Re: [ceph-users] OSD size and performance

Hi Prabu, We generally use SCSI - PR(persistent reservation) supported drives (drive firmware should support) for HA/CFS. RBD would not support this feature because it is not physical drive. But as you did we can mount the same rbd across multiple clients after writing file system(here OCFS2).

[ceph-users] very high OSD RAM usage values

Hi all, We experienced some serious trouble with our cluster: A running cluster started failing and started a chain reaction until the ceph cluster was down, as about half the OSDs are down (in a EC pool) Each host has 8 OSDS of 8 TB (i.e. RAID 0 of 2 4TB disk) for an EC pool (10+3, 14 hosts

Re: [ceph-users] Long peering - throttle at FileStore::queue_transactions

On Tue, 5 Jan 2016, Guang Yang wrote: > On Mon, Jan 4, 2016 at 7:21 PM, Sage Weil wrote: > > On Mon, 4 Jan 2016, Guang Yang wrote: > >> Hi Cephers, > >> Happy New Year! I got question regards to the long PG peering.. > >> > >> Over the last several days I have been looking into the *long peering*

[ceph-users] KVM problems when rebalance occurs

Heya, we are using a ceph cluster (6 Nodes with each having 10x4TB HDD + 2x SSD (for journal)) in combination with KVM virtualization. All our virtual machine hard disks are stored on the ceph cluster. The ceph cluster was updated to the 'infernalis' release recently. We are experiencing proble

Re: [ceph-users] bad sectors on rbd device?

I think you are running out of memory(?), or at least of the memory for the type of allocation krbd tries to use. I'm not going to decode all the logs but you can try increasing min_free_kbytes as the first step. I assume this is amd64 when there's no HIGHMEM trouble (I don't remember how to sol

Re: [ceph-users] KVM problems when rebalance occurs

-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 There has been a lot of "discussion" about osd_backfill_scan[min,max] lately. My experience with hammer has been opposite that of what people have said before. Increasing those values for us has reduced the load of recovery and has prevented a lot of

Re: [ceph-users] KVM problems when rebalance occurs

Hi, Also make sure that you optimize the debug log config. There's a lot on the ML on how to set them all to low values (0/0). Not sure how it's in infernalis but it did a lot in previous versions. Regards, Josef On 6 Jan 2016 18:16, "Robert LeBlanc" wrote: > -BEGIN PGP SIGNED MESSAGE-

[ceph-users] rbd partition table

Hi guys, Should I create a partition table on a rbd image or it is enough to create the filesystem only ? Every time I map a rbd image I get the message "unknown partition table" but I was able to create the filesystem. Thank Dan ___ ceph-users maili

[ceph-users] rados images sync

Hi guys, I there a way to replicate the rbd images of a pool on another cluster ? other than clone/snap ? -- Dan ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

[ceph-users] double rebalance when removing osd

Hi all, I am curious what practices other people follow when removing OSDs from a cluster. According to the docs, you are supposed to: 1. ceph osd out 2. stop daemon 3. ceph osd crush remove 4. ceph auth del 5. ceph osd rm What value does ceph osd out (1) add to the removal process and why is it

Re: [ceph-users] double rebalance when removing osd

I followed these steps and worked just fine http://www.sebastien-han.fr/blog/2015/12/11/ceph-properly-remove-an-osd/ -- Dan From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of Rafael Lopez Sent: Thursday, January 7, 2016 1:53 AM To: ceph-users@lists.ceph.com Subject: [ceph-u

Re: [ceph-users] rbd partition table

-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 It is just a block device, you can use it with or without a partition. I should be careful with that statement as bcache looks like a block device, but you can not partition it directly. - Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC

Re: [ceph-users] rbd partition table

I'm not sure which is *better* performance wise in terms of RBD but I've never created any tables on top of that. Thank you, Shinobu - Original Message - From: "Dan Nica" To: ceph-users@lists.ceph.com Sent: Thursday, January 7, 2016 8:27:54 AM Subject: [ceph-users] rbd partition table

Re: [ceph-users] rados images sync

Hi, You can export rbd images and import to another cluster. Note:you have to purge images if it has snapshots. AFAIK, there is no way to export images keeping their clones and snapshots. On Jan 7, 2016 6:36 AM, "Dan Nica" wrote: > Hi guys, > > > > I there a way to replicate the rbd images of a

[ceph-users] Unable to see LTTng tracepoints in Ceph

Hello Cephers, A very happy new year to you all! I wanted to enable LTTng tracepoints for a few tests with infernalis and configured Ceph with the -with-lttng option. Seeing a recent post on conf file options for tracing, I added these lines: osd_tracing = true osd_objectstore_tracing = true r

[ceph-users] Any suggestion to deal with slow request?

Hi Cephers, We have a Ceph cluster running 0.80.9, which consists of 36 OSDs with 3 replicas. Recently, some OSDs keep reporting slow request and the cluster has a performance downgrade. From the log of one OSD, I observe that all the slow requests are resulted from waiting for the replicas

Re: [ceph-users] CentOS 7.2, Infernalis, preparing osd's and partprobe issues.

Hi All... If I can step in on this issue, I just would like to report that I am experiencing the same problem. 1./ I am installing my infernalis OSDs in a Centos 7.2.1511, and 'ceph disk prepare' fails with the following message # ceph-disk prepare --cluster ceph --cluster-uuid a9431b