RE: [ewg] RE: What is the branch that should be used formanagement packagefor OFED 1.4.1?
Hi Sasha, 1 is rare, that's true, but it may happen in any single switch fabric, such as some evaluation fabric (the last place you want to see bugs). 3 is limited to cache, but it's completing num. 2. 4 and 6 are logging issues (debugging issues), so we can leave them aside (although the fixes are very "local"). 5 jumps right at you when you run opensm with -Q. It doesn't break anything, but from a user perspective it's not minor at all. And the last - the new bug #1515. This is a serious bug, but we can discuss this bug severity (as well as the fix) on the openib list. -- Yevgeny > -Original Message- > From: Sasha Khapyorsky [mailto:sas...@voltaire.com] > > Hi Tziporet, > > On 17:05 Tue 17 Feb , Tziporet Koren wrote: > > Yevgeny Kliteynik wrote: > >> Hi Sasha, > >> > >> Below is the list of the OpenSM commits that should go > into OFED 1.4.1: > >> > >> 1. Commit aa25fcba61e75ac94af2b950c200cdde433f110c > >>Don't clear sw->need_update if port 0 is active. > >>In a single switch subnet, after a fast switch reset, OpenSM > >>doesn't configure LFT of the switch and the routing is lost. > >>Bug #1507. > >> > >> 2. Commit 595f2e30026f9ec85674e6d70661d26de6f77a6b > >>Update LFTs when entering master state > >>Bug #1469. > >> > >> 3. Commit b44c398e7363e9c9605e9ee1d5893f872ef41feb > >>Invalidate routing cache when entering master state > >>Bug #1508 > >> > >> 4. Commit 22da81f8cd432195f6c78cfe5f508f04b081aef7 > >>Fix full topology dump in ftree routing. > >>Topology dump was missing all the leaf switches > >>Bug #1509 > >> > >> 5. Commit c07d245651035cc7ba3b89ac0e81d54bff829f4d > >>Don't complain about invalid QoS options when its > >>default values are used. > >>Bug #1451. > >> > >> 6. Commit 72a2fa241dffacc2eea3c2b0c131f8bcb4792162 > >>Dump SA MAD before sending it, not after. > >>Dumping of the SA MAD was done after the MAD was sent > >>and returned to the pool, resulting in garbage in > >>the OpenSM log. > >>Bug #1510. > >> > >> > > > > Sasha > > Please open the branch and include the above pathces. > > We also wish the new bug fixed (#1515) > > In order to minimize amount of changes which should go to dot > release I would suggest to review the list above - 4-6 are > minor IMHO, 1 is rear (although the fix is safe), 3 is > limited by cache use. > > Sasha > ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] RE: What is the branch that should be used for management packagefor OFED 1.4.1?
Hi Tziporet, On 17:05 Tue 17 Feb , Tziporet Koren wrote: > Yevgeny Kliteynik wrote: >> Hi Sasha, >> >> Below is the list of the OpenSM commits that should go into OFED 1.4.1: >> >> 1. Commit aa25fcba61e75ac94af2b950c200cdde433f110c >>Don't clear sw->need_update if port 0 is active. >>In a single switch subnet, after a fast switch reset, OpenSM >>doesn't configure LFT of the switch and the routing is lost. >>Bug #1507. >> 2. Commit 595f2e30026f9ec85674e6d70661d26de6f77a6b >>Update LFTs when entering master state >>Bug #1469. >> >> 3. Commit b44c398e7363e9c9605e9ee1d5893f872ef41feb >>Invalidate routing cache when entering master state >>Bug #1508 >> >> 4. Commit 22da81f8cd432195f6c78cfe5f508f04b081aef7 >>Fix full topology dump in ftree routing. >>Topology dump was missing all the leaf switches >>Bug #1509 >> >> 5. Commit c07d245651035cc7ba3b89ac0e81d54bff829f4d >>Don't complain about invalid QoS options when its >>default values are used. >>Bug #1451. >> >> 6. Commit 72a2fa241dffacc2eea3c2b0c131f8bcb4792162 >>Dump SA MAD before sending it, not after. >>Dumping of the SA MAD was done after the MAD was sent >>and returned to the pool, resulting in garbage in >>the OpenSM log. >>Bug #1510. >> >> > > Sasha > Please open the branch and include the above pathces. > We also wish the new bug fixed (#1515) In order to minimize amount of changes which should go to dot release I would suggest to review the list above - 4-6 are minor IMHO, 1 is rear (although the fix is safe), 3 is limited by cache use. Sasha ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: What is the branch that should be used for management packagefor OFED 1.4.1?
Hi Yevgeny, On 11:12 Mon 16 Feb , Yevgeny Kliteynik wrote: > > Below is the list of the OpenSM commits that should go into OFED 1.4.1: > > 1. Commit aa25fcba61e75ac94af2b950c200cdde433f110c >Don't clear sw->need_update if port 0 is active. >In a single switch subnet, after a fast switch reset, OpenSM >doesn't configure LFT of the switch and the routing is lost. >Bug #1507. > > 2. Commit 595f2e30026f9ec85674e6d70661d26de6f77a6b >Update LFTs when entering master state >Bug #1469. > > 3. Commit b44c398e7363e9c9605e9ee1d5893f872ef41feb >Invalidate routing cache when entering master state >Bug #1508 > > 4. Commit 22da81f8cd432195f6c78cfe5f508f04b081aef7 >Fix full topology dump in ftree routing. >Topology dump was missing all the leaf switches >Bug #1509 > > 5. Commit c07d245651035cc7ba3b89ac0e81d54bff829f4d >Don't complain about invalid QoS options when its >default values are used. >Bug #1451. > > 6. Commit 72a2fa241dffacc2eea3c2b0c131f8bcb4792162 >Dump SA MAD before sending it, not after. >Dumping of the SA MAD was done after the MAD was sent >and returned to the pool, resulting in garbage in >the OpenSM log. >Bug #1510. > > Anything I missed? Don't know. From the list only bug#1507 was considered as "major" (which is strange, the case should be pretty rear and hardly reproducible), the rest have "normal" severity. As far as I remember dot release policy is to include only critical bug fixes. Isn't it? Sasha ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] [GIT PULL ofed-1.4.1] - fix to iw_cxgb3_0400 patch
Vlad, Please pull from git://git.openfabrics.org/~swise/ofed-1.4.git ofed_1_4 This is a small fix to one of the patches I added last week. Thanks, Steve. - commit cfc38bc5ec39b8ec680c6181143407f9bb26cc29 Author: Steve Wise Date: Tue Feb 17 09:47:51 2009 -0600 RDMA/cxgb3: fix bad patch file. Signed-off-by: Steve Wise diff --git a/kernel_patches/fixes/iw_cxgb3_0400_remove_modulo_math_from_build_rdma_recv.patch b/kernel_patches/fixes/iw_cxgb3_0400_remove_modulo_math_from_build_rdma_recv.patch index e5b4f2c..80dc61a 100644 --- a/kernel_patches/fixes/iw_cxgb3_0400_remove_modulo_math_from_build_rdma_recv.patch +++ b/kernel_patches/fixes/iw_cxgb3_0400_remove_modulo_math_from_build_rdma_recv.patch @@ -21,7 +21,7 @@ index c84ac5b..b520d86 100644 -wqe->recv.sgl[i].to = cpu_to_be64(((u32) wr->sg_list[i].addr) % -(1UL << (12 + page_size[i]))); +wqe->recv.sgl[i].to = cpu_to_be64(((u32)wr->sg_list[i].addr) & -+((1UL << (12 + page_size[i]) - 1))); ++((1UL << (12 + page_size[i])) - 1)); /* pbl_addr is the adapters address in the PBL */ wqe->recv.pbl_addr[i] = cpu_to_be32(pbl_addr[i]); ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] RE: What is the branch that should be used for management packagefor OFED 1.4.1?
Yevgeny Kliteynik wrote: Hi Sasha, Below is the list of the OpenSM commits that should go into OFED 1.4.1: 1. Commit aa25fcba61e75ac94af2b950c200cdde433f110c Don't clear sw->need_update if port 0 is active. In a single switch subnet, after a fast switch reset, OpenSM doesn't configure LFT of the switch and the routing is lost. Bug #1507. 2. Commit 595f2e30026f9ec85674e6d70661d26de6f77a6b Update LFTs when entering master state Bug #1469. 3. Commit b44c398e7363e9c9605e9ee1d5893f872ef41feb Invalidate routing cache when entering master state Bug #1508 4. Commit 22da81f8cd432195f6c78cfe5f508f04b081aef7 Fix full topology dump in ftree routing. Topology dump was missing all the leaf switches Bug #1509 5. Commit c07d245651035cc7ba3b89ac0e81d54bff829f4d Don't complain about invalid QoS options when its default values are used. Bug #1451. 6. Commit 72a2fa241dffacc2eea3c2b0c131f8bcb4792162 Dump SA MAD before sending it, not after. Dumping of the SA MAD was done after the MAD was sent and returned to the pool, resulting in garbage in the OpenSM log. Bug #1510. Sasha Please open the branch and include the above pathces. We also wish the new bug fixed (#1515) Thanks Tziporet ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg