[ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-13 Thread dE
Hi,     I'm running ceph 10.2.5 on Debian (official package). It cant seem to create any functional pools -- ceph health detail HEALTH_ERR 64 pgs are stuck inactive for more than 300 seconds; 64 pgs stuck inactive; too few PGs per OSD (21 < min 30) pg 0.39 is stuck inactive for 652.741684, cur

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-13 Thread Michael Kuriger
You may not have enough OSDs to satisfy the crush ruleset. Mike Kuriger Sr. Unix Systems Engineer 818-434-6195 On 10/13/17, 9:53 AM, "ceph-users on behalf of dE" wrote: Hi, I'm running ceph 10.2.5 on Debian (official package). It cant s

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-13 Thread Ronny Aasen
strange that no osd is acting for your pg's can you show the output from ceph osd tree mvh Ronny Aasen On 13.10.2017 18:53, dE wrote: Hi,     I'm running ceph 10.2.5 on Debian (official package). It cant seem to create any functional pools -- ceph health detail HEALTH_ERR 64 pgs are stuck

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-13 Thread dE
On 10/13/2017 10:23 PM, dE wrote: Hi,     I'm running ceph 10.2.5 on Debian (official package). It cant seem to create any functional pools -- ceph health detail HEALTH_ERR 64 pgs are stuck inactive for more than 300 seconds; 64 pgs stuck inactive; too few PGs per OSD (21 < min 30) pg 0.39 is

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-13 Thread dE
On 10/13/2017 10:23 PM, dE wrote: Hi,     I'm running ceph 10.2.5 on Debian (official package). It cant seem to create any functional pools -- ceph health detail HEALTH_ERR 64 pgs are stuck inactive for more than 300 seconds; 64 pgs stuck inactive; too few PGs per OSD (21 < min 30) pg 0.39 is

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-13 Thread Gerhard W. Recher
you specify a mon on 0.0.0.0 my ceph.conf [mon.2] host = pve03 mon addr = 192.168.100.143:6789 [mon.3] host = pve04 mon addr = 192.168.100.144:6789 [mon.0] host = pve01 mon addr = 192.168.100.141:6789 [mon.1] host = pve02

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-13 Thread David Turner
What does your environment look like? Someone recently on the mailing list had PGs stuck creating because of a networking issue. On Fri, Oct 13, 2017 at 2:03 PM Ronny Aasen wrote: > strange that no osd is acting for your pg's > can you show the output from > ceph osd tree > > > mvh > Ronny Aase

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-13 Thread dE
On 10/14/2017 12:53 AM, David Turner wrote: What does your environment look like?  Someone recently on the mailing list had PGs stuck creating because of a networking issue. On Fri, Oct 13, 2017 at 2:03 PM Ronny Aasen > wrote: strange that no osd is act

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-14 Thread David Turner
What is the output of your `ceph status`? On Fri, Oct 13, 2017, 10:09 PM dE wrote: > On 10/14/2017 12:53 AM, David Turner wrote: > > What does your environment look like? Someone recently on the mailing > list had PGs stuck creating because of a networking issue. > > On Fri, Oct 13, 2017 at 2:0

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-14 Thread dE
On 10/14/2017 08:18 PM, David Turner wrote: What are the ownership permissions on your osd folders? Clock skew cares about partial seconds. It isn't the networking issue because your cluster isn't stuck peering. I'm not sure if the creating state happens in disk or in the cluster. On Sat

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-14 Thread Denes Dolhay
Hello, Could you include the monitors and the osds as well to your clock skew test? How did you create the osds? ceph-deploy osd create osd1:/dev/sdX osd2:/dev/sdY osd3: /dev/sdZ ? Some log from one of the osds would be great! Kind regards, Denes. On 10/14/2017 07:39 PM, dE wrote: On 10

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-14 Thread dE
On 10/15/2017 03:13 AM, Denes Dolhay wrote: Hello, Could you include the monitors and the osds as well to your clock skew test? How did you create the osds? ceph-deploy osd create osd1:/dev/sdX osd2:/dev/sdY osd3: /dev/sdZ ? Some log from one of the osds would be great! Kind regards, D

Re: [ceph-users] Brand new cluster -- pg is stuck inactive

2017-10-16 Thread Anthony Verevkin
http://docs.ceph.com/docs/master/rados/operations/crush-map/#crush-location Regards, Anthony - Original Message - > From: "dE" > To: "ceph-users" , ronny+ceph-us...@aasen.cx > Sent: Friday, October 13, 2017 2:43:54 PM > Subject: Re: [ceph-users] Bran