Re: [pve-devel] 3.4: Changes in the way quorum is formed?
On Sat, 21 Feb 2015 08:14:12 +0100 (CET) Dietmar Maurer diet...@proxmox.com wrote: 22 patches? We could also wait for Redhat;-) Redhat seems eager to put the patches in production, even so eager that they are willing to cross-cut the normal sunrise period in the linux kernel community. To me that indicates that we are dealing with a really nasty bug which should never have passed QA! -- Hilsen/Regards Michael Rasmussen Get my public GnuPG keys: michael at rasmussen dot cc http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xD3C9A00E mir at datanom dot net http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE501F51C mir at miras dot org http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE3E80917 -- /usr/games/fortune -es says: I've been on a diet for two weeks and all I've lost is two weeks. -- Totie Fields pgpsHegoBs7EL.pgp Description: OpenPGP digital signature ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
On Fri, 20 Feb 2015 16:21:24 -0500 Eric Blevins ericlb...@gmail.com wrote: I can confirm this, IPOIB multicast seems to only work intermittently with pve-kernel-2.6.32-37-pve According to this thread RHEL 6.6 kernel has introduced a regression into IPoIB which brakes multicast. The thread referrers to 3 patches which should solve the issue. https://www.mail-archive.com/linux-rdma@vger.kernel.org/msg22511.html @Dietmar If you provide a new pve-kernel-2.6.32-37-pve with the 3 patches applied I will volunteer to test it. -- Hilsen/Regards Michael Rasmussen Get my public GnuPG keys: michael at rasmussen dot cc http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xD3C9A00E mir at datanom dot net http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE501F51C mir at miras dot org http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE3E80917 -- /usr/games/fortune -es says: I got the bill for my surgery. Now I know what those doctors were wearing masks for. -- James Boren pgpIQmK1YHzwh.pgp Description: OpenPGP digital signature ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
On Fri, 20 Feb 2015 00:29:36 +0100 Michael Rasmussen m...@datanom.net wrote: I am giving up for now and have reverted back to pve-kernel-2.6.32-34-pve. Doing the Same I forgot to mention that my conclusion is that the infiniband drivers delivered with pve-kernel-2.6.32-37-pve is broken. I can confirm this, IPOIB multicast seems to only work intermittently with pve-kernel-2.6.32-37-pve Eric ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
On Fri, 20 Feb 2015 23:35:09 +0100 Michael Rasmussen m...@datanom.net wrote: According to this thread RHEL 6.6 kernel has introduced a regression into IPoIB which brakes multicast. The thread referrers to 3 patches which should solve the issue. https://www.mail-archive.com/linux-rdma@vger.kernel.org/msg22511.html The complete patchset can be found here: http://www.mail-archive.com/linux-rdma@vger.kernel.org/msg22943.html -- Hilsen/Regards Michael Rasmussen Get my public GnuPG keys: michael at rasmussen dot cc http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xD3C9A00E mir at datanom dot net http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE501F51C mir at miras dot org http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE3E80917 -- /usr/games/fortune -es says: Please help keep the world clean: others may wish to use it. pgp9DbaCsTuLK.pgp Description: OpenPGP digital signature ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
According to this thread RHEL 6.6 kernel has introduced a regression into IPoIB which brakes multicast. The thread referrers to 3 patches which should solve the issue. https://www.mail-archive.com/linux-rdma@vger.kernel.org/msg22511.html The complete patchset can be found here: http://www.mail-archive.com/linux-rdma@vger.kernel.org/msg22943.html 22 patches? ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
[pve-devel] 3.4: Changes in the way quorum is formed?
Hi all, As a follow up to my post to the forum (http://forum.proxmox.com/threads/21083-Proxmox-VE-3-4-released!?p=107495#post107495) I was wondering if anything has changed in 3.4 in the way quorum is formed? -- Hilsen/Regards Michael Rasmussen Get my public GnuPG keys: michael at rasmussen dot cc http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xD3C9A00E mir at datanom dot net http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE501F51C mir at miras dot org http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE3E80917 -- /usr/games/fortune -es says: My father was a God-fearing man, but he never missed a copy of the New York Times, either. -- E. B. White pgpdRYYU0ZvXg.pgp Description: OpenPGP digital signature ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
On Thu, 19 Feb 2015 21:18:23 +0100 Michael Rasmussen m...@datanom.net wrote: Hi all, As a follow up to my post to the forum (http://forum.proxmox.com/threads/21083-Proxmox-VE-3-4-released!?p=107495#post107495) I was wondering if anything has changed in 3.4 in the way quorum is formed? It seems this is the case. Multicast over infiniband is broken on pve-kernel-2.6.32-37-pve!! Just to be curtain I added netmtu=2044 to totem in cluster.conf but this did not change anything and was not needed on pve-kernel-2.6.32-34-pve Can anybody confirm this? -- Hilsen/Regards Michael Rasmussen Get my public GnuPG keys: michael at rasmussen dot cc http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xD3C9A00E mir at datanom dot net http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE501F51C mir at miras dot org http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE3E80917 -- /usr/games/fortune -es says: Mollison's Bureaucracy Hypothesis: If an idea can survive a bureaucratic review and be implemented it wasn't worth doing. pgphr9pTbBZEb.pgp Description: OpenPGP digital signature ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
I am giving up for now and have reverted back to pve-kernel-2.6.32-34-pve. I forgot to mention that my conclusion is that the infiniband drivers delivered with pve-kernel-2.6.32-37-pve is broken. I verified the corosync versions, and there was no update recently. So I guess a driver issue is more likely. ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
On Fri, 20 Feb 2015 00:29:36 +0100 Michael Rasmussen m...@datanom.net wrote: I am giving up for now and have reverted back to pve-kernel-2.6.32-34-pve. I forgot to mention that my conclusion is that the infiniband drivers delivered with pve-kernel-2.6.32-37-pve is broken. -- Hilsen/Regards Michael Rasmussen Get my public GnuPG keys: michael at rasmussen dot cc http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xD3C9A00E mir at datanom dot net http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE501F51C mir at miras dot org http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE3E80917 -- /usr/games/fortune -es says: The American Dental Association announced today that most plaque tends to form on teeth around 4:00 PM in the afternoon. Film at 11:00. pgpKnlMtJXq5C.pgp Description: OpenPGP digital signature ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
On Thu, 19 Feb 2015 23:55:27 +0100 Michael Rasmussen m...@datanom.net wrote: Now it gets really strange. If I configure cluster to use unicast then suddenly multicast starts to work!!! I am giving up for now and have reverted back to pve-kernel-2.6.32-34-pve. -- Hilsen/Regards Michael Rasmussen Get my public GnuPG keys: michael at rasmussen dot cc http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xD3C9A00E mir at datanom dot net http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE501F51C mir at miras dot org http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE3E80917 -- /usr/games/fortune -es says: We're overpaying him, but he's worth it. -Samuel Goldwyn pgpBDo68bXqnC.pgp Description: OpenPGP digital signature ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
Re: [pve-devel] 3.4: Changes in the way quorum is formed?
On Thu, 19 Feb 2015 23:29:17 +0100 Michael Rasmussen m...@datanom.net wrote: It seems this is the case. Multicast over infiniband is broken on pve-kernel-2.6.32-37-pve!! Just to be curtain I added netmtu=2044 to totem in cluster.conf but this did not change anything and was not needed on pve-kernel-2.6.32-34-pve Can anybody confirm this? Now it gets really strange. If I configure cluster to use unicast then suddenly multicast starts to work!!! -- Hilsen/Regards Michael Rasmussen Get my public GnuPG keys: michael at rasmussen dot cc http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xD3C9A00E mir at datanom dot net http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE501F51C mir at miras dot org http://pgp.mit.edu:11371/pks/lookup?op=getsearch=0xE3E80917 -- /usr/games/fortune -es says: There's no use in having a dog and doing your own barking. pgppjJOi1jXRL.pgp Description: OpenPGP digital signature ___ pve-devel mailing list pve-devel@pve.proxmox.com http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-devel