[ceph-users] Fwd: Separate --block.wal --block.db bluestore not working as expected.

I’m trying to create bluestore osds with separate --block.wal --block.db devices on a write intensive SSD I’ve split the SSD (/dev/sda) into two partditions sda1 and sda2 for db and wal I seems to me the osd uuid is getting changed and I’m only able to start the last OSD Do I need to

Re: [ceph-users] Ceph recovery kill VM's even with the smallest priority

I'm seconding what Greg is saying There is no reason to set nobackfill and norecover just for restarting OSDs. That will only cause the problems you're seeing without giving you any benefit. There are reasons to use norecover and nobackfill but unless you're manually editing the crush map, having

Re: [ceph-users] Ceph recovery kill VM's even with the smallest priority

ok now I understand, thanks for all this helpful answers! On Sat, Apr 7, 2018, 15:26 David Turner wrote: > I'm seconding what Greg is saying There is no reason to set nobackfill > and norecover just for restarting OSDs. That will only cause the problems > you're seeing

Re: [ceph-users] jewel ceph has PG mapped always to the same OSD's

Deep scrub doesn't help. After some steps (not sure what exact list) ceph does remap this pg to another osd, but PG doesn't move # ceph pg map 11.206 osdmap e176314 pg 11.206 (11.206) -> up [955,198,801] acting [787,697] Hangs in this state forever, 'ceph pg 11.206 query' hangs as well On Sat,

Re: [ceph-users] bluestore OSD did not start at system-boot

On Thu, Apr 5, 2018 at 6:33 AM, Ansgar Jazdzewski wrote: > hi folks, > > i just figured out that my ODS's did not start because the filsystem > is not mounted. Would love to see some ceph-volume logs (both ceph-volume.log and ceph-volume-systemd.log) because we do

Re: [ceph-users] Ceph scrub logs: _scan_snaps no head for $object?

How do you resolve these issues? Apr 7 22:39:21 c03 ceph-osd: 2018-04-07 22:39:21.928484 7f0826524700 -1 osd.13 pg_epoch: 19008 pg[17.13( v 19008'6019891 (19008'6018375,19008'6019891] local-lis/les=18980/18981 n=3825 ec=3636/3636 lis/c 18980/18980 les/c/f 18981/18982/0 18980/18980/18903)

Re: [ceph-users] Fwd: Separate --block.wal --block.db bluestore not working as expected.

On Sat, Apr 7, 2018 at 11:59 AM, Gary Verhulp wrote: > > > > > > I’m trying to create bluestore osds with separate --block.wal --block.db > devices on a write intensive SSD > > > > I’ve split the SSD (/dev/sda) into two partditions sda1 and sda2 for db and > wal > > > > > >

Re: [ceph-users] how the files in /var/lib/ceph/osd/ceph-0 are generated

On Fri, Apr 6, 2018 at 10:27 PM, Jeffrey Zhang wrote: > Yes, I am using ceph-volume. > > And i found where the keyring comes from. > > bluestore will save all the information at the starting of disk > (BDEV_LABEL_BLOCK_SIZE=4096) > this area is used for saving

Re: [ceph-users] amount of PGs/pools/OSDs for your openstack / Ceph

The general recommendation is to target around 100 PG/OSD. Have you tried the https://ceph.com/pgcalc/ tool? On Wed, 4 Apr 2018 at 21:38, Osama Hasebou wrote: > Hi Everyone, > > I would like to know what kind of setup had the Ceph community been using > for their

Re: [ceph-users] Upgrading ceph and mapped rbds

I had several kernel mapped rbds as well as ceph-fuse mounted CephFS clients when I upgraded from Jewel to Luminous. I rolled out the client upgrades over a few weeks after the upgrade. I had tested that the client use cases I had would be fine running Jewel connecting to a Luminous cluster so