* Problem with Ceph installation inside Amazon EC2
@ 2010-04-20 13:38 Christian Baun
2010-04-20 14:21 ` Wido den Hollander
0 siblings, 1 reply; 5+ messages in thread
From: Christian Baun @ 2010-04-20 13:38 UTC (permalink / raw)
To: ceph-devel
Hi,
I want to test Ceph inside Amazon EC2. Therefore I compiled and installed ceph-0.19.1.tar.gz and ceph-kclient-0.19.1.tar.gz
Two Ubuntu instances are running inside EC2.
One server with cmon, cmds, and cosd and one client.
# cat /etc/ceph/ceph.conf
[global]
pid file = /var/run/ceph/$name.pid
debug ms = 1
[mon]
mon data = /srv/ceph/mon
[mon0]
host = ceph01
mon addr = 10.194.145.203:6789
[mds]
[mds0]
host = ceph01
[osd]
sudo = true
osd data = /srv/ceph/osd
[osd1]
host = ceph01
btrfs devs = /dev/sdc
# cat /etc/hosts
127.0.0.1 localhost
10.194.145.203 ceph01
# mkcephfs -c /etc/ceph/ceph.conf --allhosts --mkbtrfs -k ~/admin.keyring
.conf --allhosts --mkbtrfs -k ~/admin.keyring
/usr/local/bin/monmaptool --create --clobber --add 10.194.145.203:6789 --print /tmp/monmap.9681
/usr/local/bin/monmaptool: monmap file /tmp/monmap.9681
/usr/local/bin/monmaptool: generated fsid 7a008165-58df-733f-deca-90faecaef60a
epoch 1
fsid 7a008165-58df-733f-deca-90faecaef60a
last_changed 10.04.20 13:34:52.518583
created 10.04.20 13:34:52.518583
mon0 10.194.145.203:6789/0
/usr/local/bin/monmaptool: writing epoch 1 to /tmp/monmap.9681 (1 monitors)
max osd in /etc/ceph/ceph.conf is 1, num osd is 2
/usr/local/bin/osdmaptool: osdmap file '/tmp/osdmap.9681'
/usr/local/bin/osdmaptool: writing epoch 1 to /tmp/osdmap.9681
Building admin keyring at /root/admin.keyring
creating /root/admin.keyring
Building monitor keyring with all service keys
creating /tmp/monkeyring.9681
importing contents of /root/admin.keyring into /tmp/monkeyring.9681
creating /tmp/keyring.mds.0
importing contents of /tmp/keyring.mds.0 into /tmp/monkeyring.9681
creating /tmp/keyring.osd.1
importing contents of /tmp/keyring.osd.1 into /tmp/monkeyring.9681
=== mon0 ===
10.04.20 13:34:54.805739 store(/srv/ceph/mon) mkfs
10.04.20 13:34:54.805853 store(/srv/ceph/mon) test -d /srv/ceph/mon && /bin/rm -rf /srv/ceph/mon ; mkdir -p /srv/ceph/mon
10.04.20 13:34:54.831017 mon0(starting).class v0 create_initial -- creating initial map
10.04.20 13:34:54.832277 mon0(starting).auth v0 create_initial -- creating initial map
10.04.20 13:34:54.832308 mon0(starting).auth v0 reading initial keyring
/usr/local/bin/mkmonfs: created monfs at /srv/ceph/mon for mon0
admin.keyring 100% 119 0.1KB/s 00:00
=== mds0 ===
WARNING: no keyring specified for mds0
=== osd1 ===
umount: /srv/ceph/osd: not mounted
umount: /dev/sdc: not mounted
WARNING! - Btrfs Btrfs v0.19 IS EXPERIMENTAL
WARNING! - see http://btrfs.wiki.kernel.org before using
fs created label (null) on /dev/sdc
nodesize 4096 leafsize 4096 sectorsize 4096 size 419.97GB
Btrfs Btrfs v0.19
Scanning for Btrfs filesystems
monmap.9681 100% 187 0.2KB/s 00:00
** WARNING: Ceph is still under heavy development, and is only suitable for **
** testing and review. Do not trust it with important data. **
created object store for osd1 fsid 7a008165-58df-733f-deca-90faecaef60a on /srv/ceph/osd
WARNING: no keyring specified for osd1
# df
Filesystem 1K-blocks Used Available Use% Mounted on
/dev/sda1 10403128 4038372 5945328 41% /
none 3804316 112 3804204 1% /dev
none 3941904 0 3941904 0% /dev/shm
none 3941904 60 3941844 1% /var/run
none 3941904 0 3941904 0% /var/lock
none 3941904 0 3941904 0% /lib/init/rw
/dev/sdb 433455904 203016 411234584 1% /mnt
/dev/sdc 440366080 32 440366048 1% /srv/ceph/osd
# mount | grep ceph
/dev/sdc on /srv/ceph/osd type btrfs (rw,flushoncommit)
At the server:
# ./ceph start
10.04.20 13:35:39.757563 7f6485c32720 -- :/10726 messenger.start
10.04.20 13:35:39.757808 7f6485c32720 -- :/10726 --> mon0 10.194.145.203:6789/0 -- auth(proto 0 30 bytes) -- ?+0 0x1e46910
10.04.20 13:35:39.757990 7f6482eb3710 -- :/10726 >> 10.194.145.203:6789/0 pipe(0x1e426a0 sd=-1 pgs=0 cs=0 l=0).fault first fault
At the client:
# mount -t ceph 10.194.145.203:/ /mnt/ceph/
mount: 10.194.145.203:/: can't read superblock
What can I do at this point?
Thanks in advance
Christian
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Problem with Ceph installation inside Amazon EC2
2010-04-20 13:38 Problem with Ceph installation inside Amazon EC2 Christian Baun
@ 2010-04-20 14:21 ` Wido den Hollander
2010-04-20 15:18 ` Christian Baun
0 siblings, 1 reply; 5+ messages in thread
From: Wido den Hollander @ 2010-04-20 14:21 UTC (permalink / raw)
To: Christian Baun; +Cc: ceph-devel
Hi,
What does "ceph -w" show?
Do you get some "xauth" messages in your mon0 logfiles?
--
Met vriendelijke groet,
Wido den Hollander
Hoofd Systeembeheer / CSO
Telefoon Support Nederland: 0900 9633 (45 cpm)
Telefoon Support België: 0900 70312 (45 cpm)
Telefoon Direct: (+31) (0)20 50 60 104
Fax: +31 (0)20 50 60 111
E-mail: support@pcextreme.nl
Website: http://www.pcextreme.nl
Kennisbank: http://support.pcextreme.nl/
Netwerkstatus: http://nmc.pcextreme.nl
On Tue, 2010-04-20 at 13:38 +0000, Christian Baun wrote:
> Hi,
>
> I want to test Ceph inside Amazon EC2. Therefore I compiled and installed ceph-0.19.1.tar.gz and ceph-kclient-0.19.1.tar.gz
>
> Two Ubuntu instances are running inside EC2.
> One server with cmon, cmds, and cosd and one client.
>
> # cat /etc/ceph/ceph.conf
> [global]
> pid file = /var/run/ceph/$name.pid
> debug ms = 1
>
> [mon]
> mon data = /srv/ceph/mon
>
> [mon0]
> host = ceph01
> mon addr = 10.194.145.203:6789
>
> [mds]
>
> [mds0]
> host = ceph01
>
> [osd]
> sudo = true
> osd data = /srv/ceph/osd
>
> [osd1]
> host = ceph01
> btrfs devs = /dev/sdc
>
>
> # cat /etc/hosts
> 127.0.0.1 localhost
> 10.194.145.203 ceph01
>
>
> # mkcephfs -c /etc/ceph/ceph.conf --allhosts --mkbtrfs -k ~/admin.keyring
> .conf --allhosts --mkbtrfs -k ~/admin.keyring
> /usr/local/bin/monmaptool --create --clobber --add 10.194.145.203:6789 --print /tmp/monmap.9681
> /usr/local/bin/monmaptool: monmap file /tmp/monmap.9681
> /usr/local/bin/monmaptool: generated fsid 7a008165-58df-733f-deca-90faecaef60a
> epoch 1
> fsid 7a008165-58df-733f-deca-90faecaef60a
> last_changed 10.04.20 13:34:52.518583
> created 10.04.20 13:34:52.518583
> mon0 10.194.145.203:6789/0
> /usr/local/bin/monmaptool: writing epoch 1 to /tmp/monmap.9681 (1 monitors)
> max osd in /etc/ceph/ceph.conf is 1, num osd is 2
> /usr/local/bin/osdmaptool: osdmap file '/tmp/osdmap.9681'
> /usr/local/bin/osdmaptool: writing epoch 1 to /tmp/osdmap.9681
> Building admin keyring at /root/admin.keyring
> creating /root/admin.keyring
> Building monitor keyring with all service keys
> creating /tmp/monkeyring.9681
> importing contents of /root/admin.keyring into /tmp/monkeyring.9681
> creating /tmp/keyring.mds.0
> importing contents of /tmp/keyring.mds.0 into /tmp/monkeyring.9681
> creating /tmp/keyring.osd.1
> importing contents of /tmp/keyring.osd.1 into /tmp/monkeyring.9681
> === mon0 ===
> 10.04.20 13:34:54.805739 store(/srv/ceph/mon) mkfs
> 10.04.20 13:34:54.805853 store(/srv/ceph/mon) test -d /srv/ceph/mon && /bin/rm -rf /srv/ceph/mon ; mkdir -p /srv/ceph/mon
> 10.04.20 13:34:54.831017 mon0(starting).class v0 create_initial -- creating initial map
> 10.04.20 13:34:54.832277 mon0(starting).auth v0 create_initial -- creating initial map
> 10.04.20 13:34:54.832308 mon0(starting).auth v0 reading initial keyring
> /usr/local/bin/mkmonfs: created monfs at /srv/ceph/mon for mon0
> admin.keyring 100% 119 0.1KB/s 00:00
> === mds0 ===
> WARNING: no keyring specified for mds0
> === osd1 ===
> umount: /srv/ceph/osd: not mounted
> umount: /dev/sdc: not mounted
>
> WARNING! - Btrfs Btrfs v0.19 IS EXPERIMENTAL
> WARNING! - see http://btrfs.wiki.kernel.org before using
>
> fs created label (null) on /dev/sdc
> nodesize 4096 leafsize 4096 sectorsize 4096 size 419.97GB
> Btrfs Btrfs v0.19
> Scanning for Btrfs filesystems
> monmap.9681 100% 187 0.2KB/s 00:00
> ** WARNING: Ceph is still under heavy development, and is only suitable for **
> ** testing and review. Do not trust it with important data. **
> created object store for osd1 fsid 7a008165-58df-733f-deca-90faecaef60a on /srv/ceph/osd
> WARNING: no keyring specified for osd1
>
>
>
> # df
> Filesystem 1K-blocks Used Available Use% Mounted on
> /dev/sda1 10403128 4038372 5945328 41% /
> none 3804316 112 3804204 1% /dev
> none 3941904 0 3941904 0% /dev/shm
> none 3941904 60 3941844 1% /var/run
> none 3941904 0 3941904 0% /var/lock
> none 3941904 0 3941904 0% /lib/init/rw
> /dev/sdb 433455904 203016 411234584 1% /mnt
> /dev/sdc 440366080 32 440366048 1% /srv/ceph/osd
>
>
> # mount | grep ceph
> /dev/sdc on /srv/ceph/osd type btrfs (rw,flushoncommit)
>
>
> At the server:
> # ./ceph start
> 10.04.20 13:35:39.757563 7f6485c32720 -- :/10726 messenger.start
> 10.04.20 13:35:39.757808 7f6485c32720 -- :/10726 --> mon0 10.194.145.203:6789/0 -- auth(proto 0 30 bytes) -- ?+0 0x1e46910
> 10.04.20 13:35:39.757990 7f6482eb3710 -- :/10726 >> 10.194.145.203:6789/0 pipe(0x1e426a0 sd=-1 pgs=0 cs=0 l=0).fault first fault
>
>
> At the client:
> # mount -t ceph 10.194.145.203:/ /mnt/ceph/
> mount: 10.194.145.203:/: can't read superblock
>
>
> What can I do at this point?
>
> Thanks in advance
> Christian
>
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Problem with Ceph installation inside Amazon EC2
2010-04-20 14:21 ` Wido den Hollander
@ 2010-04-20 15:18 ` Christian Baun
2010-04-20 15:41 ` Wido den Hollander
0 siblings, 1 reply; 5+ messages in thread
From: Christian Baun @ 2010-04-20 15:18 UTC (permalink / raw)
To: wido; +Cc: ceph-devel
Hi,
I have just these logfiles in /var/log/ceph:
# ls -l /var/log/ceph/
total 4
-rw-r--r-- 1 root root 940 2010-04-20 15:12 ip-10-194-145-203.12134
lrwxrwxrwx 1 root root 23 2010-04-20 15:12 osd1 -> ip-10-194-145-203.12134
# cat ip-10-194-145-203.12134
10.04.20 15:12:06.702434 --- opened log /var/log/ceph/ip-10-194-145-203.12134 ---
ceph version 0.19.1 (7d7f925bcd03630778e36fe633efaf92768925c7)
10.04.20 15:12:06.702550 ---- renamed symlink /var/log/ceph/osd1 -> /var/log/ceph/osd1.0 ----
10.04.20 15:12:06.702573 ---- created symlink /var/log/ceph/osd1 -> ip-10-194-145-203.12134 ----
10.04.20 15:12:06.702674 7fd59e775720 -- :/12134 messenger.start
10.04.20 15:12:06.702726 7fd59e775720 -- :/12134 shutdown complete.
10.04.20 15:12:06.702788 7fd59e775720 filestore(/srv/ceph/osd) mkfs in /srv/ceph/osd
10.04.20 15:12:06.717191 7fd59e775720 filestore(/srv/ceph/osd) mkfs done in /srv/ceph/osd
10.04.20 15:12:06.717467 7fd59e775720 filestore(/srv/ceph/osd) mount btrfs TRANS_START ioctl is supported
10.04.20 15:12:06.717481 7fd59e775720 filestore(/srv/ceph/osd) mount btrfs CLONE_RANGE ioctl is supported
10.04.20 15:12:06.717488 7fd59e775720 filestore(/srv/ceph/osd) mount detected btrfs
There is no mon0 logfile.
"ceph -w" says the same as "ceph start"
# ceph -w
10.04.20 15:14:31.755364 7fc9f7329720 -- :/12154 messenger.start
10.04.20 15:14:31.755598 7fc9f7329720 -- :/12154 --> mon0 10.194.145.203:6789/0 -- auth(proto 0 30 bytes) -- ?+0 0xc99de0
10.04.20 15:14:31.755777 7fc9f45aa710 -- :/12154 >> 10.194.145.203:6789/0 pipe(0xc9d2f0 sd=-1 pgs=0 cs=0 l=0).fault first fault
# mount -t ceph 10.194.145.203:/ /mnt/ceph/
mount: 10.194.145.203:/: can't read superblock
Best Regards,
Christian
Am Dienstag, 20. April 2010 schrieb Wido den Hollander:
> Hi,
>
> What does "ceph -w" show?
>
> Do you get some "xauth" messages in your mon0 logfiles?
>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Problem with Ceph installation inside Amazon EC2
2010-04-20 15:18 ` Christian Baun
@ 2010-04-20 15:41 ` Wido den Hollander
2010-04-20 16:13 ` Christian Baun
0 siblings, 1 reply; 5+ messages in thread
From: Wido den Hollander @ 2010-04-20 15:41 UTC (permalink / raw)
To: Christian Baun; +Cc: ceph-devel
Hi,
Do you have the following processes running?
- cmon
- cmds
- cosd
And you are trying to mount the Ceph filesystem which is running local
isn't it?
I also experienced some troubles with mounting a local Ceph filesystem,
so i switched to a dedicated client.
--
Met vriendelijke groet,
Wido den Hollander
Hoofd Systeembeheer / CSO
Telefoon Support Nederland: 0900 9633 (45 cpm)
Telefoon Support België: 0900 70312 (45 cpm)
Telefoon Direct: (+31) (0)20 50 60 104
Fax: +31 (0)20 50 60 111
E-mail: support@pcextreme.nl
Website: http://www.pcextreme.nl
Kennisbank: http://support.pcextreme.nl/
Netwerkstatus: http://nmc.pcextreme.nl
On Tue, 2010-04-20 at 15:18 +0000, Christian Baun wrote:
> Hi,
>
> I have just these logfiles in /var/log/ceph:
>
> # ls -l /var/log/ceph/
> total 4
> -rw-r--r-- 1 root root 940 2010-04-20 15:12 ip-10-194-145-203.12134
> lrwxrwxrwx 1 root root 23 2010-04-20 15:12 osd1 -> ip-10-194-145-203.12134
>
> # cat ip-10-194-145-203.12134
> 10.04.20 15:12:06.702434 --- opened log /var/log/ceph/ip-10-194-145-203.12134 ---
> ceph version 0.19.1 (7d7f925bcd03630778e36fe633efaf92768925c7)
> 10.04.20 15:12:06.702550 ---- renamed symlink /var/log/ceph/osd1 -> /var/log/ceph/osd1.0 ----
> 10.04.20 15:12:06.702573 ---- created symlink /var/log/ceph/osd1 -> ip-10-194-145-203.12134 ----
> 10.04.20 15:12:06.702674 7fd59e775720 -- :/12134 messenger.start
> 10.04.20 15:12:06.702726 7fd59e775720 -- :/12134 shutdown complete.
> 10.04.20 15:12:06.702788 7fd59e775720 filestore(/srv/ceph/osd) mkfs in /srv/ceph/osd
> 10.04.20 15:12:06.717191 7fd59e775720 filestore(/srv/ceph/osd) mkfs done in /srv/ceph/osd
> 10.04.20 15:12:06.717467 7fd59e775720 filestore(/srv/ceph/osd) mount btrfs TRANS_START ioctl is supported
> 10.04.20 15:12:06.717481 7fd59e775720 filestore(/srv/ceph/osd) mount btrfs CLONE_RANGE ioctl is supported
> 10.04.20 15:12:06.717488 7fd59e775720 filestore(/srv/ceph/osd) mount detected btrfs
>
> There is no mon0 logfile.
>
> "ceph -w" says the same as "ceph start"
>
> # ceph -w
> 10.04.20 15:14:31.755364 7fc9f7329720 -- :/12154 messenger.start
> 10.04.20 15:14:31.755598 7fc9f7329720 -- :/12154 --> mon0 10.194.145.203:6789/0 -- auth(proto 0 30 bytes) -- ?+0 0xc99de0
> 10.04.20 15:14:31.755777 7fc9f45aa710 -- :/12154 >> 10.194.145.203:6789/0 pipe(0xc9d2f0 sd=-1 pgs=0 cs=0 l=0).fault first fault
>
> # mount -t ceph 10.194.145.203:/ /mnt/ceph/
> mount: 10.194.145.203:/: can't read superblock
>
> Best Regards,
> Christian
>
>
>
>
> Am Dienstag, 20. April 2010 schrieb Wido den Hollander:
> > Hi,
> >
> > What does "ceph -w" show?
> >
> > Do you get some "xauth" messages in your mon0 logfiles?
> >
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Problem with Ceph installation inside Amazon EC2
2010-04-20 15:41 ` Wido den Hollander
@ 2010-04-20 16:13 ` Christian Baun
0 siblings, 0 replies; 5+ messages in thread
From: Christian Baun @ 2010-04-20 16:13 UTC (permalink / raw)
To: wido; +Cc: ceph-devel
Hi,
I think it is working now.
I had to do these steps:
cp src/init-ceph /etc/init.d/ceph
chmod a+x /etc/init.d/ceph
chmod u+w /etc/init.d/ceph
/etc/init.d/ceph -c /etc/ceph/ceph.conf start
Now, the server processes are running
# ps -aux | grep ceph
Warning: bad ps syntax, perhaps a bogus '-'? See http://procps.sf.net/faq.html
root 1948 0.0 0.0 0 0 ? S 11:28 0:00 [ceph-msgr/0]
root 1949 0.0 0.0 0 0 ? S 11:28 0:00 [ceph-msgr/1]
root 12467 0.0 0.0 179812 3452 ? Ssl 15:58 0:00 /usr/local/bin/cmon -i 0 -c /etc/ceph/ceph.conf
root 12495 0.0 0.0 189532 3792 ? Ssl 15:58 0:00 /usr/local/bin/cmds -i 0 -c /etc/ceph/ceph.conf
root 12545 0.0 0.2 247480 21676 ? Ssl 15:58 0:00 /usr/local/bin/cosd -i 1 -c /etc/ceph/ceph.conf
root 12597 0.0 0.0 7616 920 pts/1 R+ 16:01 0:00 grep --color=auto ceph
The mount command at the client machine was successful too:
# mount | grep ceph
10.194.145.203:/ on /mnt/ceph type ceph (rw)
A small performance test inside EC2:
I created 2 Instances. 1 Instance has an EBS-Volume attached. The EBS-Volume is the storage for the Ceoh. Both instances (m1.large) are inside EC2 us-east-1d.
Create testdata
# dd if=/dev/zero of=/tmp/testfile bs=1024 count=1000000
1000000+0 records in
1000000+0 records out
1024000000 bytes (1.0 GB) copied, 7.24084 s, 141 MB/s
# cat test.bat
cp /tmp/testfile /mnt/ceph
sync
Copy the testdata from the client to the server:
# time ./test.bat
real 0m29.211s
user 0m0.020s
sys 0m1.490s
Thanks a lot for the help.
Best Regards,
Christian
Am Dienstag, 20. April 2010 schrieb Wido den Hollander:
> Hi,
>
> Do you have the following processes running?
>
> - cmon
> - cmds
> - cosd
>
> And you are trying to mount the Ceph filesystem which is running local
> isn't it?
>
> I also experienced some troubles with mounting a local Ceph filesystem,
> so i switched to a dedicated client.
>
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2010-04-20 16:13 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2010-04-20 13:38 Problem with Ceph installation inside Amazon EC2 Christian Baun
2010-04-20 14:21 ` Wido den Hollander
2010-04-20 15:18 ` Christian Baun
2010-04-20 15:41 ` Wido den Hollander
2010-04-20 16:13 ` Christian Baun
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.