Re: [ceph-users] Collecting BlueStore per Object DB overhead

On 04/30/2018 10:25 PM, Gregory Farnum wrote: > > > On Thu, Apr 26, 2018 at 11:36 AM Wido den Hollander > wrote: > > Hi, > > I've been investigating the per object overhead for BlueStore as I've > seen this has become a topic for a lot of

Re: [ceph-users] 12.2.4 Both Ceph MDS nodes crashed. Please help.

Hello Sean, On Mon, Apr 30, 2018 at 2:32 PM, Sean Sullivan wrote: > I was creating a new user and mount point. On another hardware node I > mounted CephFS as admin to mount as root. I created /aufstest and then > unmounted. From there it seems that both of my mds nodes

Re: [ceph-users] Ceph User Survey 2018

On Mon, Apr 30, 2018 at 11:39:11PM -0300, Leonardo Vaz wrote: > Hey Cephers! > > We just announced the 2018 edition of Ceph user Survey: > > https://www.surveymonkey.com/r/ceph2018 > > It will be accepting answers until May 15th and the results will be > published on the project website. > >

[ceph-users] Ceph User Survey 2018

Hey Cephers! We just announced the 2018 edition of Ceph user Survey: https://www.surveymonkey.com/r/ceph2018 It will be accepting answers until May 15th and the results will be published on the project website. Please consider to contribute, your feedback is very important to us! Kindest

Re: [ceph-users] ceph-deploy on 14.04

Alright I'll try that. Thanks On Mon, Apr 30, 2018 at 5:45 PM Vasu Kulkarni wrote: > If you are on 14.04 or need to use ceph-disk, then you can install > version 1.5.39 from pip. to downgrade just uninstall the current one > and reinstall 1.5.39 you dont have to delete

Re: [ceph-users] 12.2.4 Both Ceph MDS nodes crashed. Please help.

I forgot that I left my VM mount command running. It hangs my VM but more alarming is that it crashes my MDS servers on the ceph cluster. The ceph cluster is all hardware nodes and the openstack vm does not have an admin keyring (although the cephX keyring for cephfs generated does have write

Re: [ceph-users] ceph-deploy on 14.04

If you are on 14.04 or need to use ceph-disk, then you can install version 1.5.39 from pip. to downgrade just uninstall the current one and reinstall 1.5.39 you dont have to delete your conf file folder. On Mon, Apr 30, 2018 at 5:31 PM, Scottix wrote: > It looks like

[ceph-users] unsubscribe

___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

[ceph-users] ceph-deploy on 14.04

It looks like ceph-deploy@2.0.0 is incompatible with systems running 14.04 and it got released in the luminous branch with the new deployment commands. Is there anyway to downgrade to an older version? Log of osd list XYZ@XYZStat200:~/XYZ-cluster$ ceph-deploy --overwrite-conf osd list

Re: [ceph-users] 12.2.4 Both Ceph MDS nodes crashed. Please help.

So I think I can reliably reproduce this crash from a ceph client. ``` root@kh08-8:~# ceph -s cluster: id: 9f58ee5a-7c5d-4d68-81ee-debe16322544 health: HEALTH_OK services: mon: 3 daemons, quorum kh08-8,kh09-8,kh10-8 mgr: kh08-8(active) mds: cephfs-1/1/1 up

Re: [ceph-users] 12.2.4 Both Ceph MDS nodes crashed. Please help.

I had 2 MDS servers (one active one standby) and both were down. I took a dumb chance and marked the active as down (it said it was up but laggy). Then started the primary again and now both are back up. I have never seen this before I am also not sure of what I just did. On Mon, Apr 30, 2018 at

[ceph-users] 12.2.4 Both Ceph MDS nodes crashed. Please help.

I was creating a new user and mount point. On another hardware node I mounted CephFS as admin to mount as root. I created /aufstest and then unmounted. From there it seems that both of my mds nodes crashed for some reason and I can't start them any more. https://pastebin.com/1ZgkL9fa -- my mds

Re: [ceph-users] Is RDMA Worth Exploring? Howto ?

The AsyncMessenger RDMA is a lot more useful/usable than we've had before, but my understanding from the guys building it is that you still shouldn't bother for production systems — the rest of the stack isn't well-tuned to take much advantage yet, and it's not in the regular testing rotation or

Re: [ceph-users] Collecting BlueStore per Object DB overhead

On Thu, Apr 26, 2018 at 11:36 AM Wido den Hollander wrote: > Hi, > > I've been investigating the per object overhead for BlueStore as I've > seen this has become a topic for a lot of people who want to store a lot > of small objects in Ceph using BlueStore. > > I've writting a

Re: [ceph-users] Have an inconsistent PG, repair not working

Mine repaired themselves after a regular deep scrub. Weird that I couldn't trigger one manually. On 30 April 2018 at 14:23, David Turner wrote: > My 3 inconsistent PGs finally decided to run automatic scrubs and now 2 of > the 3 will allow me to run deep-scrubs and

Re: [ceph-users] Have an inconsistent PG, repair not working

My 3 inconsistent PGs finally decided to run automatic scrubs and now 2 of the 3 will allow me to run deep-scrubs and repairs on them. The deep-scrub did not show any new information about the objects other than that they were missing in one of the copies. Running a repair fixed the

Re: [ceph-users] Please help me get rid of Slow / blocked requests

Hi, blocked requests are just requests that took longer than 30 seconds to complete, this just means your cluster is completely overloaded by the benchmark. Also, OSD 2 might be slower than your other OSDs. Paul 2018-04-30 15:36 GMT+02:00 Shantur Rathore : > Hi all,

[ceph-users] Please help me get rid of Slow / blocked requests

Hi all, I am trying to get my first test Ceph cluster working. Centos 7 with Elrepo 4.16.3-1.el7.elrepo.x86_64 kernel ( for iSCSI HA ) Configured using - ceph-ansible 3 Mons ( including 2 OSD nodes ) 2 OSD nodes 20 OSDs ( 10 per node ) Each OSD node has 256GB of memory and 2x10GBe Bonded

Re: [ceph-users] ceph 12.2.5 - atop DB/WAL SSD usage 0%

Shouldn't Steven see some data being written to the block/wal for object metadata? Though that might be negligible with 4MB objects On 27-04-18 16:04, Serkan Çoban wrote: rados bench is using 4MB block size for io. Try with with io size 4KB, you will see ssd will be used for write

Re: [ceph-users] trimming the MON level db

On Sat, Apr 28, 2018 at 10:24 AM, Wido den Hollander wrote: > > > On 04/27/2018 08:31 PM, David Turner wrote: >> I'm assuming that the "very bad move" means that you have some PGs not >> in active+clean. Any non-active+clean PG will prevent your mons from >> being able to compact

Re: [ceph-users] Does ceph-ansible support the LVM OSD scenario under Docker?

There is no support for ceph-volume (or LVM) with ceph-ansible and docker. On Thu, Apr 26, 2018 at 3:16 PM, Jacob DeGlopper wrote: > Hi - I'm trying to set up our first Ceph deployment with a small set of 3 > servers, using an SSD boot drive each and 2x Micron 5200 SSDs per

Re: [ceph-users] Multi-MDS Failover

On 04/27/2018 07:11 PM, Patrick Donnelly wrote: > The answer is that there may be partial availability from > the up:active ranks which may hand out capabilities for the subtrees > they manage or no availability if that's not possible because it > cannot obtain the necessary locks. additionally:

Re: [ceph-users] Deleting an rbd image hangs

Am 27.04.18 um 22:33 schrieb Jason Dillaman: > Do you have any reason for why the OSDs crash? Anything the logs? Can > you provide an "rbd info noc_tobedeleted"? The reason why they are crashing is this assert: https://github.com/ceph/ceph/blob/luminous/src/osd/PrimaryLogPG.cc#L353 With debug 20

Re: [ceph-users] Deleting an rbd image hangs

Am 27.04.18 um 20:48 schrieb David Turner: > This old [1] blog post about removing super large RBDs is not relevant > if you're using object map on the RBDs, however it's method to manually > delete an RBD is still valid.  You can see if this works for you to > manually remove the problem RBD