Roger that! 2015-09-14 12:14 GMT+08:00 Shinobu Kinjo <ski...@redhat.com>:
> Before dumping core: > > ulimit -c unlimited > > After dumping core: > > gdb <path to ceph-fuse> <path to core> > > # Just do backtrace > (gdb)bt > > # There would be some signal. > Then give full output to us. > > Shinobu > > ----- Original Message ----- > From: "谷枫" <feiche...@gmail.com> > To: "Shinobu Kinjo" <ski...@redhat.com> > Cc: "Zheng Yan" <uker...@gmail.com>, "ceph-users" < > ceph-users@lists.ceph.com> > Sent: Monday, September 14, 2015 12:52:40 PM > Subject: Re: [ceph-users] ceph-fuse auto down > > Thank you Shinobu and ZhengYan. > Because the ceph cluster run on production and i can't put up with it crash > what happend everyday. > I change the kernal mount yesterday. > I will try to have a test with the logrotate and ceph-fuse on some other > server and i have to make a large number of write/read because if there is > no or less write/read,the ceph-fuse will not crash. > > @Shinobu, > Can you do me a favor to inspect the coredump with gdb, because i have > no experiences with the C、c++ and gdb. But if you very busy and have no > time do this , it's ok to me, thank you for you help. > > 2015-09-14 11:24 GMT+08:00 Shinobu Kinjo <ski...@redhat.com>: > > > Yes, that is exactly what I'm going to do. > > Thanks for your follow-up. > > > > Shinobu > > > > ----- Original Message ----- > > From: "Zheng Yan" <uker...@gmail.com> > > To: "谷枫" <feiche...@gmail.com> > > Cc: "Shinobu Kinjo" <ski...@redhat.com>, "ceph-users" < > > ceph-users@lists.ceph.com> > > Sent: Monday, September 14, 2015 12:19:44 PM > > Subject: Re: [ceph-users] ceph-fuse auto down > > > > If it's caused by ceph-fuse crash. Please enable coredump when using > > ceph-fuse. When ceph-fuse crash, use gdb to inspect the coredump and > > send calltrace to us. This will helps us to locate the bug quickly. > > > > Yan, Zheng > > >
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
