RFR 8231264: Disable biased-locking and deprecate all flags related to biased-locking
David Holmes
david.holmes at oracle.com
Sat Nov 16 03:46:50 UTC 2019
Hi Patricio,
On 16/11/2019 12:15 pm, Patricio Chilano wrote:
> Hi all,
>
> Could you review the following patch?
>
> JBS: https://bugs.openjdk.java.net/browse/JDK-8231264
> Webrev: http://cr.openjdk.java.net/~pchilanomate/8231264/v01/webrev
>
> Biased locking will be disabled by default and all related flags will be
> deprecated. Performance gains seen when the feature was introduced in
> the VM are less clear today with modern Java code/processors. Detailed
> rationale behind the change is included on the description of the bug.
That all seems fine.
> I modified test gtest/oops/test_markWord.cpp so that it still exercises
> other cases of markword printing.
There seems to be some value in testing things in the non-biased-locking
case - though I wonder if there is not another gtest that does this?
The only criticism I have is that when BL is disabled the later comments
in the test are incorrect:
115 // Same thread tries to lock it again.
First time without BL.
121 // This is no longer biased, because ObjectLocker revokes the bias.
Was not biased to begin with without BL.
Thanks,
David
> Tested with mach5, tiers1-6 on all platforms (Linux, macOS, Windows and
> Solaris).
>
> Thanks,
> Patricio
>
>
More information about the hotspot-runtime-dev
mailing list