Integrated: 8311883: [Genshen] Adaptive tenuring threshold

[Y. Srinivas Ramakrishna]

On Thu, 15 Jun 2023 20:08:58 GMT, Y. Srinivas Ramakrishna <ysr at openjdk.org> wrote:

> JDK-8311883 [GenShen] Adaptive tenuring
> 
> I am opening this previously draft PR for formal preliminary review. It has already benefited from review feedback from a code walkthrough of an earlier version of the code. Most of that feedback and the corrections thereof are to be found in the comments in this PR. I have addressed a large majority of those comments, and am working on the last one that I plan to address as part of this PR. For the ones that I don't plan to address in this PR, I will create follow up tickets. Those will be added in the responses for the remaining feedback comments recorded in this PR's conversation.
> 
> Preliminary testing w/SPECjbb didn't yield reliable performance data from which to infer any performance improvements stemming from enabling adaptive tenuring. I believe that was because of the way SPECjbb is run, which causes excessive degenerate and full gc's. I plan to collect SPECjbb numbers with a fixed lower max HBIR so as to be able to discern performance differences from this change, as well as Extremem workloads. Those will be added here once ready over the next few days.

This pull request has now been integrated.

Changeset: ef4b4532
Author:    Y. Srinivas Ramakrishna <ysr at openjdk.org>
URL:       https://git.openjdk.org/shenandoah/commit/ef4b4532e509412fd0a21e2af36a0708d3696094
Stats:     994 lines in 30 files changed: 876 ins; 45 del; 73 mod

8311883: [Genshen] Adaptive tenuring threshold

Generational Shenandoah currently has the notion of a tenuring threshold but it isn't dynamically adapted, but rather kept fixed at 7.

We now adapt the tenuring threshold based on object demographics as determined by a recent GC that visits objects in the young generation.

We keep track of age-cohort populations at each minor GC epoch and use the historical data to determine if it would be a good idea to tenure or not based on measured mortality rates. A few tunable (experimental) knobs are exposed to play with these to determine some good settings in the future.

The object census is conducted by default at marking, and is subject to noise on account of objects whose age could not be determined because of displaced header. In this case, the computed tenuring threshold is used in the following evacuation of the same cycle. Optionally, the census can be conducted at evacuation time, but sees only objects that are in the collection set. In this case, the tenuring threshold that is computed is used for tenuring decisions in the next evacuation cycle.

Other variants are possible, and may be implemented / tested in the future as opportunity and data permit.

The computed tenuring threshold has not yet been coupled with size budgeting, but will be in a followup PR.

At this time, performance measurements have not shown any benefit, but we believe that with the framework now in place, we may be able to find an adaptive tenuring algorithm that works better than the current one and provide performance benefits. Adaptive tenuring is enabled by default, but can be optionally disabled to mimic previous behavior.

Reviewed-by: kdnilsen

-------------

PR: https://git.openjdk.org/shenandoah/pull/289