[ceph-users] Why are RGW pools all prefixed with a period (.)?

Hi, It's something which has been 'bugging' me for some time now. Why are RGW pools prefixed with a period? I tried setting the root pool to 'rgw.root', but RGW (0.94.1) refuses to start: ERROR: region root pool name must start with a period I'm sending pool statistics to Graphite and when send

Re: [ceph-users] Broken snapshots... CEPH 0.94.2

Great! Yes, behaviour exact as i described. So looks like it's root cause ) Thank you, Sam. Ilya! 2015-08-21 21:08 GMT+03:00 Samuel Just : > I think I found the bug -- need to whiteout the snapset (or decache > it) upon evict. > > http://tracker.ceph.com/issues/12748 > -Sam > > On Fri, Aug 21, 2

[ceph-users] Can't mount Cephfs

Hi, We have ceph cluster (Ceph version 0.94.2) which consists of four nodes with four disks on each node. Ceph is configured to hold two replicas (size 2). We use this cluster for ceph filesystem. Few days ago we had power outage after which I had to replace three of our cluster OSD disks. Al

[ceph-users] Ceph repository for Debian Jessie

Hi, I would like to know if there will be a new repository hosting Jessie packages in the near future. If I am not mistaken the issue for not using the existing packages is that there are a few (dependency) libraries in Jessie in newer versions and some porting may be needed. --- At the moment

Re: [ceph-users] Can't mount Cephfs

If you lost 3 disks with size 2 and at least 2 of those disks were in different host, that means you lost data with the default CRUSH. There's nothing you can do but either get those disks back in or recover from backup. Jan > On 26 Aug 2015, at 12:18, Andrzej Łukawski wrote: > > Hi, > > We

Re: [ceph-users] RadosGW - multiple dns names

On Mon, Feb 23, 2015 at 10:18 PM, Yehuda Sadeh-Weinraub wrote: > > > -- > > *From: *"Shinji Nakamoto" > *To: *ceph-us...@ceph.com > *Sent: *Friday, February 20, 2015 3:58:39 PM > *Subject: *[ceph-users] RadosGW - multiple dns names > > We have multiple interfaces on o

[ceph-users] Unexpected AIO Error

Hello, I am experiencing an issue where OSD Services fail due to an unexpected aio error. This has happend on two different OSD servers killing two different OSD Daemons services. I am running Ceph Hammer on Debian Wheezy with a backported Kernel(3.16.0-0.bpo.4-amd64). Below is the log from

Re: [ceph-users] Can't mount Cephfs

Thank you for answer. I lost 2 disks on 1st node and 1 disk on 2nd. I understand it is not possible to recover the data even partially? Unfortunatelly those disks are lost forever. Andrzej W dniu 2015-08-26 o 12:26, Jan Schermer pisze: If you lost 3 disks with size 2 and at least 2 of those di

Re: [ceph-users] Unexpected AIO Error

Did you update: http://tracker.ceph.com/issues/12100 Just question. Shinobu On Wed, Aug 26, 2015 at 8:09 PM, Pontus Lindgren wrote: > Hello, > > I am experiencing an issue where OSD Services fail due to an unexpected > aio error. This has happend on two different OSD servers killing two > di

Re: [ceph-users] which SSD / experiences with Samsung 843T vs. Intel s3700

Hi , We got a good deal on 843T and we are using it in our Openstack setup ..as journals . They have been running for last six months ... No issues . When we compared with Intel SSDs I think it was 3700 they were shade slower for our workload and considerably cheaper. We did not run any syntheti

Re: [ceph-users] Why are RGW pools all prefixed with a period (.)?

On Wed, Aug 26, 2015 at 9:36 AM, Wido den Hollander wrote: > Hi, > > It's something which has been 'bugging' me for some time now. Why are > RGW pools prefixed with a period? > > I tried setting the root pool to 'rgw.root', but RGW (0.94.1) refuses to > start: > > ERROR: region root pool name must

Re: [ceph-users] Can't mount Cephfs

There is a cephfs-journal-tool that I believe is present in hammer and ought to let you get your MDS through replay. Depending on which PGs were lost you will have holes and/or missing files, in addition to not being able to find parts of the directory hierarchy (and maybe getting crashes if you ac

[ceph-users] Migrating data into a newer ceph instance

Hi, We have been running Ceph/Radosgw version 0.80.7 (Giant) and stored quite some amount of data in it. We are only using ceph as an object store via radosgw. Last week cheph-radosgw daemon suddenly refused to start (with logs only showing "initialization timeout" error on Centos 7). This tri

Re: [ceph-users] Migrating data into a newer ceph instance

I Would say the easiest way would be to leverage all the self-healing of ceph: add the new nodes to the old cluster, allow or force all the data to migrate between nodes, and then remove the old ones out. Well to be fair you could probably just install radosgw on another node and use it as your ga

Re: [ceph-users] Migrating data into a newer ceph instance

Thanks, Luis. The motivation for using the newer version is to keep up-to-date with Ceph development, since we suspect the old versioned radosgw could not be restarted possibly due to library mismatch. Do you know whether the self-healing feature of ceph is applicable between different versions

[ceph-users] ceph monitoring with graphite

Hi Wido, On Wed, Aug 26, 2015 at 10:36 AM, Wido den Hollander wrote: > I'm sending pool statistics to Graphite We're doing the same -- stripping invalid chars as needed -- and I would guess that lots of people have written similar json2graphite convertor scripts for Ceph monitoring in the recent

Re: [ceph-users] Can't mount Cephfs

Most of the data is still here, but you won't be able to just "mount" it if it's inconsistent. I don't use CephFS so someone else could tell you if it's able to repair the filesystem with some parts missing. You lost part of the data where the copies were only on the 1 disk in one node and on

Re: [ceph-users] ceph monitoring with graphite

That would certainly be something we would use. QH On Wed, Aug 26, 2015 at 8:33 AM, Dan van der Ster wrote: > Hi Wido, > > On Wed, Aug 26, 2015 at 10:36 AM, Wido den Hollander > wrote: > > I'm sending pool statistics to Graphite > > We're doing the same -- stripping invalid chars as needed --

Re: [ceph-users] Migrating data into a newer ceph instance

I tend to not do too much each time: either upgrade or data migrate. The actual upgrade process is seamless... So you can just as easily upgrade the "current" cluster to hammer, and add/remove nodes on the fly. All of this is quite seamless and straightforward (other than the data migration itself)

Re: [ceph-users] rados bench object not correct errors on v9.0.3

> -Original Message- > From: Dałek, Piotr [mailto:piotr.da...@ts.fujitsu.com] > Sent: Wednesday, August 26, 2015 2:02 AM > To: Sage Weil; Deneau, Tom > Cc: ceph-de...@vger.kernel.org; ceph-us...@ceph.com > Subject: RE: rados bench object not correct errors on v9.0.3 > > > -Original Me

Re: [ceph-users] Ceph Day Raleigh Cancelled

Yeah, we're still working on nailing down a venue for the Melbourne event (but it looks like 05 Nov is probably the date). As soon as we have a venue confirmed we'll put out a call for speakers and post the details on the /cephdays/ page. Thanks! On Tue, Aug 25, 2015 at 7:47 PM, Goncalo Borges w

Re: [ceph-users] ceph monitoring with graphite

On Wed, Aug 26, 2015 at 3:33 PM, Dan van der Ster wrote: > Hi Wido, > > On Wed, Aug 26, 2015 at 10:36 AM, Wido den Hollander wrote: >> I'm sending pool statistics to Graphite > > We're doing the same -- stripping invalid chars as needed -- and I > would guess that lots of people have written simi

Re: [ceph-users] Ceph Day Raleigh Cancelled

Hey Daleep, Right now we're planned through the end of the year, but if you know of a location where we would get good attendance and maybe someone with a space to host it we could certainly add that to the planning for 2016. Feel free to shoot me an email if you know of any places that might fit

Re: [ceph-users] Samsung pm863 / sm863 SSD info request

Le Tue, 25 Aug 2015 17:07:18 +0200 Jan Schermer écrivait: > There's a nice whitepaper about under-provisioning > everyone using SSDs should read it > > http://www.sandisk.com/assets/docs/WP004_OverProvisioning_WhyHow_FINAL.pdf >

[ceph-users] Ceph Tech Talk Tomorrow

Hey cephers, Don't forget that tomorrow is our monthly Ceph Tech Talk. This month we're taking a look at performance measuring and tuning in Ceph. Mark Nelson, Ceph's lead performance engineer will be giving an overview of what's new in the performance world of Ceph and sharing some recent finding

Re: [ceph-users] Samsung pm863 / sm863 SSD info request

Maybe if you TRIM it first, but the correct way to do that is like this: https://www.thomas-krenn.com/en/wiki/SSD_Over-provisioning_using_hdparm Jan > On 26 Aug 2015, at 18:58, Emmanuel Florac wrote: > > Le Tue, 25 Aug 2015 17:07:18 +0200 > Jan Schermer écrivait: > >> There's a nice whitepa

Re: [ceph-users] Rados: Undefined symbol error

Hello Jason, I checked the version of my built packages and they are all 9.0.2. I purged the cluster and uninstalled the packages and there seems to be nothing else - no older version. Could you elaborate on the fix for this issue? Thanks, Aakanksha -Original Message- From: Jason Dilla

[ceph-users] [ANN] ceph-deploy 1.5.28 released

Hi everyone, A new version of ceph-deploy has been released. Version 1.5.28 includes the following: - A fix for a regression introduced in 1.5.27 that prevented importing GPG keys on CentOS 6 only. - Will prevent Ceph daemon deployment on nodes that don't have Ceph installed on them. - Makes i

Re: [ceph-users] Rados: Undefined symbol error

- Original Message - > From: "Aakanksha Pudipeddi-SSI" > To: "Jason Dillaman" > Cc: ceph-us...@ceph.com > Sent: Thursday, 27 August, 2015 6:22:45 AM > Subject: Re: [ceph-users] Rados: Undefined symbol error > > Hello Jason, > > I checked the version of my built packages and they are all

Re: [ceph-users] RadosGW - multiple dns names

On Wed, Aug 26, 2015 at 11:52:02AM +0100, Luis Periquito wrote: > On Mon, Feb 23, 2015 at 10:18 PM, Yehuda Sadeh-Weinraub > wrote: > > > > > > > -- > > > > *From: *"Shinji Nakamoto" > > *To: *ceph-us...@ceph.com > > *Sent: *Friday, February 20, 2015 3:58:39 PM > > *Su

[ceph-users] Question regarding degraded PGs

Hey guys... 1./ I have a simple question regarding the appearance of degraded PGs. First, for reference: a. I am working with 0.94.2 b. I have 32 OSDs distributed in 4 servers, meaning that I have 8 OSD per server. c. Our cluster is set with 'osd pool default size = 3' and 'osd p

Re: [ceph-users] Ceph Day Raleigh Cancelled

On that note in regards to watching /cephdays for details, the RSS feed 404's! http://ceph.com/cephdays/feed/ Regards, Matt. On 27/08/2015 02:52, Patrick McGarry wrote: Yeah, we're still working on nailing down a venue for the Melbourne event (but it looks like 05 Nov is probably the date). A

Re: [ceph-users] docker distribution

looks like it only works if an nginx is in front of radosgw, it translates absolute URIs and maybe fix other issues: https://github.com/docker/distribution/pull/808#issuecomment-135286314 https://github.com/docker/distribution/pull/902 On Mon, Aug 17, 2015 at 1:37 PM, Lorieri wrote: > Hi, > > Do

[ceph-users] shutdown primary monitor, status of the osds on it will not change, and command like 'rbd create xxx' would block

Hi sage, I'm testing ceph feature,and now have a probem make me confused. Network construction is as shown in the figure below: serverB is primary monitor , it has 5 osds serverC is secondary monitor, it has 5 osds serverD is tertiary monitor,it has 5 osds client A use a rbd block via 'rbd

[ceph-users] shutdown primary monitor, status of the osds on it will not change, and command like 'rbd create xxx' would block

Hi sage, I'm testing ceph feature,and now have a probem make me confused. Network construction is as shown in the figure below: serverB is primary monitor , it has 5 osds serverC is secondary monitor, it has 5 osds serverD is tertiary monitor,it has 5 osds client A use a rbd block via 'rbd

[ceph-users] shutdown primary monitor, status of the osds on it will not change, and command like 'rbd create xxx' would block

Hi, I'm testing ceph feature,and now have a probem make me confused. Network construction is as shown in the figure below: serverB is primary monitor , it has 5 osds serverC is secondary monitor, it has 5 osds serverD is tertiary monitor,it has 5 osds client A use a rbd block via 'rbd map'