Re: [ceph-users] Deploying ceph by hand: a few omissions
On 16-05-02 02:14, Stuart Longland wrote: On 02/05/16 00:32, Henrik Korkuc wrote: mons generate these bootstrep keys. You can find them in /var/lib/ceph/bootstrap-*/ceph.keyring on pre-infernalis there were created automagically (I guess by init). Infernalis and jewel have ceph-create-keys@.service systemd job for that. Just place that dir with file in same location on OSD hosts and you'll be able to activate OSDs. Yeah, in my case the OSD hosts are the MON hosts, and there was no such file or directory created on any of them. Monitors were running at the time. you need to run ceph-create-keys systemd job to generate these keys (or the command in there). I am not sure if it is intentional that it doesn't run automatically or just some dependency problem. I think Jewel did create keys for me. I didn't put much attention to it as it is rare for me to start new clusters. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Deploying ceph by hand: a few omissions
I have an active and a standby setup. The faillover takes less than a minute if you manually stop the active service. Add whatever the timeout is for the faillover to happen if things go pear shaped for the box. Things are back to letters now for mds servers. I had started with letters on firefly as recommended. Then somewhere (giant?), I was getting prodded to use numbers instead. Now with later hammer and infernalis, I'm back to getting scolded for not using letters :-) I'm holding off on jewel for the moment until I get things straightened out with the kde4 to plasma upgrade. I think that one got stablized before it was quite ready for prime time. Even then I'll probably take a good long time to backup some stuff before I try out the shiny new fsck utility. On 05/01/2016 07:13 PM, Stuart Longland wrote: Hi Bill, On 02/05/16 04:37, Bill Sharer wrote: Actually you didn't need to do a udev rule for raw journals. Disk devices in gentoo have their group ownership set to 'disk'. I only needed to drop ceph into that in /etc/group when going from hammer to infernalis. Yeah, I recall trying that on the Ubuntu-based Ceph cluster at work, and Ceph still wasn't happy, hence I've gone the route of making the partition owned by the ceph user. Did you poke around any of the ceph howto's on the gentoo wiki? It's been a while since I wrote this guide when I first rolled out with firefly: https://wiki.gentoo.org/wiki/Ceph/Guide That used to be https://wiki.gentoo.org/wiki/Ceph before other people came in behind me and expanded on things No, hadn't looked at that. I've pretty much had these bookmarks sitting around forever for adding and removing mons and osds http://docs.ceph.com/docs/master/rados/operations/add-or-rm-mons/ http://docs.ceph.com/docs/master/rados/operations/add-or-rm-osds/ For the MDS server I think I originally went to this blog which also has other good info. http://www.sebastien-han.fr/blog/2013/05/13/deploy-a-ceph-mds-server/ That might be my next step, depending on how stable CephFS is now. One thing that has worried me is since you can only deploy one MDS, what happens if that MDS goes down? If it's simply a case of spin up another one, then fine, I can put up with a little downtime. If there's data loss though, then no, that's not good. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] jewel, cephfs and selinux
All, I thought there was a way to mount CephFS using the kernel driver and be able to honor selinux labeling. Right now, if I do 'ls -lZ' on a mounted cephfs, I get question marks instead of any contexts. When I mount it, I see in dmesg: [858946.554719] SELinux: initialized (dev ceph, type ceph), not configured for labeling Is this something that is in the works and will be available to test? Brian Andrus ITACS/Research Computing Naval Postgraduate School Monterey, California voice: 831-656-6238 ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Deploying ceph by hand: a few omissions
On Sun, May 01, 2016 at 08:46:36PM +1000, Stuart Longland wrote: > Hi all, > > This evening I was in the process of deploying a ceph cluster by hand. > I did it by hand because to my knowledge, ceph-deploy doesn't support > Gentoo, and my cluster here runs that. You'll want the ceph-disk & ceph-detect-init pieces here: https://github.com/ceph/ceph/pull/8317 ceph-deploy on Gentoo should only a little bit of work after this. -- Robin Hugh Johnson Gentoo Linux: Developer, Infrastructure Lead, Foundation Trustee E-Mail : robb...@gentoo.org GnuPG FP : 11ACBA4F 4778E3F6 E4EDF38E B27B944E 34884E85 ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Deploying ceph by hand: a few omissions
On 02/05/16 00:32, Henrik Korkuc wrote: > mons generate these bootstrep keys. You can find them in > /var/lib/ceph/bootstrap-*/ceph.keyring > > on pre-infernalis there were created automagically (I guess by init). > Infernalis and jewel have ceph-create-keys@.service systemd job for that. > > Just place that dir with file in same location on OSD hosts and you'll > be able to activate OSDs. Yeah, in my case the OSD hosts are the MON hosts, and there was no such file or directory created on any of them. Monitors were running at the time. -- Stuart Longland Systems Engineer _ ___ \ /|_) | T: +61 7 3535 9619 \/ | \ | 38b Douglas StreetF: +61 7 3535 9699 SYSTEMSMilton QLD 4064 http://www.vrt.com.au ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Deploying ceph by hand: a few omissions
Hi Bill, On 02/05/16 04:37, Bill Sharer wrote: > Actually you didn't need to do a udev rule for raw journals. Disk > devices in gentoo have their group ownership set to 'disk'. I only > needed to drop ceph into that in /etc/group when going from hammer to > infernalis. Yeah, I recall trying that on the Ubuntu-based Ceph cluster at work, and Ceph still wasn't happy, hence I've gone the route of making the partition owned by the ceph user. > Did you poke around any of the ceph howto's on the gentoo wiki? It's > been a while since I wrote this guide when I first rolled out with firefly: > > https://wiki.gentoo.org/wiki/Ceph/Guide > > That used to be https://wiki.gentoo.org/wiki/Ceph before other people > came in behind me and expanded on things No, hadn't looked at that. > I've pretty much had these bookmarks sitting around forever for adding > and removing mons and osds > > http://docs.ceph.com/docs/master/rados/operations/add-or-rm-mons/ > http://docs.ceph.com/docs/master/rados/operations/add-or-rm-osds/ > > For the MDS server I think I originally went to this blog which also has > other good info. > > http://www.sebastien-han.fr/blog/2013/05/13/deploy-a-ceph-mds-server/ That might be my next step, depending on how stable CephFS is now. One thing that has worried me is since you can only deploy one MDS, what happens if that MDS goes down? If it's simply a case of spin up another one, then fine, I can put up with a little downtime. If there's data loss though, then no, that's not good. -- Stuart Longland Systems Engineer _ ___ \ /|_) | T: +61 7 3535 9619 \/ | \ | 38b Douglas StreetF: +61 7 3535 9699 SYSTEMSMilton QLD 4064 http://www.vrt.com.au ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Deploying ceph by hand: a few omissions
Actually you didn't need to do a udev rule for raw journals. Disk devices in gentoo have their group ownership set to 'disk'. I only needed to drop ceph into that in /etc/group when going from hammer to infernalis. Did you poke around any of the ceph howto's on the gentoo wiki? It's been a while since I wrote this guide when I first rolled out with firefly: https://wiki.gentoo.org/wiki/Ceph/Guide That used to be https://wiki.gentoo.org/wiki/Ceph before other people came in behind me and expanded on things I've pretty much had these bookmarks sitting around forever for adding and removing mons and osds http://docs.ceph.com/docs/master/rados/operations/add-or-rm-mons/ http://docs.ceph.com/docs/master/rados/operations/add-or-rm-osds/ For the MDS server I think I originally went to this blog which also has other good info. http://www.sebastien-han.fr/blog/2013/05/13/deploy-a-ceph-mds-server/ On 05/01/2016 06:46 AM, Stuart Longland wrote: Hi all, This evening I was in the process of deploying a ceph cluster by hand. I did it by hand because to my knowledge, ceph-deploy doesn't support Gentoo, and my cluster here runs that. The instructions I followed are these ones: http://docs.ceph.com/docs/master/install/manual-deployment and I'm running the 10.0.2 release of Ceph: ceph version 10.0.2 (86764eaebe1eda943c59d7d784b893ec8b0c6ff9) Things went okay bootstrapping the monitors. I'm running a 3-node cluster, with OSDs and monitors co-located. Each node has a 1TB 2.5" HDD and a 40GB partition on SSD for the journal. Things went pear shaped however when I tried bootstrapping the OSDs. All was going fine until it came time to activate my first OSD. ceph-disk activate barfed because I didn't have the bootstrap-osd key. No one told me I needed to create one, or how to do it. There's a brief note about using --activate-key, but no word on what to pass as the argument. I tried passing in my admin keyring in /etc/ceph, but it didn't like that. In the end, I muddled my way through the manual OSD deployment steps, which worked fine. After correcting permissions for the ceph user, I found the OSDs came up. As an added bonus, I now know how to work around the journal permission issue at work since I've reproduced it here, using a UDEV rules file like the following: SUBSYSTEM=="block", KERNEL=="sda7", OWNER="ceph", GROUP="ceph", MODE="0600" The cluster seems to be happy enough now, but some notes on how one generates the OSD activation keys to use with `ceph-disk activate` would be a big help. Regards, ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] Change MDS's mode from active to standby
Hi, Currently, I'm testing the functionality of multiple MDS in Jewel 10.2.0. I know increasing the value of max_mds can make the standby MDS become active(I have two MDSes and max_mds=1). But I'm wondering if there is a way to change the mode back. I tried to decrease max_mds, but it did not work. I also tried 'mds_standby_for_name', but got 'Function not implemented'. Thanks, Jevon ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] snaps & consistency group
Hello Guys . I'm a little bit confused about ceph's capability to take a a consistency snapshots ( more then one rbd image ) is there a way to do this ( we're running hammer right now ) Thanks -- This e-mail, as well as any attached document, may contain material which is confidential and privileged and may include trademark, copyright and other intellectual property rights that are proprietary to Kenshoo Ltd, its subsidiaries or affiliates ("Kenshoo"). This e-mail and its attachments may be read, copied and used only by the addressee for the purpose(s) for which it was disclosed herein. If you have received it in error, please destroy the message and any attachment, and contact us immediately. If you are not the intended recipient, be aware that any review, reliance, disclosure, copying, distribution or use of the contents of this message without Kenshoo's express permission is strictly prohibited. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Deploying ceph by hand: a few omissions
mons generate these bootstrep keys. You can find them in /var/lib/ceph/bootstrap-*/ceph.keyring on pre-infernalis there were created automagically (I guess by init). Infernalis and jewel have ceph-create-keys@.service systemd job for that. Just place that dir with file in same location on OSD hosts and you'll be able to activate OSDs. On 16-05-01 13:46, Stuart Longland wrote: Hi all, This evening I was in the process of deploying a ceph cluster by hand. I did it by hand because to my knowledge, ceph-deploy doesn't support Gentoo, and my cluster here runs that. The instructions I followed are these ones: http://docs.ceph.com/docs/master/install/manual-deployment and I'm running the 10.0.2 release of Ceph: ceph version 10.0.2 (86764eaebe1eda943c59d7d784b893ec8b0c6ff9) Things went okay bootstrapping the monitors. I'm running a 3-node cluster, with OSDs and monitors co-located. Each node has a 1TB 2.5" HDD and a 40GB partition on SSD for the journal. Things went pear shaped however when I tried bootstrapping the OSDs. All was going fine until it came time to activate my first OSD. ceph-disk activate barfed because I didn't have the bootstrap-osd key. No one told me I needed to create one, or how to do it. There's a brief note about using --activate-key, but no word on what to pass as the argument. I tried passing in my admin keyring in /etc/ceph, but it didn't like that. In the end, I muddled my way through the manual OSD deployment steps, which worked fine. After correcting permissions for the ceph user, I found the OSDs came up. As an added bonus, I now know how to work around the journal permission issue at work since I've reproduced it here, using a UDEV rules file like the following: SUBSYSTEM=="block", KERNEL=="sda7", OWNER="ceph", GROUP="ceph", MODE="0600" The cluster seems to be happy enough now, but some notes on how one generates the OSD activation keys to use with `ceph-disk activate` would be a big help. Regards, ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] Deploying ceph by hand: a few omissions
Hi all, This evening I was in the process of deploying a ceph cluster by hand. I did it by hand because to my knowledge, ceph-deploy doesn't support Gentoo, and my cluster here runs that. The instructions I followed are these ones: http://docs.ceph.com/docs/master/install/manual-deployment and I'm running the 10.0.2 release of Ceph: ceph version 10.0.2 (86764eaebe1eda943c59d7d784b893ec8b0c6ff9) Things went okay bootstrapping the monitors. I'm running a 3-node cluster, with OSDs and monitors co-located. Each node has a 1TB 2.5" HDD and a 40GB partition on SSD for the journal. Things went pear shaped however when I tried bootstrapping the OSDs. All was going fine until it came time to activate my first OSD. ceph-disk activate barfed because I didn't have the bootstrap-osd key. No one told me I needed to create one, or how to do it. There's a brief note about using --activate-key, but no word on what to pass as the argument. I tried passing in my admin keyring in /etc/ceph, but it didn't like that. In the end, I muddled my way through the manual OSD deployment steps, which worked fine. After correcting permissions for the ceph user, I found the OSDs came up. As an added bonus, I now know how to work around the journal permission issue at work since I've reproduced it here, using a UDEV rules file like the following: SUBSYSTEM=="block", KERNEL=="sda7", OWNER="ceph", GROUP="ceph", MODE="0600" The cluster seems to be happy enough now, but some notes on how one generates the OSD activation keys to use with `ceph-disk activate` would be a big help. Regards, -- Stuart Longland Systems Engineer _ ___ \ /|_) | T: +61 7 3535 9619 \/ | \ | 38b Douglas StreetF: +61 7 3535 9699 SYSTEMSMilton QLD 4064 http://www.vrt.com.au ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com