diff options
| author | Alex Markuze <amarkuze@redhat.com> | 2026-05-07 08:54:07 +0000 |
|---|---|---|
| committer | Ilya Dryomov <idryomov@gmail.com> | 2026-06-22 22:45:05 +0200 |
| commit | 7e1f9e2cd2d0e780c394a4402c40e125109fec72 (patch) | |
| tree | b6904e7660d779831c8ddf859435c9b028b4dfa4 /include | |
| parent | b52861897be8a7ba563077ae62cd48158d16a5d9 (diff) | |
| download | ath-7e1f9e2cd2d0e780c394a4402c40e125109fec72.tar.gz | |
ceph: add manual reset debugfs control and tracepoints
Add the debugfs and trace plumbing used to trigger and observe
manual client reset.
The reset interface exposes a trigger file for operator-initiated
reset and a status file for tracking the most recent run. The
tracepoints record scheduling, completion, and blocked caller
behavior so reset progress can be diagnosed from the client side.
debugfs layout under /sys/kernel/debug/ceph/<client>/reset/:
trigger - write to initiate a manual reset
status - read to see the most recent reset result
The reset directory is cleaned up via debugfs_remove_recursive()
on the parent, so individual file dentries are not stored.
Tracepoints:
ceph_client_reset_schedule - reset queued
ceph_client_reset_complete - reset finished (success or failure)
ceph_client_reset_blocked - caller blocked waiting for reset
ceph_client_reset_unblocked - caller unblocked after reset
All tracepoints use a null-safe access for monc.auth->global_id
to guard against early-init or late-teardown edge cases.
Signed-off-by: Alex Markuze <amarkuze@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Diffstat (limited to 'include')
| -rw-r--r-- | include/trace/events/ceph.h | 67 |
1 files changed, 67 insertions, 0 deletions
diff --git a/include/trace/events/ceph.h b/include/trace/events/ceph.h index 08cb0659fbfc7..1b990632f62ba 100644 --- a/include/trace/events/ceph.h +++ b/include/trace/events/ceph.h @@ -226,6 +226,73 @@ TRACE_EVENT(ceph_handle_caps, __entry->mseq) ); +/* + * Client reset tracepoints - identify the client by its monitor- + * assigned global_id so traces remain meaningful when kernel pointer + * hashing is enabled. + */ +TRACE_EVENT(ceph_client_reset_schedule, + TP_PROTO(const struct ceph_mds_client *mdsc, const char *reason), + TP_ARGS(mdsc, reason), + TP_STRUCT__entry( + __field(u64, client_id) + __string(reason, reason ? reason : "") + ), + TP_fast_assign( + __entry->client_id = mdsc->fsc->client->monc.auth ? + mdsc->fsc->client->monc.auth->global_id : 0; + __assign_str(reason); + ), + TP_printk("client_id=%llu reason=%s", + __entry->client_id, __get_str(reason)) +); + +TRACE_EVENT(ceph_client_reset_complete, + TP_PROTO(const struct ceph_mds_client *mdsc, int ret), + TP_ARGS(mdsc, ret), + TP_STRUCT__entry( + __field(u64, client_id) + __field(int, ret) + ), + TP_fast_assign( + __entry->client_id = mdsc->fsc->client->monc.auth ? + mdsc->fsc->client->monc.auth->global_id : 0; + __entry->ret = ret; + ), + TP_printk("client_id=%llu ret=%d", __entry->client_id, __entry->ret) +); + +TRACE_EVENT(ceph_client_reset_blocked, + TP_PROTO(const struct ceph_mds_client *mdsc, int blocked_count), + TP_ARGS(mdsc, blocked_count), + TP_STRUCT__entry( + __field(u64, client_id) + __field(int, blocked_count) + ), + TP_fast_assign( + __entry->client_id = mdsc->fsc->client->monc.auth ? + mdsc->fsc->client->monc.auth->global_id : 0; + __entry->blocked_count = blocked_count; + ), + TP_printk("client_id=%llu blocked_count=%d", __entry->client_id, + __entry->blocked_count) +); + +TRACE_EVENT(ceph_client_reset_unblocked, + TP_PROTO(const struct ceph_mds_client *mdsc, int ret), + TP_ARGS(mdsc, ret), + TP_STRUCT__entry( + __field(u64, client_id) + __field(int, ret) + ), + TP_fast_assign( + __entry->client_id = mdsc->fsc->client->monc.auth ? + mdsc->fsc->client->monc.auth->global_id : 0; + __entry->ret = ret; + ), + TP_printk("client_id=%llu ret=%d", __entry->client_id, __entry->ret) +); + #undef EM #undef E_ #endif /* _TRACE_CEPH_H */ |