Re: 300 active+undersized+degraded+remapped

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hi Deepak,

As Wildo pointed it out in the thread you linked, "osd crush update on start" and osd crush location are quick ways to fix this. If you are doing custom locations (like for tiering NVMe vs HDD) "osd crush location hook" (Doc: http://docs.ceph.com/docs/master/rados/operations/crush-map/#custom-location-hooks ) is a good option as well: it allows you to configure the crush location of the OSD based on a script, it shouldn't be too hard to detect if the OSD is NVMe or SATA and set its location based on that. It's really nice when you add new OSDs to see them arrive in the right location automatically.
Shameless plug: you can find an example in this blog post http://www.root314.com/2017/01/15/Ceph-storage-tiers/#tiered-crushmap I hope it helps

Cheers,
Maxime

On Sat, 1 Jul 2017 at 03:28 Deepak Naidu <dnaidu@xxxxxxxxxx> wrote:

OK, so looks like its ceph crushmap behavior http://docs.ceph.com/docs/master/rados/operations/crush-map/

 

--

Deepak

 

From: ceph-users [mailto:ceph-users-bounces@xxxxxxxxxxxxxx] On Behalf Of Deepak Naidu
Sent: Friday, June 30, 2017 7:06 PM
To: David Turner; ceph-users@xxxxxxxxxxxxxx


Subject: Re: 300 active+undersized+degraded+remapped

 

OK, I fixed the issue. But this is very weird. But will list them so its easy for other to check when there is similar issue.

 

1)      I had create rack aware osd tree

2)      I have SATA OSD’s and NVME OSD

3)      I created rack aware policy for both SATA and NVME OSD

4)      NVME OSD was used for CEPH FS Meta

5)      Recently: When I tried reboot of OSD node, it seemed that my journal volumes which were on NVME didn’t startup bcos of the UDEV rules and I had to create startup script to fix them.

6)      With that. I had rebooted all the OSD one by one monitoring the ceph status.

7)      I was at the 3rd last node, then I notice the pgstuck warning. Not sure when and what happened, but I started getting this PG stuck issue(which is listed in my original email)

8)      I wasted time to look at the issue/error, but then I found the pool 100% used issue.

9)      Now when I tried ceph osd tree. It looks like my NVME OSD’s went back to the host level OSD’s rather than the newly created/mapped NVME rack level. Ie no OSD’s under nvme-host name. This was the issue.

10)   Luckily I had created the backup of compiled version. I imported them in crushmap rule and now pool status is OK.

 

But, my question is how did ceph re-map the CRUSH rule ?

 

I had to create “new host entry” for NVME in crushmap ie

 

host OSD1-nvme              -- This is just dummy entry in crushmap ie it doesn’t resolve to any hostname

host OSD1                          -- This is the actual hostname and resolves to IP and has an hostname

 

Is that the issue ?

 

Current status

 

health HEALTH_OK

osdmap e5108: 610 osds: 610 up, 610 in

            flags sortbitwise,require_jewel_osds

      pgmap v247114: 15450 pgs, 3 pools, 322 GB data, 86102 objects

            1155 GB used, 5462 TB / 5463 TB avail

               15450 active+clean

 

 

Pool1                  15       233M          0              1820T                 3737

Pool2                 16          0                0             1820T                  0

Pool Meta               17     34928k                0                   2357G                        28

 

 

Partial list of my osd tree

 

-15    2.76392     rack rack1-nvme                                                

-18    0.69098         host OSD1-nvme                                   

 60    0.69098             osd.60                     up  1.00000          1.00000

-21    0.69098         host OSD2-nvme                                   

243    0.69098             osd.243                    up  1.00000          1.00000

-24    0.69098         host OSD3-NGN1-nvme                                   

426    0.69098             osd.426                    up  1.00000          1.00000

-1 5456.27734 root default                                                       

-12 2182.51099     rack rack1-sata                                                

 -2  545.62775         host OSD1                                        

  0    9.09380             osd.0                      up  1.00000          1.00000

  1    9.09380             osd.1                      up  1.00000          1.00000

  2    9.09380             osd.2                      up  1.00000          1.00000

  3    9.09380             osd.3                      up  1.00000          1.00000

-2  545.62775         host OSD2                                        

  0    9.09380             osd.0                      up  1.00000          1.00000

  1    9.09380             osd.1                      up  1.00000          1.00000

  2    9.09380             osd.2                      up  1.00000          1.00000

  3    9.09380             osd.3                      up  1.00000          1.00000

-2  545.62775         host OSD2                                        

  0    9.09380             osd.0                      up  1.00000          1.00000

  1    9.09380             osd.1                      up  1.00000          1.00000

  2    9.09380             osd.2                      up  1.00000          1.00000

  3    9.09380             osd.3                      up  1.00000          1.00000

 

 

--

Deepak

 

 

 

From: David Turner [mailto:drakonstein@xxxxxxxxx]
Sent: Friday, June 30, 2017 6:36 PM
To: Deepak Naidu; ceph-users@xxxxxxxxxxxxxx
Subject: Re: 300 active+undersized+degraded+remapped

 

ceph status
ceph osd tree

Is your meta pool on ssds instead of the same root and osds as the rest of the cluster?

 

On Fri, Jun 30, 2017, 9:29 PM Deepak Naidu <dnaidu@xxxxxxxxxx> wrote:

Hello,

 

I am getting the below error and I am unable to get them resolved even after starting and stopping the OSD’s. All the OSD’s seems to be up.

 

How do I repair the OSD’s or fix them manually. I am using cephFS. But oddly the ceph df is showing 100% used(which is showing in KB). But the pool is 1886G(with 3 copies). I can still write to the ceph FS without any issue. Not sure why is CEPH reporting the wrong info of 100% full

 

 

ceph version 10.2.7

 

     health HEALTH_WARN

            300 pgs degraded

            300 pgs stuck degraded

            300 pgs stuck unclean

            300 pgs stuck undersized

            300 pgs undersized

            recovery 28/19674 objects degraded (0.142%)

            recovery 56/19674 objects misplaced (0.285%)

 

 

 

GLOBAL:

    SIZE      AVAIL     RAW USED     %RAW USED

    5463T     5462T         187G             0

POOLS:

    NAME                 ID     USED       %USED       MAX AVAIL     OBJECTS

    Pool1                  15       233M          0              1820T                 3737

    Pool2                 16          0                0               1820T                  0

    PoolMeta        17     34719k     100.00             0                      28

 

 

Any help is appreciated

 

--

Deepak


This email message is for the sole use of the intended recipient(s) and may contain confidential information.  Any unauthorized review, use, disclosure or distribution is prohibited.  If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message.


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

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

[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Ceph Dev]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux