[ceph-users] Pg inactive when back filling?

Hi Ceph users, I found that some pg are inactive after I added some osds and PGs. ceph pg dump_stuck inactive: PG_STAT STATE UP UP_PRIMARY ACTING ACTING_PRIMARY 10.9b undersized+degraded+remapped+backfilling+peered [8,9] 8[3]

[ceph-users] 答复: 答复: No "snapset" attribute for clone object

Yes, I believe so. Is there any workarounds? -邮件原件- 发件人: Jason Dillaman [mailto:jdill...@redhat.com] 发送时间: 2017年7月13日 21:13 收件人: 许雪寒 抄送: ceph-users@lists.ceph.com 主题: Re: [ceph-users] 答复: No "snapset" attribute for clone object Quite possibly the same as this issue? [1] [1]

Re: [ceph-users] Stealth Jewel release?

So only the ceph-mds is affected? Let's say if we have mons and osds on 10.2.8 and the MDS on 10.2.6 or 10.2.7 we would be "safe"? I'm asking since we need to add new storage nodes to our production cluster. Best, Martin On Wed, Jul 12, 2017 at 10:44 PM, Patrick Donnelly

Re: [ceph-users] Ceph mount rbd

Hi, Why you would like to maintain copies by yourself. You replicate on ceph and then on different files inside ceph? Let ceph take care of counting. Create a pool with 3 or more copies and let ceph take care of what's stored and where. Best regards, El 13/07/17 a las 17:06,

Re: [ceph-users] Stealth Jewel release?

Hi, 10.2.9 is there: apt list --upgradable Listing... Done ceph/stable 10.2.9-1~bpo80+1 amd64 [upgradable from: 10.2.8-1~bpo80+1] Change-File?? Udo Am 2017-07-14 09:26, schrieb Martin Palma: So only the ceph-mds is affected? Let's say if we have mons and osds on 10.2.8 and the MDS on 10.2.6

[ceph-users] PGs per OSD guidance

Hi All, I have been reviewing the sizing of our PGs with a view to some intermittent performance issues. When we have scrubs running, even when only a few are, we can sometimes get severe impacts on the performance of RBD images, enough to start causing VMs to appear stalled or

Re: [ceph-users] upgrade procedure to Luminous

On Fri, 14 Jul 2017, Joao Eduardo Luis wrote: > Dear all, > > > The current upgrade procedure to jewel, as stated by the RC's release notes, You mean (jewel or kraken) -> luminous, I assume... > can be boiled down to > > - upgrade all monitors first > - upgrade osds only after we have a

Re: [ceph-users] upgrade procedure to Luminous

On 07/14/2017 03:12 PM, Sage Weil wrote: On Fri, 14 Jul 2017, Joao Eduardo Luis wrote: Dear all, The current upgrade procedure to jewel, as stated by the RC's release notes, You mean (jewel or kraken) -> luminous, I assume... Yeah. *sigh* -Joao

Re: [ceph-users] 答复: 答复: No "snapset" attribute for clone object

The only people that have experienced it seem to be using cache tiering. I don't know if anyone has deeply investigate it yet. You could attempt to evict those objects from the cache tier so that the snapdir request is proxied down to the base tier to see if that works. On Fri, Jul 14, 2017 at

Re: [ceph-users] upgrade procedure to Luminous

On 07/14/2017 03:12 PM, Sage Weil wrote: On Fri, 14 Jul 2017, Joao Eduardo Luis wrote: On top of this all, I found during my tests that any OSD, running luminous prior to the luminous quorum, will need to be restarted before it can properly boot into the cluster. I'm guessing this is a bug

[ceph-users] upgrade procedure to Luminous

Dear all, The current upgrade procedure to jewel, as stated by the RC's release notes, can be boiled down to - upgrade all monitors first - upgrade osds only after we have a **full** quorum, comprised of all the monitors in the monmap, of luminous monitors (i.e., once we have the

Re: [ceph-users] Stealth Jewel release?

On Fri, Jul 14, 2017 at 12:26 AM, Martin Palma wrote: > So only the ceph-mds is affected? Let's say if we have mons and osds > on 10.2.8 and the MDS on 10.2.6 or 10.2.7 we would be "safe"? Yes, only the MDS was affected. As Udo mentioned, v10.2.9 is out so feel free to upgrade

Re: [ceph-users] 答复: calculate past_intervals wrong, lead to choose wrong authority osd, then osd assert(newhead >= log.tail)

On Fri, 14 Jul 2017, Chenyehua wrote: > Thanks, Sage. > > It doesn't happen every time, but the probability is high > > Reproduce as Follows: > HOST-A HOST-B HOST-C > osd 7 osd 21 osd11 > 1. osdmap epoch95, pg 1.20f on osd acting set [11,7]/ up

Re: [ceph-users] upgrade procedure to Luminous

On 2017-07-14T10:34:35, Mike Lowe wrote: > Having run ceph clusters in production for the past six years and upgrading > from every stable release starting with argonaut to the next, I can honestly > say being careful about order of operations has not been a problem.

[ceph-users] how to list and reset the scrub schedules

Hi, Occasionally we want to change the scrub schedule for a pool or whole cluster, but we want to do this by injecting new settings without restarting every daemon. I've noticed that in jewel, changes to scrub_min/max_interval and deep_scrub_interval do not take immediate effect, presumably

Re: [ceph-users] Ceph mount rbd

Gonzalo, You are right, i told so much about my enviroment actual and maybe i didn't know explain my problem the better form, with ceph in the moment, mutiple hosts clients can mount and write datas in my system and this is one problem, because i could have filesystem corruption. Example,

Re: [ceph-users] upgrade procedure to Luminous

On 2017-07-14T14:12:08, Sage Weil wrote: > > Any thoughts on how to mitigate this, or on whether I got this all wrong and > > am missing a crucial detail that blows this wall of text away, please let me > > know. > I don't know; the requirement that mons be upgraded before

Re: [ceph-users] upgrade procedure to Luminous

Having run ceph clusters in production for the past six years and upgrading from every stable release starting with argonaut to the next, I can honestly say being careful about order of operations has not been a problem. > On Jul 14, 2017, at 10:27 AM, Lars Marowsky-Bree wrote:

Re: [ceph-users] upgrade procedure to Luminous

It was required for Bobtail to Cuttlefish and Cuttlefish to Dumpling. Exactly how many mons do you have such that you are concerned about failure? If you have let’s say 3 mons, you update all the bits, then it shouldn’t take you more than 2 minutes to restart the mons one by one. You can

Re: [ceph-users] upgrade procedure to Luminous

On Fri, 14 Jul 2017, Lars Marowsky-Bree wrote: > On 2017-07-14T14:12:08, Sage Weil wrote: > > > > Any thoughts on how to mitigate this, or on whether I got this all wrong > > > and > > > am missing a crucial detail that blows this wall of text away, please let > > > me > > >

Re: [ceph-users] Stealth Jewel release?

Is there going to be an announcement for 10.2.9 either? I haven't seen anything other than users noticing the packages. On Fri, Jul 14, 2017, 10:30 AM Martin Palma wrote: > Thank you for the clarification and yes we saw that v10.2.9 was just > released. :-) > > Best, > Martin >

Re: [ceph-users] ceph-deploy mgr create error No such file or directory:

I've been trying to work through similar mgr issues for Xenial-Luminous... roger@desktop:~/ceph-cluster$ ceph-deploy mgr create mon1 nuc2 [ceph_deploy.conf][DEBUG ] found configuration file at: /home/roger/.cephdeploy.conf [ceph_deploy.cli][INFO ] Invoked (1.5.38): /usr/bin/ceph-deploy mgr

Re: [ceph-users] how to list and reset the scrub schedules

On Fri, Jul 14, 2017 at 5:41 AM Dan van der Ster wrote: > Hi, > > Occasionally we want to change the scrub schedule for a pool or whole > cluster, but we want to do this by injecting new settings without > restarting every daemon. > > I've noticed that in jewel, changes to

[ceph-users] v10.2.9 Jewel released

v10.2.9 Jewel released == This point release fixes a regression introduced in v10.2.8. We recommend that all Jewel users upgrade. For more detailed information, see the complete changelog[1] and release notes[2]. Notable Changes --- * cephfs: Damaged MDS with

[ceph-users] v10.2.8 Jewel released

v10.2.8 Jewel released == This point release brought a number of important bugfixes in all major components of Ceph. However, it also introduced a regression that could cause MDS damage, and a new release, v10.2.9, was published to address this. Therefore, Jewel users should

Re: [ceph-users] Ceph mount rbd

> -Original Message- > From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of > Jason Dillaman > Sent: 14 July 2017 16:40 > To: li...@marcelofrota.info > Cc: ceph-users > Subject: Re: [ceph-users] Ceph mount rbd > > On Fri, Jul 14, 2017 at

Re: [ceph-users] ceph-deploy mgr create error No such file or directory:

On Fri, Jul 14, 2017 at 10:37 AM, Oscar Segarra wrote: > I'm testing on latest Jewell version I've found in repositories: > you can skip that command then, I will fix the document to add a note for jewel or pre luminous build. > > [root@vdicnode01 yum.repos.d]# ceph

Re: [ceph-users] Ceph mount rbd

On Fri, Jul 14, 2017 at 9:44 AM, wrote: > Gonzalo, > > > > You are right, i told so much about my enviroment actual and maybe i didn't > know explain my problem the better form, with ceph in the moment, mutiple > hosts clients can mount and write datas in my system and

Re: [ceph-users] PG stuck inconsistent, but appears ok?

You probably have osd_max_scrubs=1 and the PG just isn't getting a slot to start. Here's a little trick to get that going right away: ceph osd set noscrub ceph osd set nodeep-scrub ceph tell osd.* injectargs -- --osd_max_scrubs 2 ceph pg deep-scrub 22.1611 ... wait until it starts scrubbing ...

[ceph-users] cluster network question

Dear all, I'm reading the docs at http://docs.ceph.com/docs/master/rados/configuration/network-config-ref/ regarding the cluster network and I wonder which nodes are connected to the dedicated cluster network? The digram on the mentioned page only shows the OSDs connected to the cluster

Re: [ceph-users] ceph-deploy mgr create error No such file or directory:

It is tested for master and is working fine, I will run those same tests on luminous and check if there is an issue and update here. mgr create is needed for luminous+ bulids only. On Fri, Jul 14, 2017 at 10:18 AM, Roger Brown wrote: > I've been trying to work through

Re: [ceph-users] ceph-deploy mgr create error No such file or directory:

I'm testing on latest Jewell version I've found in repositories: [root@vdicnode01 yum.repos.d]# ceph --version ceph version 10.2.8 (f5b1f1fd7c0be0506ba73502a675de9d048b744e) thanks a lot! 2017-07-14 19:21 GMT+02:00 Vasu Kulkarni : > It is tested for master and is working

Re: [ceph-users] PG stuck inconsistent, but appears ok?

I issued the pg deep scrub command ~24 hours ago and nothing has changed. I see nothing in the active osd's log about kicking off the scrub. On Jul 13, 2017, at 2:24 PM, David Turner > wrote: # ceph pg deep-scrub 22.1611 On Thu, Jul 13, 2017

Re: [ceph-users] cluster network question

Only the osds use the dedicated cluster network. Ping the mons and mds services on the network will do nothing. On Fri, Jul 14, 2017, 11:39 AM Laszlo Budai wrote: > Dear all, > > I'm reading the docs at >

Re: [ceph-users] RBD cache being filled up in small increases instead of 4MB

On Fri, Jul 14, 2017 at 3:43 PM, Ruben Rodriguez wrote: > > I'm having an issue with small sequential reads (such as searching > through source code files, etc), and I found that multiple small reads > withing a 4MB boundary would fetch the same object from the OSD multiple >

[ceph-users] FW: Regarding Ceph Debug Logs

Hi All, I am new to ceph and I am trying to debug a few scenarios . I have 2 queries as listed below - 1.Regarding enabling debug logs for ceph 2.Regarding internal processes of ceph QUERY 1 I have enabled the logs by setting the log level in ceph conf file attached above - But none of this

Re: [ceph-users] hammer -> jewel 10.2.8 upgrade and setting sortbitwise

On Mon, Jul 10, 2017 at 5:06 PM, Sage Weil wrote: > On Mon, 10 Jul 2017, Luis Periquito wrote: >> Hi Dan, >> >> I've enabled it in a couple of big-ish clusters and had the same >> experience - a few seconds disruption caused by a peering process >> being triggered, like any

Re: [ceph-users] Stealth Jewel release?

Thank you for the clarification and yes we saw that v10.2.9 was just released. :-) Best, Martin On Fri, Jul 14, 2017 at 3:53 PM, Patrick Donnelly wrote: > On Fri, Jul 14, 2017 at 12:26 AM, Martin Palma wrote: >> So only the ceph-mds is affected? Let's say

Re: [ceph-users] missing feature 400000000000000 ?

On 14/07/17 11:03, Ilya Dryomov wrote: > On Fri, Jul 14, 2017 at 11:29 AM, Riccardo Murri > wrote: >> Hello, >> >> I am trying to install a test CephFS "Luminous" system on Ubuntu 16.04. >> >> Everything looks fine, but the `mount.ceph` command fails (error 110, >>

Re: [ceph-users] Regarding Ceph Debug Logs

Hi All, I am new to ceph and I am trying to debug a few scenarios . I have 2 queries as listed below - 1.Regarding enabling debug logs for ceph 2.Regarding internal processes of ceph QUERY 1 I have enabled the logs by setting the log level in /etc/ceph/ceph.conf attached above - But none of

[ceph-users] Regarding Ceph Debug Logs

Hi All, I am new to ceph and I am trying to debug a few scenarios . I have 2 queries as listed below - 1.Regarding enabling debug logs for ceph 2.Regarding internal processes of ceph QUERY 1 >> I have enabled the logs by setting the log level in /etc/ceph/ceph.conf attached above - But none

[ceph-users] missing feature 400000000000000 ?

Hello, I am trying to install a test CephFS "Luminous" system on Ubuntu 16.04. Everything looks fine, but the `mount.ceph` command fails (error 110, timeout); kernel logs show a number of messages like these before the `mount` prog gives up: libceph: ... feature set mismatch, my

Re: [ceph-users] autoconfigured haproxy service?

> Op 11 juli 2017 om 22:35 schreef Sage Weil : > > > On Tue, 11 Jul 2017, Wido den Hollander wrote: > > > Op 11 juli 2017 om 17:03 schreef Sage Weil : > > > > > > > > > Hi all, > > > > > > Luminous features a new 'service map' that lets rgw's (and rgw nfs

Re: [ceph-users] missing feature 400000000000000 ?

according to some slide in https://www.youtube.com/watch?v=gp6if858HUI the support is: > TUNABLE RELEASE CEPH_VERSION KERNEL > CRUSH_TUNABLES argonaut v0.48.1 v3.6 > CRUSH_TUNABLES2 bobtail v0.55 v3.9 > CRUSH_TUNABLES3 firefly v0.78 v3.15 > CRUSH_V4

Re: [ceph-users] missing feature 400000000000000 ?

On Fri, Jul 14, 2017 at 11:29 AM, Riccardo Murri wrote: > Hello, > > I am trying to install a test CephFS "Luminous" system on Ubuntu 16.04. > > Everything looks fine, but the `mount.ceph` command fails (error 110, > timeout); > kernel logs show a number of messages

[ceph-users] 答复: calculate past_intervals wrong, lead to choose wrong authority osd, then osd assert(newhead >= log.tail)

Thanks, Sage. It doesn't happen every time, but the probability is high Reproduce as Follows: HOST-A HOST-B HOST-C osd 7 osd 21 osd11 1. osdmap epoch95, pg 1.20f on osd acting set [11,7]/ up set[11,7],then shutdown HOST-C 2. for a long time, cluster

Re: [ceph-users] libceph: auth method 'x' error -1

On Wed, Jul 12, 2017 at 7:11 PM, wrote: > Hi! > > I have installed Ceph using ceph-deploy. > The Ceph Storage Cluster setup includes these nodes: > ld4257 Monitor0 + Admin > ld4258 Montor1 > ld4259 Monitor2 > ld4464 OSD0 > ld4465 OSD1 > > Ceph Health status is OK. > > However, I