From rhel_cluster at ckimaru.com Tue Oct 1 15:32:21 2013 From: rhel_cluster at ckimaru.com (Cedric Kimaru) Date: Tue, 1 Oct 2013 11:32:21 -0400 Subject: [Linux-cluster] Rhel 6.4 : GFS2 Mountgroups - flags 0x00000005 blocked, join Message-ID: Dear List, I'm running a Rhel 6.4 cluster and periodically i'm unable to mount some volumes. The volumes are iSCSI attached and clvm confirms them to be healthy and reachable. The mount fails, actually just hangs. The failing volumes have the"blocked,join" status. Any ideas on how to unblock these specific volumes without rebooting the whole cluster ? root at node12:~# uname -a Linux node12 2.6.32-358.18.1.el6.x86_64 #1 SMP Fri Aug 2 17:04:38 EDT 2013 x86_64 x86_64 x86_64 GNU/Linux root at node12:~# group_tool fence domain member count 6 victim count 0 victim now 0 master nodeid 3 wait state none members 1 3 10 11 12 16 dlm lockspaces name disk10-thin id 0xbcc604bc flags 0x00000008 fs_reg change member 4 joined 1 remove 0 failed 0 seq 1,1 members 3 10 11 12 name clvmd id 0x4104eefa flags 0x00000000 change member 6 joined 1 remove 0 failed 0 seq 4,4 members 1 3 10 11 12 16 gfs mountgroups name disk10-thin id 0x8016e569 flags 0x00000008 mounted change member 3 joined 1 remove 0 failed 0 seq 1,1 members 10 11 12 name cluster4_disk8 id 0xef70c9dc flags 0x00000005 blocked,join change member 5 joined 1 remove 0 failed 0 seq 3,3 members 3 10 11 12 16 name disk2 id 0xe1c9eb17 flags 0x00000005 blocked,join change member 3 joined 1 remove 0 failed 0 seq 1,1 members 3 11 12 -------------- next part -------------- An HTML attachment was scrubbed... URL: From joes_ith at zoho.com Sat Oct 5 18:10:16 2013 From: joes_ith at zoho.com (joes_ith) Date: Sat, 05 Oct 2013 11:10:16 -0700 Subject: [Linux-cluster] RHEL Cluster System Administrator, Cambridge UK Message-ID: <14189d00ffb.8273223934808969422.-5188157437859828942@zoho.com> http://www.embl.de/aboutus/jobs/searchjobs/index.php?newlang=1&ref=EBI_00329&back=%2Faboutus%2Fjobs%2Fsearchjobs%2Findex.php%3Floc%3D2%26list%3D1 -------------- next part -------------- An HTML attachment was scrubbed... URL: From rpeterso at redhat.com Mon Oct 7 14:00:03 2013 From: rpeterso at redhat.com (Bob Peterson) Date: Mon, 7 Oct 2013 10:00:03 -0400 (EDT) Subject: [Linux-cluster] gfs:gfs_assert_i+0x67/0x92 seen when node joining cluster In-Reply-To: <5CBE4DF16DF0DE4A99CCC64ACC08A8791434BBAC@G5W2714.americas.hpqcorp.net> References: <5CBE4DF16DF0DE4A99CCC64ACC08A8791434BBAC@G5W2714.americas.hpqcorp.net> Message-ID: <875604356.2880900.1381154403096.JavaMail.root@redhat.com> ----- Original Message ----- | Hello Folks, | RE: gfs:gfs_assert_i+0x67/0x92 seen when node joining cluster | | Has this been seen at other sites? | | Call Trace: | [] :gfs:gfs_assert_i+0x67/0x92 | [] :gfs:unlinked_scan_elements+0x99/0x180 | [] :gfs:gfs_dreread+0x87/0xc6 | [] :gfs:foreach_descriptor+0x229/0x305 | [] :gfs:fill_super+0x0/0x642 | [] :gfs:gfs_recover_dump+0xdd/0x14e | [] :gfs:gfs_make_fs_rw+0xc0/0x11a | [] :gfs:init_journal+0x279/0x34c | [] :gfs:fill_super+0x48e/0x642 | [] get_sb_bdev+0x10a/0x16c | [] vfs_kern_mount+0x93/0x11a | [] do_kern_mount+0x36/0x4d | [] do_mount+0x6a9/0x719 | [] enqueue_task+0x41/0x56 | [] do_sock_read+0xcf/0x110 | [] sock_aio_read+0x4f/0x5e | [] do_sync_read+0xc7/0x104 | [] zone_statistics+0x3e/0x6d | [] __alloc_pages+0x78/0x308 | [] sys_mount+0x8a/0xcd | | Sep 18 04:09:51 hpium2 syslogd 1.4.1: restart. | Sep 18 04:09:51 hpium2 kernel: klogd 1.4.1, log source = /proc/kmsg started. | | Regards, | James Hofmeister Hewlett Packard Linux Engineering Resolution Team | Hi James, This might possibly be caused by corruption in the GFS file system. It's hard to say without detailed analysis of the GFS metadata. There was likely an "assert" message that appeared earlier; do you have that message? Regards, Bob Peterson Red Hat File Systems From mgrac at redhat.com Mon Oct 7 15:44:19 2013 From: mgrac at redhat.com (Marek Grac) Date: Mon, 07 Oct 2013 17:44:19 +0200 Subject: [Linux-cluster] fence-agents-4.0.4 stable release Message-ID: <5252D6D3.2070408@redhat.com> Welcome to the fence-agents 4.0.4 release. This release includes minor bug fixes: * Symlink vulnerability for fence_vmware_soap and fence_ovh was fixed * new fence agent fence_netio was added to support Koukaam NETIO-230B PDU and similar devices * fence agent for zVM was completely rewritten and now it does not depends on s3270 package * Information about automatic unfence operation was added to metadata The new source tarball can be downloaded here: https://fedorahosted.org/releases/f/e/fence-agents/fence-agents-4.0.4.tar.xz To report bugs or issues: https://bugzilla.redhat.com/ Would you like to meet the cluster team or members of its community? Join us on IRC (irc.freenode.net #linux-cluster) and share your experience with other sysadministrators or power users. Thanks/congratulations to all people that contributed to achieve this great milestone. m, From rbravo at di.uc3m.es Mon Oct 7 22:01:12 2013 From: rbravo at di.uc3m.es (Rafael Bravo) Date: Tue, 08 Oct 2013 00:01:12 +0200 Subject: [Linux-cluster] slow NFS performance on GFS2 In-Reply-To: <52415B63.8060707@ac-versailles.fr> References: <52415B63.8060707@ac-versailles.fr> Message-ID: <52532F28.8030806@di.uc3m.es> El 24/09/2013 11:29, Olivier Desport escribi?: > Hello, > > I've installed a two nodes GFS2 cluster on Debian 7. The nodes are > connected to the datas by iSCSI and multipathing with a 10 Gb/s link. > I can write a 1g file with dd at 500 Mbytes/s. I export with NFS (on a > 10 Gb/s network) and I only can reach 220 Mbytes/s. I think that it's > a little bit far from 500 Mbytes/s... > > Do you how to tune my settings to increase the speed for NFS ? > > GFS2 mount : > /dev/vg-bigfiles/lv-bigfiles /export/bigfiles gfs2 > _netdev,nodiratime,noatime 0 0 > > NFS export : > /export/bigfiles > 172.16.0.0/16(fsid=2,rw,async,no_root_squash,no_subtree_check) > > mount on NFS clients : > nfs-server:/export/bigfiles /data/bigfiles nfs4 > _netdev,rw,user,nodiratime,noatime,intr 0 0 Use options on NFS clients: rsize=32768,wsize=32768 From olivier.desport at ac-versailles.fr Tue Oct 8 06:48:01 2013 From: olivier.desport at ac-versailles.fr (Olivier Desport) Date: Tue, 08 Oct 2013 08:48:01 +0200 Subject: [Linux-cluster] slow NFS performance on GFS2 In-Reply-To: <52532F28.8030806@di.uc3m.es> References: <52415B63.8060707@ac-versailles.fr> <52532F28.8030806@di.uc3m.es> Message-ID: <5253AAA1.3010801@ac-versailles.fr> Le 08/10/2013 00:01, Rafael Bravo a ?crit : > El 24/09/2013 11:29, Olivier Desport escribi?: >> Hello, >> >> I've installed a two nodes GFS2 cluster on Debian 7. The nodes are >> connected to the datas by iSCSI and multipathing with a 10 Gb/s link. >> I can write a 1g file with dd at 500 Mbytes/s. I export with NFS (on >> a 10 Gb/s network) and I only can reach 220 Mbytes/s. I think that >> it's a little bit far from 500 Mbytes/s... >> >> Do you how to tune my settings to increase the speed for NFS ? >> >> GFS2 mount : >> /dev/vg-bigfiles/lv-bigfiles /export/bigfiles gfs2 >> _netdev,nodiratime,noatime 0 0 >> >> NFS export : >> /export/bigfiles >> 172.16.0.0/16(fsid=2,rw,async,no_root_squash,no_subtree_check) >> >> mount on NFS clients : >> nfs-server:/export/bigfiles /data/bigfiles nfs4 >> _netdev,rw,user,nodiratime,noatime,intr 0 0 > Use options on NFS clients: rsize=32768,wsize=32768 > > > Thnaks. I've already tried these settings and it doesn't inscrease the perfs. -------------- next part -------------- An HTML attachment was scrubbed... URL: From merc1984 at f-m.fm Tue Oct 15 23:33:38 2013 From: merc1984 at f-m.fm (merc1984 at f-m.fm) Date: Tue, 15 Oct 2013 16:33:38 -0700 Subject: [Linux-cluster] Building a HP Cluster Message-ID: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> Hi, I'd like to build a high performance cluster out of my three nodes, but there is such a haystack of random and old info out there I'm pretty confused. This will just be for learning. All nodes are very different and have different resources, joined by a router. OS is Fed. -- http://www.fastmail.fm - A no graphics, no pop-ups email service From giulio.dippolito at gmail.com Wed Oct 16 12:57:41 2013 From: giulio.dippolito at gmail.com (Giulio D'Ippolito) Date: Wed, 16 Oct 2013 14:57:41 +0200 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> Message-ID: well, I guess the best option will be starting with the official documentation. https://access.redhat.com/site/documentation/Red_Hat_Enterprise_Linux/?locale=en-US The Red Hat cluster administrator guide is clear and up-to-date 2013/10/16 > Hi, I'd like to build a high performance cluster out of my three nodes, > but there is such a haystack of random and old info out there I'm pretty > confused. > > This will just be for learning. All nodes are very different and have > different resources, joined by a router. > > OS is Fed. > > > > -- > http://www.fastmail.fm - A no graphics, no pop-ups email service > > -- > Linux-cluster mailing list > Linux-cluster at redhat.com > https://www.redhat.com/mailman/listinfo/linux-cluster > -------------- next part -------------- An HTML attachment was scrubbed... URL: From tony at specialistdevelopment.com Wed Oct 16 15:53:47 2013 From: tony at specialistdevelopment.com (Tony Davis) Date: Wed, 16 Oct 2013 16:53:47 +0100 Subject: [Linux-cluster] GNBD Multiple GNBD Server Nodes Message-ID: <87C18629-514D-455C-B5C3-0CA31EF0F577@specialistdevelopment.com> Hi, I wonder if anyone can help with a problem I'm having trying to setup multiple GNBD server nodes. I have 2x GNBD servers configured which both have access to the same SAN storage backend with two clients connected. I currently have the 2 clients connected to the one node and the GNBD setup works fine. I am trying to introduce some further redundancy to the backend with the 2x GNBD Server nodes. Unfortunately I haven't been able to find any information on such a setup, apart from the odd snippet here and there about the cluster config. If I understand correctly it works in the same way that a server is connected to a SAN, in that you need to setup multipath to see both GNBD servers from the client, which creates the two redundant paths back to the servers. Again I haven't been able to find any information on this apart from a really old mailing list, which didn't really help. Can anyone help with this please? Kind Regards Tony From merc1984 at f-m.fm Wed Oct 16 16:24:34 2013 From: merc1984 at f-m.fm (merc1984 at f-m.fm) Date: Wed, 16 Oct 2013 09:24:34 -0700 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> Message-ID: <1381940674.17690.34764577.58A4F83C@webmail.messagingengine.com> I know. But keep in mind that RedHat's cluster is --High Availability--. What I am asking about is --High Performance-- as I say below. On Wed, Oct 16, 2013, at 5:57, Giulio D'Ippolito wrote: > well, I guess the best option will be starting with the official > documentation. > https://access.redhat.com/site/documentation/Red_Hat_Enterprise_Linux/?locale=en-US > The Red Hat cluster administrator guide is clear and up-to-date > > > > > 2013/10/16 > > > Hi, I'd like to build a high performance cluster out of my three nodes, > > but there is such a haystack of random and old info out there I'm pretty > > confused. > > > > This will just be for learning. All nodes are very different and have > > different resources, joined by a router. > > > > OS is Fed. > > > > > > > > -- > > http://www.fastmail.fm - A no graphics, no pop-ups email service > > > > -- > > Linux-cluster mailing list > > Linux-cluster at redhat.com > > https://www.redhat.com/mailman/listinfo/linux-cluster > > > -- > Linux-cluster mailing list > Linux-cluster at redhat.com > https://www.redhat.com/mailman/listinfo/linux-cluster -- http://www.fastmail.fm - Faster than the air-speed velocity of an unladen european swallow From lists at alteeve.ca Wed Oct 16 16:30:57 2013 From: lists at alteeve.ca (Digimer) Date: Wed, 16 Oct 2013 12:30:57 -0400 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: <1381940674.17690.34764577.58A4F83C@webmail.messagingengine.com> References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> <1381940674.17690.34764577.58A4F83C@webmail.messagingengine.com> Message-ID: <525EBF41.1070301@alteeve.ca> On 16/10/13 12:24, merc1984 at f-m.fm wrote: > I know. But keep in mind that RedHat's cluster is --High > Availability--. > > What I am asking about is --High Performance-- as I say below. As was mentioned in IRC, you need to come up with a particular goal in order for people to offer useful advice. What do you want to make go faster? Answer that and you will start getting help. Cheers -- Digimer Papers and Projects: https://alteeve.ca/w/ What if the cure for cancer is trapped in the mind of a person without access to education? From merc1984 at f-m.fm Wed Oct 16 17:01:58 2013 From: merc1984 at f-m.fm (merc1984 at f-m.fm) Date: Wed, 16 Oct 2013 10:01:58 -0700 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: <525EBF41.1070301@alteeve.ca> References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> <1381940674.17690.34764577.58A4F83C@webmail.messagingengine.com> <525EBF41.1070301@alteeve.ca> Message-ID: <1381942918.1844.34778437.4D358F80@webmail.messagingengine.com> And as I said several times in IRC, I am doing this for purposes of -learning-. How many times do I have to say it? I am doing this to learn about HP clusters. I am trying to get a handle on the landscape and the practical aspects of building a supercomputer. And I said this again in my first email here, that I am doing this to learn. Seems like you two don't have enough experience with this to advise, so please stand down. I'll figure out my own answers if this is the landscape. On Wed, Oct 16, 2013, at 9:30, Digimer wrote: > On 16/10/13 12:24, merc1984 at f-m.fm wrote: > > I know. But keep in mind that RedHat's cluster is --High > > Availability--. > > > > What I am asking about is --High Performance-- as I say below. > > As was mentioned in IRC, you need to come up with a particular goal in > order for people to offer useful advice. What do you want to make go > faster? Answer that and you will start getting help. > > Cheers > > -- > Digimer > Papers and Projects: https://alteeve.ca/w/ > What if the cure for cancer is trapped in the mind of a person without > access to education? > > -- > Linux-cluster mailing list > Linux-cluster at redhat.com > https://www.redhat.com/mailman/listinfo/linux-cluster -- http://www.fastmail.fm - mmm... Fastmail... From morpheus.ibis at gmail.com Wed Oct 16 17:11:15 2013 From: morpheus.ibis at gmail.com (Pavel Herrmann) Date: Wed, 16 Oct 2013 19:11:15 +0200 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: <1381942918.1844.34778437.4D358F80@webmail.messagingengine.com> References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> <525EBF41.1070301@alteeve.ca> <1381942918.1844.34778437.4D358F80@webmail.messagingengine.com> Message-ID: <1433214.cNihUPhze3@bloomfield> Hey Im in no way an expert in the field, but i might be able to help you a bit for a HPC cluster you would usually have a HA cluster for shared resources (like storage). then you would have a couple of compute nodes, preferrably with a fast interconnect (infiniband) the HPC part would be part of the application, be it MPI or hadoop or whatever On Wednesday 16 of October 2013 10:01:58 merc1984 at f-m.fm wrote: > And as I said several times in IRC, I am doing this for purposes of > -learning-. How many times do I have to say it? > > I am doing this to learn about HP clusters. I am trying to get a handle > on the landscape and the practical aspects of building a supercomputer. > > And I said this again in my first email here, that I am doing this to > learn. > > Seems like you two don't have enough experience with this to advise, so > please stand down. I'll figure out my own answers if this is the > landscape. > > On Wed, Oct 16, 2013, at 9:30, Digimer wrote: > > On 16/10/13 12:24, merc1984 at f-m.fm wrote: > > > I know. But keep in mind that RedHat's cluster is --High > > > Availability--. > > > > > > What I am asking about is --High Performance-- as I say below. > > > > As was mentioned in IRC, you need to come up with a particular goal in > > order for people to offer useful advice. What do you want to make go > > faster? Answer that and you will start getting help. > > > > Cheers From merc1984 at f-m.fm Wed Oct 16 17:18:07 2013 From: merc1984 at f-m.fm (merc1984 at f-m.fm) Date: Wed, 16 Oct 2013 10:18:07 -0700 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: <1433214.cNihUPhze3@bloomfield> References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> <525EBF41.1070301@alteeve.ca> <1381942918.1844.34778437.4D358F80@webmail.messagingengine.com> <1433214.cNihUPhze3@bloomfield> Message-ID: <1381943887.9107.34785829.334BBEC7@webmail.messagingengine.com> Oh ho, thank you Pavel. So a HA cluster would be the base. From my research it seems that oVirt+Gluster is up-and-coming. Uses KVM as a base, which should give flexibility. I'd also like to find out what Amazon AWS uses for their ECC. Whether it's based on open-source or is entirely in-house. On Wed, Oct 16, 2013, at 10:11, Pavel Herrmann wrote: > Hey > > Im in no way an expert in the field, but i might be able to help you a > bit > > for a HPC cluster you would usually have a HA cluster for shared > resources > (like storage). then you would have a couple of compute nodes, > preferrably > with a fast interconnect (infiniband) > > the HPC part would be part of the application, be it MPI or hadoop or > whatever > > > On Wednesday 16 of October 2013 10:01:58 merc1984 at f-m.fm wrote: > > And as I said several times in IRC, I am doing this for purposes of > > -learning-. How many times do I have to say it? > > > > I am doing this to learn about HP clusters. I am trying to get a handle > > on the landscape and the practical aspects of building a supercomputer. > > > > And I said this again in my first email here, that I am doing this to > > learn. > > > > Seems like you two don't have enough experience with this to advise, so > > please stand down. I'll figure out my own answers if this is the > > landscape. > > > > On Wed, Oct 16, 2013, at 9:30, Digimer wrote: > > > On 16/10/13 12:24, merc1984 at f-m.fm wrote: > > > > I know. But keep in mind that RedHat's cluster is --High > > > > Availability--. > > > > > > > > What I am asking about is --High Performance-- as I say below. > > > > > > As was mentioned in IRC, you need to come up with a particular goal in > > > order for people to offer useful advice. What do you want to make go > > > faster? Answer that and you will start getting help. > > > > > > Cheers > -- http://www.fastmail.fm - Send your email first class From merc1984 at f-m.fm Wed Oct 16 17:55:28 2013 From: merc1984 at f-m.fm (merc1984 at f-m.fm) Date: Wed, 16 Oct 2013 10:55:28 -0700 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: <1381943887.9107.34785829.334BBEC7@webmail.messagingengine.com> References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> <525EBF41.1070301@alteeve.ca> <1381942918.1844.34778437.4D358F80@webmail.messagingengine.com> <1433214.cNihUPhze3@bloomfield> <1381943887.9107.34785829.334BBEC7@webmail.messagingengine.com> Message-ID: <1381946128.24452.34801209.42A6F93D@webmail.messagingengine.com> It is the case that Amazon's AWS is entirely in-house. But enough information is here: EC2 Origins: http://blog.b3k.us/2009/01/25/ec2-origins.html To indicate that oVirt + Gluster would be a good start, at least off-the-shelf. -- http://www.fastmail.fm - A no graphics, no pop-ups email service From merc1984 at f-m.fm Wed Oct 16 18:44:01 2013 From: merc1984 at f-m.fm (merc1984 at f-m.fm) Date: Wed, 16 Oct 2013 11:44:01 -0700 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: <1381946128.24452.34801209.42A6F93D@webmail.messagingengine.com> References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> <525EBF41.1070301@alteeve.ca> <1381942918.1844.34778437.4D358F80@webmail.messagingengine.com> <1433214.cNihUPhze3@bloomfield> <1381943887.9107.34785829.334BBEC7@webmail.messagingengine.com> <1381946128.24452.34801209.42A6F93D@webmail.messagingengine.com> Message-ID: <1381949041.13951.34821093.3CE83A33@webmail.messagingengine.com> ... And development is smokin'... Testing oVirt 3.3 with Nested KVM http://community.redhat.com/testing-ovirt-3-3-with-nested-kvm/ +Up and Running with oVirt 3.3 http://community.redhat.com/up-and-running-with-ovirt-3-3/ oVirt 3.3 Spices Up the Software Defined Datacenter with OpenStack and Gluster Integration http://community.redhat.com/ovirt-3-3-spices-up-the-software-defined-datacenter-with-openstack-and-gluster-integration/ oVirt 3.3, Glusterized http://community.redhat.com/ovirt-3-3-glusterized/ Neutron Networking on OpenStack for Networking Dummies http://community.redhat.com/neutron-networking-on-openstack-for-networking-dummies/ On Wed, Oct 16, 2013, at 10:55, merc1984 at f-m.fm wrote: > It is the case that Amazon's AWS is entirely in-house. > > But enough information is here: > EC2 Origins: http://blog.b3k.us/2009/01/25/ec2-origins.html > > To indicate that oVirt + Gluster would be a good start, at least > off-the-shelf. > > > -- > http://www.fastmail.fm - A no graphics, no pop-ups email service > > -- > Linux-cluster mailing list > Linux-cluster at redhat.com > https://www.redhat.com/mailman/listinfo/linux-cluster -- http://www.fastmail.fm - Accessible with your email software or over the web From merc1984 at f-m.fm Wed Oct 16 19:09:56 2013 From: merc1984 at f-m.fm (merc1984 at f-m.fm) Date: Wed, 16 Oct 2013 12:09:56 -0700 Subject: [Linux-cluster] Building a HP Cluster In-Reply-To: <1381949041.13951.34821093.3CE83A33@webmail.messagingengine.com> References: <1381880018.14720.34462481.786E49C7@webmail.messagingengine.com> <525EBF41.1070301@alteeve.ca> <1381942918.1844.34778437.4D358F80@webmail.messagingengine.com> <1433214.cNihUPhze3@bloomfield> <1381943887.9107.34785829.334BBEC7@webmail.messagingengine.com> <1381946128.24452.34801209.42A6F93D@webmail.messagingengine.com> <1381949041.13951.34821093.3CE83A33@webmail.messagingengine.com> Message-ID: <1381950596.24692.34828657.57BFBE49@webmail.messagingengine.com> But, according to this http://community.redhat.com/up-and-running-with-ovirt-3-3/ ... hardware virtualization extensions are mandatory, and the Atom D510 in my backups server does not qualify. So it can't join the cluster. I couldn't possible have foreseen this years ago when I built the machine. http://www.supermicro.com/products/motherboard/ATOM/ICH9/X7SPA.cfm?typ=H&IPMI=Y For heaven's sake, that was my first candidate... not worth it to replace the mobo for this. They may not even make a miniITX with IPMI and VT-x. On Wed, Oct 16, 2013, at 11:44, merc1984 at f-m.fm wrote: > > ... And development is smokin'... > > Testing oVirt 3.3 with Nested KVM > http://community.redhat.com/testing-ovirt-3-3-with-nested-kvm/ > > +Up and Running with oVirt 3.3 > http://community.redhat.com/up-and-running-with-ovirt-3-3/ > > oVirt 3.3 Spices Up the Software Defined Datacenter with OpenStack and > Gluster Integration > http://community.redhat.com/ovirt-3-3-spices-up-the-software-defined-datacenter-with-openstack-and-gluster-integration/ > > oVirt 3.3, Glusterized > http://community.redhat.com/ovirt-3-3-glusterized/ > > Neutron Networking on OpenStack for Networking Dummies > http://community.redhat.com/neutron-networking-on-openstack-for-networking-dummies/ > > > > On Wed, Oct 16, 2013, at 10:55, merc1984 at f-m.fm wrote: > > It is the case that Amazon's AWS is entirely in-house. > > > > But enough information is here: > > EC2 Origins: http://blog.b3k.us/2009/01/25/ec2-origins.html > > > > To indicate that oVirt + Gluster would be a good start, at least > > off-the-shelf. > > > > > > -- > > http://www.fastmail.fm - A no graphics, no pop-ups email service > > > > -- > > Linux-cluster mailing list > > Linux-cluster at redhat.com > > https://www.redhat.com/mailman/listinfo/linux-cluster > > -- > http://www.fastmail.fm - Accessible with your email software > or over the web > > -- > Linux-cluster mailing list > Linux-cluster at redhat.com > https://www.redhat.com/mailman/listinfo/linux-cluster -- http://www.fastmail.fm - A fast, anti-spam email service. From yamato at redhat.com Thu Oct 17 12:28:40 2013 From: yamato at redhat.com (Masatake YAMATO) Date: Thu, 17 Oct 2013 21:28:40 +0900 (JST) Subject: [Linux-cluster] [PATCH] totemsrp: Show English message when memb_state_gather_enter is called Message-ID: <20131017.212840.1985968949959330205.yamato@redhat.com> The reason why memb_state_gather_enter is invoked was printed in integer code. This patch introduces human readable English messages for the code. Signed-off-by: Masatake YAMATO --- exec/totemsrp.c | 88 ++++++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 69 insertions(+), 19 deletions(-) diff --git a/exec/totemsrp.c b/exec/totemsrp.c index 8c7698f..f6e31d7 100644 --- a/exec/totemsrp.c +++ b/exec/totemsrp.c @@ -524,6 +524,55 @@ struct message_handlers { int endian_conversion_needed); }; +enum gather_state_from { + TOTEMSRP_GSFROM_CONSENSUS_TIMEOUT = 0, + TOTEMSRP_GSFROM_GATHER_MISSING1 = 1, + TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_OPERATIONAL_STATE = 2, + TOTEMSRP_GSFROM_THE_CONSENSUS_TIMEOUT_EXPIRED = 3, + TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_COMMIT_STATE = 4, + TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_RECOVERY_STATE = 5, + TOTEMSRP_GSFROM_FAILED_TO_RECEIVE = 6, + TOTEMSRP_GSFROM_FOREIGN_MESSAGE_IN_OPERATIONAL_STATE = 7, + TOTEMSRP_GSFROM_FOREIGN_MESSAGE_IN_GATHER_STATE = 8, + TOTEMSRP_GSFROM_MERGE_DURING_OPERATIONAL_STATE = 9, + TOTEMSRP_GSFROM_MERGE_DURING_GATHER_STATE = 10, + TOTEMSRP_GSFROM_MERGE_DURING_JOIN = 11, + TOTEMSRP_GSFROM_JOIN_DURING_OPERATIONAL_STATE = 12, + TOTEMSRP_GSFROM_JOIN_DURING_COMMIT_STATE = 13, + TOTEMSRP_GSFROM_JOIN_DURING_RECOVERY = 14, + TOTEMSRP_GSFROM_INTERFACE_CHANGE = 15, + TOTEMSRP_GSFROM_MAX = TOTEMSRP_GSFROM_INTERFACE_CHANGE, +}; + +const char* gather_state_from_desc [] = { + [TOTEMSRP_GSFROM_CONSENSUS_TIMEOUT] = "consensus timeout", + [TOTEMSRP_GSFROM_GATHER_MISSING1] = "MISSING", + [TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_OPERATIONAL_STATE] = "The token was lost in the OPERATIONAL state.", + [TOTEMSRP_GSFROM_THE_CONSENSUS_TIMEOUT_EXPIRED] = "The consensus timeout expired.", + [TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_COMMIT_STATE] = "The token was lost in the COMMIT state.", + [TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_RECOVERY_STATE] = "The token was lost in the RECOVERY state.", + [TOTEMSRP_GSFROM_FAILED_TO_RECEIVE] = "failed to receive", + [TOTEMSRP_GSFROM_FOREIGN_MESSAGE_IN_OPERATIONAL_STATE] = "foreign message in operational state", + [TOTEMSRP_GSFROM_FOREIGN_MESSAGE_IN_GATHER_STATE] = "foreign message in gather state", + [TOTEMSRP_GSFROM_MERGE_DURING_OPERATIONAL_STATE] = "merge during operational state", + [TOTEMSRP_GSFROM_MERGE_DURING_GATHER_STATE] = "merge during gather state", + [TOTEMSRP_GSFROM_MERGE_DURING_JOIN] = "merge during join", + [TOTEMSRP_GSFROM_JOIN_DURING_OPERATIONAL_STATE] = "join during operational state", + [TOTEMSRP_GSFROM_JOIN_DURING_COMMIT_STATE] = "join during commit state", + [TOTEMSRP_GSFROM_JOIN_DURING_RECOVERY] = "join during recovery", + [TOTEMSRP_GSFROM_INTERFACE_CHANGE] = "interface change", +}; + +const char* gsfrom_to_msg(enum gather_state_from gsfrom) +{ + if (0 <= gsfrom && gsfrom <= TOTEMSRP_GSFROM_MAX) { + return gather_state_from_desc[gsfrom]; + } + else { + return "UNKNOWN"; + } +} + /* * forward decls */ @@ -586,7 +635,7 @@ static void memb_leave_message_send (struct totemsrp_instance *instance); static void memb_ring_id_create_or_load (struct totemsrp_instance *, struct memb_ring_id *); static void token_callbacks_execute (struct totemsrp_instance *instance, enum totem_callback_token_type type); -static void memb_state_gather_enter (struct totemsrp_instance *instance, int gather_from); +static void memb_state_gather_enter (struct totemsrp_instance *instance, gather_state_from gather_from); static void messages_deliver_to_app (struct totemsrp_instance *instance, int skip, unsigned int end_point); static int orf_token_mcast (struct totemsrp_instance *instance, struct orf_token *oken, int fcc_mcasts_allowed); @@ -1601,7 +1650,7 @@ static void memb_state_consensus_timeout_expired ( memb_set_merge (no_consensus_list, no_consensus_list_entries, instance->my_failed_list, &instance->my_failed_list_entries); - memb_state_gather_enter (instance, 0); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_CONSENSUS_TIMEOUT); } } @@ -1623,7 +1672,7 @@ static void timer_function_pause_timeout (void *data) static void memb_recovery_state_token_loss (struct totemsrp_instance *instance) { old_ring_state_restore (instance); - memb_state_gather_enter (instance, 5); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_RECOVERY_STATE); instance->stats.recovery_token_lost++; } @@ -1638,7 +1687,7 @@ static void timer_function_orf_token_timeout (void *data) log_printf (instance->totemsrp_log_level_notice, "A processor failed, forming new configuration."); totemrrp_iface_check (instance->totemrrp_context); - memb_state_gather_enter (instance, 2); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_OPERATIONAL_STATE); instance->stats.operational_token_lost++; break; @@ -1646,14 +1695,14 @@ static void timer_function_orf_token_timeout (void *data) log_printf (instance->totemsrp_log_level_debug, "The consensus timeout expired."); memb_state_consensus_timeout_expired (instance); - memb_state_gather_enter (instance, 3); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_THE_CONSENSUS_TIMEOUT_EXPIRED); instance->stats.gather_token_lost++; break; case MEMB_STATE_COMMIT: log_printf (instance->totemsrp_log_level_debug, "The token was lost in the COMMIT state."); - memb_state_gather_enter (instance, 4); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_THE_TOKEN_WAS_LOST_IN_THE_COMMIT_STATE); instance->stats.commit_token_lost++; break; @@ -1986,7 +2035,7 @@ static void memb_state_operational_enter (struct totemsrp_instance *instance) static void memb_state_gather_enter ( struct totemsrp_instance *instance, - int gather_from) + gather_state_from gather_from) { instance->orf_token_discard = 1; @@ -2033,12 +2082,13 @@ static void memb_state_gather_enter ( memb_consensus_set (instance, &instance->my_id); log_printf (instance->totemsrp_log_level_debug, - "entering GATHER state from %d.", gather_from); + "entering GATHER state from %d(%s).", + gather_from, gsfrom_to_msg(gather_from)); instance->memb_state = MEMB_STATE_GATHER; instance->stats.gather_entered++; - if (gather_from == 3) { + if (TOTEMSRP_GSFROM_THE_CONSENSUS_TIMEOUT_EXPIRED == 3) { /* * State 3 means gather, so we are continuously gathering. */ @@ -3719,7 +3769,7 @@ printf ("token seq %d\n", token->seq); instance->my_failed_list, &instance->my_failed_list_entries); - memb_state_gather_enter (instance, 6); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_FAILED_TO_RECEIVE); } else { instance->my_token_seq = token->token_seq; token->token_seq += 1; @@ -3974,7 +4024,7 @@ static int message_handler_mcast ( memb_set_merge ( &mcast_header.system_from, 1, instance->my_proc_list, &instance->my_proc_list_entries); - memb_state_gather_enter (instance, 7); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_FOREIGN_MESSAGE_IN_OPERATIONAL_STATE); break; case MEMB_STATE_GATHER: @@ -3986,7 +4036,7 @@ static int message_handler_mcast ( memb_set_merge (&mcast_header.system_from, 1, instance->my_proc_list, &instance->my_proc_list_entries); - memb_state_gather_enter (instance, 8); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_FOREIGN_MESSAGE_IN_GATHER_STATE); return (0); } break; @@ -4078,7 +4128,7 @@ static int message_handler_memb_merge_detect ( case MEMB_STATE_OPERATIONAL: memb_set_merge (&memb_merge_detect.system_from, 1, instance->my_proc_list, &instance->my_proc_list_entries); - memb_state_gather_enter (instance, 9); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_MERGE_DURING_OPERATIONAL_STATE); break; case MEMB_STATE_GATHER: @@ -4090,7 +4140,7 @@ static int message_handler_memb_merge_detect ( memb_set_merge (&memb_merge_detect.system_from, 1, instance->my_proc_list, &instance->my_proc_list_entries); - memb_state_gather_enter (instance, 10); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_MERGE_DURING_GATHER_STATE); return (0); } break; @@ -4217,7 +4267,7 @@ static void memb_join_process ( } } } - memb_state_gather_enter (instance, 11); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_MERGE_DURING_JOIN); gather_entered = 1; } @@ -4225,7 +4275,7 @@ out: if (gather_entered == 0 && instance->memb_state == MEMB_STATE_OPERATIONAL) { - memb_state_gather_enter (instance, 12); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_JOIN_DURING_OPERATIONAL_STATE); } } @@ -4395,7 +4445,7 @@ static int message_handler_memb_join ( memb_join->ring_seq >= instance->my_ring_id.seq) { memb_join_process (instance, memb_join); - memb_state_gather_enter (instance, 13); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_JOIN_DURING_COMMIT_STATE); } break; @@ -4409,7 +4459,7 @@ static int message_handler_memb_join ( memb_join_process (instance, memb_join); memb_recovery_state_token_loss (instance); - memb_state_gather_enter (instance, 14); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_JOIN_DURING_RECOVERY); } break; } @@ -4598,7 +4648,7 @@ void main_iface_change_fn ( } if (instance->iface_changes >= instance->totem_config->interface_count) { - memb_state_gather_enter (instance, 15); + memb_state_gather_enter (instance, TOTEMSRP_GSFROM_INTERFACE_CHANGE); } } -- 1.8.3.1 From ajb2 at mssl.ucl.ac.uk Mon Oct 21 14:58:18 2013 From: ajb2 at mssl.ucl.ac.uk (Alan Brown) Date: Mon, 21 Oct 2013 15:58:18 +0100 Subject: [Linux-cluster] NFS-ganesha - worthwhile replacement for kernel NFS? Message-ID: <5265410A.90904@site.mssl.ucl.ac.uk> As anyone who's tried to use kernel NFS in a clustered environment knows, it's fraught with issues which risk severe data corruption. has anyone tried using the Userspace nfs-ganesha server? I'd be interested ot hear how you got on. From lmb at suse.de Tue Oct 22 08:24:44 2013 From: lmb at suse.de (Lars Marowsky-Bree) Date: Tue, 22 Oct 2013 10:24:44 +0200 Subject: [Linux-cluster] NFS-ganesha - worthwhile replacement for kernel NFS? In-Reply-To: <5265410A.90904@site.mssl.ucl.ac.uk> References: <5265410A.90904@site.mssl.ucl.ac.uk> Message-ID: <20131022082444.GD3908@suse.de> On 2013-10-21T15:58:18, Alan Brown wrote: > As anyone who's tried to use kernel NFS in a clustered environment knows, > it's fraught with issues which risk severe data corruption. Is it? How so? Regards, Lars -- Architect Storage/HA SUSE LINUX Products GmbH, GF: Jeff Hawn, Jennifer Guild, Felix Imend?rffer, HRB 21284 (AG N?rnberg) "Experience is the name everyone gives to their mistakes." -- Oscar Wilde From Colin.Simpson at iongeo.com Tue Oct 22 09:25:40 2013 From: Colin.Simpson at iongeo.com (Colin Simpson) Date: Tue, 22 Oct 2013 09:25:40 +0000 Subject: [Linux-cluster] NFS-ganesha - worthwhile replacement for kernel NFS? In-Reply-To: <20131022082444.GD3908@suse.de> References: <5265410A.90904@site.mssl.ucl.ac.uk> <20131022082444.GD3908@suse.de> Message-ID: <1382433940.21434.10.camel@bhac.iouk.ioroot.tld> On Tue, 2013-10-22 at 10:24 +0200, Lars Marowsky-Bree wrote: > On 2013-10-21T15:58:18, Alan Brown wrote: > > > As anyone who's tried to use kernel NFS in a clustered environment knows, > > it's fraught with issues which risk severe data corruption. > > Is it? How so? > > > Regards, > Lars > > -- > Architect Storage/HA > SUSE LINUX Products GmbH, GF: Jeff Hawn, Jennifer Guild, Felix Imend??rffer, HRB 21284 (AG N??rnberg) > "Experience is the name everyone gives to their mistakes." -- Oscar Wilde > The only thing I know about (and has bitten me) is that a GFS2 filesystem isn't allowed to be exported on NFS and perform local access on it (e.g. Samba). Bad interaction between flocks (NFS) and plocks and the GFS2 glocks. The interaction on other filesystems between plocks and flocks could lead to file corruption. But in GFS2 this can and does lead to whole filesystem corruption. There is a bug open about it, but it's a tricky problem. I have a Red Hat information on this, not sure if it can be passed on. I guess a user space NFS would fix that. And IMHO would be easier to manage as all filesystem access would be in userspace (so potentially more stable on NFS server issues (complexity moved out of kernel space)). Thanks Colin ________________________________ This email and any files transmitted with it are confidential and are intended solely for the use of the individual or entity to whom they are addressed. If you are not the original recipient or the person responsible for delivering the email to the intended recipient, be advised that you have received this email in error, and that any use, dissemination, forwarding, printing, or copying of this email is strictly prohibited. If you received this email in error, please immediately notify the sender and delete the original. From queszama at yahoo.in Tue Oct 22 10:17:06 2013 From: queszama at yahoo.in (Zama Ques) Date: Tue, 22 Oct 2013 18:17:06 +0800 (SGT) Subject: [Linux-cluster] Local Partitions detected as Multipath Device Message-ID: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> My local partitions are detected as multipath device $multipath -l mpathb (360014380125d90420000a000003e0000) dm-9 HP,HSV450 size=200G features='1 queue_if_no_path' hwhandler='0' wp=rw `-+- policy='round-robin 0' prio=0 status=active `- 3:0:0:1 sdb 8:16 active undef running mpatha (3600508b1001c02143bc59c6862d97353) dm-0 HP,LOGICAL VOLUME size=137G features='1 queue_if_no_path' hwhandler='0' wp=rw `-+- policy='round-robin 0' prio=0 status=active `- 0:0:0:1 sda 8:0 active undef running I added the following lines in multipath.conf so that local partitions are not considered as multipath device blacklist { wwid 3600508b1001c02143bc59c6862d97353 } Executed the following commands after that . #service multipathd reload # multipath -F Oct 22 12:10:42 | mpathb: map in use Oct 22 12:10:42 | mpatha: map in use So , tried rebooting the server , but no luck . Any clues to resolve the issue will be highly appreciated . Thanks Zaman -------------- next part -------------- An HTML attachment was scrubbed... URL: From mohit.m.kumar at ericsson.com Tue Oct 22 10:40:50 2013 From: mohit.m.kumar at ericsson.com (Mohit) Date: Tue, 22 Oct 2013 16:10:50 +0530 Subject: [Linux-cluster] Local Partitions detected as Multipath Device In-Reply-To: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> References: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> Message-ID: <52665632.1070506@ericsson.com> what multipath version you are using ?? Ericsson Signature line *Mohit Kumar* * Back Office* Ericsson India Global Services Pvt. Ltd BUGS-GSC, Back Office A-8, Tower- A, 3rd Floor, Knowledge Boulevard, Sector-62, Noida, Uttar Pradesh-201301, India mohit.m.kumar at ericsson.com Mobile: +91 9654873797 www.ericsson.com http://www.ericsson.com/current_campaign This Communication is Confidential. We only send and receive email on the basis of the terms set out at www.ericsson.com/email_disclaimer On 10/22/2013 03:47 PM, Zama Ques wrote: > My local partitions are detected as multipath device > |$multipath -l > > mpathb (360014380125d90420000a000003e0000) dm-9 HP,HSV450 > size=200G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 3:0:0:1 sdb 8:16 active undef running > mpatha (3600508b1001c02143bc59c6862d97353) dm-0 HP,LOGICAL VOLUME > size=137G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 0:0:0:1 sda 8:0 active undef running > | > I added the following lines in multipath.conf so that local partitions > are not considered as multipath device > |blacklist { > wwid 3600508b1001c02143bc59c6862d97353 > } > | > Executed the following commands after that . > |#service multipathd reload > > # multipath -F > Oct 22 12:10:42 | mpathb: map in use > Oct 22 12:10:42 | mpatha: map in use > | > So , tried rebooting the server , but no luck . Any clues to resolve > the issue will be highly appreciated . > > Thanks > Zaman > > -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Email_line.gif Type: image/gif Size: 1417 bytes Desc: not available URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Email_campaigns.gif Type: image/gif Size: 80387 bytes Desc: not available URL: From vijaykakkars at gmail.com Tue Oct 22 10:57:07 2013 From: vijaykakkars at gmail.com (Vijay Kakkar) Date: Tue, 22 Oct 2013 16:27:07 +0530 Subject: [Linux-cluster] Local Partitions detected as Multipath Device In-Reply-To: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> References: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> Message-ID: Hi, Can you send the details of OS version and multipath version ? Do cross your wwid number again. Thanks, Vijay On Tue, Oct 22, 2013 at 3:47 PM, Zama Ques wrote: > My local partitions are detected as multipath device > > $multipath -l > > mpathb (360014380125d90420000a000003e0000) dm-9 HP,HSV450 > size=200G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 3:0:0:1 sdb 8:16 active undef running > mpatha (3600508b1001c02143bc59c6862d97353) dm-0 HP,LOGICAL VOLUME > size=137G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 0:0:0:1 sda 8:0 active undef running > > I added the following lines in multipath.conf so that local partitions are > not considered as multipath device > > blacklist { > wwid 3600508b1001c02143bc59c6862d97353 > } > > Executed the following commands after that . > > #service multipathd reload > > # multipath -F > Oct 22 12:10:42 | mpathb: map in use > Oct 22 12:10:42 | mpatha: map in use > > So , tried rebooting the server , but no luck . Any clues to resolve the > issue will be highly appreciated . > > Thanks > Zaman > > -- > Linux-cluster mailing list > Linux-cluster at redhat.com > https://www.redhat.com/mailman/listinfo/linux-cluster > -- Regards Vijay Kakkar -------------- next part -------------- An HTML attachment was scrubbed... URL: From ekuric at redhat.com Tue Oct 22 11:08:42 2013 From: ekuric at redhat.com (Elvir Kuric) Date: Tue, 22 Oct 2013 13:08:42 +0200 Subject: [Linux-cluster] Local Partitions detected as Multipath Device In-Reply-To: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> References: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> Message-ID: <52665CBA.1060908@redhat.com> On 10/22/2013 12:17 PM, Zama Ques wrote: > My local partitions are detected as multipath device > |$multipath -l > > mpathb (360014380125d90420000a000003e0000) dm-9 HP,HSV450 > size=200G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 3:0:0:1 sdb 8:16 active undef running > mpatha (3600508b1001c02143bc59c6862d97353) dm-0 HP,LOGICAL VOLUME > size=137G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 0:0:0:1 sda 8:0 active undef running > | > I added the following lines in multipath.conf so that local partitions > are not considered as multipath device > |blacklist { > wwid 3600508b1001c02143bc59c6862d97353 > } > | > Executed the following commands after that . > |#service multipathd reload > > # multipath -F > Oct 22 12:10:42 | mpathb: map in use > Oct 22 12:10:42 | mpatha: map in use > | > So , tried rebooting the server , but no luck . Any clues to resolve > the issue will be highly appreciated . > > Thanks > Zaman > > hi, /me wonders what OS ( and version ) is in use? service multipathd relaod ... suggest it is something RHEL based ( not 100 % sure ) Check /etc/multipath/* files ( if rhel 6 ) and see is there WWID from above, and also check initramfs ( RHEL 6 ) or initrd file ( RHEL 5 ) from /boot dobelow # mkdir /tmp/initrdtest # cp /boot/initramfs-$$$$.img ( or initrd ... ) /tmp/initrdtest unpack it # cd tmp/initrdtest # zcat initrd.img | cpio -i and check what is there for multiapth devices written. In short, I think you will need to ensure there are not records for devices you want to blacklist in /etc/multipath/* ( rhel 6 ) or /var/lib/multipath/* ( rhel 5 ) and rebuild initramfs / initrd ( depending is it RHEL 5 - initrd / RHEL 6 -initramfs ) once these records are not present.Rebuilding initrd/initramfs will pick values from /etc/multipath/* ( rhel 6 ) or /var/lib/multipath/ ( rhel 5 ) to rebuild initrd/initramfs check docs out there but in short process is ( after you remove records for WWID from wwid and bindings files - read above ) RHEL 5: # cd /boot # cp initrd-$(uname -r).img initrd-$(uname -r).img.backup [ make backup ] # mkinitrd -v -f initrd-$(uname -r).img # reboot ( to boot to new initramfs ) RHEL 6: same as above with small corrections ;) # cd /boot # cp initramfs-$(uname -r).img initramfs-$(uname -r).img.backup [ make backup ] # dracut -v -f initramfs-$(uname -r).img # reboot ( to boot to new initramfs ) good reading https://access.redhat.com/site/documentation/en-US/Red_Hat_Enterprise_Linux/5/html/DM_Multipath/config_file_blacklist.html hope this helps Kind regards, -- Elvir Kuric, Senior Technical Support Engineer / Red Hat / GSS EMEA / -------------- next part -------------- An HTML attachment was scrubbed... URL: From queszama at yahoo.in Tue Oct 22 11:16:21 2013 From: queszama at yahoo.in (Zama Ques) Date: Tue, 22 Oct 2013 19:16:21 +0800 (SGT) Subject: [Linux-cluster] Local Partitions detected as Multipath Device In-Reply-To: References: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> Message-ID: <1382440581.79332.YahooMailNeo@web193502.mail.sg3.yahoo.com> Hi Vijay, Please find OS and multipath version . === device-mapper-multipath-0.4.9-46.el6.x86_64 # cat /etc/redhat-release Red Hat Enterprise Linux Server release 6.2 (Santiago) === Thanks Zaman On Tuesday, 22 October 2013 4:27 PM, Vijay Kakkar wrote: Hi, Can you send the details of OS version and multipath version ? Do cross your wwid number again. Thanks, Vijay On Tue, Oct 22, 2013 at 3:47 PM, Zama Ques wrote: My local partitions are detected as multipath device > >$multipath -l mpathb (360014380125d90420000a000003e0000) dm-9 HP,HSV450 size=200G features='1 queue_if_no_path' hwhandler='0' wp=rw `-+- policy='round-robin 0' prio=0 status=active `- 3:0:0:1 sdb 8:16 active undef running mpatha (3600508b1001c02143bc59c6862d97353) dm-0 HP,LOGICAL VOLUME size=137G features='1 queue_if_no_path' hwhandler='0' wp=rw `-+- policy='round-robin 0' prio=0 status=active `- 0:0:0:1 sda 8:0 active undef running >I added the following lines in multipath.conf so that local partitions are not considered as multipath device >blacklist { wwid 3600508b1001c02143bc59c6862d97353 } >Executed the following commands after that . >#service multipathd reload # multipath -F Oct 22 12:10:42 | mpathb: map in use Oct 22 12:10:42 | mpatha: map in use >So , tried rebooting the server , but no luck . Any clues to resolve the issue will be highly appreciated . > > > >Thanks >Zaman > >-- >Linux-cluster mailing list >Linux-cluster at redhat.com >https://www.redhat.com/mailman/listinfo/linux-cluster > -- Regards Vijay Kakkar -------------- next part -------------- An HTML attachment was scrubbed... URL: From mohit.m.kumar at ericsson.com Tue Oct 22 11:33:41 2013 From: mohit.m.kumar at ericsson.com (Mohit) Date: Tue, 22 Oct 2013 17:03:41 +0530 Subject: [Linux-cluster] Local Partitions detected as Multipath Device In-Reply-To: <1382440581.79332.YahooMailNeo@web193502.mail.sg3.yahoo.com> References: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> <1382440581.79332.YahooMailNeo@web193502.mail.sg3.yahoo.com> Message-ID: <52666295.7080801@ericsson.com> try with this, cp /usr/share/doc/device-mapper-multipath-0.4.9/multipath.conf /etc and restart the multipath service Ericsson Signature line *Mohit Kumar* * Back Office* Ericsson India Global Services Pvt. Ltd BUGS-GSC, Back Office A-8, Tower- A, 3rd Floor, Knowledge Boulevard, Sector-62, Noida, Uttar Pradesh-201301, India mohit.m.kumar at ericsson.com Mobile: +91 9654873797 www.ericsson.com http://www.ericsson.com/current_campaign This Communication is Confidential. We only send and receive email on the basis of the terms set out at www.ericsson.com/email_disclaimer On 10/22/2013 04:46 PM, Zama Ques wrote: > Hi Vijay, > > Please find OS and multipath version . > > === > device-mapper-multipath-0.4.9-46.el6.x86_64 > > # cat /etc/redhat-release > Red Hat Enterprise Linux Server release 6.2 (Santiago) > === > > Thanks > Zaman > > > On Tuesday, 22 October 2013 4:27 PM, Vijay Kakkar > wrote: > Hi, > Can you send the details of OS version and multipath version ? Do > cross your wwid number again. > > Thanks, > Vijay > > > On Tue, Oct 22, 2013 at 3:47 PM, Zama Ques > wrote: > > My local partitions are detected as multipath device > > |$multipath -l > > mpathb (360014380125d90420000a000003e0000) dm-9 HP,HSV450 > size=200G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 3:0:0:1 sdb 8:16 active undef running > mpatha (3600508b1001c02143bc59c6862d97353) dm-0 HP,LOGICAL VOLUME > size=137G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 0:0:0:1 sda 8:0 active undef running > | > > I added the following lines in multipath.conf so that local > partitions are not considered as multipath device > > |blacklist { > wwid 3600508b1001c02143bc59c6862d97353 > } > | > > Executed the following commands after that . > > |#service multipathd reload > > # multipath -F > Oct 22 12:10:42 | mpathb: map in use > Oct 22 12:10:42 | mpatha: map in use > | > > So , tried rebooting the server , but no luck . Any clues to > resolve the issue will be highly appreciated . > > Thanks > Zaman > > -- > Linux-cluster mailing list > Linux-cluster at redhat.com > https://www.redhat.com/mailman/listinfo/linux-cluster > > > > > -- > Regards > Vijay Kakkar > > > > -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Email_line.gif Type: image/gif Size: 1417 bytes Desc: not available URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Email_campaigns.gif Type: image/gif Size: 80387 bytes Desc: not available URL: From ekuric at redhat.com Tue Oct 22 11:37:11 2013 From: ekuric at redhat.com (Elvir Kuric) Date: Tue, 22 Oct 2013 13:37:11 +0200 Subject: [Linux-cluster] Local Partitions detected as Multipath Device In-Reply-To: <1382440581.79332.YahooMailNeo@web193502.mail.sg3.yahoo.com> References: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> <1382440581.79332.YahooMailNeo@web193502.mail.sg3.yahoo.com> Message-ID: <52666367.10302@redhat.com> On 10/22/2013 01:16 PM, Zama Ques wrote: > # cat /etc/redhat-release > Red Hat Enterprise Linux Server release 6.2 (Santiago) > === Reading above,so it looks like you are Red Hat customer,if you have proper contract ( and not self support support level ) can you please open case with Red Hat support so we can take it and work on it properly.Please follow instructions under https://access.redhat.com -> cases -> open new case. Thank you Kind regards, Elvir Kuric From vijaykakkars at gmail.com Tue Oct 22 11:47:28 2013 From: vijaykakkars at gmail.com (Vijay Kakkar) Date: Tue, 22 Oct 2013 17:17:28 +0530 Subject: [Linux-cluster] Local Partitions detected as Multipath Device In-Reply-To: <1382440581.79332.YahooMailNeo@web193502.mail.sg3.yahoo.com> References: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> <1382440581.79332.YahooMailNeo@web193502.mail.sg3.yahoo.com> Message-ID: Hi Zama, I suggest you should one more time check your wwid else follow what Elvir and Mohit has said. On Tue, Oct 22, 2013 at 4:46 PM, Zama Ques wrote: > Hi Vijay, > > Please find OS and multipath version . > > === > device-mapper-multipath-0.4.9-46.el6.x86_64 > > # cat /etc/redhat-release > Red Hat Enterprise Linux Server release 6.2 (Santiago) > === > > Thanks > Zaman > > > On Tuesday, 22 October 2013 4:27 PM, Vijay Kakkar < > vijaykakkars at gmail.com> wrote: > Hi, > Can you send the details of OS version and multipath version ? Do cross > your wwid number again. > > Thanks, > Vijay > > > On Tue, Oct 22, 2013 at 3:47 PM, Zama Ques wrote: > > My local partitions are detected as multipath device > > $multipath -l > > mpathb (360014380125d90420000a000003e0000) dm-9 HP,HSV450 > size=200G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 3:0:0:1 sdb 8:16 active undef running > mpatha (3600508b1001c02143bc59c6862d97353) dm-0 HP,LOGICAL VOLUME > size=137G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 0:0:0:1 sda 8:0 active undef running > > I added the following lines in multipath.conf so that local partitions are > not considered as multipath device > > blacklist { > wwid 3600508b1001c02143bc59c6862d97353 > } > > Executed the following commands after that . > > #service multipathd reload > > # multipath -F > Oct 22 12:10:42 | mpathb: map in use > Oct 22 12:10:42 | mpatha: map in use > > So , tried rebooting the server , but no luck . Any clues to resolve the > issue will be highly appreciated . > > Thanks > Zaman > > -- > Linux-cluster mailing list > Linux-cluster at redhat.com > https://www.redhat.com/mailman/listinfo/linux-cluster > > > > > -- > Regards > Vijay Kakkar > > > -- Regards Vijay Kakkar -------------- next part -------------- An HTML attachment was scrubbed... URL: From albrecht at opensourceservices.de Tue Oct 22 12:34:58 2013 From: albrecht at opensourceservices.de (Peter Albrecht) Date: Tue, 22 Oct 2013 14:34:58 +0200 Subject: [Linux-cluster] Local Partitions detected as Multipath Device In-Reply-To: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> References: <1382437026.69206.YahooMailNeo@web193505.mail.sg3.yahoo.com> Message-ID: <201310221434.58587.albrecht@opensourceservices.de> Hi, On Tuesday 22 October 2013 12:17:06 Zama Ques wrote: > My local partitions are detected as multipath device > > $multipath -l mpathb (360014380125d90420000a000003e0000) dm-9 HP,HSV450 > size=200G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 3:0:0:1 sdb 8:16 active undef running > mpatha (3600508b1001c02143bc59c6862d97353) dm-0 HP,LOGICAL VOLUME > size=137G features='1 queue_if_no_path' hwhandler='0' wp=rw > `-+- policy='round-robin 0' prio=0 status=active > `- 0:0:0:1 sda 8:0 active undef running > I added the following lines in multipath.conf so that local partitions > are not considered as multipath device blacklist { wwid > 3600508b1001c02143bc59c6862d97353 > } > Executed the following commands after that . > #service multipathd reload # multipath -F > Oct 22 12:10:42 | mpathb: map in use > Oct 22 12:10:42 | mpatha: map in use > So , tried rebooting the server , but no luck . Any clues to resolve the > issue will be highly appreciated . See here: https://access.redhat.com/site/documentation/en-US/Red_Hat_Enterprise_Linux/6/html-single/DM_Multipath/ Try using the "find_multipaths yes" option in /etc/multipath.conf (in the defaults section). This should instruct multipathd to only look for real multipath devices, not for local disks. Regards, Peter From expertalert at gmail.com Tue Oct 22 12:41:24 2013 From: expertalert at gmail.com (fosiul alam) Date: Tue, 22 Oct 2013 13:41:24 +0100 Subject: [Linux-cluster] Can i use 2 nodes from a cluster? Message-ID: Hi I am trying to build a redhat cluster with 4 nodes for High Availability and load balancing. example : node1,node2,node3,node4 for apache service + Centralized Storage. now when those 4 nodes are connecting into cluster, i can only use 1 node at a time and when 1 node goes down then it shift all services into node2 . but can i not use all 4 nodes a time ?? example, i have a hardware load balancer, From this can i not pass the http trafiq to all 4 nodes ?? if not then how can i have load balanced between these 4 nodes ?? Thanks Kind regards -------------- next part -------------- An HTML attachment was scrubbed... URL: From lists at alteeve.ca Tue Oct 22 14:50:29 2013 From: lists at alteeve.ca (Digimer) Date: Tue, 22 Oct 2013 10:50:29 -0400 Subject: [Linux-cluster] Can i use 2 nodes from a cluster? In-Reply-To: References: Message-ID: <526690B5.7070702@alteeve.ca> On 22/10/13 08:41, fosiul alam wrote: > Hi > > I am trying to build a redhat cluster with 4 nodes for High Availability > and load balancing. > > example : > > node1,node2,node3,node4 for apache service + Centralized Storage. > > now when those 4 nodes are connecting into cluster, i can only use 1 node > at a time and when 1 node goes down then it shift all services into node2 . > > but can i not use all 4 nodes a time ?? > > example, i have a hardware load balancer, From this can i not pass the > http trafiq to all 4 nodes ?? > > if not then how can i have load balanced between these 4 nodes ?? > > Thanks > Kind regards I don't use load balancing myself, but I think what you're looking for might be Red Hat's LVS (Linux Virtual Server). It's a load-balancing setup for web services. cheers -- Digimer Papers and Projects: https://alteeve.ca/w/ What if the cure for cancer is trapped in the mind of a person without access to education? From roccas at gmail.com Tue Oct 22 16:23:23 2013 From: roccas at gmail.com (Marcelo Roccasalva) Date: Tue, 22 Oct 2013 14:23:23 -0200 Subject: [Linux-cluster] Can i use 2 nodes from a cluster? In-Reply-To: References: Message-ID: On Tue, Oct 22, 2013 at 9:41 AM, fosiul alam wrote: > Hi > > I am trying to build a redhat cluster with 4 nodes for High Availability and > load balancing. > > example : > > node1,node2,node3,node4 for apache service + Centralized Storage. > > now when those 4 nodes are connecting into cluster, i can only use 1 node at > a time and when 1 node goes down then it shift all services into node2 . > > but can i not use all 4 nodes a time ?? > > example, i have a hardware load balancer, From this can i not pass the http > trafiq to all 4 nodes ?? > > if not then how can i have load balanced between these 4 nodes ?? You need a failoverdomain nofailback restricted for every node, and a service for apache on every node, Untested relevant part of cluster.conf: