Hi,
I'm not a GFS expert either :-) In fact, I erased all the configuration of the cluster and try to do it again from scratch with luci/ricci configuration tools (perhaps I did something wrong last time)
mount -vv gives the following information: [root@node1 gfs]# mount -t gfs -vv /dev/home2/home2 /home2 /sbin/mount.gfs: mount /dev/mapper/home2-home2 /home2 /sbin/mount.gfs: parse_opts: opts = "rw" /sbin/mount.gfs: clear flag 1 for "rw", flags = 0 /sbin/mount.gfs: parse_opts: flags = 0 /sbin/mount.gfs: parse_opts: extra = "" /sbin/mount.gfs: parse_opts: hostdata = "" /sbin/mount.gfs: parse_opts: lockproto = "" /sbin/mount.gfs: parse_opts: locktable = "" /sbin/mount.gfs: message to gfs_controld: asking to join mountgroup: /sbin/mount.gfs: write "join /home2 gfs lock_dlm gfs-test:gfs-data rw /dev/mapper/home2-home2" ...
And hangs at that point (On the other node it happens the same)
I tried it turning off the local firewalls on the nodes and they reached each other without problem with pings. Also, there are no more firewalls between them.
The new configuration is more simple: [root@node1 gfs]# more /etc/cluster/cluster.conf <?xml version="1.0"?> <cluster alias="gfs-test" config_version="6" name="gfs-test"> <fence_daemon clean_start="0" post_fail_delay="0" post_join_delay="3"/> <clusternodes> <clusternode name="node1.fib.upc.es" nodeid="1" votes="1"> <fence> <method name="1"> <device name="test" nodename="node1.fib.upc.es"/> </method> </fence> </clusternode> <clusternode name="node2.fib.upc.es" nodeid="2" votes="1"> <fence> <method name="1"> <device name="test" nodename="node2.fib.upc.es"/> <device name="test" nodename="node2.fib.upc.es"/> </method> </fence> </clusternode> </clusternodes> <cman expected_votes="1" two_node="1"/> <fencedevices> <fencedevice agent="fence_manual" name="test"/> </fencedevices> <rm> <failoverdomains/> <resources> <clusterfs device="/dev/home2/home2" force_unmount="0" fsid="3280" fstype="gfs" mountpoint="/home2" name="home" self_fence="0"/> </resources> </rm> </cluster>
Finally, I reformatted /dev/home2/home2 with the following command that gave no errors but it doesn't affect the final result: gfs_mkfs -O -j 3 -p lock_dlm -t gfs-test:gfs-data /dev/home2/home2
Thanks,
Sandra
PD: I append an strace but I can't see anything useful.
[root@node1 gfs]# strace mount /home2 execve("/bin/mount", ["mount", "/home2"], [/* 17 vars */]) = 0 brk(0) = 0x9874000 access("/etc/ld.so.preload", R_OK) = -1 ENOENT (No such file or directory) open("/etc/ld.so.cache", O_RDONLY) = 3 fstat64(3, {st_mode=S_IFREG|0644, st_size=26154, ...}) = 0 mmap2(NULL, 26154, PROT_READ, MAP_PRIVATE, 3, 0) = 0xb7f51000 close(3) = 0 open("/lib/libblkid.so.1", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0\300 O\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0755, st_size=38620, ...}) = 0 mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7f50000 mmap2(0x4f0000, 40000, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x4f0000 mmap2(0x4f9000, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x8) = 0x4f9000 close(3) = 0 open("/lib/libuuid.so.1", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0\340\316V\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0755, st_size=15704, ...}) = 0 mmap2(0x56c000, 12792, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x56c000 mmap2(0x56f000, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x3) = 0x56f000 close(3) = 0 open("/lib/libselinux.so.1", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0000\245T\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0755, st_size=93508, ...}) = 0 mmap2(0x547000, 97112, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x547000 mmap2(0x55d000, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x15) = 0x55d000 close(3) = 0 open("/lib/libc.so.6", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0\340_8\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0755, st_size=1611564, ...}) = 0 mmap2(0x370000, 1328580, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x370000 mmap2(0x4af000, 12288, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x13f) = 0x4af000 mmap2(0x4b2000, 9668, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x4b2000 close(3) = 0 open("/lib/libdevmapper.so.1.02", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0\300\220M\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0555, st_size=98576, ...}) = 0 mmap2(0x4d6000, 95648, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x4d6000 mmap2(0x4ec000, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x16) = 0x4ec000 close(3) = 0 open("/lib/libdl.so.2", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0PzK\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0755, st_size=16428, ...}) = 0 mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7f4f000 mmap2(0x4b7000, 12408, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x4b7000 mmap2(0x4b9000, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1) = 0x4b9000 close(3) = 0 open("/lib/libsepol.so.1", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0\20\37P\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0755, st_size=245376, ...}) = 0 mmap2(0x4ff000, 285024, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x4ff000 mmap2(0x53a000, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x3b) = 0x53a000 mmap2(0x53b000, 39264, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x53b000 close(3) = 0 open("/lib/librt.so.1", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0\200(V\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0755, st_size=44060, ...}) = 0 mmap2(0x561000, 33324, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x561000 mmap2(0x568000, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x6) = 0x568000 close(3) = 0 open("/lib/libpthread.so.0", O_RDONLY) = 3 read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0@\30L\0004\0\0\0"..., 512) = 512 fstat64(3, {st_mode=S_IFREG|0755, st_size=129716, ...}) = 0 mmap2(0x4bd000, 90596, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x4bd000 mmap2(0x4d0000, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x13) = 0x4d0000 mmap2(0x4d2000, 4580, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x4d2000 close(3) = 0 mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7f4e000 mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7f4d000 set_thread_area({entry_number:-1 -> 6, base_addr:0xb7f4d710, limit:1048575, seg_32bit:1, contents:0, read_exec_only:0, limit_in_pages:1, seg_not_present:0, useable:1}) = 0 mprotect(0x4af000, 8192, PROT_READ) = 0 mprotect(0x367000, 4096, PROT_READ) = 0 mprotect(0x4b9000, 4096, PROT_READ) = 0 mprotect(0x568000, 4096, PROT_READ) = 0 mprotect(0x4d0000, 4096, PROT_READ) = 0 munmap(0xb7f51000, 26154) = 0 set_tid_address(0xb7f4d758) = 3702 set_robust_list(0xb7f4d760, 0xc) = 0 futex(0xbfb40774, FUTEX_WAKE_PRIVATE, 1) = 0 rt_sigaction(SIGRTMIN, {0x4c13d0, [], SA_SIGINFO}, NULL, 8) = 0 rt_sigaction(SIGRT_1, {0x4c12e0, [], SA_RESTART|SA_SIGINFO}, NULL, 8) = 0 rt_sigprocmask(SIG_UNBLOCK, [RTMIN RT_1], NULL, 8) = 0 getrlimit(RLIMIT_STACK, {rlim_cur=10240*1024, rlim_max=RLIM_INFINITY}) = 0 uname({sys="Linux", node="node1.fib.upc.es", ...}) = 0 access("/etc/selinux/", F_OK) = 0 brk(0) = 0x9874000 brk(0x9895000) = 0x9895000 open("/etc/selinux/config", O_RDONLY|O_LARGEFILE) = 3 fstat64(3, {st_mode=S_IFREG|0644, st_size=448, ...}) = 0 mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7f57000 read(3, "# This file controls the state o"..., 4096) = 448 read(3, "", 4096) = 0 close(3) = 0 munmap(0xb7f57000, 4096) = 0 open("/proc/mounts", O_RDONLY|O_LARGEFILE) = 3 fstat64(3, {st_mode=S_IFREG|0444, st_size=0, ...}) = 0 mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7f57000 read(3, "rootfs / rootfs rw 0 0\n/dev/root"..., 4096) = 744 close(3) = 0 munmap(0xb7f57000, 4096) = 0 open("/selinux/mls", O_RDONLY|O_LARGEFILE) = 3 read(3, "1", 19) = 1 close(3) = 0 socket(PF_FILE, SOCK_STREAM, 0) = 3 connect(3, {sa_family=AF_FILE, path="/var/run/setrans/.setrans-unix"...}, 110) = 0 sendmsg(3, {msg_name(0)=NULL, msg_iov(5)=[{"\1\0\0\0", 4}, {"\1\0\0\0", 4}, {"\1\0\0\0", 4}, {"\0", 1}, {"\0", 1}], msg_controllen=0, msg_flags=0}, MSG_NOSIGNAL) = 14 readv(3, [{"\1\0\0\0", 4}, {"\1\0\0\0", 4}, {"\0\0\0\0", 4}], 3) = 12 readv(3, [{"\0", 1}], 1) = 1 close(3) = 0 open("/usr/lib/locale/locale-archive", O_RDONLY|O_LARGEFILE) = 3 fstat64(3, {st_mode=S_IFREG|0644, st_size=56430448, ...}) = 0 mmap2(NULL, 2097152, PROT_READ, MAP_PRIVATE, 3, 0) = 0xb7d4d000 close(3) = 0 umask(022) = 022 open("/dev/null", O_RDWR|O_LARGEFILE) = 3 close(3) = 0 getuid32() = 0 geteuid32() = 0 getgid32() = 0 getegid32() = 0 prctl(0x3, 0, 0, 0, 0) = 1 open("/etc/blkid/blkid.tab", O_RDONLY) = 3 fstat64(3, {st_mode=S_IFREG|0644, st_size=972, ...}) = 0 fcntl64(3, F_GETFL) = 0 (flags O_RDONLY) fstat64(3, {st_mode=S_IFREG|0644, st_size=972, ...}) = 0 mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7f57000 _llseek(3, 0, [0], SEEK_CUR) = 0 read(3, "<device DEVNO="0xfd03" TIME="126"..., 4096) = 972 read(3, "", 4096) = 0 close(3) = 0 munmap(0xb7f57000, 4096) = 0 getuid32() = 0 geteuid32() = 0 lstat64("/etc/mtab", {st_mode=S_IFREG|0644, st_size=446, ...}) = 0 readlink("/home2", 0xbfb3e637, 4096) = -1 EINVAL (Invalid argument) umask(077) = 022 open("/etc/fstab", O_RDONLY|O_LARGEFILE) = 3 umask(022) = 077 fstat64(3, {st_mode=S_IFREG|0644, st_size=1178, ...}) = 0 mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7f57000 read(3, "/dev/system/root / "..., 4096) = 1178 read(3, "", 4096) = 0 close(3) = 0 munmap(0xb7f57000, 4096) = 0 stat64("/sbin/mount.gfs", {st_mode=S_IFREG|0755, st_size=41368, ...}) = 0 clone(child_stack=0, flags=CLONE_CHILD_CLEARTID|CLONE_CHILD_SETTID|SIGCHLD, child_tidptr=0xb7f4d758) = 3703 wait4(-1,
0xbfb4028c, 0, NULL) = ? ERESTARTSYS (To be restarted)