thx Paul - I suspect these shadow trees causing this misbehaviour.
I have a second luminous cluster where these balancer settings work as expected
- this working one has hdd+ssd osds
i cannot use the upmap balancer because of some jewel-krbd clients - at least
they are being reported as jewel c
Hi!
In our cluster I ran some benchmarks.
The results are always similar but strange to me.
I don't know what the results mean.
The cluster consists of 7 (nearly) identical hosts for osds. Two of them have
one an additional hdd.
The hdds are from identical type. The ssds for the journal and wal a
Hi friends
i have installed ceph mimic with zabbix 3.0. i configured everything to
monitor my cluster with zabbix and i could get data from zabbix frontend.
but in ceph -s command it says Failed to send data to Zabbix.
why this happen?
my ceph version :ceph version 13.2.6
(7b695f835b03642f85998b2a
Have you configured any encryption on your Zabbix infrastructure? We took
a brief look at ceph+Zabbix a while ago, and the exporter didn't have the
capability to use encryption. I don't know if it's changed in the
meantime though.
On Thu, 27 Jun 2019 at 09:43, Majid Varzideh wrote:
> Hi frie
Hi Team,
We have a requirement to create multiple copies of an object and currently
we are handling it in client side to write as separate objects and this
causes huge network traffic between client and cluster.
Is there possibility of cloning an object to multiple copies using librados
api?
Pleas
Hi folks,
I have a nautilus 14.2.1 cluster with a non-default cluster name (ceph_stag
instead of ceph). I set “cluster = ceph_stag” in /etc/ceph/ceph_stag.conf.
ceph-volume is using the correct config file but does not use the specified
clustername. Did I hit a bug or do I need to define the cl
Although ceph-volume does a best-effort to support custom cluster
names, the Ceph project does not support custom cluster names anymore
even though you can still see settings/options that will allow you to
set it.
For reference see: https://bugzilla.redhat.com/show_bug.cgi?id=1459861
On Thu, Jun
Hello community,
we have developed a cluster on latest mimic release. We are on quite old
hardware, but using Centos7. Monitor, manager and all the same host.
Cluster has been running for some week without actual workload. There
might have been some sort of power failure (not proved), but at s
Well that caused some excitement (either that or the small power
disruption did)! One of my OSDs is now down because it keeps crashing
due to a failed assert (stacktraces attached, also I'm apparently
running mimic, not luminous).
In the past a failed assert on an OSD has meant removing the disk,
All;
I built a demonstration and testing cluster, just 3 hosts (10.0.200.110, 111,
112). Each host runs mon, mgr, osd, mds.
During the demonstration yesterday, I pulled the power on one of the hosts.
After bringing the host back up, I'm getting several error messages every
second or so:
2019-
Are these dual-socket machines? Perhaps NUMA is involved?
On Thu., Jun. 27, 2019, 4:56 a.m. Lars Täuber, wrote:
> Hi!
>
> In our cluster I ran some benchmarks.
> The results are always similar but strange to me.
> I don't know what the results mean.
> The cluster consists of 7 (nearly) identical
Hi,
some more information about the cluster status would be helpful, such as
ceph -s
ceph osd tree
service status of all MONs, MDSs, MGRs.
Are all services up? Did you configure the spare MDS as standby for
rank 0 so that a failover can happen?
Regards,
Eugen
Zitat von dhils...@performair
On Thu, Jun 27, 2019 at 10:36 AM ☣Adam wrote:
> Well that caused some excitement (either that or the small power
> disruption did)! One of my OSDs is now down because it keeps crashing
> due to a failed assert (stacktraces attached, also I'm apparently
> running mimic, not luminous).
>
> In the
Eugen;
All services are running, yes, though they didn't all start when I brought the
host up (configured not to start because the last thing I had done is
physically relocate the entire cluster).
All services are running, and happy.
# ceph status
cluster:
id: 1a8a1693-fa54-4cb3-89d2
@David Turner
Did your bucket delete ever finish? I am up to 35M incomplete uploads,
and I doubt that I actually had that many upload attempts. I could be
wrong though.
Is there a way to force bucket deletion, even at the cost of not
cleaning up space?
On Tue, Jun 25, 2019 at 12:29 PM J. Eric Ivan
I'm still going at 452M incomplete uploads. There are guides online for
manually deleting buckets kinda at the RADOS level that tend to leave data
stranded. That doesn't work for what I'm trying to do so I'll keep going
with this and wait for that PR to come through and hopefully help with
bucket d
What does it take for a monitor to consider an OSD down which has been dead as
a doornail since the cluster started?
A couple of times, I have seen 'ceph status' report an OSD was up, when it was
quite dead. Recently, a couple of OSDs were on machines that failed to boot
up after a power failure.
On 12/06/2019 22.33, Yan, Zheng wrote:
> I have tracked down the bug. thank you for reporting this. 'echo 2 >
> /proc/sys/vm/drop_cache' should fix the hang. If you can compile ceph
> from source, please try following patch.
I managed to get the packages built for Xenial properly and tested and
On Thu, Jun 27, 2019 at 8:58 PM nokia ceph wrote:
>
> Hi Team,
>
> We have a requirement to create multiple copies of an object and currently we
> are handling it in client side to write as separate objects and this causes
> huge network traffic between client and cluster.
> Is there possibility
Hi Nathan,
yes the osd hosts are dual-socket machines. But does this make such difference?
osd.0: bench: wrote 1 GiB in blocks of 4 MiB in 15.0133 sec at 68 MiB/sec 17
IOPS
osd.1: bench: wrote 1 GiB in blocks of 4 MiB in 6.98357 sec at 147 MiB/sec 36
IOPS
Doubling the IOPS?
Thanks,
Lars
Thu
20 matches
Mail list logo
