Issues running jcstress on multi-core systems

[Pavel Punegov]

I found that we’ve actually had the same issue some time ago. I just haven’t remembered it. I’m sorry.

Here is an issue https://bugs.openjdk.java.net/browse/CODETOOLS-7901764 <https://bugs.openjdk.java.net/browse/CODETOOLS-7901764>. I’m not quite sure if it's still applicable and correct, but it looks the same.

— Thanks,
Pavel Punegov

> On 11 Aug 2016, at 02:24, Johnson, Andy <johnsona at cboe.com> wrote:
> 
> I set "-time 2000" (the default value is 1000) and actually got more failures (25) than I did with the default setting.  If I run just the interrupt tests ("-t interrupt."), they all pass.  
> 
> -----Original Message-----
> From: Aleksey Shipilev [mailto:aleksey.shipilev at gmail.com] 
> Sent: Wednesday, August 10, 2016 3:54 PM
> To: Johnson, Andy <johnsona at cboe.com>; 'jcstress-dev at openjdk.java.net' <jcstress-dev at openjdk.java.net>
> Subject: Re: Issues running jcstress on multi-core systems
> 
> On 08/10/2016 07:41 PM, Johnson, Andy wrote:
>> I have recently downloaded, built and run jcstress (custom suite only, 
>> for now) on a 24-core Linux server-class system.  I am finding that 
>> several of the "interrupt" tests are failing.  However, I have 
>> discovered that the number of failures seems to be related to the 
>> number of processor cores being used during the test.
> 
> "interrupt" tests are inherently time-based: they usually wait for timeout. There is a chance that timeout is not enough on busy machines
> -- while the test tries to assert that the code quits, it runs out of time before quitting, and infra fails it.
> 
> Now, I realized we have a hard-coded timeout in the tests. Oops. Fixed, now it is derived from the iteration time:
>  http://hg.openjdk.java.net/code-tools/jcstress/rev/b0c5e26af669
> 
> So, with an updated jcstress, you may want to try different "-time <msec>" settings and see if it helps. If it does help, we may need to throttle other tests while interrupt tests are executing.
> 
>> I am using "taskset" to control the number of cores used by java.
> 
> jcstress harness accepts "-sc <numCPUs>" to artificially limit the number of hardware threads to use.
> 
> Thanks,
> -Aleksey
>