ndo2db problems on solaris 10 (ndoutils 1.4b7)
Michael Prochaska
michael at prochas.net
Thu Mar 6 10:46:43 CET 2008
hello,
i've applied the two patches you sent out yesterday:
ndoutils_remove_multiple_children.patch
ndoutils_retry_on_soft_read_errors.patch
but the SIGSEGV error is still there. besides i've seen a SIGBUS error.
sometimes the nagios process dies when this signal occurs (not in this
trace).
is there anything else i can trace or try to get more useful information?
any hints or ideas?
best regards,
michael
nagios.log:
[1204796396] ndomod: Successfully reconnected to data sink! 0 items lost,
290 queued items to flush.
[1204796396] ndomod: Error writing to data sink! Some output may get
lost. 273 queued items to flush.
[1204796412] ndomod: Successfully reconnected to data sink! 0 items lost,
353 queued items to flush.
[1204796412] ndomod: Error writing to data sink! Some output may get
lost. 329 queued items to flush.
truss:
4252: accept(5, 0xFFBFF4F4, 0xFFBFF504, SOV_DEFAULT) = 6
4252: fork1() = 4622
4252: lwp_sigmask(SIG_SETMASK, 0x00000000, 0x00000000) = 0xFFBFFEFF
[0x0000FFFF]
4622: fork1() (returning as child ...) = 4252
4622: getpid() = 4622 [4252]
4252: close(6) = 0
4622: lwp_self() = 1
4622: lwp_sigmask(SIG_SETMASK, 0x00000000, 0x00000000) = 0xFFBFFEFF
[0x0000FFFF]
4622: llseek(3, 0, SEEK_CUR) = 0
4622: close(3) = 0
4622: open("/usr/local/nagios/var/ndo2db.debug",
O_RDWR|O_APPEND|O_CREAT, 0666) = 3
4622: sigaction(SIGQUIT, 0xFFBFED20, 0xFFBFEDC0) = 0
4622: sigaction(SIGTERM, 0xFFBFED20, 0xFFBFEDC0) = 0
4622: sigaction(SIGINT, 0xFFBFED20, 0xFFBFEDC0) = 0
4622: sigaction(SIGSEGV, 0xFFBFED20, 0xFFBFEDC0) = 0
4622: sigaction(SIGFPE, 0xFFBFED20, 0xFFBFEDC0) = 0
4622: open("/etc/netconfig", O_RDONLY|O_LARGEFILE) = 7
4622: fcntl(7, F_DUPFD, 0x00000100) Err#22 EINVAL
4622: read(7, " # p r a g m a i d e n".., 1024) = 1024
4622: read(7, " t s t p i _ c".., 1024) = 215
4622: read(7, 0x00040338, 1024) = 0
4622: lseek(7, 0, SEEK_SET) = 0
4622: read(7, " # p r a g m a i d e n".., 1024) = 1024
4622: read(7, " t s t p i _ c".., 1024) = 215
4622: read(7, 0x00040338, 1024) = 0
4622: close(7) = 0
4622: open("/dev/udp", O_RDONLY) = 7
4622: ioctl(7, SIOCGLIFNUM, 0xFFBFEB74) = 0
4622: close(7) = 0
4622: getuid() = 100 [100]
4622: getuid() = 100 [100]
4622: door_info(4, 0xFFBFE880) = 0
4622: door_call(4, 0xFFBFE928) = 0
4622: sigaction(SIGPIPE, 0xFFBFEBE0, 0xFFBFEC80) = 0
4622: so_socket(PF_INET, SOCK_STREAM, IPPROTO_IP, "", SOV_DEFAULT) = 7
4622: brk(0x00041D20) = 0
4622: brk(0x00045D20) = 0
4622: fcntl(7, F_SETFL, (no flags)) = 0
4622: fcntl(7, F_GETFL) = 2
4622: connect(7, 0xFFBFECC0, 16, SOV_DEFAULT) = 0
4622: setsockopt(7, SOL_SOCKET, SO_RCVTIMEO, 0xFFBFE158, 8, SOV_DEFAULT)
Err#99 ENOPROTOOPT
4622: setsockopt(7, SOL_SOCKET, SO_SNDTIMEO, 0xFFBFE158, 8, SOV_DEFAULT)
Err#99 ENOPROTOOPT
4622: brk(0x00045D20) = 0
4622: brk(0x00047D20) = 0
4622: setsockopt(7, ip, 3, 0xFFBFE23C, 4, SOV_DEFAULT) = 0
4622: setsockopt(7, tcp, TCP_NODELAY, 0xFFBFE238, 4, SOV_DEFAULT) = 0
4622: setsockopt(7, SOL_SOCKET, SO_KEEPALIVE, 0xFFBFE2AC, 4,
SOV_DEFAULT) = 0
4622: read(7, " 4\0\0\0\n 5 . 0 . 5 1\0".., 16384) = 56
4622: brk(0x00047D20) = 0
4622: brk(0x00049D20) = 0
4622: brk(0x00049D20) = 0
4622: brk(0x0004BD20) = 0
4622: stat64("/usr/local/mysql/share/mysql/charsets/Index.xml",
0xFFBFDAA8) = 0
4622: brk(0x0004BD20) = 0
4622: brk(0x0004FD20) = 0
4622: open64("/usr/local/mysql/share/mysql/charsets/Index.xml",
O_RDONLY) = 8
4622: read(8, " < ? x m l v e r s i o".., 18173) = 18173
4622: close(8) = 0
4622: brk(0x0004FD20) = 0
4622: brk(0x00051D20) = 0
4622: brk(0x00051D20) = 0
4622: brk(0x00053D20) = 0
4622: write(7, " C\0\001\rA2\0\0\0\0\0 @".., 71) = 71
4622: read(7, "07\0\002\0\0\002\0\0\0", 16384) = 11
4622: getpid() = 4622 [4252]
4622: open("/proc/4622/psinfo", O_RDONLY) = 8
4622: read(8, "02\0\0\0\0\0\001\0\0120E".., 336) = 336
4622: close(8) = 0
4622: fstat(-1, 0xFFBFE0E0) Err#9 EBADF
4622: open("/dev/conslog", O_WRONLY) = 8
4622: fcntl(8, F_SETFD, 0x00000001) = 0
4622: fstat(8, 0xFFBFE0E0) = 0
4622: fstat(8, 0xFFBFEB40) = 0
4622: time() = 1204796380
4622: open("/usr/share/lib/zoneinfo/Europe/Vienna", O_RDONLY) = 9
4622: fstat64(9, 0xFFBFDF70) = 0
4622: read(9, " T Z i f\0\0\0\0\0\0\0\0".., 801) = 801
4622: close(9) = 0
4622: getpid() = 4622 [4252]
4622: putmsg(8, 0xFFBFE1F8, 0xFFBFE1EC, 0) = 0
4622: open("/var/run/syslog_door", O_RDONLY) = 9
4622: door_info(9, 0xFFBFE130) = 0
4622: getpid() = 4622 [4252]
4622: door_call(9, 0xFFBFE118) = 0
4622: close(9) = 0
4622: read(6, "\n\n H E L L O\n P R O T".., 511) = 511
4622: getpid() = 4622 [4252]
4622: fstat64(3, 0xFFBFDF18) = 0
4622: brk(0x00053D20) = 0
4622: brk(0x00055D20) = 0
4622: fstat64(3, 0xFFBFDDC0) = 0
4622: ioctl(3, TCGETA, 0xFFBFDEA4) Err#25 ENOTTY
4622: write(3, " [ 1 2 0 4 7 9 6 3 8 0 .".., 110) = 110
4622: llseek(3, 0, SEEK_CUR) = 2979
4622: Incurred fault #5, FLTACCESS %pc = 0xFF1FDFA4
4622: siginfo: SIGBUS BUS_ADRALN addr=0x2F6E680B
4622: Received signal #10, SIGBUS [default]
4622: siginfo: SIGBUS BUS_ADRALN addr=0x2F6E680B
4252: accept(5, 0xFFBFF4F4, 0xFFBFF504, SOV_DEFAULT) (sleeping...)
4252: accept(5, 0xFFBFF4F4, 0xFFBFF504, SOV_DEFAULT) = 6
4252: fork1() = 4629
4252: lwp_sigmask(SIG_SETMASK, 0x00000000, 0x00000000) = 0xFFBFFEFF
[0x0000FFFF]
4629: fork1() (returning as child ...) = 4252
4629: getpid() = 4629 [4252]
4629: lwp_self() = 1
4629: lwp_sigmask(SIG_SETMASK, 0x00000000, 0x00000000) = 0xFFBFFEFF
[0x0000FFFF]
4252: close(6) = 0
4629: llseek(3, 0, SEEK_CUR) = 0
4629: close(3) = 0
4629: open("/usr/local/nagios/var/ndo2db.debug",
O_RDWR|O_APPEND|O_CREAT, 0666) = 3
4629: sigaction(SIGQUIT, 0xFFBFED20, 0xFFBFEDC0) = 0
4629: sigaction(SIGTERM, 0xFFBFED20, 0xFFBFEDC0) = 0
4629: sigaction(SIGINT, 0xFFBFED20, 0xFFBFEDC0) = 0
4629: sigaction(SIGSEGV, 0xFFBFED20, 0xFFBFEDC0) = 0
4629: sigaction(SIGFPE, 0xFFBFED20, 0xFFBFEDC0) = 0
4629: open("/etc/netconfig", O_RDONLY|O_LARGEFILE) = 7
4629: fcntl(7, F_DUPFD, 0x00000100) Err#22 EINVAL
4629: read(7, " # p r a g m a i d e n".., 1024) = 1024
4629: read(7, " t s t p i _ c".., 1024) = 215
4629: read(7, 0x00040338, 1024) = 0
4629: lseek(7, 0, SEEK_SET) = 0
4629: read(7, " # p r a g m a i d e n".., 1024) = 1024
4629: read(7, " t s t p i _ c".., 1024) = 215
4629: read(7, 0x00040338, 1024) = 0
4629: close(7) = 0
4629: open("/dev/udp", O_RDONLY) = 7
4629: ioctl(7, SIOCGLIFNUM, 0xFFBFEB74) = 0
4629: close(7) = 0
4629: getuid() = 100 [100]
4629: getuid() = 100 [100]
4629: door_info(4, 0xFFBFE880) = 0
4629: door_call(4, 0xFFBFE928) = 0
4629: sigaction(SIGPIPE, 0xFFBFEBE0, 0xFFBFEC80) = 0
4629: so_socket(PF_INET, SOCK_STREAM, IPPROTO_IP, "", SOV_DEFAULT) = 7
4629: brk(0x00041D20) = 0
4629: brk(0x00045D20) = 0
4629: fcntl(7, F_SETFL, (no flags)) = 0
4629: fcntl(7, F_GETFL) = 2
4629: connect(7, 0xFFBFECC0, 16, SOV_DEFAULT) = 0
4629: setsockopt(7, SOL_SOCKET, SO_RCVTIMEO, 0xFFBFE158, 8, SOV_DEFAULT)
Err#99 ENOPROTOOPT
4629: setsockopt(7, SOL_SOCKET, SO_SNDTIMEO, 0xFFBFE158, 8, SOV_DEFAULT)
Err#99 ENOPROTOOPT
4629: brk(0x00045D20) = 0
4629: brk(0x00047D20) = 0
4629: setsockopt(7, ip, 3, 0xFFBFE23C, 4, SOV_DEFAULT) = 0
4629: setsockopt(7, tcp, TCP_NODELAY, 0xFFBFE238, 4, SOV_DEFAULT) = 0
4629: setsockopt(7, SOL_SOCKET, SO_KEEPALIVE, 0xFFBFE2AC, 4,
SOV_DEFAULT) = 0
4629: read(7, " 4\0\0\0\n 5 . 0 . 5 1\0".., 16384) = 56
4629: brk(0x00047D20) = 0
4629: brk(0x00049D20) = 0
4629: brk(0x00049D20) = 0
4629: brk(0x0004BD20) = 0
4629: stat64("/usr/local/mysql/share/mysql/charsets/Index.xml",
0xFFBFDAA8) = 0
4629: brk(0x0004BD20) = 0
4629: brk(0x0004FD20) = 0
4629: open64("/usr/local/mysql/share/mysql/charsets/Index.xml",
O_RDONLY) = 8
4629: read(8, " < ? x m l v e r s i o".., 18173) = 18173
4629: close(8) = 0
4629: brk(0x0004FD20) = 0
4629: brk(0x00051D20) = 0
4629: brk(0x00051D20) = 0
4629: brk(0x00053D20) = 0
4629: write(7, " C\0\001\rA2\0\0\0\0\0 @".., 71) = 71
4629: read(7, "07\0\002\0\0\002\0\0\0", 16384) = 11
4629: getpid() = 4629 [4252]
4629: open("/proc/4629/psinfo", O_RDONLY) = 8
4629: read(8, "02\0\0\0\0\0\001\0\01215".., 336) = 336
4629: close(8) = 0
4629: fstat(-1, 0xFFBFE0E0) Err#9 EBADF
4629: open("/dev/conslog", O_WRONLY) = 8
4629: fcntl(8, F_SETFD, 0x00000001) = 0
4629: fstat(8, 0xFFBFE0E0) = 0
4629: fstat(8, 0xFFBFEB40) = 0
4629: time() = 1204796396
4629: open("/usr/share/lib/zoneinfo/Europe/Vienna", O_RDONLY) = 9
4629: fstat64(9, 0xFFBFDF70) = 0
4629: read(9, " T Z i f\0\0\0\0\0\0\0\0".., 801) = 801
4629: close(9) = 0
4629: getpid() = 4629 [4252]
4629: putmsg(8, 0xFFBFE1F8, 0xFFBFE1EC, 0) = 0
4629: open("/var/run/syslog_door", O_RDONLY) = 9
4629: door_info(9, 0xFFBFE130) = 0
4629: getpid() = 4629 [4252]
4629: door_call(9, 0xFFBFE118) = 0
4629: close(9) = 0
4629: read(6, "\n\n H E L L O\n P R O T".., 511) = 511
4629: getpid() = 4629 [4252]
4629: fstat64(3, 0xFFBFDF18) = 0
4629: brk(0x00053D20) = 0
4629: brk(0x00055D20) = 0
4629: fstat64(3, 0xFFBFDDC0) = 0
4629: ioctl(3, TCGETA, 0xFFBFDEA4) Err#25 ENOTTY
4629: write(3, " [ 1 2 0 4 7 9 6 3 9 6 .".., 110) = 110
4629: llseek(3, 0, SEEK_CUR) = 3089
4629: Incurred fault #6, FLTBOUNDS %pc = 0xFF1FDFA4
4629: siginfo: SIGSEGV SEGV_MAPERR addr=0x206F7910
4629: Received signal #11, SIGSEGV [caught]
4629: siginfo: SIGSEGV SEGV_MAPERR addr=0x206F7910
4629: schedctl() = 0xFECA0000
4629: lwp_sigmask(SIG_SETMASK, 0x00000000, 0x00000000) = 0xFFBFFEFF
[0x0000FFFF]
4629: _exit(0)
4252: accept(5, 0xFFBFF4F4, 0xFFBFF504, SOV_DEFAULT) (sleeping...)
-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/
More information about the Developers
mailing list