Are there any "magic" counters which (on intel) wrap at ~40-50 days
uptime? We've got a couple of processes gone nuts (even after they are
restarted). When I say "go nuts", I mean "chewing a lot of CPU".
strace shows they are repeatedly doing the following set of syscalls (see
end of mail).
Suspiciously, tcpdump also chews CPU and that of course will also be
calling gettimeofday() heavily.
Cheers
Chris
oldselect(1, NULL, NULL, NULL, {0, 1}) = 0 (Timeout)
gettimeofday({934830292, 915696}, {0, 0}) = 0
gettimeofday({934830292, 915875}, {0, 0}) = 0
oldselect(1, [0], NULL, NULL, {0, 0}) = 1 (in [0], left {0, 0})
read(0, "", 256) = 0
gettimeofday({934830292, 917076}, {0, 0}) = 0
ioctl(8, FIONREAD, [0]) = 0
gettimeofday({934830292, 917940}, {0, 0}) = 0
oldselect(1, NULL, NULL, NULL, {0, 1}) = 0 (Timeout)
gettimeofday({934830292, 925664}, {0, 0}) = 0
oldselect(1, NULL, NULL, NULL, {0, 1}) = 0 (Timeout)
gettimeofday({934830292, 935660}, {0, 0}) = 0
oldselect(1, NULL, NULL, NULL, {0, 1}) = 0 (Timeout)
gettimeofday({934830292, 945663}, {0, 0}) = 0
oldselect(1, NULL, NULL, NULL, {0, 1}) = 0 (Timeout)
gettimeofday({934830292, 955684}, {0, 0}) = 0
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/