[11u] RFR: 8222518: Remove unnecessary caching of Parker object in java.lang.Thread

[Hohensee, Paul]

Thanks once more, Volker. :)

An m4.10xlarge is dual socket and the runs I posted were done running on both. I've just added a comparison running on a single socket. It shows much less variance, small gains on three of the sub-workloads, and a minor (< 1%) loss on the fourth.

Thanks,
Paul

-----Original Message-----
From: Volker Simonis <volker.simonis at gmail.com>
Date: Wednesday, January 13, 2021 at 10:47 AM
To: "Hohensee, Paul" <hohensee at amazon.com>
Cc: Andrew Haley <aph at redhat.com>, "jdk-updates-dev at openjdk.java.net" <jdk-updates-dev at openjdk.java.net>
Subject: RE: [11u] RFR: 8222518: Remove unnecessary caching of Parker object in java.lang.Thread

Thanks Paul.

Still looks good to me :)

On Wed, Jan 13, 2021 at 5:32 PM Hohensee, Paul <hohensee at amazon.com> wrote:
>
> I've added performance data to the JBS issue (https://bugs.openjdk.java.net/browse/JDK-8222518).
>
> Thanks,
> Paul
>
> -----Original Message-----
> From: jdk-updates-dev <jdk-updates-dev-retn at openjdk.java.net> on behalf of Andrew Haley <aph at redhat.com>
> Date: Tuesday, January 12, 2021 at 2:36 AM
> To: "jdk-updates-dev at openjdk.java.net" <jdk-updates-dev at openjdk.java.net>
> Subject: RE: [11u] RFR: 8222518: Remove unnecessary caching of Parker object in java.lang.Thread
>
> On 12/23/20 4:13 PM, Hohensee, Paul wrote:
> > I've little knowledge or experience in the area of hotspot thread synchronization. With that disclaimer, the patch looks benign to me but I would want to hear another expert's assessment before being able to approve this with a good conscience.
> >
> > I could ask Richard from our team (on cc) to have a look when he's back from vacation. Or feel free to find somebody else to review and assess this backport from a technical pov.
>
> This area does seem to ave changed a fair bit. Do we know if the
> performance analysis done by David Holmes in 2019 is valid for JDK 11?
> We should check that it is before applying this.
>
> --
> Andrew Haley  (he/him)
> Java Platform Lead Engineer
> Red Hat UK Ltd. <https://www.redhat.com>
> https://keybase.io/andrewhaley
> EAC8 43EB D3EF DB98 CC77 2FAD A5CD 6035 332F A671
>
>