Am Montag 07 Januar 2008 18:05:29 schrieben Sie: > Sascha, > please roll back to patch-629. The self heal changes are half done. In the > mean time, can you open the core with gdb : > > gdb -c /core.PID glusterfs > > and at the gdb prompt: > > (gdb) bt > > and give us this output. it will be of great help. > avati here your go; hmm, doesn't look very much different to what was in the logfile: Core was generated by `[glusterfs] '. Program terminated with signal 11, Segmentation fault. #0 0x00002aaaaaab2dec in client_protocol_xfer () from /usr/lib/glusterfs/1.3.8/xlator/protocol/client.so (gdb) bt #0 0x00002aaaaaab2dec in client_protocol_xfer () from /usr/lib/glusterfs/1.3.8/xlator/protocol/client.so #1 0x00002aaaaabc4499 in afr_setdents () from /usr/lib/glusterfs/1.3.8/xlator/cluster/afr.so #2 0x00002aaaaace3d7b in unify_sh_ns_getdents_cbk () from /usr/lib/glusterfs/1.3.8/xlator/cluster/unify.so #3 0x00002aaaaabc4c4b in afr_getdents_cbk () from /usr/lib/glusterfs/1.3.8/xlator/cluster/afr.so #4 0x00002aaaaaab0db3 in fini () from /usr/lib/glusterfs/1.3.8/xlator/protocol/client.so #5 0x00002aaaaaab196c in notify () from /usr/lib/glusterfs/1.3.8/xlator/protocol/client.so #6 0x00002b1218a565df in sys_epoll_iteration () from /usr/lib/libglusterfs.so.0 #7 0x00002b1218a55a75 in poll_iteration () from /usr/lib/libglusterfs.so.0 #8 0x000000000040338d in main () (gdb) Cheers, Sascha > > 2008/1/7, Sascha Ottolski <ottolski@xxxxxx>: > > Am Montag 07 Januar 2008 17:39:15 schrieben Sie: > > > Sascha, > > > these patches are still not final (self heal enhancements are on the > > > > way) > > > > > but, as-is they should be stable. > > > > thanks, but I think there is a problem :-( just gave'em a whirl, but the > > client would segfault on first acces of the mount point: > > > > --------- > > got signal (11), printing backtrace > > --------- > > /lib/libc.so.6[0x2b15ff9f9110] > > /usr/lib/glusterfs/1.3.8/xlator/protocol/client.so[0x2aaaaaab2dec] > > /usr/lib/glusterfs/1.3.8/xlator/cluster/afr.so(afr_setdents+0x1b9) > > [0x2aaaaabc4499] > > > > /usr/lib/glusterfs/1.3.8/xlator/cluster/unify.so(unify_sh_ns_getdents_cbk > >+0x15b) [0x2aaaaace3d7b] > > /usr/lib/glusterfs/1.3.8/xlator/cluster/afr.so(afr_getdents_cbk+0x20b) > > [0x2aaaaabc4c4b] > > /usr/lib/glusterfs/1.3.8/xlator/protocol/client.so[0x2aaaaaab0db3] > > /usr/lib/glusterfs/1.3.8/xlator/protocol/client.so(notify+0x8fc) > > [0x2aaaaaab196c] > > /usr/lib/libglusterfs.so.0(sys_epoll_iteration+0xbf)[0x2b15ff47c5df] > > /usr/lib/libglusterfs.so.0(poll_iteration+0x75)[0x2b15ff47ba75] > > glusterfs(main+0x39d)[0x40338d] > > /lib/libc.so.6(__libc_start_main+0xda)[0x2b15ff9e64ca] > > glusterfs[0x402f5a] > > > > > > Let me know if I can help tracking it down. > > > > > > Cheers, Sascha > > > > > avati > > > > > > 2008/1/7, Sascha Ottolski <ottolski@xxxxxx>: > > > > Hi, > > > > > > > > does anyone know if the patches 629 till 633 can be considered > > > > stable? they > > > > sound as if they could increase performance, is this the case? > > > > > > > > > > > > Thanks a lot, > > > > > > > > Sascha > > > > > > > > > > > > _______________________________________________ > > > > Gluster-devel mailing list > > > > Gluster-devel@xxxxxxxxxx > > > > http://lists.nongnu.org/mailman/listinfo/gluster-devel
