Re: Luminous missing osd_backfill_full_ratio

[David C <dcsysengineer@xxxxxxxxx>]

In the end if was because I hadn't completed the upgrade with "ceph osd require-osd-release luminous", after setting that I had the default backfill full (0.9 I think) and was able to change it with ceph osd set backfillfull-ratio.

Potential gotcha for a Jewel -> Luminous upgrade if you delay the "...require-osd-release luminous" for whatever reason as it appears to leave you with no backfillfull limit

Still having a bit of an issue with new OSDs over filling but will start a new thread for that

Cheers,

On Thu, Aug 30, 2018 at 10:34 PM David Turner <drakonstein@xxxxxxxxx> wrote:

This moved to the PG map in luminous. I think it might have been there in Jewel as well.

http://docs.ceph.com/docs/luminous/man/8/ceph/#pg

ceph pg set_full_ratio <float[0.0-1.0]>

ceph pg set_backfillfull_ratio <float[0.0-1.0]>

ceph pg set_nearfull_ratio <float[0.0-1.0]>

On Thu, Aug 30, 2018, 1:57 PM David C <dcsysengineer@xxxxxxxxx> wrote:

Hi All

I feel like this is going to be a silly query with a hopefully simple answer. I don't seem to have the osd_backfill_full_ratio config option on my OSDs and can't inject it. This a Lumimous 12.2.1 cluster that was upgraded from Jewel.

I added an OSD to the cluster and woke up the next day to find the OSD had hit OSD_FULL. I'm pretty sure the reason it filled up was because the new host was weighted too high (I initially add two OSDs but decided to only backfill one at a time). The thing that surprised me was why a backfill full ratio didn't kick in to prevent this from happening.

One potentially key piece of info is I haven't run the "ceph osd require-osd-release luminous" command yet (I wasn't sure what impact this would have so was waiting for a window with quiet client I/O).

ceph osd dump is showing zero for all full ratios:

# ceph osd dump | grep full_ratio

full_ratio 0

backfillfull_ratio 0

nearfull_ratio 0

Do I simply need to run ceph osd set -backfillfull-ratio? Or am I missing something here. I don't understand why I don't have a default backfill_full ratio on this cluster.

Thanks,

_______________________________________________
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