Hi Tony,
On 4/26/22 05:13, Tony Liu wrote:
> I understand that, for rbd mirror to work, the rbd mirror service
requires the
> connectivity to all nodes from both cluster.
>
> In my case, for security purpose, the "public" network is actually a
private network,
> which is not routable to external.
Thanks for your input, Casey! Your response seems to align with my mental model.
It makes sense that choosing the number of bucket index shards
involves a tradeoff between write parallelism and bucket listing
performance. Your point about the relevancy of the number of PGs is
also reasonable. If t
So,
I just checked the logs on one of our smaller cluster and it looks like
this error happened twice last week.
The cluster contains 12x8TB OSDs without any SSDs as cache. And it started
with octopus (so no upgrade from nautilus was performed)
root@3cecef08a104:~# zgrep -i marked /var/log/ceph/c
So,
I just checked the logs on one of our smaller cluster and it looks like
this error happened twice last week.
The cluster contains 12x8TB OSDs without any SSDs as cache. And it started
with octopus (so no upgrade from nautilus was performed)
root@3cecef08a104:~# zgrep -i marked /var/log/ceph/c
Hi,
After some load HDD's will be not perform well. You should move block.db's to
NVMe for avoid database vacuuming problems
k
Sent from my iPhone
> On 26 Apr 2022, at 13:58, Boris Behrens wrote:
>
> The cluster contains 12x8TB OSDs without any SSDs as cache
_
Hi Luis,
Was the osd spec responsible for creating this osd set to unmanaged? Having
it re-pickup available disks is the expected behavior right now (see
https://docs.ceph.com/en/latest/cephadm/services/osd/#declarative-state)
although we've been considering changing this as it seems like in the
m
I have this problem also with OSDs that are with SSDs as block.db.
>
> Am 26.04.2022 um 17:10 schrieb Konstantin Shalygin :
>
> Hi,
>
> After some load HDD's will be not perform well. You should move block.db's to
> NVMe for avoid database vacuuming problems
>
> k
> Sent from my iPhone
>
>
Le lundi 11 avril 2022, 10:26:31 CEST Gilles Mocellin a écrit :
> Just a follow-up.
>
> I've found that a specific network interface is causing this.
> We have bonds :
> - 1 management bond0
> - 1 storage access on bond1
> - 1 storage replication on bond2
>
> As the crc errors are all between cl
Le lundi 25 avril 2022, 17:46:04 CEST Chris Page a ?crit :
> Hi,
>
> Every now and then I am getting the following logs -
>
> pve01 2022-04-25T16:41:03.109+0100 7ff35b6da700 0 bad crc in data
> 3860390385 != exp 919468086 from v1:10.0.0.111:0/873787122
> pve01 2022-04-25T16:41:04.361+0100 7fb0e2
> Was the osd spec responsible for creating this osd set to unmanaged? Having
> it re-pickup available disks is the expected behavior right now (see
> https://docs.ceph.com/en/latest/cephadm/services/osd/#declarative-state)
> although we've been considering changing this as it seems like in the
Hi,
We currently remove drives without --zap if we do not want them to be
automatically re-added. After full removal from the cluster or on addition
of new drives we set `ceph orch pause` to do be able to work on the drives
without ceph interfering. To add the drives we resume the background
orche
I agree that it would be better if it was less sensitive to unrelated
backfill. I've noticed this recently too, especially if you're purging
multiple osds (like a whole host). The first one succeeds but the next
one fails even though I have no rebalance set and the osd was already
out.
I guess if m
Hey guys and girls,
Can you recommend some books to get started with ceph? I know the docs are
probably a good source, but books, in my experience, do a better job of
glueing it all together and painting the big picture. And I can take a book
to places where reading docs on a laptop is inconvenien
On 4/27/22 3:40 AM, Vladimir Brik wrote:
I am attaching MDS log with debug set to 25 of a time period (few
seconds' worth) during which a dd command got stuck (it never got
unstuck) and resulted in an empty file. I am guessing it was able to
create the file but was blocked from writing to it.
Just for memo record, what is your network card and driver?
ethtool -i eth0
Thanks,
k
Sent from my iPhone
> On 26 Apr 2022, at 20:02, Gilles Mocellin
> wrote:
>
> Just to end that thread :
> I have changed the network card, and no more errors in Ceph logs since days.
>
> It's really bad if
15 matches
Mail list logo
