Re: Ho to identify location of Primary Copy Of Obj ?

2012-09-26 Thread hemant surale
Hi Dan , I have set replication factor to 3 of pool 'newbyh' . Then when i tried to execute cmds told by you I got that it reported like root@third-virtual-machine:~# osdmaptool --test-map-object Obj1 osdmap osdmaptool: osdmap file

Re: Ho to identify location of Primary Copy Of Obj ?

2012-09-26 Thread hemant surale
Hi Sage, Dan , When I tried to execute cmd osdmaptool --test-map-object anyrandomname osdmap it still shows some random number as mapped osds. Because I havnt created Object even for that result is shown as some random numbers/ as osds where that Object is mapped. And with

Slow ceph fs performance

2012-09-26 Thread Bryan K. Wright
Hi folks, I'm seeing reasonable performance when I run rados benchmarks, but really slow I/O when reading or writing from a mounted ceph filesystem. The rados benchmarks show about 150 MB/s for both read and write, but when I go to a client machine with a mounted ceph filesystem and try

Re: Ho to identify location of Primary Copy Of Obj ?

2012-09-26 Thread Sage Weil
On Wed, 26 Sep 2012, hemant surale wrote: Hi Dan , I have set replication factor to 3 of pool 'newbyh' . Then when i tried to execute cmds told by you I got that it reported like root@third-virtual-machine:~# osdmaptool

Re: Slow ceph fs performance

2012-09-26 Thread Mark Nelson
On 09/26/2012 09:50 AM, Bryan K. Wright wrote: Hi folks, Hi Bryan! I'm seeing reasonable performance when I run rados benchmarks, but really slow I/O when reading or writing from a mounted ceph filesystem. The rados benchmarks show about 150 MB/s for both read and write, but when I

Re: Hardware Requirements for RADOS Gateway Cluster

2012-09-26 Thread Tommi Virtanen
On Mon, Sep 24, 2012 at 3:58 PM, Brice Burgess briceb...@gmail.com wrote: 1. Is it preferable to run the RADOS Gateway on a MDS machine [for latency ... My assumption is to provision a dedicated machine for the RADOS Gateway. I'd treat this machine as a front end proxy/caching server meaning it

Re: Slow ceph fs performance

2012-09-26 Thread Bryan K. Wright
Hi Mark, Thanks for your help. Some answers to your questions are below. mark.nel...@inktank.com said: On 09/26/2012 09:50 AM, Bryan K. Wright wrote: Hi folks, Hi Bryan! I'm seeing reasonable performance when I run rados benchmarks, but really slow I/O when reading or

Re: Ho to identify location of Primary Copy Of Obj ?

2012-09-26 Thread Dan Mick
Ah, yeah, that assumption would be a problem. So, Hemant, does ceph osd dump poolname objectname show you information that makes sense? On 09/26/2012 08:21 AM, Sage Weil wrote: On Wed, 26 Sep 2012, hemant surale wrote: Hi Dan , I have set replication factor to 3 of pool

Max Message Size For AIO calls

2012-09-26 Thread Ian Pye
Hi, I'm periodically getting librados aio_operate() calls to fail on me and return a code of -90: Message too long. Does anyone know how long is too long of a message here? Thanks, Ian -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to

Re: Max Message Size For AIO calls

2012-09-26 Thread Noah Watkins
Looks like this here is the relevant config option: osd_max_write_size which has a default value of 90 megabytes (adjusted below with the 20) in my tree In osd/OSD.cc: // too big? if (g_conf-osd_max_write_size m-get_data_len() g_conf-osd_max_write_size 20) { //

Re: Ho to identify location of Primary Copy Of Obj ?

2012-09-26 Thread Sage Weil
On Wed, 26 Sep 2012, Dan Mick wrote: Ah, yeah, that assumption would be a problem. So, Hemant, does ceph osd dump poolname objectname Ahem, ceph osd map poolname objectname :) sage show you information that makes sense? On 09/26/2012 08:21 AM, Sage Weil wrote: On

Re: CEPH RBD client kernel panic when OSD connection is lost on kernel 3.2, 3.5, 3.5.4

2012-09-26 Thread Christian Huang
Hi Alex, should we open an issue on the tracker to better track it? Best Regards, Chris On Tue, Sep 25, 2012 at 11:49 PM, Alex Elder el...@inktank.com wrote: On 09/25/2012 09:38 AM, Christian Huang wrote: Hi Alex, just realized I made a mistake on the provided environment

Re: CEPH RBD client kernel panic when OSD connection is lost on kernel 3.2, 3.5, 3.5.4

2012-09-26 Thread Alex Elder
On 09/26/2012 08:34 PM, Christian Huang wrote: Hi Alex, should we open an issue on the tracker to better track it? Sorry, I should have mentioned this before. Sage already did. http://tracker.newdream.net/issues/3204 I've been trying to learn things about the problem when I reproduce it

How to create nova volumes inside rbd pool .

2012-09-26 Thread ramu eppa
Hi all, I want to create volumes inside rbd pool,please help me to create volumes inside rbd pool. Thanks, Ramu. -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at

Re: How to create nova volumes inside rbd pool .

2012-09-26 Thread Dan Mick
http://ceph.com/docs/master/rbd/rbd-openstack/ On 09/26/2012 09:45 PM, ramu eppa wrote: Hi all, I want to create volumes inside rbd pool,please help me to create volumes inside rbd pool. Thanks, Ramu. -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a

Re: Ho to identify location of Primary Copy Of Obj ?

2012-09-26 Thread Dan Mick
AGH! So sorry Hemant. I really was thinking 'map' when I typed that. On 09/26/2012 04:41 PM, Sage Weil wrote: On Wed, 26 Sep 2012, Dan Mick wrote: Ah, yeah, that assumption would be a problem. So, Hemant, does ceph osd dump poolname objectname Ahem, ceph osd map poolname

Problem creating osd.0 ??

2012-09-26 Thread hemant surale
Hi Folks , I am unable to figure it out the -- root@hemant-virtual-machine:/etc/ceph# mkcephfs -a -c /etc/ceph/ceph.conf -k ceph.keyring temp dir is /tmp/mkcephfs.E1M7ay6HBa preparing monmap in /tmp/mkcephfs.E1M7ay6HBa/monmap /usr/bin/monmaptool --create --clobber