Has anyone noticed their sge_execd proceses suddenly taking up a lot of
CPU, possibly since around July 2nd this year?
I think it might be to do with the Linux "leap second" bug, which affects
processes that use "futexes".  It doesn't happen to all nodes on a queue,
just some.
The only way I know to resolve this is to reboot the machine.


If you do "strace -p <pid>" on the sge_execd process, you'll see output
like the following.

BTW, I think I am not on this list right now.

Dan

futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276699, {1342229400, 776755000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276701, {1342229400, 776871000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276703, {1342229400, 776988000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276705, {1342229400, 777102000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276707, {1342229400, 777219000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276709, {1342229400, 777335000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276711, {1342229400, 777452000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276713, {1342229400, 777567000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276715, {1342229400, 777683000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
futex(0x7fb381006b30, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7fb381006b94, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME,
2027276717, {1342229400, 777799000}, ffffffff) = -1 ETIMEDOUT (Connection
timed out)
_______________________________________________
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/users

Reply via email to