Discussion:
[ceph-users] Migrate OSD journal to SSD partition
D***@Dell.com
2018-11-08 07:40:34 UTC
Permalink
Hi all,

I have been trying to migrate the journal to SSD partition for an while, basically I followed the guide here [1], I have the below configuration defined in the ceph.conf

[osd.0]
osd_journal = /dev/disk/by-partlabel/journal-1

And then create the journal in this way,
# ceph-osd -i 0 -mkjournal

After that, I started the osd, and I saw the service is started successfully from the log print out on the console,
08 14:03:35 ceph1 ceph-osd[5111]: starting osd.0 at :/0 osd_data /var/lib/ceph/osd/ceph-0 /dev/disk/by-partlabel/journal-1
08 14:03:35 ceph1 ceph-osd[5111]: 2018-11-08 14:03:35.618247 7fe8b54b28c0 -1 osd.0 766 log_to_monitors {default=true}

But I not sure whether the new journal is effective or not, looks like it is still using the old partition (/dev/sdc2) for journal, and new partition which is actually "dev/sde1" has no information on the journal,

# ceph-disk list

/dev/sdc :
/dev/sdc2 ceph journal, for /dev/sdc1
/dev/sdc1 ceph data, active, cluster ceph, osd.0, journal /dev/sdc2
/dev/sdd :
/dev/sdd2 ceph journal, for /dev/sdd1
/dev/sdd1 ceph data, active, cluster ceph, osd.1, journal /dev/sdd2
/dev/sde :
/dev/sde1 other, 0fc63daf-8483-4772-8e79-3d69d8477de4
/dev/sdf other, unknown

# ls -l /var/lib/ceph/osd/ceph-0/journal
lrwxrwxrwx 1 ceph ceph 58 21 2018 /var/lib/ceph/osd/ceph-0/journal -> /dev/disk/by-partuuid/5b5cd6f6-5de4-44f3-9d33-e8a7f4b59f61

# ls -l /dev/disk/by-partuuid/5b5cd6f6-5de4-44f3-9d33-e8a7f4b59f61
lrwxrwxrwx 1 root root 10 8 13:59 /dev/disk/by-partuuid/5b5cd6f6-5de4-44f3-9d33-e8a7f4b59f61 -> ../../sdc2


My question is how I know which partition is taking the role of journal? Where can I see the new journal partition is linked?

Any comments is highly appreciated!


[1] https://fatmin.com/2015/08/11/ceph-show-osd-to-journal-mapping/


Best Regards,
Dave Chen
David Turner
2018-11-19 17:27:50 UTC
Permalink
For this the procedure is generally to stop the osd, flush the journal,
update the symlink on the osd to the new journal location, mkjournal, start
osd. You shouldn't need to do anything in the ceph.conf file.
Post by D***@Dell.com
Hi all,
I have been trying to migrate the journal to SSD partition for an while,
basically I followed the guide here [1], I have the below configuration
defined in the ceph.conf
[osd.0]
osd_journal = /dev/disk/by-partlabel/journal-1
And then create the journal in this way,
# ceph-osd -i 0 –mkjournal
After that, I started the osd, and I saw the service is started
successfully from the log print out on the console,
08 14:03:35 ceph1 ceph-osd[5111]: starting osd.0 at :/0 osd_data
/var/lib/ceph/osd/ceph-0 /dev/disk/by-partlabel/journal-1
08 14:03:35 ceph1 ceph-osd[5111]: 2018-11-08 14:03:35.618247 7fe8b54b28c0
-1 osd.0 766 log_to_monitors {default=true}
But I not sure whether the new journal is effective or not, looks like it
is still using the old partition (/dev/sdc2) for journal, and new partition
which is actually “dev/sde1” has no information on the journal,
# ceph-disk list
/dev/sdc2 ceph journal, for /dev/sdc1
/dev/sdc1 ceph data, active, cluster ceph, osd.0, journal /dev/sdc2
/dev/sdd2 ceph journal, for /dev/sdd1
/dev/sdd1 ceph data, active, cluster ceph, osd.1, journal /dev/sdd2
/dev/sde1 other, 0fc63daf-8483-4772-8e79-3d69d8477de4
/dev/sdf other, unknown
# ls -l /var/lib/ceph/osd/ceph-0/journal
lrwxrwxrwx 1 ceph ceph 58 21 2018 /var/lib/ceph/osd/ceph-0/journal ->
/dev/disk/by-partuuid/5b5cd6f6-5de4-44f3-9d33-e8a7f4b59f61
# ls -l /dev/disk/by-partuuid/5b5cd6f6-5de4-44f3-9d33-e8a7f4b59f61
lrwxrwxrwx 1 root root 10 8 13:59
/dev/disk/by-partuuid/5b5cd6f6-5de4-44f3-9d33-e8a7f4b59f61 -> ../../sdc2
My question is how I know which partition is taking the role of journal?
Where can I see the new journal partition is linked?
Any comments is highly appreciated!
[1] https://fatmin.com/2015/08/11/ceph-show-osd-to-journal-mapping/
Best Regards,
Dave Chen
_______________________________________________
ceph-users mailing list
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Loading...