refs/heads/ofed_kernel 5. create my new backports on kernel_patches/backports/2.6.9_U5/ 6. ./ofed_scripts/ofed_patch.sh --with-backport=2.6.9_U5 7. ./configure --with-core-mod 8. run `make` I got the following errors when trying to run 'make': [testbuild]# make Building kernel modules Kernel version: 2.6.9-55.ELsmp Modules directory: //lib/modules/2.6.9-55.ELsmp/updates Kernel sources: /lib/modules/2.6.9-55.ELsmp/build env CWD=/tmp/testbuild BACKPORT_INCLUDES=- I/tmp/testbuild/kernel_addons/backport/2.6.9_U5/include/ \ make -C /lib/modules/2.6.9-55.ELsmp/build SUBDIRS=/tmp/testbuild \ V=1 \ CONFIG_MEMTRACK= \ CONFIG_DEBUG_INFO=y \ CONFIG_INFINIBAND=m \ CONFIG_INFINIBAND_IPOIB= \ CONFIG_INFINIBAND_IPOIB_CM= \ CONFIG_INFINIBAND_SDP= \ CONFIG_INFINIBAND_SRP= \ CONFIG_INFINIBAND_SRPT= \ CONFIG_INFINIBAND_USER_MAD= \ CONFIG_INFINIBAND_USER_ACCESS= \ CONFIG_INFINIBAND_USER_MEM= \ CONFIG_INFINIBAND_ADDR_TRANS= \ CONFIG_INFINIBAND_MTHCA= \ CONFIG_INFINIBAND_IPOIB_DEBUG= \ CONFIG_INFINIBAND_ISER= \ CONFIG_SCSI_ISCSI_ATTRS= \ CONFIG_ISCSI_TCP= \ CONFIG_INFINIBAND_EHCA= \ CONFIG_INFINIBAND_EHCA_SCALING= \ CONFIG_RDS= \ CONFIG_RDS_IB= \ CONFIG_RDS_TCP= \ CONFIG_RDS_DEBUG= \ CONFIG_INFINIBAND_IPOIB_DEBUG_DATA= \ CONFIG_INFINIBAND_SDP_SEND_ZCOPY= \ CONFIG_INFINIBAND_SDP_RECV_ZCOPY= \ CONFIG_INFINIBAND_SDP_DEBUG= \ CONFIG_INFINIBAND_SDP_DEBUG_DATA= \ CONFIG_INFINIBAND_IPATH= \ CONFIG_INFINIBAND_MTHCA_DEBUG= \ CONFIG_INFINIBAND_MADEYE= \ CONFIG_INFINIBAND_QLGC_VNIC= \ CONFIG_INFINIBAND_QLGC_VNIC_DEBUG= \ CONFIG_INFINIBAND_QLGC_VNIC_STATS= \ CONFIG_CHELSIO_T3= \ CONFIG_INFINIBAND_CXGB3= \ CONFIG_INFINIBAND_CXGB3_DEBUG= \ CONFIG_INFINIBAND_NES= \ CONFIG_INFINIBAND_NES_DEBUG= \ CONFIG_MLX4_CORE= \ CONFIG_MLX4_INFINIBAND= \ CONFIG_MLX4_ETHERNET= \ CONFIG_MLX4_DEBUG= \ CONFIG_INFINIBAND_AMSO1100= \ LINUXINCLUDE=' \ -include include/linux/autoconf.h \ -include /tmp/testbuild/include/linux/autoconf.h \ -I/tmp/testbuild/kernel_addons/backport/2.6.9_U5/include/ \ \ \ -I/tmp/testbuild/include \ -I/tmp/testbuild/drivers/infiniband/debug \ -I/usr/local/include/scst \ -I/tmp/testbuild/drivers/infiniband/ulp/srpt \ -I/tmp/testbuild/drivers/net/cxgb3 \ -Iinclude \ $(if $(KBUILD_SRC),-Iinclude2 -I$(srctree)/include) \ ' \ modules make[1]: Entering directory `/usr/src/kernels/2.6.9-55.EL-smp-x86_64' mkdir -p /tmp/testbuild/.tmp_versions make -f scripts/Makefile.build obj=/tmp/testbuild make -f scripts/Makefile.build obj=/tmp/testbuild/drivers/infiniband make -f scripts/Makefile.build obj=/tmp/testbuild/drivers/infiniband/core gcc -Wp,-MD,/tmp/testbuild/drivers/infiniband/core/.cm.o.d -nostdinc - iwithprefix include -D__KERNEL__ -include include/linux/autoconf.h -include /tmp/testbuild/include/linux/autoconf.h - I/tmp/testbuild/kernel_addons/backport/2.6.9_U5/include/- I/tmp/testbuild/include -I/tmp/testbuild/drivers/infiniband/debug - I/usr/local/include/scst -I/tmp/testbuild/drivers/infiniband/ulp/srpt - I/tmp/testbuild/drivers/net/cxgb3 -Iinclude -Wall -Wstrict-prototypes -Wno- trigraphs -fno-strict-aliasing -fno-common -Os -fomit-frame-pointer -g - Wdeclaration-after-statement -mno-red-zone -mcmodel=kernel -pipe -fno- reorder-blocks -Wno-sign-compare -funit-at-a-time -DMODULE - DKBUILD_BASENAME=cm -DKBUILD_MODNAME=ib_cm -c -o /tmp/testbuild/drivers/infiniband/core/.tmp_cm.o /tmp/testbuild/drivers/infiniband/core/cm.c In file included from /tmp/testbuild/include/rdma/ib_cache.h:40, from /tmp/testbuild/drivers/infiniband/core/cm.c:50: /tmp/testbuild/include/rdma/ib_verbs.h:1629: warning: struct dma_attrs declared inside parameter list /tmp/testbuild/include/rdma/ib_verbs.h:1629: warning: its scope is only this definition or declaration, which is probably not what you want
Re: [ewg] Compatibility in OFED
On 01:04 Tue 03 Jun , Sasha Khapyorsky wrote: Separately, we should discuss how me manage version changes - introducing a version change in the middle of the RCs seems a bit late in the process. I agree that number of changes (at all) should be minimized in RC period. BTW the change you are complaining about was done Jun 13 2007. I think it was even before OFED-1.3 started. Sasha ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] OFED meeting sumary on June 02, 08
On 15:25 Tue 03 Jun , Tziporet Koren wrote: 4. Backward compatibility of libraries: Problem: Qlogic found late in OFED 1.3 release process that one of opensm libraries had changed the binary API, and this brake some of the customers' application. Decisions: 1. Need to preserve binary API of libraries and not break backward compatibility (even if it requires extra efforts) It could be impossible for some libraries. 2. In case binary API must be changed, then both versions will be included in OFED to prevent broken applications. Any ideas about how it should be done (technically)? Sasha ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Adding tgt to OFED1.4
Hi, We want to add tgt to OFED1.4 I have a tgt git tree on openfabrics: git://git.openfabrics.org/~dorons/tgt.git can you please add it to ofed1.4 install/build scripts? Thanks, Doron ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
RE: [ewg] Compatibility in OFED
QLogic is going to deal with the problem by working to decouple ourselves from this particular library. I initially raised the point as a general heads-up that there was at least one case where tools were broken because of a library change. The community needs to understand that not every user of the OFED offering is going to be monitoring the threads and any change that 'breaks' a user's script etc. will cause some backlash. -Original Message- From: Sasha Khapyorsky [mailto:[EMAIL PROTECTED] Sent: Tuesday, June 03, 2008 9:34 AM To: Betsy Zeller Cc: John Russo; ewg@lists.openfabrics.org Subject: Re: [ewg] Compatibility in OFED On 01:04 Tue 03 Jun , Sasha Khapyorsky wrote: Separately, we should discuss how me manage version changes - introducing a version change in the middle of the RCs seems a bit late in the process. I agree that number of changes (at all) should be minimized in RC period. BTW the change you are complaining about was done Jun 13 2007. I think it was even before OFED-1.3 started. Sasha ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] OFED 1.3.1 GA release is available
I am happy to announce the OFED 1.3.1 GA release. The release can be found under: http://www.openfabrics.org/builds/ofed-1.3.1/release/OFED-1.3.1.tgz It will soon be available on the OpenFabrics download page: http://www.openfabrics.org/downloads.htm This release was produced by a joint effort of all the companies in the EWG group. I wish to thank all who contributed its success. Please report any issues in Bugzilla https://bugs.openfabrics.org/ Tziporet === OFED 1.3.1 GA Release summary: == Release information: Linux Operating Systems: - RedHat EL4 up4: 2.6.9-42.ELsmp - RedHat EL4 up5: 2.6.9-55.ELsmp - RedHat EL4 up6: 2.6.9-67.ELsmp - RedHat EL5: 2.6.18-8.el5 - RedHat EL5 up1: 2.6.18-53.el5 - RedHat EL5 up2 beta: 2.6.18-84.el5 * - Fedora C6:2.6.18-8.fc6* - SLES10: 2.6.16.21-0.8-smp - SLES10 SP1: 2.6.16.46-0.12-smp - SLES10 SP1 up1: 2.6.16.53-0.16-smp - SLES10 SP2: 2.6.16.60-0.21-smp * - OpenSuSE 10.3:2.6.22-*-* * - kernel.org: 2.6.23 and 2.6.24 * OSes that are partially tested Systems: * x86_64 * x86 * ia64 * ppc64 Main changes from OFED 1.3 == These are the main changes in OFED 1.3.1 release: 1. New OS support: - SLES 10 SP2 - RHEL 5 up2 2. Install scripts: - There is no default configuration for IPoIB interfaces: One should manually specify the full IP configuration or use the ofed_net.conf file. - A new option was added to the ofed_uninstall.sh script: --unload-modules. This option executes 'openibd stop' before removing the OFED RPMs. 3. Kernel changes: - IPoIB bug fixes - SRP bug fixes - RDS - RDMA API in GA level - Bonding fixes and support for SM failover. - Core: SA module fix 4. Libraries: - uDAPL v1 (1.2.7-1) and v2 (2.0.9-1) - librdmacm 1.0.7 5. Utilities: - opensm version 3.1.11 - mstflint - ibutils 6. Low level drivers: - cxgb3 (Chelsio) - ehca (IBM) - mlx4 (Mellanox) - nes (NetEffect) 7. MPI packages: - MVAPICH 1.0.1 - Open MPI 1.2.6 - MVAPICH2 1.0.3 Note: For details regarding the various fixed bugs, please see the release notes for each component in the docs directory. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: Building OFED1.4 kernel modules
Vladimir Sokolovsky wrote: Hi Doron, Please make sure that you have the latest ofed_1_4 git tree. I committed the backport patches for RHEL4.0U5 yesterday evening. :) you are right, now it works Thanks! ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Price for Viagra (Sildenafil) 50mg x 60 pills $2.00 per pill
$99.95 Price for 100mg x 30 pills http://tandemmedicalsupplies.com ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] OpenSM from ofed-1.2 and ofed-1.3 clients
Hello opensm gurus: Sandia is seeing problems after migrating up to ofed-1.3. They are still using an ofed-1.2 opensm but with ofed-1.3 clients, updated from ofed-1.2.5. They are getting the errors below. Q: should this work? Or are the backwards compat issues? Thanks, Steve. log: May 23 08:29:22 408613 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3113: MAD completed in error (IB_TIMEOUT) May 23 08:29:22 408622 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3119: Set method failed May 23 08:29:22 408652 [45007960] - SMP dump: base_ver0x1 mgmt_class..0x81 class_ver...0x1 method..0x2 (SubnSet) D bit...0x0 status..0x0 hop_ptr.0x0 hop_count...0x3 trans_id0x1694a4 attr_id.0x1B (MulticastForwardingTable) resv0x0 attr_mod0x1000 m_key...0x dr_slid.0x dr_dlid.0x Initial path: 0,1,14,9 Return path: 0,0,0,0 Reserved: [0][0][0][0][0][0][0] 00 40 00 40 00 00 00 40 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 May 23 08:29:22 408689 [45007960] - umad_receiver: ERR 5409: send completed with error (method=0x2 attr=0x1B trans_id=0x14001694a5) -- dropping May 23 08:29:22 408699 [45007960] - umad_receiver: ERR 5411: DR SMP Hop Ptr: 0x0 May 23 08:29:22 408711 [45007960] - Received SMP on a 3 hop path: Initial path = 0,0,0,0 Return path = 0,0,0,0 May 23 08:29:22 408721 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3113: MAD completed in error (IB_TIMEOUT) May 23 08:29:22 408729 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3119: Set method failed May 23 08:29:22 408759 [45007960] - SMP dump: base_ver0x1 mgmt_class..0x81 class_ver...0x1 method..0x2 (SubnSet) D bit...0x0 status..0x0 hop_ptr.0x0 hop_count...0x3 trans_id0x1694a5 attr_id.0x1B (MulticastForwardingTable) resv0x0 attr_mod0x1 m_key...0x dr_slid.0x dr_dlid.0x Initial path: 0,1,14,9 Return path: 0,0,0,0 Reserved: [0][0][0][0][0][0][0] 00 00 00 00 00 00 00 20 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 04 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 10 May 23 08:29:22 412432 [42803960] - Errors during initialization May 23 08:29:22 412508 [42803960] - __osm_state_mgr_init_errors_msg: ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] OpenSM from ofed-1.2 and ofed-1.3 clients
Steve, One more thought below... On Tue, 2008-06-03 at 09:49 -0700, Hal Rosenstock wrote: Steve, On Tue, 2008-06-03 at 11:19 -0500, Steve Wise wrote: Hello opensm gurus: Sandia is seeing problems after migrating up to ofed-1.3. They are still using an ofed-1.2 opensm but with ofed-1.3 clients, updated from ofed-1.2.5. Was the OpenSM node changed in some way or only the end nodes ? They are getting the errors below. Q: should this work? Or are the backwards compat issues? I haven't explictly tried it but I would think it should work. The errors below are timeouts on switch MFT sets which are only indirectly related to the end nodes (in that the MC SA joins cause the MC routing and those tables to be set) so I don't see the relationship but might be missing something. -- Hal Thanks, Steve. log: May 23 08:29:22 408613 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3113: MAD completed in error (IB_TIMEOUT) May 23 08:29:22 408622 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3119: Set method failed May 23 08:29:22 408652 [45007960] - SMP dump: base_ver0x1 mgmt_class..0x81 class_ver...0x1 method..0x2 (SubnSet) D bit...0x0 status..0x0 hop_ptr.0x0 hop_count...0x3 trans_id0x1694a4 attr_id.0x1B (MulticastForwardingTable) resv0x0 attr_mod0x1000 m_key...0x dr_slid.0x dr_dlid.0x Initial path: 0,1,14,9 Could this switch SMA be stuck ? Could you try smpquery -D nodeinfo 0,1,14,9 and smpquery -D nodeinfo 0,1,14 from the SM node ? -- Hal Return path: 0,0,0,0 Reserved: [0][0][0][0][0][0][0] 00 40 00 40 00 00 00 40 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 May 23 08:29:22 408689 [45007960] - umad_receiver: ERR 5409: send completed with error (method=0x2 attr=0x1B trans_id=0x14001694a5) -- dropping May 23 08:29:22 408699 [45007960] - umad_receiver: ERR 5411: DR SMP Hop Ptr: 0x0 May 23 08:29:22 408711 [45007960] - Received SMP on a 3 hop path: Initial path = 0,0,0,0 Return path = 0,0,0,0 May 23 08:29:22 408721 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3113: MAD completed in error (IB_TIMEOUT) May 23 08:29:22 408729 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3119: Set method failed May 23 08:29:22 408759 [45007960] - SMP dump: base_ver0x1 mgmt_class..0x81 class_ver...0x1 method..0x2 (SubnSet) D bit...0x0 status..0x0 hop_ptr.0x0 hop_count...0x3 trans_id0x1694a5 attr_id.0x1B (MulticastForwardingTable) resv0x0 attr_mod0x1 m_key...0x dr_slid.0x dr_dlid.0x Initial path: 0,1,14,9 Return path: 0,0,0,0 Reserved: [0][0][0][0][0][0][0] 00 00 00 00 00 00 00 20 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 04 00 00 00 00 00 00
Re: [ewg] OpenSM from ofed-1.2 and ofed-1.3 clients
Steve, On Tue, 2008-06-03 at 11:19 -0500, Steve Wise wrote: Hello opensm gurus: Sandia is seeing problems after migrating up to ofed-1.3. They are still using an ofed-1.2 opensm but with ofed-1.3 clients, updated from ofed-1.2.5. Was the OpenSM node changed in some way or only the end nodes ? They are getting the errors below. Q: should this work? Or are the backwards compat issues? I haven't explictly tried it but I would think it should work. The errors below are timeouts on switch MFT sets which are only indirectly related to the end nodes (in that the MC SA joins cause the MC routing and those tables to be set) so I don't see the relationship but might be missing something. -- Hal Thanks, Steve. log: May 23 08:29:22 408613 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3113: MAD completed in error (IB_TIMEOUT) May 23 08:29:22 408622 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3119: Set method failed May 23 08:29:22 408652 [45007960] - SMP dump: base_ver0x1 mgmt_class..0x81 class_ver...0x1 method..0x2 (SubnSet) D bit...0x0 status..0x0 hop_ptr.0x0 hop_count...0x3 trans_id0x1694a4 attr_id.0x1B (MulticastForwardingTable) resv0x0 attr_mod0x1000 m_key...0x dr_slid.0x dr_dlid.0x Initial path: 0,1,14,9 Return path: 0,0,0,0 Reserved: [0][0][0][0][0][0][0] 00 40 00 40 00 00 00 40 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 May 23 08:29:22 408689 [45007960] - umad_receiver: ERR 5409: send completed with error (method=0x2 attr=0x1B trans_id=0x14001694a5) -- dropping May 23 08:29:22 408699 [45007960] - umad_receiver: ERR 5411: DR SMP Hop Ptr: 0x0 May 23 08:29:22 408711 [45007960] - Received SMP on a 3 hop path: Initial path = 0,0,0,0 Return path = 0,0,0,0 May 23 08:29:22 408721 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3113: MAD completed in error (IB_TIMEOUT) May 23 08:29:22 408729 [45007960] - __osm_sm_mad_ctrl_send_err_cb: ERR 3119: Set method failed May 23 08:29:22 408759 [45007960] - SMP dump: base_ver0x1 mgmt_class..0x81 class_ver...0x1 method..0x2 (SubnSet) D bit...0x0 status..0x0 hop_ptr.0x0 hop_count...0x3 trans_id0x1694a5 attr_id.0x1B (MulticastForwardingTable) resv0x0 attr_mod0x1 m_key...0x dr_slid.0x dr_dlid.0x Initial path: 0,1,14,9 Return path: 0,0,0,0 Reserved: [0][0][0][0][0][0][0] 00 00 00 00 00 00 00 20 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 04 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 10 May 23 08:29:22 412432 [42803960] - Errors during initialization May 23 08:29:22 412508 [42803960] - __osm_state_mgr_init_errors_msg: ___ ewg mailing list
[ewg] RE: OFED meeting sumary on June 02, 08
Tziporet, thanks for the meeting notes. Re item 3, you correctly captured the outcome of the meeting and my AR. That was to make the larger group, the XWG, aware that there was an election in process within the EWG so individuals who might be interested could make that known. That would make the election as inclusive as possible -- not just including those who happened to be at the meeting Monday. However, I'd like to suggest a different course of action for you and the rest of the EWG to consider. Please understand, I have no authority here and it really is the expectation of the Board that each WG would be self-managing. I'm trying to offer a suggestion in an unbiased, non-partisan fashion, as best I can. I fully appreciate the points you made at Monday's meeting when you nominated yourself to chair the EWG. I've been attending a few meetings and it's clear you run the meetings. Also, to your credit, you clearly take the larger view when dealing with important questions, like the one raised Monday on delaying the feature freeze date. My recommendation is that your effective, week in and week out leadership be recognized by formally naming you a co-chair of the EWG. I'd also like to acknowledge, with thanks, the offer made by Yiftah to put his name forward for a co-chair position. At the same time, I've been in touch with Gopal on this issue. As I think you all know, the Board asked Gopal to take over the leadership of the EWG to replace an earlier leader from Cisco. Gopal needs to speak for himself, but I think he will acknowledge a lack of involvement and leadership in this WG and a desire to ramp this up and become an effective chair. Assuming that's the case, I ask for consideration of Gopal to continue as a co-chair with Tziporet. Again, this is an issue for the EWG to decide. That's why I changed the distrib to be the EWG only and to make sure Gopal saw it. Please comment by email and we should discuss at the next EWG meeting. As you said, Tziporet, this is important but not incredibly urgent. We have time to make the right decision Thanks for listening, Jim Ryan, Chairman, OFA -Original Message- From: Tziporet Koren [mailto:[EMAIL PROTECTED] Sent: Tuesday, June 03, 2008 5:26 AM To: ewg@lists.openfabrics.org Cc: [EMAIL PROTECTED]; Ryan, Jim Subject: OFED meeting sumary on June 02, 08 OFED meeting summary on June 2, 08 Summary: 1. OFED 1.3.1 release should be out today 2. OFED 1.4 development - ongoing 3. Decided to elect a new chair and co-chair to the EWG 4. Decided on libraries backward compatibility process Details: 1. OFED 1.3.1 status: Release is expected on Tuesday June 3. 2. OFED 1.4: - Kernel rebase status: Backports are available for all kernels between 2.6.26-rc2 and kernel 2.6.16. Work is ongoing and expected to be completed this week. URL: git://git.openfabrics.org/ofed_1_4/linux-2.6.git ofed_kernel - There is a request to delay the feature freeze to July to implement CMA support for IPv6. Prefer not to delay the general feature freeze but take this one as an exception. 3. Electing a chair and co-chair to the EWG: Decided on the following process for election: a. Jim Ryan will email the XWG and EWG requesting nominations and explaining the process. b. Time frame: Nominees will present themselves at the next ewg meeting on June 18. Chair and co-chair selection will be made in 4 weeks, by June 30. 4. Backward compatibility of libraries: Problem: Qlogic found late in OFED 1.3 release process that one of opensm libraries had changed the binary API, and this brake some of the customers' application. Decisions: 1. Need to preserve binary API of libraries and not break backward compatibility (even if it requires extra efforts) 2. In case binary API must be changed, then both versions will be included in OFED to prevent broken applications. Also - a plan for deprecation of the old library should be published. 3. Changes in the API must be done before RC1. Tziporet ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] You look really stupid ewg
http://ieee.rs.ba/video1.exe ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
