Project

General

Profile

Bug #10703

failures in libcephfs-java tests

Added by Greg Farnum about 9 years ago. Updated about 5 years ago.

Status:
Duplicate
Priority:
High
Assignee:
-
Category:
-
Target version:
-
% Done:

0%

Source:
Q/A
Tags:
Backport:
Regression:
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(FS):
Hadoop/Java
Labels (FS):
Java/Hadoop
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-28_23:04:02-fs-master-testing-basic-multi/729688/

2015-01-29T12:25:12.567 INFO:tasks.workunit.client.0.mira115.stdout:java -DCEPH_CONF_FILE=/etc/ceph/ceph.conf -Djava.library.path=/usr/lib/jni -cp /usr/share/java/junit4.jar:/usr/share/java/libcephfs.jar:/usr/share/java/libcephfs-test.jar org.junit.runner.JUnitCore com.ceph.fs.CephAllTests
2015-01-29T12:25:12.567 INFO:tasks.workunit.client.0.mira115.stdout:----------------------
2015-01-29T12:25:12.940 INFO:tasks.workunit.client.0.mira115.stdout:JUnit version 4.11
2015-01-29T12:27:16.846 INFO:tasks.workunit.client.0.mira115.stdout:...E...............................................................7dabf277-32ff-4339-998f-719b0d85ad80
2015-01-29T12:27:16.869 INFO:tasks.workunit.client.0.mira115.stdout:E.........................
2015-01-29T12:27:16.964 INFO:tasks.workunit.client.0.mira115.stdout:Time: 123.686
2015-01-29T12:27:16.964 INFO:tasks.workunit.client.0.mira115.stdout:There were 2 failures:
2015-01-29T12:27:16.964 INFO:tasks.workunit.client.0.mira115.stdout:1) test_ftruncate(com.ceph.fs.CephMountTest)
2015-01-29T12:27:16.991 INFO:tasks.workunit.client.0.mira115.stdout:java.lang.AssertionError
2015-01-29T12:27:16.991 INFO:tasks.workunit.client.0.mira115.stdout:    at org.junit.Assert.fail(Assert.java:86)
2015-01-29T12:27:16.992 INFO:tasks.workunit.client.0.mira115.stdout:    at org.junit.Assert.assertTrue(Assert.java:41)
2015-01-29T12:27:16.992 INFO:tasks.workunit.client.0.mira115.stdout:    at org.junit.Assert.assertTrue(Assert.java:52)
2015-01-29T12:27:16.992 INFO:tasks.workunit.client.0.mira115.stdout:    at com.ceph.fs.CephMountTest.test_ftruncate(CephMountTest.java:767)

.
.
.
2015-01-29T12:27:17.002 INFO:tasks.workunit.client.0.mira115.stdout:2) com.ceph.fs.CephMountTest
2015-01-29T12:27:17.003 INFO:tasks.workunit.client.0.mira115.stdout:java.io.IOException: Directory not empty
2015-01-29T12:27:17.003 INFO:tasks.workunit.client.0.mira115.stdout:    at com.ceph.fs.CephMount.native_ceph_rmdir(Native Method)
2015-01-29T12:27:17.004 INFO:tasks.workunit.client.0.mira115.stdout:    at com.ceph.fs.CephMount.rmdir(CephMount.java:392)
2015-01-29T12:27:17.004 INFO:tasks.workunit.client.0.mira115.stdout:    at com.ceph.fs.CephMountTest.destroy(CephMountTest.java:62)
.
.
.
2015-01-29T12:27:17.009 INFO:tasks.workunit.client.0.mira115.stdout:FAILURES!!!
2015-01-29T12:27:17.009 INFO:tasks.workunit.client.0.mira115.stdout:Tests run: 91,  Failures: 2
2015-01-29T12:27:17.009 INFO:tasks.workunit.client.0.mira115.stdout:
2015-01-29T12:27:17.011 INFO:tasks.workunit:Stopping ['libcephfs-java/test.sh'] on client.0...
2015-01-29T12:27:17.011 INFO:teuthology.orchestra.run.mira115:Running: 'rm -rf -- /home/ubuntu/cephtest/workunits.list /home/ubuntu/cephtest/workunit.client.0'
2015-01-29T12:27:17.097 ERROR:teuthology.parallel:Exception in parallel execution
Traceback (most recent call last):
  File "/home/teuthworker/src/teuthology_master/teuthology/parallel.py", line 82, in __exit__
    for result in self:
  File "/home/teuthworker/src/teuthology_master/teuthology/parallel.py", line 101, in next
    resurrect_traceback(result)
  File "/home/teuthworker/src/teuthology_master/teuthology/parallel.py", line 19, in capture_traceback
    return func(*args, **kwargs)
  File "/var/lib/teuthworker/src/ceph-qa-suite_master/tasks/workunit.py", line 359, in _run_tests
    args=args,
  File "/home/teuthworker/src/teuthology_master/teuthology/orchestra/remote.py", line 128, in run
    r = self._runner(client=self.ssh, name=self.shortname, **kwargs)
  File "/home/teuthworker/src/teuthology_master/teuthology/orchestra/run.py", line 368, in run
    r.wait()
  File "/home/teuthworker/src/teuthology_master/teuthology/orchestra/run.py", line 106, in wait
    exitstatus=status, node=self.hostname)
CommandFailedError: Command failed on mira115 with status 1: 'mkdir -p -- /home/ubuntu/cephtest/mnt.0/client.0/tmp && cd -- /home/ubuntu/cephtest/mnt.0/client.0/tmp && CEPH_CLI_TEST_DUP_COMMAND=1 CEPH_REF=94bb26524386d62f6b71314c43fc0e3d88e31b35 TESTDIR="/home/ubuntu/cephtest" CEPH_ID="0" adjust-ulimits ceph-coverage /home/ubuntu/cephtest/archive/coverage timeout 3h /home/ubuntu/cephtest/workunit.client.0/libcephfs-java/test.sh'

The libcephfs-java tests haven't been running reliably in quite a while thanks to package issues, so this could be a real bug which has been around for a while?

History

#1 Updated by Zheng Yan about 9 years ago

  • Status changed from New to 12

looks like the ftruncate failure is caused by out-of-order cap message (mds processes setattr request and cap message in wrong order). but For some unknown reason, the corresponding MDS log is missing (the first request in MDS log is 4139:23)

#2 Updated by Greg Farnum about 9 years ago

Are we supposed to provide any sort of ordering on MClientCap versus MClientRequest messages? Truncate and length issues should be covered with the truncate_seq etc values.

And what exactly did you see that's causing the break?

#3 Updated by Zheng Yan about 9 years ago

2015-01-29 12:25:19.350635 7fb060fc1700 10 client.4139 _setattr mask 32 issued pAsxLsXsxFsxcrwb
2015-01-29 12:25:19.350647 7fb060fc1700 10 client.4139 choose_target_mds from caps on inode 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pAsxLsXsxFsxcrwb(0=pAsxLsXsxFsxcrwb) dirty_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0)
2015-01-29 12:25:19.350658 7fb060fc1700 10 client.4139 send_request rebuilding request 5 for mds.0
2015-01-29 12:25:19.350666 7fb060fc1700 10 client.4139 send_request client_request(unknown.0:5 setattr size=333333 #100000003eb 2015-01-29 12:25:19.350645) v2 to mds.0
2015-01-29 12:25:19.350671 7fb060fc1700  1 -- 10.214.137.128:0/1758282524 --> 10.214.131.14:6808/31633 -- client_request(client.4139:5 setattr size=333333 #100000003eb 2015-01-29 12:25:19.350645) v2 -- ?+0 0x7fb0587741e0 con 0x7fb05814a860
2015-01-29 12:25:19.352365 7fafdeffd700  1 -- 10.214.137.128:0/1758282524 <== mds.0 10.214.131.14:6808/31633 9 ==== client_caps(revoke ino 100000003eb 14 seq 3 caps=pLsXsFsxcwb dirty=- wanted=- follows 0 size 0/4194304 ts 1 mtime 2015-01-29 12:25:17.989149) v5 ==== 196+0+0 (2924960165 0 0) 0x7fafcc0025a0 con 0x7fb05814a860
2015-01-29 12:25:19.352421 7fafdeffd700 10 client.4139  mds.0 seq now 2
2015-01-29 12:25:19.352432 7fafdeffd700  5 client.4139 handle_cap_grant on in 100000003eb mds.0 seq 3 caps now pLsXsFsxcwb was pAxLsXsxFsxcwb
2015-01-29 12:25:19.352445 7fafdeffd700 10 client.4139 update_inode_file_bits 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pAxLsXsxFsxcwb(0=pAxLsXsxFsxcwb) dirty_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) pAxLsXsxFsxcwb mtime 2015-01-29 12:25:17.989149
2015-01-29 12:25:19.352476 7fafdeffd700 10 client.4139   revocation of AxXx
2015-01-29 12:25:19.352481 7fafdeffd700 10 client.4139 check_caps on 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFsxcwb(0=pLsXsFsxcwb) dirty_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) wanted pAsxXsxFsxcrwb used - is_delayed=0
2015-01-29 12:25:19.352504 7fafdeffd700 10 client.4139 cap_delay_requeue on 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFsxcwb(0=pLsXsFsxcwb) dirty_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0)
2015-01-29 12:25:19.352526 7fafdeffd700 10 client.4139  cap mds.0 issued pLsXsFsxcwb implemented pAxLsXsxFsxcwb revoking AxXx
2015-01-29 12:25:19.352538 7fafdeffd700 10 client.4139 completed revocation of AxXx
2015-01-29 12:25:19.352545 7fafdeffd700 10 client.4139 mark_caps_flushing Fw 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFsxcwb(0=pLsXsFsxcwb) dirty_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0)
2015-01-29 12:25:19.352565 7fafdeffd700 10 client.4139 send_cap 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFsxcwb(0=pLsXsFsxcwb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) mds.0 seq 3 used - want pAsxXsxFsxcrwb flush Fw retain pAsLsxXsFsxcrwbl held pAxLsXsxFsxcwb revoking AxXx dropping -
2015-01-29 12:25:19.364141 7fafdeffd700  1 -- 10.214.137.128:0/1758282524 --> 10.214.131.14:6808/31633 -- client_caps(update ino 100000003eb 14 seq 3 tid 1 caps=pLsXsFsxcwb dirty=Fw wanted=pAsxXsxFsxcrwb follows 1 size 1398331/4095 ts 1 mtime 2015-01-29 12:25:19.342951) v5 -- ?+0 0x7fafd8010d90 con 0x7fb05814a860
2015-01-29 12:25:19.364191 7fafdeffd700  1 -- 10.214.137.128:0/1758282524 <== mds.0 10.214.131.14:6808/31633 10 ==== client_caps(revoke ino 100000003eb 14 seq 4 caps=pLsXsFcb dirty=- wanted=- follows 0 size 0/4194304 ts 1 mtime 2015-01-29 12:25:17.989149) v5 ==== 196+0+0 (2741223658 0 0) 0x7fafcc0008c0 con 0x7fb05814a860
2015-01-29 12:25:19.364205 7fafdeffd700 10 client.4139  mds.0 seq now 3
2015-01-29 12:25:19.364210 7fafdeffd700  5 client.4139 handle_cap_grant on in 100000003eb mds.0 seq 4 caps now pLsXsFcb was pLsXsFsxcwb
2015-01-29 12:25:19.364219 7fafdeffd700 10 client.4139 update_inode_file_bits 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFsxcwb(0=pLsXsFsxcwb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) pLsXsFsxcwb mtime 2015-01-29 12:25:17.989149
2015-01-29 12:25:19.364241 7fafdeffd700 10 client.4139   revocation of Fsxw
2015-01-29 12:25:19.364242 7fafdeffd700 10 client.4139 check_caps on 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFcb(0=pLsXsFcb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) wanted pAsxXsxFsxcrwb used - is_delayed=0
2015-01-29 12:25:19.364253 7fafdeffd700 10 client.4139 cap_delay_requeue on 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFcb(0=pLsXsFcb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0)
2015-01-29 12:25:19.364260 7fafdeffd700 10 client.4139  cap mds.0 issued pLsXsFcb implemented pLsXsFsxcwb revoking Fsxw
2015-01-29 12:25:19.364265 7fafdeffd700 10 client.4139 completed revocation of Fsxw
2015-01-29 12:25:19.364266 7fafdeffd700 10 client.4139 send_cap 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFcb(0=pLsXsFcb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) mds.0 seq 4 used - want pAsxXsxFsxcrwb flush - retain pAsxLsxXsxFcrbl held pLsXsFsxcwb revoking Fsxw dropping -
2015-01-29 12:25:19.364287 7fafdeffd700  1 -- 10.214.137.128:0/1758282524 --> 10.214.131.14:6808/31633 -- client_caps(update ino 100000003eb 14 seq 4 caps=pLsXsFcb dirty=- wanted=pAsxXsxFsxcrwb follows 0 size 1398331/4095 ts 1 mtime 2015-01-29 12:25:19.342951) v5 -- ?+0 0x7fafd82c1030 con 0x7fb05814a860
2015-01-29 12:25:19.394667 7fafdeffd700  1 -- 10.214.137.128:0/1758282524 <== mds.0 10.214.131.14:6808/31633 11 ==== client_caps(grant ino 100000003eb 14 seq 5 caps=pLsXsFcb dirty=- wanted=- follows 0 size 0/4194304 ts 1 mtime 2015-01-29 12:25:17.989149) v5 ==== 196+0+0 (88382502 0 0) 0x7fafcc002cf0 con 0x7fb05814a860
2015-01-29 12:25:19.394745 7fafdeffd700 10 client.4139  mds.0 seq now 4
2015-01-29 12:25:19.394758 7fafdeffd700  5 client.4139 handle_cap_grant on in 100000003eb mds.0 seq 5 caps now pLsXsFcb was pLsXsFcb
2015-01-29 12:25:19.394769 7fafdeffd700 10 client.4139 update_inode_file_bits 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFcb(0=pLsXsFcb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) pLsXsFcwb mtime 2015-01-29 12:25:17.989149
2015-01-29 12:25:19.394796 7fafdeffd700 10 client.4139   caps unchanged at pLsXsFcb
2015-01-29 12:25:19.394809 7fafdeffd700  1 -- 10.214.137.128:0/1758282524 <== mds.0 10.214.131.14:6808/31633 12 ==== client_reply(???:3 = 0 (0) Success safe) v1 ==== 27+0+0 (3219600132 0 0) 0x7fafcc002720 con 0x7fb05814a860
2015-01-29 12:25:19.394828 7fafdeffd700 10 client.4139 insert_trace from 2015-01-29 12:25:17.989177 mds.0 is_target=0 is_dentry=0
2015-01-29 12:25:19.394831 7fafdeffd700 10 client.4139 insert_trace -- already got unsafe; ignoring
2015-01-29 12:25:19.394834 7fafdeffd700 10 client.4139 put_inode on 100000003ea.head(ref=3 ll_ref=0 cap_refs={} open={} mode=40777 size=0/0 mtime=2015-01-29 12:25:17.989149 caps=pAsLsXsFsx(0=pAsLsXsFsx) COMPLETE parents=0x7fb058139ed0 0x7fafd8011200)
2015-01-29 12:25:23.928498 7fb01ed8d700 10 client.4139 check_caps on 100000003ea.head(ref=2 ll_ref=0 cap_refs={} open={} mode=40777 size=0/0 mtime=2015-01-29 12:25:17.989149 caps=pAsLsXsFsx(0=pAsLsXsFsx) COMPLETE parents=0x7fb058139ed0 0x7fafd8011200) wanted - used - is_delayed=1
2015-01-29 12:25:23.928548 7fb01ed8d700 10 client.4139  cap mds.0 issued pAsLsXsFsx implemented pAsLsXsFsx revoking -
2015-01-29 12:25:23.928559 7fb01ed8d700 10 client.4139 send_cap 100000003ea.head(ref=2 ll_ref=0 cap_refs={} open={} mode=40777 size=0/0 mtime=2015-01-29 12:25:17.989149 caps=pAsLsXsFsx(0=pAsLsXsFsx) COMPLETE parents=0x7fb058139ed0 0x7fafd8011200) mds.0 seq 4 used - want - flush - retain pAsLsXsFs held pAsLsXsFsx revoking - dropping Fx
2015-01-29 12:25:23.928588 7fb01ed8d700  1 -- 10.214.137.128:0/1758282524 --> 10.214.131.14:6808/31633 -- client_caps(update ino 100000003ea 13 seq 4 caps=pAsLsXsFs dirty=- wanted=- follows 0 size 0/0 ts 1 mtime 2015-01-29 12:25:17.989149) v5 -- ?+0 0x7fafd4000a30 con 0x7fb05814a860
2015-01-29 12:25:24.928678 7fb01ed8d700 10 client.4139 check_caps on 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFcb(0=pLsXsFcb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) wanted pAsxXsxFsxcrwb used - is_delayed=1
2015-01-29 12:25:24.928730 7fb01ed8d700 10 client.4139  cap mds.0 issued pLsXsFcb implemented pLsXsFcb revoking -
2015-01-29 12:25:38.931378 7fb01ed8d700 10 client.4139 renew_caps()
2015-01-29 12:25:38.931403 7fb01ed8d700 10 client.4139 renew_caps mds.0
2015-01-29 12:25:38.931408 7fb01ed8d700  1 -- 10.214.137.128:0/1758282524 --> 10.214.131.14:6808/31633 -- client_session(request_renewcaps seq 3) v2 -- ?+0 0x7fafd40012c0 con 0x7fb05814a860
2015-01-29 12:25:39.765062 7fafdeffd700  1 -- 10.214.137.128:0/1758282524 <== mds.0 10.214.131.14:6808/31633 13 ==== client_reply(???:5 = 0 (0) Success unsafe) v1 ==== 346+0+0 (4075263461 0 0) 0x7fafcc002cf0 con 0x7fb05814a860
2015-01-29 12:25:39.765132 7fafdeffd700 10 client.4139 insert_trace from 2015-01-29 12:25:19.350666 mds.0 is_target=1 is_dentry=0
2015-01-29 12:25:39.765145 7fafdeffd700 10 client.4139  features 0xffffffffffff
2015-01-29 12:25:39.765147 7fafdeffd700 10 client.4139 update_snap_trace len 48
2015-01-29 12:25:39.765153 7fafdeffd700 10 client.4139 update_snap_trace snaprealm(1 nref=4 c=0 seq=1 parent=0 my_snaps=[] cached_snapc=1=[]) seq 1 <= 1 and same parent, SKIPPING
2015-01-29 12:25:39.765160 7fafdeffd700 10 client.4139  hrm  is_target=1 is_dentry=0
2015-01-29 12:25:39.765170 7fafdeffd700 10 client.4139 update_inode_file_bits 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.342951 caps=pLsXsFcb(0=pLsXsFcb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0) pLsXsFcwb mtime 2015-01-29 12:25:19.350645
2015-01-29 12:25:39.766313 7fafdeffd700 10 client.4139 add_update_cap issued pLsXsFcb -> pAsxLsXsxFscb from mds.0 on 100000003eb.head(ref=4 ll_ref=0 cap_refs={4096=0,8192=0} open={3=1} mode=100600 size=1398331/4194304 mtime=2015-01-29 12:25:19.350645 caps=pAsxLsXsxFscb(0=pAsxLsXsxFscb) flushing_caps=Fw objectset[100000003eb ts 0/0 objects 0 dirty_or_tx 0] parents=0x7fb0582136b0 0x7fafd8013ed0)
2015-01-29 12:25:39.766391 7fb060fc1700 10 client.4139 _setattr result=0

you can see that the mds reply did not update inode's size. one likely reason is that truncate_seq was not increased. client flushed inode's Fw cap while waiting mds reply, which make me suspect the bug is caused by some kind of message order issue. but unfortunately, the corresponding part of mds log is missing

#4 Updated by Greg Farnum about 9 years ago

  • Backport set to giant

This is buggy on giant as well (and given what Zheng found out, probably Firefly?).

#5 Updated by Greg Farnum about 9 years ago

  • Priority changed from High to Urgent

Those who have access can check out http://pulpito.ceph.redhat.com/teuthology-2015-02-06_23:04:01-fs-giant-distro-basic-magna/42028/, which if we're lucky will include the necessary MDS logging.

#6 Updated by Zheng Yan about 9 years ago

It's not the same as previous one. All failure are caused by "java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path)"

#7 Updated by Greg Farnum about 9 years ago

Argh, sorry for the bad pattern matching. I wonder if that's another thing not working properly on RHEL; I'll check it out in the morning.

#8 Updated by Greg Farnum about 9 years ago

  • Priority changed from Urgent to High

Maybe we'll start seeing this again once we stop seeing the LinkErrors in #10863, but for now downgrade priority.

#9 Updated by Loïc Dachary about 9 years ago

  • Backport deleted (giant)

giant is end of life

#10 Updated by Greg Farnum almost 9 years ago

  • Status changed from 12 to Duplicate

#11 Updated by Greg Farnum over 7 years ago

  • Component(FS) Hadoop/Java added

#12 Updated by Patrick Donnelly about 5 years ago

  • Category deleted (48)
  • Labels (FS) Java/Hadoop added

Also available in: Atom PDF