>If you run 'rbd info --pool RBD-01 CEPH_006__000001__NA__0003__ESX__ALL_EXT', what is the output?
size 2048 GB in 524288 objects
order 22 (4096 kB objects)
block_name_prefix: rb.0.19b1.238e1f29
format: 1
>Does 'rbd diff' work against the image (i.e. more than a few kilobyes of deltas)?
it looks fine
time rbd diff --cluster cluster1 --pool NETAP-RBD-01 CEPH_006__000001__NA__0003__ESX__ALL_EXT |wc -c
14593264
real 22m35.316s
user 2m39.537s
sys 1m24.177s
>Also, would it be possible for you to create a new, test image in the same pool, snapshot it, use 'rbd bench-write' to generate some data, and then verify if export-diff is properly working against the new image?
i will try.. i can create only 1-100gb image in this pool
2015-05-12 19:30 GMT+05:00 Jason Dillaman <dillaman@xxxxxxxxxx>:
Very strange. I'll see if I can reproduce on a giant release. If you run 'rbd info --pool RBD-01 CEPH_006__000001__NA__0003__ESX__ALL_EXT', what is the output? I want to use the same settings as your image.
Does 'rbd diff' work against the image (i.e. more than a few kilobyes of deltas)? Also, would it be possible for you to create a new, test image in the same pool, snapshot it, use 'rbd bench-write' to generate some data, and then verify if export-diff is properly working against the new image?
--
Jason Dillaman
Red Hat
dillaman@xxxxxxxxxx
http://www.redhat.com
----- Original Message -----
From: "Ultral" <ultralisc@xxxxxxxxx>
To: "Jason Dillaman" <dillaman@xxxxxxxxxx>
Cc: "ceph-users" <ceph-users@xxxxxxxx>
Sent: Sunday, May 10, 2015 5:40:00 AM
Subject: Re: export-diff exported only 4kb instead of 200-600gb
Hello Jason,
> but to me it sounds like you are saying that there are no/minimal deltas between snapshots move2db24-20150428 and 2015-05-05 (both from the export-diff and from your clone).
yep, it correct. difference between snapshots move2db24-20150428 & 2015-05-05 is too small 4kb instead of 200-800gb..
> Are you certain that you made 700-800GBs of changes between the two snapshots and no trim operations released your changes back?
VM locate on the image, it is intranet for 1000 peoples. it has web+mysql+sphinx+backups
vast majority of changed data are backups(2 day rotation) inside VM on the image. it made about 200gb of data each day
also we store users uploads (0.3-3gb per day)
and databases (about 30gb )
so i suppose that changes should be more than 4kb
> If you diff from move2db24-20150428 to HEAD, do you see all your changes?
rbd export-diff --cluster cluster1 --pool RBD-01 CEPH_006__000001__NA__0003__ESX__ALL_EXT --from-snap move2db24-20150428 -|wc -c
6786
Exporting image: 100% complete...done.
it is too small.. i've added some video files to the VM, however it shows only 6kb
2015-05-08 18:43 GMT+05:00 Jason Dillaman < dillaman@xxxxxxxxxx > :
There is probably something that I am not understanding, but to me it sounds like you are saying that there are no/minimal deltas between snapshots move2db24-20150428 and 2015-05-05 (both from the export-diff and from your clone). Are you certain that you made 700-800GBs of changes between the two snapshots and no trim operations released your changes back? If you diff from move2db24-20150428 to HEAD, do you see all your changes?
--
Jason Dillaman
Red Hat
dillaman@xxxxxxxxxx
http://www.redhat.com
----- Original Message -----
From: "Ultral" < ultralisc@xxxxxxxxx >
To: "ceph-users" < ceph-users@xxxxxxxx >
Sent: Thursday, May 7, 2015 11:45:46 AM
Subject: export-diff exported only 4kb instead of 200-600gb
Hi all,
Something strange occurred.
I have ceph 0.87 version and 2048gb image format 1. I decided to made incremental backups between clusters
i've made initial copy,
time bbcp -x 7M -P 3600 -w 32M -s 6 -Z 5030:5035 -N io "rbd export-diff --cluster cluster1 --pool RBD-01 --image CEPH_006__000001__NA__0003__ESX__ALL_EXT --snap move2db24-20150428 -" 1.1.1.1 :"rbd import-diff - --cluster cluster2 --pool TST-INT-SD-RBD-1DC --image temp
and decide to move incremental(it should be about 200-600gb of changes)
time bbcp -c -x 7M -P 3600 -w 32M -s 6 -Z 5030:5035 -N io "rbd --cluster cluster1 --pool RBD-01 --image CEPH_006__000001__NA__0003__ESX__ALL_EXT --from-snap move2db24-20150428 --snap 2015-05-05 -" 1.1.1.1 :"rbd import-diff - --cluster cluster2 --pool TST-INT-SD-RBD-1DC --image temp "
it itakes about 30min(it was too fast because i have limitation 7M bettween clusters) and i decided to check how much data was transfered
time rbd export-diff --cluster cluster1 --pool RBD-01 --image CEPH_006__000001__NA__0003__ESX__ALL_EXT --from-snap move2db24-20150428 --snap 2015-05-05 -|wc -c
4753
Exporting image: 100% complete...done.
i've double checked it.. it was really 4753 bytes, i've decided to check export-diff file
0000000: 7262 6420 6469 6666 2076 310a 6612 0000 rbd diff v1.f...
0000010: 006d 6f76 6532 6462 3234 2d32 3031 3530 .move2db24-20150
0000020: 3432 3874 0a00 0000 3230 3135 2d30 352d 428t....2015-05-
0000030: 3035 7300 0000 0000 0200 0077 0080 5501 05s........w..U.
0000040: 0000 0000 0002 0000 0000 0000 02ef cdab ................
0000050: 0080 3500 0000 0000 0d00 0000 0000 0000 ..5.............
0000060: 2d58 3aff 5002 0000 bc56 2255 08fc 14a9 -X:.P....V"U....
0000070: e6c0 e839 351a 942c 01de 4603 0e00 0000 ...95..,..F.....
0000080: 3a00 0000 0000 0000 0000 0000 0000 0000 :...............
0000090: 0000 0000 0000 0000 0000 0000 0000 0000 ................
00000a0: 0000 0000 0000 0000 0000 0000 0000 0000 ................
......
0001270: 0000 0000 0000 0000 0000 0000 0000 0000 ................
0001280: 0000 0000 0000 0000 0000 0000 0000 0000 ................
0001290: 65 e
it look like correct format..
i've made clone(like flex clone) from snapshot 2015-05-05 & found that it doesn't have changes from snap move2db24-20150428
Do you have any ideas, what should i check? why is it hapend?
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
