[LU-5905] Interop 2.6.0<->master conf-sanity test_56: import is not in FULL state Created: 11/Nov/14 Updated: 15/Jan/15 Resolved: 15/Jan/15 |
|
| Status: | Closed |
| Project: | Lustre |
| Component/s: | None |
| Affects Version/s: | Lustre 2.7.0, Lustre 2.5.4 |
| Fix Version/s: | Lustre 2.7.0, Lustre 2.5.4 |
| Type: | Bug | Priority: | Minor |
| Reporter: | Maloo | Assignee: | WC Triage |
| Resolution: | Fixed | Votes: | 0 |
| Labels: | None | ||
| Environment: |
server: 2.6.0 |
||
| Severity: | 3 |
| Rank (Obsolete): | 16495 |
| Description |
|
This issue was created by maloo for sarah <sarah@whamcloud.com> This issue relates to the following test suite run: https://testing.hpdd.intel.com/test_sets/ecdcd6b4-68fc-11e4-9444-5254006e85c2. The sub-test test_56 failed with the following error: import is not in FULL state 22:59:25:Lustre: DEBUG MARKER: lctl set_param -n mdt.lustre*.enable_remote_dir=1 22:59:25:LustreError: 14098:0:(osd_io.c:1273:osd_ldiskfs_read()) lustre-MDT0000: can't read 8@8000 on ino 106: rc = 0 22:59:25:LustreError: 14098:0:(osp_dev.c:188:osp_init_last_objid()) lustre-OST03e8-osc-MDT0000: can't initialize lov_objid: rc = -14 22:59:25:LustreError: 14098:0:(osp_dev.c:242:osp_last_used_init()) lustre-OST03e8-osc-MDT0000: Can not get ids -14 from old objid! 22:59:25:LustreError: 14098:0:(obd_config.c:568:class_setup()) setup lustre-OST03e8-osc-MDT0000 failed (-14) 22:59:25:LustreError: 14098:0:(obd_config.c:1720:class_config_llog_handler()) MGC10.2.4.225@tcp: cfg command failed: rc = -14 22:59:25:Lustre: cmd=cf003 0:lustre-OST03e8-osc-MDT0000 1:lustre-OST03e8_UUID 2:10.2.4.226@tcp 22:59:25: 22:59:25:LustreError: 13810:0:(mgc_request.c:517:do_requeue()) failed processing log: -14 22:59:25:Lustre: DEBUG MARKER: /usr/sbin/lctl get_param -n version 22:59:25:Lustre: DEBUG MARKER: /usr/sbin/lctl get_param -n version 22:59:25:Lustre: DEBUG MARKER: lctl list_param osc.lustre-OST*-osc > /dev/null 2>&1 22:59:25:Lustre: DEBUG MARKER: lctl get_param -n at_min 22:59:25:Lustre: DEBUG MARKER: PATH=/usr/lib64/lustre/tests:/usr/lib/lustre/tests:/usr/lib64/lustre/tests:/opt/iozone/bin:/usr/lib64/lustre/tests//usr/lib64/lustre/tests:/usr/lib64/lustre/tests:/usr/lib64/lustre/tests/../utils:/opt/iozone/bin:/usr/lib64/lustre/tests/mpi:/usr/lib64/lust 22:59:25:Lustre: DEBUG MARKER: /usr/sbin/lctl mark osc.lustre-OST2710-osc-MDT0000.ost_server_uuid in FULL state after 0 sec 22:59:25:Lustre: DEBUG MARKER: /usr/sbin/lctl mark osc.lustre-OST2710-osc-MDT0000.ost_server_uuid in FULL state after 0 sec 22:59:25:Lustre: DEBUG MARKER: osc.lustre-OST2710-osc-MDT0000.ost_server_uuid in FULL state after 0 sec 22:59:25:Lustre: DEBUG MARKER: osc.lustre-OST2710-osc-MDT0000.ost_server_uuid in FULL state after 0 sec 23:00:27:Lustre: DEBUG MARKER: /usr/sbin/lctl get_param -n version 23:00:27:Lustre: DEBUG MARKER: /usr/sbin/lctl get_param -n version 23:00:27:Lustre: DEBUG MARKER: lctl list_param osc.lustre-OST*-osc > /dev/null 2>&1 23:00:27:Lustre: DEBUG MARKER: lctl get_param -n at_min 23:00:27:Lustre: DEBUG MARKER: PATH=/usr/lib64/lustre/tests:/usr/lib/lustre/tests:/usr/lib64/lustre/tests:/opt/iozone/bin:/usr/lib64/lustre/tests//usr/lib64/lustre/tests:/usr/lib64/lustre/tests:/usr/lib64/lustre/tests/../utils:/opt/iozone/bin:/usr/lib64/lustre/tests/mpi:/usr/lib64/lust 23:00:27:Lustre: DEBUG MARKER: /usr/sbin/lctl mark rpc : @@@@@@ FAIL: can\'t put import for osc.lustre-OST03e8-osc-MDT0000.ost_server_uuid into FULL state after 40 sec, have 23:00:27:Lustre: DEBUG MARKER: /usr/sbin/lctl mark rpc : @@@@@@ FAIL: can\'t put import for osc.lustre-OST03e8-osc-MDT0000.ost_server_uuid into FULL state after 40 sec, have 23:00:27:Lustre: DEBUG MARKER: rpc : @@@@@@ FAIL: can't put import for osc.lustre-OST03e8-osc-MDT0000.ost_server_uuid into FULL state after 40 sec, have Info required for matching: conf-sanity 56 |
| Comments |
| Comment by Andreas Dilger [ 12/Nov/14 ] |
|
It looks like there was a patch landed to change this test v2_6_53_0-29-g3dc2329: commit 3dc232918c7c9b95398ac6a0dc4c2130adc2851d
Author: Li Wei <wei.g.li@intel.com>
Date: Wed Sep 24 12:12:37 2014 +0800
LU-5654 osd-ldiskfs: Handle holes in osd_ldiskfs_read()
Current osd_ldiskfs_read() incorrectly returns zero and leaves the
corresponding portion of the buffer untouched when a block to be read
is not allocated.
Test-Parameters: testlist=conf-sanity,conf-sanity,conf-sanity,conf-sanity,conf-sanity
Change-Id: I3044f771fccfdddf1fee0c931e8996cbdd8df0c8
Signed-off-by: Li Wei <wei.g.li@intel.com>
Reviewed-on: http://review.whamcloud.com/12145
Is it possible this patch is causing the 2.6 server to fail? |
| Comment by Jian Yu [ 02/Dec/14 ] |
|
Lustre client build: https://build.hpdd.intel.com/job/lustre-b2_5/104 conf-sanity test 56 hit the same failure: |
| Comment by Gerrit Updater [ 12/Dec/14 ] |
|
Jian Yu (jian.yu@intel.com) uploaded a new patch: http://review.whamcloud.com/13045 |
| Comment by Gerrit Updater [ 12/Dec/14 ] |
|
Jian Yu (jian.yu@intel.com) uploaded a new patch: http://review.whamcloud.com/13046 |
| Comment by Gerrit Updater [ 26/Dec/14 ] |
|
Oleg Drokin (oleg.drokin@intel.com) merged in patch http://review.whamcloud.com/13045/ |
| Comment by Gerrit Updater [ 15/Jan/15 ] |
|
Oleg Drokin (oleg.drokin@intel.com) merged in patch http://review.whamcloud.com/13046/ |
| Comment by Jian Yu [ 15/Jan/15 ] |
|
Patches landed to master and b2_5 branches. |