On 9/26/19 5:05 AM, zhanrzh...@teamsun.com.cn wrote:
> Thanks for your reply.
> We don't maintain it frequently.
> My confusion is whether the more monitor is more advantage for
> client(osd,rbdclient...) to get clustermap.
> Do All clients comunicate with one monitor of the cluster at the m
On 9/25/19 12:39 AM, João Victor Rodrigues Soares wrote:
My question is if what is happening may have to do with the amount of
disk dedicated to DB / WAL. In the CEPH documentation it says it is
recommended that the block.db size is not smaller than 4% of block.
In this case for each disk in
Hi,
I am also using CephFS with Docker for the same reason you said. Also
Ubuntu 18.04. I used the kernel client before Nautilus, but now FUSE,
because the kernel client is to old (might work now with the newest HWE
kernel).
I don't have any problems at all, neither in Portainer nor any other
con
Thanks for your reply.
We don't maintain it frequently.
My confusion is whether the more monitor is more advantage for
client(osd,rbdclient...) to get clustermap.
Do All clients comunicate with one monitor of the cluster at the mean time ?
If not how client to decide to communicat with which
On Mon, Sep 23, 2019 at 6:50 AM Josh Haft wrote:
>
> Hi,
>
> I've been migrating data from one EC pool to another EC pool: two
> directories are mounted with ceph.dir.layout.pool file attribute set
> appropriately, then rsync from old to new and finally, delete the old
> files. I'm using the kerne
On Wed, Sep 25, 2019 at 1:56 PM Sasha Litvak
wrote:
>
> I guess for me the more crucial questions should be answered:
>
> 1. How can a busted release be taken out of repos (some metadata
> update I hope)?
It's hard to define the word "busted" in a way that satisfies everyone.
For example, in
Worked around it by doing a fail of the mds because I read somewhere
about restarting it. However would be nice to know what causes this and
how to prevent it.
ceph mds fail c
-Original Message-
Subject: [ceph-users] Re: Luminous 12.2.12 "clients failing to respond
to capability re
These are not excessive values, are they? How to resolve this?
[@~]# ceph daemon mds.c cache status
{
"pool": {
"items": 266303962,
"bytes": 7599982391
}
}
[@~]# ceph daemon mds.c objecter_requests
{
"ops": [],
"linger_ops": [],
"pool_ops": [],
"pool_st
I guess for me the more crucial questions should be answered:
1. How can a busted release be taken out of repos (some metadata update I
hope)?
2. Can some fix(es) be added into a test release so they can be accessed
by community and tested / used before next general release is avaialble.
I was
Hi,
I am trying to figure out why my portainer and pi-hole in docker keeps getting
broken databases. All other docker applications are working flawlessly but not
these.
I am running Ubuntu 18.04 + kernel ceph mount for the data directory.
Have looked at how others do it, and they seem to all u
I kind of doubt this will provide much of an advantage, I think recovery is
the only time you might have some chance of speedup, but i'm not sure
network throughput is always the bottleneck. There was some discussion a
while back about this, client IO is still going to be impacted by recovery.
O
On 9/25/19 6:52 PM, Nathan Fish wrote:
> You don't need more mons to scale; but going to 5 mons would make the
> cluster more robust, if it is cheap for you to do so.
> If you assume that 1 mon rebooting for updates or maintenance is
> routine, then 2/3 is vulnerable to one failure. 4/5 can survi
You don't need more mons to scale; but going to 5 mons would make the
cluster more robust, if it is cheap for you to do so.
If you assume that 1 mon rebooting for updates or maintenance is
routine, then 2/3 is vulnerable to one failure. 4/5 can survive an
unexpected additional failure while one is
hello
as far as I know and according to the document the mon just share the
cluster map with the client. Not the data
"Storage cluster clients retrieve a copy of the cluster map from the
Ceph Monitor."
https://docs.ceph.com/docs/master/architecture/
Le mercredi 25 septembre 2019 à 22:25 +0800,
On Wed, Sep 25, 2019 at 10:26 AM 展荣臻（信泰） wrote:
>
> hi all:
> I have a production cluster, and it had 24 hosts (528 osds,3mons) at a
> former.
> Now we want to add 36 hosts so the osd increase to 1320 .
>
We use 3 mons in this size cluster with no issues.
> does the monitor need to inc
On the client I have this
[@~]# cat /proc/sys/fs/file-nr
10368 0 381649
-Original Message-
Subject: [ceph-users] Luminous 12.2.12 "clients failing to respond to
capability release"
I am getting this error
I have in two sessions[0] num_caps high ( I assume the error is ab
Hi all,
I'm happy to announce that next Oct 16th we will have the Ceph Day
Argentina in Buenos Aires. The event will be held in the Museo de
Informatica de Argentina, so apart from hearing the latest features from
core developers, real use cases from our users and usage experiences from
customers
hi all:
I have a production cluster, and it had 24 hosts (528 osds,3mons) at a
former.
Now we want to add 36 hosts so the osd increase to 1320 .
does the monitor need to increase?how many numbers of monitor node is
recommended?
Another question is which monitor does monclient c
I am getting this error
I have in two sessions[0] num_caps high ( I assume the error is about
num_caps ). I am using a default luminous and a default centos7 with
default kernel 3.10.
Do I really still need to change to a not stock kernel to resolve this?
I read this in posts of 2016 and 2
On 9/25/19 3:22 PM, nalexand...@innologica.com wrote:
> Hi everyone,
>
> We are running Nautilus 14.2.2 with 6 nodes and a total of 44 OSDs, all are
> 2TB spinning disks.
> # ceph osd count-metadata osd_objectstore
> "bluestore": 44
> # ceph osd pool get one size
> size: 3
> # ceph df
> R
Hello,
In my company, we currently have the following infrastructure:
- Ceph Luminous
- OpenStack Pike.
We have a cluster of 3 osd nodes with the following configuration:
- 1 x Xeon (R) D-2146NT CPU @ 2.30GHz
- 128GB RAM
- 128GB ROOT DISK
- 12 x 10TB SATA ST1NM0146 (OSD)
- 1 x Intel Optane
Hi,
I need your advice about the following setup.
Currently, we have a Ceph nautilus cluster used by Openstack Cinder with
single NIC in 10Gbps on OSD hosts.
We will upgrade the cluster by adding 7 new hosts dedicated to
Nova/Glance and we would like to add a cluster network to isolate
replica
Hi everyone,
We are running Nautilus 14.2.2 with 6 nodes and a total of 44 OSDs, all are 2TB
spinning disks.
# ceph osd count-metadata osd_objectstore
"bluestore": 44
# ceph osd pool get one size
size: 3
# ceph df
RAW STORAGE:
CLASS SIZE AVAIL USED RAW USED %RAW
Hi Reed,
I'm not sure what is meant with the grouping / chassis and "set your
failure domain to chassis" respectively.
This is my current crush map:
# begin crush map
tunable choose_local_tries 0
tunable choose_local_fallback_tries 0
tunable choose_total_tries 50
tunable chooseleaf_descend_onc
After updating the CRUSH rule from
rule cephfs_ec {
id 1
type erasure
min_size 8
max_size 8
step set_chooseleaf_tries 5
step set_choose_tries 100
step take default
step choose indep 4 type host
step choose indep 2 type osd
step emit
}
to
rule cephfs_ec {
25 matches
Mail list logo
