-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA256 Just use the built in Ceph recovery to move data to the new disk. By changing disk sizes, you also change the mapping across the cluster so you are going to be moving more data than necessary. My recommendation, bring the new disk in as a new OSD. Then set the old disk to 'out'. This will keep the OSD participating in the backfills until it is empty. Once the backfill is done, stop the old OSD and remove it from the cluster. - ---------------- Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 On Sat, Sep 19, 2015 at 2:30 AM, wsnote wrote: > I know another way: out 1TB osd, up 2TB osd as osd.X without data, then > rados will backfill the data to 2TB disks. > Now I use rsync to mv data form 1TB disk to 2TB disk, but the new osd > coredump. > What's the problem? > > ceph version:0.80.1 > osd.X > host1 with 1TB disks > host2 with 2TB disks > > on host1: > osd.X down > ceph-osd -i X --flush-journal > rsync -av /data/osd/osd.X/ root:host2:/data/osd/osd.X/ > on host2: > vim ceph.conf > ceph-osd -i X --mkjournal > ceph-osd -i X > > then osd.X coredump > osd log: > -1> 2015-09-19 14:52:22.371149 7f008cd007a0 0 osd.29 416 load_pgs > 0> 2015-09-19 14:52:22.378677 7f008cd007a0 -1 osd/PG.cc: In function 'static > epoch_t PG::peek_map_epoch(ObjectStore*, coll_t, hobject_t&, > ceph::bufferlist*)' thread 7f008cd007a0 time 2015-09-19 14:52:22.377569 > osd/PG.cc: 2559: FAILED assert(r > 0) > > ceph version 0.80.1 (a38fe1169b6d2ac98b427334c12d7cf81f809b74) > 1: (PG::peek_map_epoch(ObjectStore*, coll_t, hobject_t&, > ceph::buffer::list*)+0x48d) [0x7fa4ad] > 2: (OSD::load_pgs()+0x18f1) [0x63c771] > 3: (OSD::init()+0x22b0) [0x6550e0] > 4: (main()+0x359e) [0x5f931e] > 5: (__libc_start_main()+0xfd) [0x3073c1ed5d] > 6: ceph-osd() [0x5f59c9] > > coredump: > (gdb) bt > > 0 0x000000307400f5db in raise () from /lib64/libpthread.so.0 > > 1 0x00000000009ab7f4 in ?? () > > 2 > > 3 0x0000003073c32635 in raise () from /lib64/libc.so.6 > > 4 0x0000003073c33e15 in abort () from /lib64/libc.so.6 > > 5 0x0000003b4febea7d in __gnu_cxx::__verbose_terminate_handler() () from > /usr/lib64/libstdc++.so.6 > > 6 0x0000003b4febcbd6 in ?? () from /usr/lib64/libstdc++.so.6 > > 7 0x0000003b4febcc03 in std::terminate() () from /usr/lib64/libstdc++.so.6 > > 8 0x0000003b4febcd22 in __cxa_throw () from /usr/lib64/libstdc++.so.6 > > 9 0x0000000000aec612 in ceph::__ceph_assert_fail(char const*, char const*, > int, char const*) () > > 10 0x00000000007fa4ad in PG::peek_map_epoch(ObjectStore*, coll_t, > hobject_t&, ceph::buffer::list*) () > > 11 0x000000000063c771 in OSD::load_pgs() () > > 12 0x00000000006550e0 in OSD::init() () > > 13 0x00000000005f931e in main () > > > > > > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > -----BEGIN PGP SIGNATURE----- Version: Mailvelope v1.1.0 Comment: https://www.mailvelope.com wsFcBAEBCAAQBQJV/XWUCRDmVDuy+mK58QAAfLgP/RPZkQDcV+odf2eaI3vR CVt0nxWq4RDf6jARMPtQRO9k+BROvoNON0UGFeOeeX3AXGd46gw/DqrAiswb PsYfM5FSmirWAjB6vQ0A4+nZsVfSPyazA2/XZJ6oIGjiS3RVLDFB+ZrLZO7C +/XBGet7LUjvp6F8WtQr7lBWY+i93aYeNHdmD3u7hIypSgyNqbWvpjM9xZR1 nJLvoUan/qG96bvAGWyJQz1CSmEfYxJeFTooOZTeCXTKu+bGwQxFqsam4JoJ Og4t7vlo0zA4LRrT6q/8SdO3u1cPf6CZJ1LY4uPmNlu8FsBQpk44ILsCY3hY wj49JVGistxK3ADJSPxxJRs/Tuh53lvBYaY5D16sMLVw98lhEBXEyTH6ivII cUc60HK/v91iVFef2oVNBlVtxIMHK9PXxIBfnmLffjcRcl22w9crvtUuz9ts ime/ebMiFTUnK/xUqrDbjgvgBDWkpdvYb7Mq/koGhG+7TJXx5cEktd1q0rvr WWaphubYPXTfPF/UCjX73jAKIMav8Frl+LbKzZyQtNuJbdwI8s9DrbTaMVKa 711Du6G+YzccAZ4BdKk32+8xuNtblnnEanbLHdrhwwuTBpsb+ynrtf2yCqix yHW7DSeK19y+aEu0PurBvOUMmu41viUQQEd4aXYVh8hAExpjqVVBsr3T/Ow1 Qen3 =klMb -----END PGP SIGNATURE----- _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |