I have set the logfile to be opened with SYNC and that seems to be giving me more consistent output I see the crash is mostly happening around queue_aio_write. Most of the time the last thing I see is this entry "librados: queue_aio_write 0x7f0928004390 completion 0x1ea65d0 write_seq 147". I've never seen it happen in a read operation. And always where there are lots of writes queued. >From adding further debug statements, I can see that the exact point of the crash is very soon after that but not at a constant point. I'm thinking that the crash is actually happening somewhere in the callback chain, although definitely before librbd callbacks are invoked as debug prints in the rados end of the callbacks shows nothing. Where is the 'top' of the callback chain on a write? I can see that librados calls librbd (which then calls the callback in tapdisk), but what calls librados? Thanks James -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
