So I put a, nginx proxy in front of rgw since I couldn't find any definitive
answer on whether or not it allows OPTIONS. Now the browser is doing a POST,
and it's still getting a MethodNotAllowed response. This is a fresh install of
luminous. Is this an rgw error or a civetweb error? I found an
I'm trying to do direct-from-browser upload to rgw using pre-signed urls, and
I'm getting stuck because the browser is doing a pre-flight OPTIONS request and
rgw is giving me a MethodNotAllowed response.
Is this supported?
OPTIONS http://storage-test01:7480/ HTTP/1.1
Host: storage-test01:7480
C
On 13/02/2018 11:19 AM, Brad Hubbard wrote:
> On Tue, Feb 13, 2018 at 10:23 AM, Mike O'Connor wrote:
>> Hi All
>>
>> Where can I find the source packages that the Proxmox Ceph Luminous was
>> built from ?
> You can find any source packages we release on http://download.ceph.com/
>
> You'd have to
On Tue, Feb 13, 2018 at 10:23 AM, Mike O'Connor wrote:
> Hi All
>
> Where can I find the source packages that the Proxmox Ceph Luminous was
> built from ?
You can find any source packages we release on http://download.ceph.com/
You'd have to ask Proxmox which one they used and whether they modif
Hi,
For the past few weeks I've been seeing a large number of pgs on our
main erasure coded pool being flagged inconsistent, followed by them
becoming active+recovery_wait+inconsistent with unfound objects. The
cluster is currently running luminous 12.2.2 but has in the past also
run its way
Thanks Ilya,
We can probably handle ~6.2MB for a 100TB volume. Is it reasonable to
expect a librbd client such as QEMU to only hold one object-map per guest?
Cheers,
On 12 February 2018 at 21:01, Ilya Dryomov wrote:
> On Mon, Feb 12, 2018 at 6:25 AM, Blair Bethwaite
> wrote:
> > Hi all,
> >
>
Hi All
Where can I find the source packages that the Proxmox Ceph Luminous was
built from ?
Mike
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
why not use collectd? centos7 rpms should do fine.
On Feb 12, 2018 9:50 PM, Benjeman Meekhof wrote:
>
> In our case I think we grabbed the SRPM from Fedora and rebuilt it on
> Scientific Linux (another RHEL derivative). Presumably the binary
> didn't work or I would have installed it direct
Hi Janne and others,
We used the “ceph osd reweight-by-utilization “ command to move a small amount
of data off of the top four OSDs by utilization. Then we updated the pg_num
and pgp_num on the pool from 512 to 1024 which started moving roughly 50% of
the objects around as a result. The unfo
Hi friends,
I have rgw-user (_sc) with with the same access key:
radosgw-admin metadata user info --uid _sc
{
"user_id": "_sc",
"display_name": "_sc",
"email": "",
"suspended": 0,
"max_buckets": 0,
"auid": 0,
"subusers": [],
"keys": [
{
"user":
In our case I think we grabbed the SRPM from Fedora and rebuilt it on
Scientific Linux (another RHEL derivative). Presumably the binary
didn't work or I would have installed it directly. I'm not quite sure
why it hasn't migrated to EPEL yet.
I haven't tried the SRPM for latest releases, we're ac
If you look at the PGs that are primary on an OSD that has primary affinity
0, you'll find that they are only on OSDs with primary affinity of 0, so 1
of them has to take the reins or nobody would be responsible for the PG.
To prevent this from happening, you would need to configure your crush map
Why are you using force and lazy options to umount cephfs? Those should
only be done if there are problems unmounting the volume. Lazy umount will
indeed leave things running, but just quickly remove the FS from it's mount
point. You should rarely use umount -f and even more rarely use umount
-l
I do know that there is a pause flag in Ceph.
What I do not know is if that also pauses recovery traffic, in addition to
client traffic.
Also worth mentioning, this is a cluster-wide flag, not a pool level flag.
Reed
> On Feb 11, 2018, at 11:45 AM, David Turner wrote:
>
> If you set min_size
Hans van den Bogert writes:
> Hi Wido,
>
> Did you ever get an answer? I'm eager to know as well.
We're currently testing 12.2.3; once the QE process completes we can
publish the packages, hopefully by the end of this week
>
>
> Hans
>
> On Tue, Jan 30, 2018 at 10:35 AM, Wido den Hollander wrot
Dear all,
I'd like to store ceph luminous metrics into influxdb. It seems like influx plugin has been already
backported for lumious:
rpm -ql ceph-mgr-12.2.2-0.el7.x86_64|grep -i influx
/usr/lib64/ceph/mgr/influx
/usr/lib64/ceph/mgr/influx/__init__.py
/usr/lib64/ceph/mgr/influx/__init__.pyc
/us
Hi,
I'm looking into storing the primary copy on SSDs, and replicas on spinners.
One way to achieve this should be the primary affinity setting, as outlined in
this post:
https://www.sebastien-han.fr/blog/2015/08/06/ceph-get-the-best-of-your-ssd-with-primary-affinity
So I've deployed a small te
Hello,
Warning, this is a long story! There's a TL;DR; close to the end.
We are replacing some of our spinning drives with SSDs. We have 14 OSD
nodes with 12 drives each. We are replacing 4 drives from each node
with SSDs. The cluster is running Ceph Jewel (10.2.7). The affected pool
had min_size
On 02/12/2018 03:16 PM, Behnam Loghmani wrote:
so you mean that rocksdb and osdmap filled disk about 40G for only 800k
files?
I think it's not reasonable and it's too high
Could you check the output of the OSDs using a 'perf dump' on their
admin socket?
The 'bluestore' and 'bluefs' sectio
Hi Wido,
how do you know about that beforehand? There's no official upcoming
event on the ceph.com page?
Just because I'm curious :)
Thanks
Kai
On 12.02.2018 10:39, Wido den Hollander wrote:
> The next one is in London on April 19th
--
SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard,
The pause flag also pauses recovery traffic. It is literally a flag to
stop anything and everything in the cluster so you can get an expert in to
prevent something even worse from happening.
On Mon, Feb 12, 2018 at 1:56 PM Reed Dier wrote:
> I do know that there is a pause flag in Ceph.
>
> Wha
On Sun, Feb 11, 2018 at 8:19 PM Chris Apsey wrote:
> All,
>
> Recently doubled the number of OSDs in our cluster, and towards the end
> of the rebalancing, I noticed that recovery IO fell to nothing and that
> the ceph mons eventually looked like this when I ran ceph -s
>
>cluster:
>
Anyone?
Am 9. Februar 2018 09:59:54 MEZ schrieb Dietmar Rieder
:
>Hi,
>
>we are running ceph version 12.2.2 (10 nodes, 240 OSDs, 3 mon). While
>monitoring the WAL db used bytes we noticed that there are some OSDs
>that use proportionally more WAL db bytes than others (800Mb vs 300Mb).
>These OSDs
Hi Wido,
Did you ever get an answer? I'm eager to know as well.
Hans
On Tue, Jan 30, 2018 at 10:35 AM, Wido den Hollander wrote:
> Hi,
>
> Is there a ETA yet for 12.2.3? Looking at the tracker there aren't that many
> outstanding issues: http://tracker.ceph.com/projects/ceph/roadmap
>
> On Git
so you mean that rocksdb and osdmap filled disk about 40G for only 800k
files?
I think it's not reasonable and it's too high
On Mon, Feb 12, 2018 at 5:06 PM, David Turner wrote:
> Some of your overhead is the Wal and rocksdb that are on the OSDs. The Wal
> is pretty static in size, but rocksdb g
Some of your overhead is the Wal and rocksdb that are on the OSDs. The Wal
is pretty static in size, but rocksdb grows with the amount of objects you
have. You also have copies of the osdmap on each osd. There's just overhead
that adds up. The biggest is going to be rocksdb with how many objects yo
Hi there,
I am using ceph Luminous 12.2.2 with:
3 osds (each osd is 100G) - no WAL/DB separation.
3 mons
1 rgw
cluster size 3
I stored lots of thumbnails with very small size on ceph with radosgw.
Actual size of files is something about 32G but it filled 70G of each osd.
what's the reason of t
Hi!
I am trying out NFS-Ganesha-RGW (2.5.4 and also Git V2.5-stable) with
Ceph 12.2.2.
Mounting the RGW works fine, but if I try to archive all files, some
paths seem to "disappear":
...
tar: /store/testbucket/nhxYgfUgFivgzRxw: File removed before we read it
tar: /store/testbucket/nlkijFwq
On Mon, Feb 12, 2018 at 6:25 AM, Blair Bethwaite
wrote:
> Hi all,
>
> Wondering if anyone can clarify whether there are any significant overheads
> from rbd features like object-map, fast-diff, etc. I'm interested in both
> performance overheads from a latency and space perspective, e.g., can
> ob
Sometimes I'm just blind. Way to less ML :D
Thanks!
On 12.02.2018 10:51, Wido den Hollander wrote:
> Because I'm co-organizing it! :) It send out a Call for Papers last
> week to this list.
--
SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard, Graham Norton, HRB 21284
(AG Nürnberg)
s
On 02/12/2018 10:42 AM, Kai Wagner wrote:
Hi Wido,
how do you know about that beforehand? There's no official upcoming
event on the ceph.com page?
Because I'm co-organizing it! :) It send out a Call for Papers last week
to this list.
Waiting for the page to come online on ceph.com, but t
On 02/12/2018 12:33 AM, c...@elchaka.de wrote:
Am 9. Februar 2018 11:51:08 MEZ schrieb Lenz Grimmer :
Hi all,
On 02/08/2018 11:23 AM, Martin Emrich wrote:
I just want to thank all organizers and speakers for the awesome Ceph
Day at Darmstadt, Germany yesterday.
I learned of some cool stu
32 matches
Mail list logo
