Hello everyonel:
Recently, I have put up a simple test platform. Now I want to test
the MDS cluster's performance,but I don't how to get it. Can anyone
give me some advices or some tools may help me get it.
Thank you very much and best wishes.
--
To unsubscribe from this list: sen
> I tried them all:
>
> # cauthtool -l /etc/ceph/admin.keyring
> [client.admin]
> key = AQATSKdNGBnwLhAAnNDKnH65FmVKpXZJVasUeQ==
> auid = 18446744073709551615
> # mount.ceph 192.168.178.100:6789:/ /vol -v -o
> name=18446744073709551615,secret=AQATSKdNGBnwLhAAnNDKnH65FmVKpXZJVasUeQ==
On 04/15/2011 02:00 AM, Tommi Virtanen wrote:
> It looks like you're passing in the key the right way, but it's hard
> to tell as you've obscured the actual key. The error you are seeing
> is exactly what you would get if the key was invalid, or didn't have
> the capabilities needed for mounting
On Fri, Apr 15, 2011 at 01:44:39AM +0200, Zenon Panoussis wrote:
> I'm facing yet another one of "those problems", more likely caused by
> lack of knowledge and/or documentation than by anything else.
>
> # mount.ceph 192.168.178.100:6789:/ /vol
> mount error 22 = Invalid argument
>
> # dmesg -c
I'm facing yet another one of "those problems", more likely caused by
lack of knowledge and/or documentation than by anything else.
# mount.ceph 192.168.178.100:6789:/ /vol
mount error 22 = Invalid argument
# dmesg -c
libceph: no secret set (for auth_x protocol)
libceph: error -22 on auth protoc
On 04/14/2011 09:00 PM, Tommi Virtanen wrote:
>> 2011-04-14 20:22:24.887172 7fdc84de1720 OSD::mkfs: couldn't mount FileStore:
>> error -95
>> 2011-04-14 20:22:24.887226 7fdc84de1720 ** ERROR: error creating empty
>> object store in /mnt/osd: error 95: Operation not supported
>> failed: '/sbin/
On Thu, Apr 14, 2011 at 08:41:50PM +0200, Zenon Panoussis wrote:
> 2011-04-14 20:22:24.887172 7fdc84de1720 OSD::mkfs: couldn't mount FileStore:
> error -95
> 2011-04-14 20:22:24.887226 7fdc84de1720 ** ERROR: error creating empty
> object store in /mnt/osd: error 95: Operation not supported
> fai
Hi all
Attempting to create a store on a device-mapper ext4 partition fails.
Creating the exact same store in the same directory on a native ext4
partition works just fine. Success and failure output below.
It's not the presence of lost+found in the store that confuses ceph,
because it also fail
On Thu, Mar 31, 2011 at 11:39:46AM -0700, Sage Weil wrote:
> Ha! Applied. :)
> sage
>
>
> On Thu, 31 Mar 2011, Wido den Hollander wrote:
> > -echo mkfs.btrfs $btrfs_devs
> > +mkfs.btrfs $btrfs_devs
Apparently, this got lost somewhere. Now it's in master,
as commit 08e9855dcdca097f524b9
On Thu, Apr 14, 2011 at 1:52 AM, Sylar Shen wrote:
> Hi Sage,
> Thanks for your reply. I really appreciated.
> I tried what you suggested to set the argument "sync" in /etc/exports.
> I also checked "man 5 exports" and it showed that sync means reply to
> requests only after the changes have been
Hi Christoph,
As Zenon pointed out, you have to install src/init-ceph yourself (as
/etc/init.d/ceph). The RPM package should do this for you.
We considered having "make install" perform this step for users, but
unfortunately every Linux distribution puts the init scripts in a
slightly different p
On Thu, 14 Apr 2011, Sylar Shen wrote:
> Hi Sage,
> Thanks for your reply. I really appreciated.
> I tried what you suggested to set the argument "sync" in /etc/exports.
> I also checked "man 5 exports" and it showed that sync means reply to
> requests only after the changes have been committed to
On Wednesday, April 13, 2011 at 12:32 PM, Fyodor Ustinov wrote:
On this kernel (2.6.38-8-server ubuntu 11.04) i have trouble with ext4 also.
>
> I mount fresh ceph partition on client, test by bonnie++, unmount, stop
> ceph cluster, umount osd ext4 partition and forced fsck this partition.
>
> M
Hi Linus,
Please pull from
git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git for-linus
This might be the first time I've only had a single bug fix to push!
This fixes a null dereference on RBD when an osd daemon restarts. The
patch in the last pull didn't get it quite righ
On Wed, Apr 13, 2011 at 3:04 PM, Zenon Panoussis wrote:
...
> I got ceph-client-standalone from git and fixed the specific 2.6.32
> problems according to http://marc.info/?l=ceph-devel&m=129813044300561&w=2 .
>
> Then I run into this:
>
> ./dkms/add-to-dkms-and-build
>
> Creating symlink /var/li
On Thu, Apr 14, 2011 at 2:46 AM, huang jun wrote:
> hi developers,
> I have a question about the prealloc_inos variable in SessionMap.h
> when the client first request to allocate an inode,
> prepare_new_inode function will prepare new inodes to the session. so
> if the client's first request
Have you tried the option no_wdelay with sync? Perhaps that's what you
want since it minimizes the cache effect.
2011/4/14 Sylar Shen :
> Yes, after testing I found that "sync" will still do the cache in memory.
> But what I want to know is the real speed to write data into the disks.
> I know it
Yes, after testing I found that "sync" will still do the cache in memory.
But what I want to know is the real speed to write data into the disks.
I know it may not be safe without using memory and the speed may go very slow.
However, that's what I am trying to find out.
Thanks~~^^
2011/4/14 Brian
I don't think 'sync' will prevent data from going into cache, it just
means that a copy has to be on stable storage/disk as well. Whether
there's a copy in memory wont matter.
On Thu, Apr 14, 2011 at 1:52 AM, Sylar Shen wrote:
> Hi Sage,
> Thanks for your reply. I really appreciated.
> I tried w
On 04/14/2011 08:56 AM, Christoph Raible wrote:
> ...i want to start ceph with /etc/init.d/ceph -a start oder service
> ceph -a start but the service is unknown and in /etc/init.d there
> is noch such file!
You will find it in the sources, src/init-ceph. Copy it to /etc/init.d/ceph
or /et
hi developers,
I have a question about the prealloc_inos variable in SessionMap.h
when the client first request to allocate an inode,
prepare_new_inode function will prepare new inodes to the session. so
if the client's first request is to make a dir, the MDS always
return a safe message t
Hi Sage,
Thanks for your reply. I really appreciated.
I tried what you suggested to set the argument "sync" in /etc/exports.
I also checked "man 5 exports" and it showed that sync means reply to
requests only after the changes have been committed to stable storage.
It didn't mention that the export
Hi @all,
I compilied & configured ceph 0.26 today and now i want to start ceph
with /etc/init.d/ceph -a start oder service ceph -a start but the
service is unknown and in /etc/init.d there is noch such file!
I compiled ceph with following commands:
##
./autogen
23 matches
Mail list logo
