Helo, Ceph users,
TL;DR: PG autoscaler should not cause the "too few PGs per OSD" warning
Detailed:
Some time ago, I upgraded the HW in my virtualization+Ceph cluster,
replacing 30+ old servers with <10 modern servers. I immediately got
"Too much PGs per OSD" warning, so I had to add
You need to set the pg number before setting the pgp number, it's a
two step process.
ceph osd pool set cephfs_data pg_num 64
Setting the pg number creates new placement groups by splitting
existing ones but keeps them on the local OSD. Setting the pgp number
allows ceph to move the new pg's to
I have a new deployment and it always has this problem even if I increase
the size of the OSD, it stays at 8. I saw examples where others had this
problem but it was with the RBD pool, I don't have an RBD pool, and just
deployed it fresh with ansible.
health: HEALTH_WARN
1 MDSs
"143 active+clean
17 activating"
Wait until all of the PG's finish activating and you should be good. Let's
revisit your 160 PG's, though. If you had 128 PGs and 8TB of data in your
pool, then you each PG would have about 62.5GB in size. Because you set it
to 160 instead of a base 2 number,
And now :
ceph status
cluster 800221d2-4b8c-11e7-9bb9-cffc42889917
health HEALTH_OK
monmap e1: 2 mons at {ceph-storage-rbx-1=
172.29.20.30:6789/0,ceph-storage-rbx-2=172.29.20.31:6789/0}
election epoch 4, quorum 0,1
ceph-storage-rbx-1,ceph-storage-rbx-2
osdmap e21: 6
You increased your pg_num and it finished creating them "160
active+clean". Now you need to increase your pgp_num to match the 160 and
you should be good to go.
On Wed, Jun 14, 2017 at 10:57 AM Stéphane Klein
wrote:
> 2017-06-14 16:40 GMT+02:00 David Turner
And now:
2017-06-14 17:00 GMT+02:00 Stéphane Klein :
> Ok, I missed:
>
> ceph osd pool set rbd pgp_num 160
>
> Now I have:
>
> ceph status
> cluster 800221d2-4b8c-11e7-9bb9-cffc42889917
> health HEALTH_ERR
> 9 pgs are stuck inactive for more
Ok, I missed:
ceph osd pool set rbd pgp_num 160
Now I have:
ceph status
cluster 800221d2-4b8c-11e7-9bb9-cffc42889917
health HEALTH_ERR
9 pgs are stuck inactive for more than 300 seconds
9 pgs stuck inactive
9 pgs stuck unclean
monmap e1: 2
2017-06-14 16:40 GMT+02:00 David Turner :
> Once those PG's have finished creating and the cluster is back to normal
>
How can I see Cluster migration progression?
Now I have:
# ceph status
cluster 800221d2-4b8c-11e7-9bb9-cffc42889917
health HEALTH_WARN
A few things to note, it is recommended to have your PG count, per pool, to
be a base 2 value. Also, the number of PG's per OSD is an aggregate number
between all of your pools. If you're planning to add 3 more pools for
cephfs and other things, then you really want to be mindful of how many
Hi,
see comments below.
JC
> On Jun 14, 2017, at 07:23, Stéphane Klein wrote:
>
> Hi,
>
> I have this parameter in my Ansible configuration:
>
> pool_default_pg_num: 300 # (100 * 6) / 2 = 300
>
> But I have this error:
>
> # ceph status
> cluster
Hi,
I have this parameter in my Ansible configuration:
pool_default_pg_num: 300 # (100 * 6) / 2 = 300
But I have this error:
# ceph status
cluster 800221d2-4b8c-11e7-9bb9-cffc42889917
health HEALTH_ERR
73 pgs are stuck inactive for more than 300 seconds
22 pgs
Hi
We have created EC pool ( k =10 and m =3) with 540 osds. We followed the
following rule to calculate the pgs count for the EC pool.
(OSDs * 100)
Total PGs =
pool size
Where *pool size* is either the number of replicas for replicated
Hi Greg,
Do you have any idea about the health warning?
Regards
K.Mohamed Pakkeer
On Tue, Feb 10, 2015 at 4:49 PM, Mohamed Pakkeer mdfakk...@gmail.com
wrote:
Hi
We have created EC pool ( k =10 and m =3) with 540 osds. We followed the
following rule to calculate the pgs count for the EC
14 matches
Mail list logo