Description of problem: When tried to rm -rf a folder from an nfs client, a specific brick crashed the folder was sitting on a non-replicated volume. We are able to see the folders on all the bricks. rm over nfs and crash brick is very consistent and reproducible. We were able to rm that folder over glusterfs mount Version-Release number of selected component (if applicable): 3.5.2 How reproducible: Steps to Reproduce: 1. rm -rf <folder> 2. brick crash 3. gluster volume <vol> start force Actual results: Expected results: Additional info: rm error http://fpaste.org/199727/70542214/ crash log http://fpaste.org/199708/14267042/
When tried to remove another folder over glusterfs it crashed a brick too This time we getting these error: rm: cannot remove `qa_trunk.old/qa_trunk/externals/shipserv_api/.svn/text-base': Transport endpoint is not connected rm: cannot remove `qa_trunk.old/qa_trunk/externals/shipserv_api/.svn/prop-base': Transport endpoint is not connected rm: cannot remove `qa_trunk.old/qa_trunk/externals/shipserv_api/.svn/props': Transport endpoint is not connected rm: cannot remove `qa_trunk.old/qa_trunk/externals/shipserv_api/.svn/tmp/text-base': Transport endpoint is not connected rm: cannot remove `qa_trunk.old/qa_trunk/externals/shipserv_api/.svn/tmp/prop-base': Transport endpoint is not connected rm: cannot remove `qa_trunk.old/qa_trunk/externals/shipserv_api/.svn/tmp/props': Transport endpoint is not connected same crash pattern [2015-03-18 19:38:14.507657] W [quota.c:3669:quota_statfs_validate_cbk] 0-sas01-quota: quota context is not present in inode (gfid:00000000-0000-0000-0000-000000000001) pending frames: frame : type(0) op(0) patchset: git://git.gluster.com/glusterfs.git signal received: 11 time of crash: 2015-03-18 19:38:17configuration details: argp 1 backtrace 1 dlfcn 1 fdatasync 1 libpthread 1 llistxattr 1 setfsid 1 spinlock 1 epoll.h 1 xattr.h 1 st_atim.tv_nsec 1 package-string: glusterfs 3.5.2 /lib/x86_64-linux-gnu/libc.so.6(+0x36150)[0x7f62349c6150] /lib/x86_64-linux-gnu/libc.so.6(+0x162761)[0x7f6234af2761] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/features/marker.so(mq_loc_fill_from_name+0x89)[0x7f622b393c59] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/features/marker.so(mq_readdir_cbk+0x21f)[0x7f622b39473f] /usr/lib/x86_64-linux-gnu/libglusterfs.so.0(default_readdir_cbk+0xc2)[0x7f62353b7292] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/performance/io-threads.so(iot_readdir_cbk+0xc2)[0x7f622b7b3c02] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/features/access-control.so(posix_acl_readdir_cbk+0xc2)[0x7f622bbe4ca2] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/storage/posix.so(posix_do_readdir+0x1b8)[0x7f62303688c8] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/storage/posix.so(posix_readdir+0x13)[0x7f6230368d43] /usr/lib/x86_64-linux-gnu/libglusterfs.so.0(default_readdir+0x88)[0x7f62353c0c58] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/features/access-control.so(posix_acl_readdir+0x23c)[0x7f622bbe708c] /usr/lib/x86_64-linux-gnu/libglusterfs.so.0(default_readdir+0x88)[0x7f62353c0c58] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/performance/io-threads.so(iot_readdir_wrapper+0x150)[0x7f622b7b7a80] /usr/lib/x86_64-linux-gnu/libglusterfs.so.0(call_resume+0x1c5)[0x7f62353d6235] /usr/lib/x86_64-linux-gnu/glusterfs/3.5.2/xlator/performance/io-threads.so(iot_worker+0x146)[0x7f622b7bba66] /lib/x86_64-linux-gnu/libpthread.so.0(+0x7e9a)[0x7f6234d56e9a] /lib/x86_64-linux-gnu/libc.so.6(clone+0x6d)[0x7f6234a838bd] ---------
Created attachment 1005506 [details] Core file on brick crash on Mar 18
Should be fixed in recent versions. *** This bug has been marked as a duplicate of bug 1144315 ***