On 08/14/2019 02:09 PM, Mike Christie wrote: > On 08/14/2019 07:35 AM, Marc Schöchlin wrote: >>>> 3. I wonder if we are hitting a bug with PF_MEMALLOC Ilya hit with krbd. >>>> He removed that code from the krbd. I will ping him on that. >> >> Interesting. I activated Coredumps for that processes - probably we can >> find something interesting here... >> > > Can you replicate the problem with timeout=0 on a 4.4 kernel (ceph > version does not matter as long as its known to hit the problem). When > you start to see IO hang and it gets jammed up can you do: > > dmesg -c; echo w >/proc/sysrq-trigger; dmesg -c >waiting-tasks.txt > > and give me the waiting-tasks.txt so I can check if we are stuck in the > kernel waiting for memory. Don't waste your time. I found a way to replicate it now. _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com