Chuck Lever writes via Kernel.org Bugzilla: During server operation, you can capture trace events that might lead up to the hang with this command: # trace-cmd record -e nfsd:nfsd_cb_\* -e sunrpc:svc_xprt_detach -p function -l nfsd4_destroy_session These events are infrequent and tracing is lightweight, so this capture won't be a burden. When a server hang is observed, typically, "INFO: task has been blocked for 120 seconds" appears in the server's system journal. Basic collection instructions are: # rpcdebug -m rpc -c && echo t > /proc/sysrq-trigger Then stop the trace and package trace.dat and the system journal and attach them to this bug. View: https://bugzilla.kernel.org/show_bug.cgi?id=219710#c2 You can reply to this message to join the discussion. -- Deet-doot-dot, I am a bot. Kernel.org Bugzilla (bugspray 0.1-dev)
