Hello,
When you deploy ceph to other nodes with the orchestrator, they "just" have the
containers you deployed to them.
This means in your case, you started the monitor container on ceph101 and you
must have installed at least the ceph-common package (else the ceph command
would not work).
If
Hi all.
My cluster has many osds down, 1 mon log has many line :
2020-06-15 18:00:22.575 7fa2deffe700 0 log_channel(cluster) log [DBG] : scrub
ok on 0,1,2,3,4: ScrubResult(keys {osd_snap=100} crc {osd_snap=2176495218})
2020-06-15 18:00:22.661 7fa2deffe700 0 log_channel(cluster) log [DBG] : scr
Yep, I think the ceph_fsid tells OSDs how to recognize the cluster. It
should be the same as the fsid in ceph.conf.
于2020年6月16日周二 上午6:28写道：
> I am having a problem on my cluster where OSDs on one host are down after
> reboot. When I run ceph-disk activate-all I get an error message stating
> "No
I am having a problem on my cluster where OSDs on one host are down after
reboot. When I run ceph-disk activate-all I get an error message stating "No
cluster conf found in /etc/ceph with fsid e1d7b4ae-2dcd-40ee-bea5-d103fe1fa9c9
When I look at the /etc/ceph/ceph.conf file I can see that the fsid
I have installed simple ceph system with two nodes (ceph100, ceph101)
with cephadm and ceph orch host add command. I put the ssh-copy-id -f -i
/etc/ceph/ceph.pub key to the second host (ceph101). I can execute the
ceph -s command from the first host(ceph100) but when I execute the
command in t
On Mon, Jun 15, 2020 at 7:01 PM wrote:
> Ceph version 10.2.7
>
> ceph.conf
> [global]
> fsid = 75d6dba9-2144-47b1-87ef-1fe21d3c58a8
>
(...)
> mount_activate: Failed to activate
> ceph-disk: Error: No cluster conf found in /etc/ceph with fsid
> e1d7b4ae-2dcd-40ee-bea5-d103fe1fa9c9
>
--
Paul
Ceph version 10.2.7
ceph.conf
[global]
fsid = 75d6dba9-2144-47b1-87ef-1fe21d3c58a8
mon_initial_members = chad, jesse, seth
mon_host = 192.168.10.41,192.168.10.40,192.168.10.39
mon warn on legacy crush tunables = false
auth_cluster_required = cephx
auth_service_required = cephx
auth_client_require
Also, if you are using a newer kernel, add rsize=16777216,wsize=16777216
(or smaller) if you don't want to run out or memory buffers after a few
mount/unmount cycles.
On 6/15/20 6:44 AM, Marc Roos wrote:
>
>
> Thanks for these I was missing the x-systemd. entries. I assume these
> are necessar
On Sun, 2020-06-14 at 15:17 +0200, Marc Roos wrote:
> When rsyncing to a nfs-ganesha exported cephfs the process hangs, and
> escalates into "cache pressure" of other cephfs clients[1].
>
> When testing the rsync with more debugging on, I noticed that rsync
> stalled at the 'set modtime of . '[2
On Mon, Jun 15, 2020 at 7:27 PM Giulio Fidente wrote:
>
> hi David, thanks for helping
>
> python3-Cython seems to be already in the centos8 PowerTools repo:
>
> http://mirror.centos.org/centos-8/8/PowerTools/x86_64/os/Packages/
>
> Is it possible we're not enabling all the additional/extra repos
On 14/06/2020 17:07, Khodayar Doustar wrote:
Now I want to add the other two nodes as monitor and rgw.
Can I just modify the ansible host file and re-run the site.yml?
Yes.
I've done some modification in Storage classes, I've added some OSD and
uploaded a lot of data up to now. Is it safe t
Hello all,
can the NFS ganesha rados recovery for multi headed active/active setup
work with NFS 3 or it requires NFS 4/4.1 specifics ?
Thanks for any help /Maged
___
ceph-users mailing list -- ceph-users@ceph.io
To unsubscribe send an email to cep
hi David, thanks for helping
python3-Cython seems to be already in the centos8 PowerTools repo:
http://mirror.centos.org/centos-8/8/PowerTools/x86_64/os/Packages/
Is it possible we're not enabling all the additional/extra repos when
launching the build?
On 6/11/20 8:09 PM, David Galloway wrote:
The systemd autofs will mount cephfs successfully, with both kernel and
fuse clients.
Marc Roos 于2020年6月15日周一 下午6:44写道：
>
>
> Thanks for these I was missing the x-systemd. entries. I assume these
> are necessary so booting does not 'hang' on trying to mount these? I
> thought the _netdev was for
Thanks for these I was missing the x-systemd. entries. I assume these
are necessary so booting does not 'hang' on trying to mount these? I
thought the _netdev was for this and sufficient?
-Original Message-
To: Derrick Lin
Cc: ceph-users
Subject: [ceph-users] Re: mount cephfs with
Yes, it's faster but I'd like to continue managing the cluster with
Ansible, is that possible?
On Mon, Jun 15, 2020 at 12:02 PM Marc Roos wrote:
>
> Just do manual install that is faster.
>
>
>
> -Original Message-
> To: ceph-users
> Subject: [ceph-users] Fwd: Re-run ansible to add moni
Just do manual install that is faster.
-Original Message-
To: ceph-users
Subject: [ceph-users] Fwd: Re-run ansible to add monitor and RGWs
Any ideas on this?
-- Forwarded message -
From: Khodayar Doustar
Date: Sun, Jun 14, 2020 at 6:07 PM
Subject: Re-run ansible to a
Any ideas on this?
-- Forwarded message -
From: Khodayar Doustar
Date: Sun, Jun 14, 2020 at 6:07 PM
Subject: Re-run ansible to add monitor and RGWs
To: ceph-users
Hi,
I've installed my ceph cluster with ceph-ansible a few months ago. I've
just added one monitor and one rgw at
Just to add that a dump of that live config does indeed not show the v1 port.
So it seems to be ignoring the config. I tried the alternative mon host
syntaxes without success.
root@aio1 ~ # ceph mon dump
dumped monmap epoch 2
epoch 2
fsid bb204a5c-957d-4a06-a372-redacted
last_changed 2020-06-09T
Hi,
I have a lab single node cluster with octopus installed via ceph-ansible.
Both v1 and v2 were enabled in ceph-ansible vars with the correct suffixes.
The configuration was generated correctly and both ports were included in
the mon array.
[global]
cluster network = 172.16.6.0/24
fsid = bb204
Can these also be set with 'ceph tell'
No, those options can't be injected, you have to restart the OSDs.
Zitat von Marc Roos :
Can these also be set with 'ceph tell'
-Original Message-
From: Andrej Filipcic [mailto:andrej.filip...@ijs.si]
Sent: woensdag 10 juni 2020 12:22
To: ceph
I have encountered an issue on clients hanging on by opening a file.
Besides, any other client
who visited the same file or directory hung as well. The only way to
resolve it is rebooting the
clients server. This happened on kernel client only, Luminous version.
After that I chose fuse client excep
Hi,
With CentOS 7.8 you can use the systemd autofs options in /etc/fstab.
Here are two examples from our clusters, first with fuse and second
with kernel:
none /cephfs fuse.ceph
ceph.id=admin,ceph.conf=/etc/ceph/dwight.conf,ceph.client_mountpoint=/,x-systemd.device-timeout=30,x-systemd.mount-time
We're using autofs with CephFS since a couple of years now, what
exactly doesn't work, can you share more details?
Zitat von Derrick Lin :
Hi guys,
I can mount my cephfs via mount command and access it without any problem.
Now I want to integrate it in autofs which is used on our cluster.
Hi guys,
I tried to mount via kernel driver, it works beautifully. I was surprised,
below is one of the FIO test, which wasn't able to run at all in FUSE mount:
# /usr/bin/fio --randrepeat=1 --ioengine=libaio --direct=1
--gtod_reduce=1 --name=FIO --filename=fio.test --bs=4M --iodepth=16
--size=50
Hi guys,
I can mount my cephfs via mount command and access it without any problem.
Now I want to integrate it in autofs which is used on our cluster.
It seems this is not a popular approach and I found only this link:
https://drupal.star.bnl.gov/STAR/blog/mpoat/how-mount-cephfs
I followed the
In our test based v15.2.2, i found osd_numa_prefer_iface/osd_numa_auto_affinity
make onlye half cpu used. for 4K RW, it make performance drop much. So you can
check this whether occur.
___
ceph-users mailing list -- ceph-users@ceph.io
To unsubscribe sen
Hi,
although I've read many threads mentioning these two osd config
options I didn't know what to expect of it. But since you explicitly
referred the slow requests I decided to give it a try and changed 'osd
op queue cut off' to "high" ('osd op queue' was already "wpq"). We've
had two dee
28 matches
Mail list logo
