100% cpu usage on CentOS/RHEL 6

[David Holmes]

On 3/07/2012 9:07 PM, Amol Kulkarni wrote:
> I dont think this is the leap-second bug bcos I can simulate it at any
> time using foll script.
> #!/bin/bash
>
> while [ 1 ]
> do
> /usr/lib/jvm/java-1.6.0-openjdk-1.6.0.0.x86_64/bin/java -version &
> sleep 1s
> done
>
>
> The leap second bug seems to be occuring only near 30 Jun or 1 Jul.

That's when it activates but unless you take steps to fix it it remains 
in your system. The time offset used by the hrtimers remains 1 second 
out of sync with actual time.

> I did generate a backtrace with this prb but I dont have openjdk with
> debug symbols - can u tell me where I can get it?

No sorry, I don't know about the OpenJDK distros available for CentOS.

Further discussion should move to hotspot-dev at openjdk.java.net cc'd.

David
-----

>
> On Tue, Jul 3, 2012 at 7:54 AM, David Holmes <david.holmes at oracle.com
> <mailto:david.holmes at oracle.com>> wrote:
>
>     Yes this sounds like the linux leap-second bug.
>
>     Despite a lot of ignorant comments on the web this is not a bug in Java.
>
>     But I would really appreciate it if someone experience this can send
>     me a stack trace from the problematic thread(s). I think I know what
>     is happening but need to confirm.
>
>     Thanks,
>     David Holmes
>
>
>     On 3/07/2012 12:02 AM, Mark Thornton wrote:
>
>         On 02/07/12 14:45, Amol Kulkarni wrote:
>
>             Hi,
>
>             I have a java app running on CentOS 6.0. It always runs in
>             background via
>             cron. Sometimes this app goes into wait state while using
>             100% cpu.
>
>             My java version is :
>
>             java version "1.6.0_17"
>             OpenJDK Runtime Environment (IcedTea6 1.7.4)
>             (rhel-1.21.b17.el6-x86_64)
>             OpenJDK 64-Bit Server VM (build 14.0-b16, mixed mode)
>
>             Other symptoms are :
>
>             a. One thread of the process seems to be in a loop waiting
>             for something.
>             When traced using strace, it shows following o/p continuously :
>
>                 futex(0x7fb8000ac728, FUTEX_WAKE_PRIVATE, 1) = 0
>                 futex(0x7fb8000ac754,
>                 FUTEX_WAIT_BITSET_PRIVATE|__FUTEX_CLOCK_REALTIME,
>
>
>         Could it be related to this:
>         https://bugzilla.kernel.org/__show_bug.cgi?id=32922
>         <https://bugzilla.kernel.org/show_bug.cgi?id=32922>
>
>         Mark Thornton
>
>