Re-added ML.
On Mon, 28 Jul 2014 20:38:37 +1000 Matt Harlum wrote:
>
> On 27 Jul 2014, at 1:45 am, Christian Balzer wrote:
>
> > On Sat, 26 Jul 2014 20:49:46 +1000 Matt Harlum wrote:
> >
> >>
> >> On 25 Jul 2014, at 5:54 pm, Christian Balzer wrote:
> >>
> >>> On Fri, 25 Jul 2014 13:31:34
On Mon, 28 Jul 2014 18:11:33 -0400 Robert Fantini wrote:
> "target replication level of 3"
> " with a min of 1 across the node level"
>
> After reading http://ceph.com/docs/master/rados/configuration/ceph-conf/
> , I assume that to accomplish that then set these in ceph.conf ?
>
> osd pool
"target replication level of 3"
" with a min of 1 across the node level"
After reading http://ceph.com/docs/master/rados/configuration/ceph-conf/
, I assume that to accomplish that then set these in ceph.conf ?
osd pool default size = 3
osd pool default min size = 1
On Mon, Jul 28, 201
You can use multiple "steps" in your crush map in order to do things
like choose two different hosts then choose a further OSD on one of the
hosts and do another replication so that you can get three replicas onto
two hosts without risking ending up with three replicas on a single node.
On 28/
If you've two rooms then I'd go for two OSD nodes in each room, a target
replication level of 3 with a min of 1 across the node level, then have
5 monitors and put the last monitor outside of either room (The other
MON's can share with the OSD nodes if needed). Then you've got 'safe'
replicatio
Hey cephers,
Less than four days left to tweet a photo of "how you're celebrating
Ceph's 10th birthday" (be bold, be creative, be awesome) to @Ceph.
Include the hastag #cephturns10 and the best photo will win a desktop
Ceph cluster built by our own Mark Nelson.
https://wiki.ceph.com/Community/Con
> >> Running ' ceph osd reweight-by-utilization' clears the issue up
> >> temporarily, but additional data inevitably causes certain OSDs to be
> >> overloaded again.
> >>
> > The only time I've ever seen this kind of uneven distribution is when
> > using too little (and using the default formula w
Perhaps Cristian is thinking of the clone from journal work that we were
talking about last year:
http://wiki.ceph.com/Planning/Sideboard/osd%3A_clone_from_journal_on_btrfs
I think we never did much beyond Sage's test branch, and it didn't seem
to help as much as you would hope. Speaking of wh
On Mon, Jul 28, 2014 at 12:14 PM, Christian Balzer wrote:
> On Mon, 28 Jul 2014 14:24:02 + Edward Huyer wrote:
>
>> > > Ceph has a default pool size of 3. Is it a bad idea to run a pool of
>> > > size 2? What about size 2 min_size 1?
>> > >
>> > min_size 1 is sensible, 2 obviously won't protec
OK for higher availability then 5 nodes is better then 3 . So we'll run 5
. However we want normal operations with just 2 nodes. Is that possible?
Eventually 2 nodes will be next building 10 feet away , with a brick wall
in between. Connected with Infiniband or better. So one room can go off
It still helps; the journal does just as much work. Less of the work
*can* be in the critical path for IO, but for most of the applications
it will be.
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Sat, Jul 26, 2014 at 2:18 AM, Cristian Falcas
wrote:
> Hello,
>
> I'm usin
On 07/28/2014 11:28 AM, Steve Anthony wrote:
While searching for more information I happened across the following
post (http://dachary.org/?p=2961) which vaguely resembled the symptoms
I've been experiencing. I ran tcpdump and noticed what appeared to be a
high number of retransmissions on the ho
That's expected. You need > 50% of the monitors up. If you only have 2
machines, rebooting one means that 50% are up, so the cluster halts
operations. That's done on purpose to avoid problems when the cluster is
divided in exactly half, and both halves continue to run thinking the other
half is
(Sorry for the duplicate email, I forgot to CC the list)
Assuming you're using the default setup (RadosGW, FastCGI, and Apache),
it's the same as monitoring a web site. On every node, verify that request
for / returns a 200. If the RadosGW agent is down, or FastCGI is
mis-configured, the request
Hi,
Currently I am evalutating multiple distributed storage solutions with an
S3-like interface.
We have two huge machines with big amounts of storage. Is it possible to
let these two behave exactly the same with Ceph? My idea is runninng both
MON and OSD on these two machines.
With quick tests t
On Mon, 28 Jul 2014, James Eckersall wrote:
> Hi,
> I'm trying to understand what a lot of the values mean that are reported by
> "perf dump" on the ceph admin socket. I have a collectd plugin which sends
> all of these values to graphite.
>
> Does anyone have a cross-reference list that explains
Simon Ironside writes:
>
> Hi Brian,
>
> I have a fresh install working on RHEL 7 running the same version of
> python as you. I did have trouble installing from the ceph.com yum repos
> though and worked around it by creating and installing from my own local
> yum repos instead.
>
> I then
While searching for more information I happened across the following
post (http://dachary.org/?p=2961) which vaguely resembled the symptoms
I've been experiencing. I ran tcpdump and noticed what appeared to be a
high number of retransmissions on the host where the images are mounted
during a read f
Hi,
I'm trying to understand what a lot of the values mean that are reported by
"perf dump" on the ceph admin socket. I have a collectd plugin which sends
all of these values to graphite.
Does anyone have a cross-reference list that explains what they are in more
detail? You can glean so much f
On Mon, 28 Jul 2014 11:22:38 +0100 Joao Eduardo Luis wrote:
> On 07/28/2014 08:49 AM, Christian Balzer wrote:
> >
> > Hello,
> >
> > On Sun, 27 Jul 2014 18:20:43 -0400 Robert Fantini wrote:
> >
> >> Hello Christian,
> >>
> >> Let me supply more info and answer some questions.
> >>
> >> * Our main
Hi Brian,
I have a fresh install working on RHEL 7 running the same version of
python as you. I did have trouble installing from the ceph.com yum repos
though and worked around it by creating and installing from my own local
yum repos instead.
I then skip the ceph-deploy install step, as I'v
On Mon, 28 Jul 2014 14:24:02 + Edward Huyer wrote:
> > > Ceph has a default pool size of 3. Is it a bad idea to run a pool of
> > > size 2? What about size 2 min_size 1?
> > >
> > min_size 1 is sensible, 2 obviously won't protect you against dual
> > disk failures. Which happen and happen with
See the anti-cephalopod thread on this ML.
On Mon, 28 Jul 2014 12:23:02 +0200 Josef Johansson wrote:
> Hi,
>
> I'm trying to compile a strategy to avoid performance problems if osds
> or osd hosts fails.
>
> If I encounter a re-balance of one OSD during mid-day, there'll be
> problems with per
I'm installing the latest firefly on a fresh centos 7 machine using the rhel
7 yum repo. I'm getting a few dependency issues when using ceph-deploy
install. Mostly it looks like it doesn't like python 2.7.
[monitor01][DEBUG ] --> Processing Dependency: libboost_system-mt.so.5()
(64bit) for pack
On Mon, 28 Jul 2014, Joao Eduardo Luis wrote:
> On 07/28/2014 02:07 PM, Robert Fantini wrote:
> > Is the '15 minutes or so ' something that can be configured at run time?
>
> Someone who knows this better than I do should probably chime in, but from a
> quick look throughout the code it seems to
> > Ceph has a default pool size of 3. Is it a bad idea to run a pool of
> > size 2? What about size 2 min_size 1?
> >
> min_size 1 is sensible, 2 obviously won't protect you against dual disk
> failures.
> Which happen and happen with near certainty once your cluster gets big
> enough.
I though
On 07/28/2014 02:07 PM, Robert Fantini wrote:
Is the '15 minutes or so ' something that can be configured at run time?
Someone who knows this better than I do should probably chime in, but
from a quick look throughout the code it seems to be
'client_mount_interval', which by default is 300 s
Is the '15 minutes or so ' something that can be configured at run time?
On Mon, Jul 28, 2014 at 8:44 AM, Joao Eduardo Luis
wrote:
> (CC'ing ceph-users)
>
> On 07/28/2014 12:34 PM, Marc wrote:
>
>> Hi,
>>
>>
>> This said, if out of 3 monitors you have 2 monitors down, your cluster
>>> will ce
(CC'ing ceph-users)
On 07/28/2014 12:34 PM, Marc wrote:
Hi,
This said, if out of 3 monitors you have 2 monitors down, your cluster
will cease functioning (no admin commands, no writes or reads served).
This is not entirely true. (At least) RBDs will continue being fully
functional even if th
Hi,
I'm trying to compile a strategy to avoid performance problems if osds
or osd hosts fails.
If I encounter a re-balance of one OSD during mid-day, there'll be
problems with performance right now, if I could see the issue and let it
re-balance during evening, that would be great.
I.e. if two O
On 07/28/2014 08:49 AM, Christian Balzer wrote:
Hello,
On Sun, 27 Jul 2014 18:20:43 -0400 Robert Fantini wrote:
Hello Christian,
Let me supply more info and answer some questions.
* Our main concern is high availability, not speed.
Our storage requirements are not huge.
However we want good
Hi Karan,
Once you are able to put objects using RadosGW created user name and
password 90% of the job is done. We have to follow only these steps
afterwards:
1. Put the configurations specified in
http://ceph.com/docs/master/radosgw/keystone/
2. Make sure you create object-service and endpoint i
It's fixed now. Apparently we can not share a journal across different
OSDs. I added a journal /dev/sdc1 (20GB) with my first OSD. I was trying
to add the same journal with my second OSD and it was causing the issue.
Then I added the secons OSD with a new journal and it worked fine.
Thanks,
Kapil
Hi Cephers,
I have configured Ceph RadosGW for Swift. I have also set authentication
using keystone. Using Swift CLI I can do all stuff viz. uploading
container, object, listing. But while using Dashboard I am able to do all
the stuff apart from uploading an object.
While uploading an object I am
the osd's were created using proxmox web page .
there is not data that I want to save..
so I'd like to start from scratch but not do a reinstall of the operating
system.
I'll check the documentation that you mentioned.
On Mon, Jul 28, 2014 at 4:38 AM, Christian Balzer wrote:
>
> On Mon, 28 J
On Mon, 28 Jul 2014 04:19:16 -0400 Robert Fantini wrote:
> I have 3 hosts that i want to use to test new setup...
>
> Currently they have 3-4 OSD's each.
>
How did you create the current cluster?
ceph-deploy or something withing Proxmox?
> Could you suggest a fast way to remove all the OSD's
On 07/25/2014 04:54 AM, Deven Phillips wrote:
Hi all,
I am in the process of installing and setting up Ceph on a group of
Allwinner A20 SoC mini computers. They are armhf devices and I have
installed Cubian (http://cubian.org/), which is a port of Debian Wheezy.
I tried to follow the instru
I have 3 hosts that i want to use to test new setup...
Currently they have 3-4 OSD's each.
Could you suggest a fast way to remove all the OSD's ?
On Mon, Jul 28, 2014 at 3:49 AM, Christian Balzer wrote:
>
> Hello,
>
> On Sun, 27 Jul 2014 18:20:43 -0400 Robert Fantini wrote:
>
> > Hello Chri
Hello,
On Sun, 27 Jul 2014 18:20:43 -0400 Robert Fantini wrote:
> Hello Christian,
>
> Let me supply more info and answer some questions.
>
> * Our main concern is high availability, not speed.
> Our storage requirements are not huge.
> However we want good keyboard response 99.99% of the time
Hi Karan,
So that means I can't have RBD on 2.6.32. Do you know where can I find
source for rbd.ko for other kernel versions like 2.6.34?
Regards,
Pratik Rupala
On 7/28/2014 12:32 PM, Karan Singh wrote:
Yes you can use other features like CephFS and Object Store on this
kernel release that y
Looks like osd.1 has a valid auth ID , which was defined previously.
Trust this is your test cluster , try this
ceph osd crush rm osd.1
ceph osd rm osd.1
ceph auth del osd.1
Once again try to add osd.1 using ceph-deploy ( prepare and then activate
commands ) , check the logs carefully for any
The output that you have provided says that OSDs are not IN , Try the below
ceph osd in osd.0
ceph osd in osd.1
service ceph start osd.0
service ceph start osd.1
If you have 1 more host with 1 disk , add it , starting Ceph Firefly default
rep size is 3
- Karan -
On 27 Jul 2014, at 11:17, 10
Yes you can use other features like CephFS and Object Store on this kernel
release that you are running.
- Karan Singh
On 28 Jul 2014, at 07:45, Pratik Rupala wrote:
> Hi Karan,
>
> I have basic setup of Ceph storage cluster in active+clean state on Linux
> kernel 2.6.32. As per your sugge
43 matches
Mail list logo
