[ceph-users] Speed limit on RadosGW?

2013-09-25 Thread Chu Duc Minh
I have a CEPH cluster with 9 nodes (6 data nodes & 3 mon/mds nodes) And i setup 4 separate nodes to test performance of Rados-GW: - 2 node run Rados-GW - 2 node run multi-process put file to [multi] Rados-GW Result: a) When i use 1 RadosGW node & 1 upload-node, speed upload = 50MB/s /upload-node

[ceph-users] Ceph deployment issue in physical hosts

2013-09-25 Thread Guang
Hi ceph-users, I deployed a cluster successfully in VMs, and today I tried to deploy a cluster in physical nodes. However, I came across a problem when I started creating a monitor. -bash-4.1$ ceph-deploy mon create x [ceph_deploy.mon][DEBUG ] Deploying mon, cluster ceph hosts [ceph

[ceph-users] radosgw-admin users list?

2013-09-25 Thread Valery Tschopp
Hi guys, How do I get a list of all users with the radosgw-admin command and/or REST API? # radosgw-admin --version ceph version 0.61.8 (a6fdcca3bddbc9f177e4e2bf0d9cdd85006b028b) Cheers, Valery -- SWITCH -- Valery Tschopp, Software Engineer, Peta Solutions Werdstrasse

Re: [ceph-users] Ceph deployment issue in physical hosts

2013-09-25 Thread Wolfgang Hennerbichler
On 09/25/2013 10:03 AM, Guang wrote: > Hi ceph-users, > I deployed a cluster successfully in VMs, and today I tried to deploy a > cluster in physical nodes. However, I came across a problem when I started > creating a monitor. > > -bash-4.1$ ceph-deploy mon create x > ssh: Could not r

Re: [ceph-users] Using RBD with LVM

2013-09-25 Thread John-Paul Robinson
Thanks. This fixed the problem. BTW, after adding this line I still got the same error on my pvcreate but then I ran pvcreate -vvv and found that it was ignorning my /dev/rbd1 device because it had detected a partition signature (which I had added in an earlier attempt to work around this "ignore

Re: [ceph-users] Using RBD with LVM

2013-09-25 Thread John-Paul Robinson
Thanks. After fixing the issue with the types entry in lvm.conf, I discovered the -vvv option which helped me detect a the second cause for the "ignored" error: pvcreate saw a partition signature and skipped the device. The -vvv is s good flag. :) ~jpr On 09/25/2013 01:52 AM, Wido den Hollander

Re: [ceph-users] Ceph deployment issue in physical hosts

2013-09-25 Thread Guang
Thanks Wolfgang. -bash-4.1$ ping web2 PING web2 (10.193.244.209) 56(84) bytes of data. 64 bytes from web2 (10.193.244.209): icmp_seq=1 ttl=64 time=0.505 ms 64 bytes from web2 (10.193.244.209): icmp_seq=2 ttl=64 time=0.194 ms ... [I omit part of the host name]. It can ping to the host and I actua

[ceph-users] Could radosgw disable S3 authentication?

2013-09-25 Thread david zhang
Hi ceph-users, I see RADOS Gateway (RGW) can be either authenticated or unauthenticated from http://ceph.com/docs/master/radosgw/s3/authentication/. But there is no details about how to disable it. So is there any way to do it? Thanks for sharing. -- Regards, Zhi ___

Re: [ceph-users] Speed limit on RadosGW?

2013-09-25 Thread Mark Nelson
On 09/25/2013 02:49 AM, Chu Duc Minh wrote: I have a CEPH cluster with 9 nodes (6 data nodes & 3 mon/mds nodes) And i setup 4 separate nodes to test performance of Rados-GW: - 2 node run Rados-GW - 2 node run multi-process put file to [multi] Rados-GW Result: a) When i use 1 RadosGW node & 1

Re: [ceph-users] Ceph deployment issue in physical hosts

2013-09-25 Thread Alfredo Deza
On Wed, Sep 25, 2013 at 5:08 AM, Guang wrote: > Thanks Wolfgang. > > -bash-4.1$ ping web2 > PING web2 (10.193.244.209) 56(84) bytes of data. > 64 bytes from web2 (10.193.244.209): icmp_seq=1 ttl=64 time=0.505 ms > 64 bytes from web2 (10.193.244.209): icmp_seq=2 ttl=64 time=0.194 ms > ... > > [I om

Re: [ceph-users] Ceph deployment issue in physical hosts

2013-09-25 Thread Guang
Thanks for the reply! I don't know the reason, but I work-around this issue by add a new entry in the /etc/hosts with something like 'web2 {id_address_of_web2}' and it can work. I am not sure if that is due to some mis-config by my end of the deployment script, will further investigate. Than

[ceph-users] Question regarding plugin class

2013-09-25 Thread Chen, Ching-Cheng (KFRM 1)
Hi: I have question regarding using the class plugin API. We finally able to make a test plugin class worked. We was able to invoke the exec() call and execute our test plugin class successfully. However, we have a hard time trying to figure out what object this plugin class been ran on OSD.

Re: [ceph-users] Ceph deployment issue in physical hosts

2013-09-25 Thread Alfredo Deza
On Wed, Sep 25, 2013 at 9:31 AM, Guang wrote: > Thanks for the reply! > > I don't know the reason, but I work-around this issue by add a new entry in > the /etc/hosts with something like 'web2 {id_address_of_web2}' and it can > work. > > I am not sure if that is due to some mis-config by my en

Re: [ceph-users] Question regarding plugin class

2013-09-25 Thread Gregory Farnum
On Wed, Sep 25, 2013 at 6:40 AM, Chen, Ching-Cheng (KFRM 1) wrote: > Hi: > > > > I have question regarding using the class plugin API. > > > > We finally able to make a test plugin class worked. We was able to invoke > the exec() call and execute our test plugin class successfully. > > > > Howev

[ceph-users] failure starting radosgw after setting up object storage

2013-09-25 Thread Gruher, Joseph R
Hi all- I am following the object storage quick start guide. I have a cluster with two OSDs and have followed the steps on both. Both are failing to start radosgw but each in a different manner. All the previous steps in the quick start guide appeared to complete successfully. Any tips on h

[ceph-users] RBD on CentOS 6

2013-09-25 Thread John-Paul Robinson
Hi, We've been working with Ceph 0.56 on Ubuntu 12.04 and are able to create, map, and mount ceph block devices via the RBD kernel module. We have a CentOS6.4 box one which we would like to do the same. http://ceph.com/docs/next/install/os-recommendations/ OS recommedations state that we should

Re: [ceph-users] Ceph write performance and my Dell R515's

2013-09-25 Thread Quenten Grasso
G'day Mark, I stumbled across an older thread it looks like you were involved with the centos and poor seq write performance on the R515's. Were you using centos or Ubuntu on your server at the time? (I'm wondering if this could be related to Ubuntu) http://marc.info/?t=13481911702&r=1&w=2

Re: [ceph-users] Ceph write performance and my Dell R515's

2013-09-25 Thread Mark Nelson
On 09/25/2013 06:46 PM, Quenten Grasso wrote: G'day Mark, I stumbled across an older thread it looks like you were involved with the centos and poor seq write performance on the R515's. Were you using centos or Ubuntu on your server at the time? (I'm wondering if this could be related to Ubun

[ceph-users] CephFS multi-tenancy and OpenStack Manila

2013-09-25 Thread Blair Bethwaite
Hi there, Now that there is fledgling shared filesystem project starting up for OpenStack (see: https://launchpad.net/manila) I'm wondering whether there has been any progress towards full multi-tenancy for CephFS, i.e., the ability for clients to mount their own CephFS (complete with separate met

Re: [ceph-users] CephFS multi-tenancy and OpenStack Manila

2013-09-25 Thread Sage Weil
On Thu, 26 Sep 2013, Blair Bethwaite wrote: > Hi there, > Now that there is fledgling shared filesystem project starting up for > OpenStack (see: https://launchpad.net/manila) I'm wondering whether there > has been any progress towards full multi-tenancy for CephFS, i.e., the > ability for clients

[ceph-users] CephFS Pool Specification?

2013-09-25 Thread Aaron Ten Clay
Hi all, Does anyone know how to specify which pool the mds and CephFS data will be stored in? After creating a new cluster, the pools "data", "metadata", and "rbd" all exist but with pg count too small to be useful. The documentation indicates the pg count can be set only at pool creation time, s

Re: [ceph-users] CephFS Pool Specification?

2013-09-25 Thread Yan, Zheng
On Thu, Sep 26, 2013 at 9:57 AM, Aaron Ten Clay wrote: > Hi all, > > Does anyone know how to specify which pool the mds and CephFS data will be > stored in? > > After creating a new cluster, the pools "data", "metadata", and "rbd" all > exist but with pg count too small to be useful. The documenta

Re: [ceph-users] Could radosgw disable S3 authentication?

2013-09-25 Thread david zhang
Hi ceph-users, Could some one give some suggestions? Anything will be appreciated. Thanks! On Wed, Sep 25, 2013 at 8:06 PM, david zhang wrote: > Hi ceph-users, > > I see RADOS Gateway (RGW) can be either authenticated or unauthenticated > from > http://ceph.com/docs/master/radosgw/s3/authentica

Re: [ceph-users] CephFS Pool Specification?

2013-09-25 Thread Sage Weil
On Wed, 25 Sep 2013, Aaron Ten Clay wrote: > Hi all, > > Does anyone know how to specify which pool the mds and CephFS data will be > stored in? > > After creating a new cluster, the pools "data", "metadata", and "rbd" all > exist but with pg count too small to be useful. The documentation indica