Ceph » CephFS

2020-02-29T08:18:13.932 INFO:tasks.mds_thrash.fs.[cephfs]:mds.a has gained rank=0, replacing gid=4541
2020-02-29T08:18:13.932 INFO:tasks.mds_thrash.fs.[cephfs]:waiting for 9 secs before reviving mds.b
...
2020-02-29T08:22:55.701 INFO:teuthology.orchestra.run.smithi197.stdout:2020-02-29T08:19:18.807316+0000 mon.b (mon.0) 202 : cluster [WRN] Health check failed: 1 clients failing to respond to capability release (MDS_CLIENT_LATE_RELEASE)

From: /ceph/teuthology-archive/pdonnell-2020-02-29_02:56:38-kcephfs-wip-pdonnell-testing-20200229.001503-distro-basic-smithi/4810918/1$

Failure: "2020-02-29T08:19:18.807316+0000 mon.b (mon.0) 202 : cluster [WRN] Health check failed: 1 clients failing to respond to capability release (MDS_CLIENT_LATE_RELEASE)" in cluster log
2 jobs: ['4810918', '4811103']
suites intersection: ['clusters/1-mds-1-client.yaml', 'conf/{client.yaml', 'k-testing.yaml}', 'kcephfs/thrash/{begin.yaml', 'kclient/{mount.yaml', 'log-config.yaml', 'mds.yaml', 'mon.yaml', 'ms-die-on-skipped.yaml}}', 'objectstore-ec/filestore-xfs.yaml', 'osd-asserts.yaml', 'osd.yaml}', 'overrides/{frag_enable.yaml', 'thrash-health-whitelist.yaml', 'thrashers/mds.yaml', 'whitelist_health.yaml', 'whitelist_wrongly_marked_down.yaml}', 'workloads/kclient_workunit_suites_ffsb.yaml}']
suites union: ['clusters/1-mds-1-client.yaml', 'conf/{client.yaml', 'k-testing.yaml}', 'kcephfs/thrash/{begin.yaml', 'kclient/{mount.yaml', 'log-config.yaml', 'mds.yaml', 'mon.yaml', 'ms-die-on-skipped.yaml}}', 'objectstore-ec/filestore-xfs.yaml', 'osd-asserts.yaml', 'osd.yaml}', 'overrides/{distro/testing/{flavor/centos_latest.yaml', 'overrides/{distro/testing/{flavor/ubuntu_latest.yaml', 'overrides/{frag_enable.yaml', 'thrash-health-whitelist.yaml', 'thrashers/mds.yaml', 'whitelist_health.yaml', 'whitelist_wrongly_marked_down.yaml}', 'workloads/kclient_workunit_suites_ffsb.yaml}']

Looks like a testing kernel regression.